Search

Background: Early prediction of delayed cerebral ischemia (DCI) is critical to improving the prognosis of aneurysmal subarachnoid hemorrhage (aSAH). Machine learning (ML) algorithms can learn from intricate information unbiasedly and facilitate the early identification of clinical outcomes. This study aimed to construct and compare the ability of different ML models to predict DCI after aSAH. Then, we identified and analyzed the essential risk of DCI occurrence by preoperative clinical scores and postoperative laboratory test results. Methods: This was a multicenter, retrospective cohort study. A total of 1039 post-operation patients with aSAH were finally included from three hospitals in China. The training group contained 919 patients, and the test group comprised 120 patients. We used five popular machine-learning algorithms to construct the models. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, precision, and f1 score were used to evaluate and compare the five models. Finally, we performed a Shapley Additive exPlanations analysis for the model with the best performance and significance analysis for each feature. Results: A total of 239 patients with aSAH (23.003%) developed DCI after the operation. Our results showed that in the test cohort, Random Forest (RF) had an AUC of 0.79, which was better than other models. The five most important features for predicting DCI in the RF model were the admitted modified Rankin Scale, D-Dimer, intracranial parenchymal hematoma, neutrophil/lymphocyte ratio, and Fisher score. Interestingly, clamping or embolization for the aneurysm treatment was the fourth button-down risk factor in the ML model. Conclusions: In this multicenter study, we compared five ML methods, among which RF performed the best in DCI prediction. In addition, the essential risks were identified to help clinicians monitor the patients at high risk for DCI more precisely and facilitate timely intervention. [ABSTRACT FROM AUTHOR]

Background: Alzheimer's disease (AD) is a chronic neurodegenerative disorder that poses a substantial economic burden. The Random forest algorithm is effective in predicting AD; however, the key factors influencing AD onset remain unclear. This study aimed to analyze the key lipoprotein and metabolite factors influencing AD onset using machine-learning methods. It provides new insights for researchers and medical personnel to understand AD and provides a reference for the early diagnosis, treatment, and early prevention of AD. Methods: A total of 603 participants, including controls and patients with AD with complete lipoprotein and metabolite data from the Alzheimer's disease Neuroimaging Initiative (ADNI) database between 2005 and 2016, were enrolled. Random forest, Lasso regression, and CatBoost algorithms were employed to rank and filter 213 lipoprotein and metabolite variables. Variables with consistently high importance rankings from any two methods were incorporated into the models. Finally, the variables selected from the three methods, with the participants' age, sex, and marital status, were used to construct a random forest predictive model. Results: Fourteen lipoprotein and metabolite variables were screened using the three methods, and 17 variables were included in the AD prediction model based on age, sex, and marital status of the participants. The optimal random forest modeling was constructed with "mtry" set to 3 and "ntree" set to 300. The model exhibited an accuracy of 71.01%, a sensitivity of 79.59%, a specificity of 65.28%, and an AUC (95%CI) of 0.724 (0.645–0.804). When Mean Decrease Accuracy and Gini were used to rank the proteins, age, phospholipids to total lipids ratio in intermediate-density lipoproteins (IDL_PL_PCT), and creatinine were among the top five variables. Conclusions: Age, IDL_PL_PCT, and creatinine levels play crucial roles in AD onset. Regular monitoring of lipoproteins and their metabolites in older individuals is significant for early AD diagnosis and prevention. [ABSTRACT FROM AUTHOR]

The goal is to enhance an automated sleep staging system's performance by leveraging the diverse signals captured through multi-modal polysomnography recordings. Three modalities of PSG signals, namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), were considered to obtain the optimal fusions of the PSG signals, where 63 features were extracted. These include frequency-based, time-based, statistical-based, entropy-based, and non-linear-based features. We adopted the ReliefF (ReF) feature selection algorithms to find the suitable parts for each signal and superposition of PSG signals. Twelve top features were selected while correlated with the extracted feature sets' sleep stages. The selected features were fed into the AdaBoost with Random Forest (ADB + RF) classifier to validate the chosen segments and classify the sleep stages. This study's experiments were investigated by obtaining two testing schemes: epoch-wise testing and subject-wise testing. The suggested research was conducted using three publicly available datasets: ISRUC-Sleep subgroup1 (ISRUC-SG1), sleep-EDF(S-EDF), Physio bank CAP sleep database (PB-CAPSDB), and S-EDF-78 respectively. This work demonstrated that the proposed fusion strategy overestimates the common individual usage of PSG signals. [ABSTRACT FROM AUTHOR]

Background: Hospital-acquired influenza (HAI) is under-recognized despite its high morbidity and poor health outcomes. The early detection of HAI is crucial for curbing its transmission in hospital settings. Aim: This study aimed to investigate factors related to HAI, develop predictive models, and subsequently compare them to identify the best performing machine learning algorithm for predicting the occurrence of HAI. Methods: This retrospective observational study was conducted in 2022 and included 111 HAI and 73,748 non-HAI patients from the 2011–2012 and 2019–2020 influenza seasons. General characteristics, comorbidities, vital signs, laboratory and chest X-ray results, and room information within the electronic medical record were analysed. Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) techniques were used to construct the predictive models. Employing randomized allocation, 80% of the dataset constituted the training set, and the remaining 20% comprised the test set. The performance of the developed models was assessed using metrics such as the area under the receiver operating characteristic curve (AUC), the count of false negatives (FN), and the determination of feature importance. Results: Patients with HAI demonstrated notable differences in general characteristics, comorbidities, vital signs, laboratory findings, chest X-ray result, and room status compared to non-HAI patients. Among the developed models, the RF model demonstrated the best performance taking into account both the AUC (83.3%) and the occurrence of FN (four). The most influential factors for prediction were staying in double rooms, followed by vital signs and laboratory results. Conclusion: This study revealed the characteristics of patients with HAI and emphasized the role of ventilation in reducing influenza incidence. These findings can aid hospitals in devising infection prevention strategies, and the application of machine learning-based predictive models especially RF can enable early intervention to mitigate the spread of influenza in healthcare settings. [ABSTRACT FROM AUTHOR]

Background: Although high tibial osteotomy (HTO) is an established treatment option for medial compartment osteoarthritis, predictive factors for HTO treatment success remain unclear. This study aimed to identify informative variables associated with HTO treatment success and to develop and internally validate machine learning algorithms to predict which patients will achieve HTO treatment success for medial compartmental osteoarthritis. Methods: This study retrospectively reviewed patients who underwent medial opening-wedge HTO (MOWHTO) at our center between March 2010 and December 2015. The primary outcomes were a lack of conversion to total knee arthroplasty (TKA) and achievement of a minimal clinically important difference of improvement in the Knee Injury and Osteoarthritis Outcome Score (KOOS) at a minimum of five years postoperatively. Recursive feature selection was used to identify the combination of variables from an initial pool of 25 features that optimized model performance. Five machine learning algorithms (XGBoost, multilayer perception, support vector machine, elastic-net penalized logistic regression, and random forest) were trained using five-fold cross-validation three times and applied to an independent test set of patients. The performance of the model was evaluated by the area under the receiver operating characteristic curve (AUC). Results: A total of 231 patients were included, and 200 patients (86.6%) achieved treatment success at the mean of 9 years of follow-up. A combination of seven variables optimized algorithm performance, and the following specific cutoffs increased the likelihood of MOWHTO treatment success: body mass index (BMI) ≤ 26.8 kg/m2, preoperative KOOS for pain ≤ 46.0, preoperative KOOS for quality of life ≤ 33.0, preoperative International Knee Documentation Committee score ≤ 42.0, preoperative Short-Form 36 questionnaire (SF-36) score > 42.25, three-month postoperative hip-knee-ankle angle > 1.0°, and three-month postoperative medial proximal tibial angle (MPTA) > 91.5° and ≤ 94.7°. The random forest model demonstrated the best performance (F1 score: 0.93; AUC: 0.81) and was transformed into an online application as an educational tool to demonstrate the capabilities of machine learning. Conclusions: The random forest machine learning algorithm best predicted MOWHTO treatment success. Patients with a lower BMI, poor clinical status, slight valgus overcorrection, and postoperative MPTA < 94.7 more frequently achieved a greater likelihood of treatment success. Level of evidence: Level III, retrospective cohort study. [ABSTRACT FROM AUTHOR]

The global spread of the SARS-CoV-2 pandemic, originating in Wuhan, China, has had profound consequences on both health and the economy. Traditional alignment-based phylogenetic tree methods for tracking epidemic dynamics demand substantial computational power due to the growing number of sequenced strains. Consequently, there is a pressing need for an alignment-free approach to characterize these strains and monitor the dynamics of various variants. In this work, we introduce a swift and straightforward tool named GenoSig, implemented in C++. The tool exploits the Di and Tri nucleotide frequency signatures to delineate the taxonomic lineages of SARS-CoV-2 by employing diverse machine learning (ML) and deep learning (DL) models. Our approach achieved a tenfold cross-validation accuracy of 87.88% (± 0.013) for DL and 86.37% (± 0.0009) for Random Forest (RF) model, surpassing the performance of other ML models. Validation using an additional unexposed dataset yielded comparable results. Despite variations in architectures between DL and RF, it was observed that later clades, specifically GRA, GRY, and GK, exhibited superior performance compared to earlier clades G and GH. As for the continental origin of the virus, both DL and RF models exhibited lower performance than in predicting clades. However, both models demonstrated relatively higher accuracy for Europe, North America, and South America compared to other continents, with DL outperforming RF. Both models consistently demonstrated a preference for cytosine and guanine over adenine and thymine in both clade and continental analyses, in both Di and Tri nucleotide frequencies signatures. Our findings suggest that GenoSig provides a straightforward approach to address taxonomic, epidemiological, and biological inquiries, utilizing a reductive method applicable not only to SARS-CoV-2 but also to similar research questions in an alignment-free context. [ABSTRACT FROM AUTHOR]

Background: Following China's official designation as malaria-free country by WHO, the imported malaria has emerged as a significant determinant impacting the malaria reestablishment within China. The objective of this study is to explore the application prospects of machine learning algorithms in imported malaria risk assessment of China. Methods: The data of imported malaria cases in China from 2011 to 2019 was provided by China CDC; historical epidemic data of malaria endemic country was obtained from World Malaria Report, and the other data used in this study are open access data. All the data processing and model construction based on R, and map visualization used ArcGIS software. Results: A total of 27,088 malaria cases imported into China from 85 countries between 2011 and 2019. After data preprocessing and classification, clean dataset has 765 rows (85 * 9) and 11 cols. Six machine learning models was constructed based on the training set, and Random Forest model demonstrated the best performance in model evaluation. According to RF, the highest feature importance were the number of malaria deaths and Indigenous malaria cases. The RF model demonstrated high accuracy in forecasting risk for the year 2019, achieving commendable accuracy rate of 95.3%. This result aligns well with the observed outcomes, indicating the model's reliability in predicting risk levels. Conclusions: Machine learning algorithms have reliable application prospects in risk assessment of imported malaria in China. This study provides a new methodological reference for the risk assessment and control strategies adjusting of imported malaria in China. [ABSTRACT FROM AUTHOR]

Background: Secondary immunodeficiency can arise from various clinical conditions that include HIV infection, chronic diseases, malignancy and long-term use of immunosuppressives, which makes the suffering patients susceptible to all types of pathogenic infections. Other than HIV infection, the possible pathogen profiles in other aetiology-induced secondary immunodeficiency are largely unknown. Methods: Medical records of the patients with secondary immunodeficiency caused by various aetiologies were collected from the First Affiliated Hospital of Nanchang University, China. Based on these records, models were developed with the machine learning method to predict the potential infectious pathogens that may inflict the patients with secondary immunodeficiency caused by various disease conditions other than HIV infection. Results: Several metrics were used to evaluate the models' performance. A consistent conclusion can be drawn from all the metrics that Gradient Boosting Machine had the best performance with the highest accuracy at 91.01%, exceeding other models by 13.48, 7.14, and 4.49% respectively. Conclusions: The models developed in our study enable the prediction of potential infectious pathogens that may affect the patients with secondary immunodeficiency caused by various aetiologies except for HIV infection, which will help clinicians make a timely decision on antibiotic use before microorganism culture results return. [ABSTRACT FROM AUTHOR]

Background: Maternal vitamin D deficiency during pregnancy has been associated with various maternal adverse events (MAE). However, the evidence regarding the effect of vitamin D supplementation on these outcomes is still inconclusive. Methods: This secondary analysis utilized a case–control design. 403 samples with MAE and 403 samples without any outcomes were selected from the Khuzestan Vitamin D Deficiency Screening Program in Pregnancy study. Random forest (RF) analysis was used to evaluate the effect of maternal vitamin D changes during pregnancy on MAE. Results: The results showed that women who remained deficient (35.2%) or who worsened from sufficient to deficient (30.0%) had more MAE than women who improved (16.4%) or stayed sufficient (11.8%). The RF model had an AUC of 0.74, sensitivity of 72.6%, and specificity of 69%, which indicate a moderate to high performance for predicting MAE. The ranked variables revealed that systolic blood pressure is the most important variable for MAE, followed by diastolic blood pressure and vitamin D changes during pregnancy. Conclusion: This study provides evidence that maternal vitamin D changes during pregnancy have a significant impact on MAE. Our findings suggest that monitoring and treatment of vitamin D deficiency during pregnancy may be a potential preventive strategy for reducing the risk of MAE. The presented RF model had a moderate to high performance for predicting MAE. [ABSTRACT FROM AUTHOR]

Rationale: Cancer of unknown primary (CUP) is a group of rare malignancies with poor prognosis and unidentifiable tissue-of-origin. Distinct DNA methylation patterns in different tissues and cancer types enable the identification of the tissue of origin in CUP patients, which could help risk assessment and guide site-directed therapy. Methods: Using genome-wide DNA methylation profile datasets from The Cancer Genome Atlas (TCGA) and machine learning methods, we developed a 200-CpG methylation feature classifier for CUP tissue of origin prediction (MFCUP). MFCUP was further validated with public-available methylation array data of 2977 specimens and targeted methylation sequencing of 78 Formalin‐fixed paraffin‐embedded (FFPE) samples from a single center. Results: MFCUP achieved an accuracy of 97.2% in a validation cohort (n = 5923) representing 25 cancer types. When applied to an Infinium 450 K array dataset (n = 1052) and an Infinium EPIC (850 K) array dataset (n = 1925), MFCUP achieved an overall accuracy of 93.4% and 84.8%, respectively. Based on MFCUP, we established a targeted bisulfite sequencing panel and validated it with FFPE sections from 78 patients of 20 cancer types. This methylation sequencing panel correctly identified tissue of origin in 88.5% (69/78) of samples. We also found that the methylation levels of specific CpGs can distinguish one cancer type from others, indicating their potential as biomarkers for cancer diagnosis and screening. Conclusion: Our methylation-based cancer classifier and targeted methylation sequencing panel can predict tissue of origin in diverse cancer types with high accuracy. [ABSTRACT FROM AUTHOR]

Background: Mendelian randomization is a popular method for causal inference with observational data that uses genetic variants as instrumental variables. Similarly to a randomized trial, a standard Mendelian randomization analysis estimates the population-averaged effect of an exposure on an outcome. Dividing the population into subgroups can reveal effect heterogeneity to inform who would most benefit from intervention on the exposure. However, as covariates are measured post-"randomization", naive stratification typically induces collider bias in stratum-specific estimates. Method: We extend a previously proposed stratification method (the "doubly-ranked method") to form strata based on a single covariate, and introduce a data-adaptive random forest method to calculate stratum-specific estimates that are robust to collider bias based on a high-dimensional covariate set. We also propose measures based on the Q statistic to assess heterogeneity between stratum-specific estimates (to understand whether estimates are more variable than expected due to chance alone) and variable importance (to identify the key drivers of effect heterogeneity). Result: We show that the effect of body mass index (BMI) on lung function is heterogeneous, depending most strongly on hip circumference and weight. While for most individuals, the predicted effect of increasing BMI on lung function is negative, it is positive for some individuals and strongly negative for others. Conclusion: Our data-adaptive approach allows for the exploration of effect heterogeneity in the relationship between an exposure and an outcome within a Mendelian randomization framework. This can yield valuable insights into disease aetiology and help identify specific groups of individuals who would derive the greatest benefit from targeted interventions on the exposure. [ABSTRACT FROM AUTHOR]

Building Single Sample Predictors (SSPs) from gene expression profiles presents challenges, notably due to the lack of calibration across diverse gene expression measurement technologies. However, recent research indicates the viability of classifying phenotypes based on the order of expression of multiple genes. Existing SSP methods often rely on Top Scoring Pairs (TSP), which are platform-independent and easy to interpret through the concept of "relative expression reversals". Nevertheless, TSP methods face limitations in classifying complex patterns involving comparisons of more than two gene expressions. To overcome these constraints, we introduce a novel approach that extends TSP rules by constructing rank-based trees capable of encompassing extensive gene-gene comparisons. This method is bolstered by incorporating two ensemble strategies, boosting and random forest, to mitigate the risk of overfitting. Our implementation of ensemble rank-based trees employs boosting with LogitBoost cost and random forests, addressing both binary and multi-class classification problems. In a comparative analysis across 12 cancer gene expression datasets, our proposed methods demonstrate superior performance over both the k-TSP classifier and nearest template prediction methods. We have further refined our approach to facilitate variable selection and the generation of clear, precise decision rules from rank-based trees, enhancing interpretability. The cumulative evidence from our research underscores the significant potential of ensemble rank-based trees in advancing disease classification via gene expression data, offering a robust, interpretable, and scalable solution. Our software is available at https://CRAN.R-project.org/package=ranktreeEnsemble. [ABSTRACT FROM AUTHOR]

In recent years, corneal refractive surgery has been widely used in clinics as an effective means to restore vision and improve the quality of life. When choosing myopia-refractive surgery, it is necessary to comprehensively consider the differences in equipment and technology as well as the specificity of individual patients, which heavily depend on the experience of ophthalmologists. In our study, we took advantage of machine learning to learn about the experience of ophthalmologists in decision-making and assist them in the choice of corneal refractive surgery in a new case. Our study was based on the clinical data of 7,081 patients who underwent corneal refractive surgery between 2000 and 2017 at the Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences. Due to the long data period, there were data losses and errors in this dataset. First, we cleaned the data and deleted the samples of key data loss. Then, patients were divided into three groups according to the type of surgery, after which we used SMOTE technology to eliminate imbalance between groups. Six statistical machine learning models, including NBM, RF, AdaBoost, XGBoost, BP neural network, and DBN were selected, and a ten-fold cross-validation and grid search were used to determine the optimal hyperparameters for better performance. When tested on the dataset, the multi-class RF model showed the best performance, with agreement with ophthalmologist decisions as high as 0.8775 and Macro F1 as high as 0.8019. Furthermore, the results of the feature importance analysis based on the SHAP technique were consistent with an ophthalmologist's practical experience. Our research will assist ophthalmologists in choosing appropriate types of refractive surgery and will have beneficial clinical effects. [ABSTRACT FROM AUTHOR]

Background: Enzymes play an irreplaceable and important role in maintaining the lives of living organisms. The Enzyme Commission (EC) number of an enzyme indicates its essential functions. Correct identification of the first digit (family class) of the EC number for a given enzyme is a hot topic in the past twenty years. Several previous methods adopted functional domain composition to represent enzymes. However, it would lead to dimension disaster, thereby reducing the efficiency of the methods. On the other hand, most previous methods can only deal with enzymes belonging to one family class. In fact, several enzymes belong to two or more family classes. Results: In this study, a fast and efficient multi-label classifier, named PredictEFC, was designed. To construct this classifier, a novel feature extraction scheme was designed for processing functional domain information of enzymes, which counting the distribution of each functional domain entry across seven family classes in the training dataset. Based on this scheme, each training or test enzyme was encoded into a 7-dimenion vector by fusing its functional domain information and above statistical results. Random k-labelsets (RAKEL) was adopted to build the classifier, where random forest was selected as the base classification algorithm. The two tenfold cross-validation results on the training dataset shown that the accuracy of PredictEFC can reach 0.8493 and 0.8370. The independent test on two datasets indicated the accuracy values of 0.9118 and 0.8777. Conclusion: The performance of PredictEFC was slightly lower than the classifier directly using functional domain composition. However, its efficiency was sharply improved. The running time was less than one-tenth of the time of the classifier directly using functional domain composition. In additional, the utility of PredictEFC was superior to the classifiers using traditional dimensionality reduction methods and some previous methods, and this classifier can be transplanted for predicting enzyme family classes of other species. Finally, a web-server available at http://124.221.158.221/ was set up for easy usage. [ABSTRACT FROM AUTHOR]

Background: Nowadays, the chance of discovering the best antibody candidates for predicting clinical malaria has notably increased due to the availability of multi-sera data. The analysis of these data is typically divided into a feature selection phase followed by a predictive one where several models are constructed for predicting the outcome of interest. A key question in the analysis is to determine which antibodies should be included in the predictive stage and whether they should be included in the original or a transformed scale (i.e. binary/dichotomized). Methods: To answer this question, we developed three approaches for antibody selection in the context of predicting clinical malaria: (i) a basic and simple approach based on selecting antibodies via the nonparametric Mann–Whitney-Wilcoxon test; (ii) an optimal dychotomizationdichotomization approach where each antibody was selected according to the optimal cut-off via maximization of the chi-squared (χ2) statistic for two-way tables; (iii) a hybrid parametric/non-parametric approach that integrates Box-Cox transformation followed by a t-test, together with the use of finite mixture models and the Mann–Whitney-Wilcoxon test as a last resort. We illustrated the application of these three approaches with published serological data of 36 Plasmodium falciparum antigens for predicting clinical malaria in 121 Kenyan children. The predictive analysis was based on a Super Learner where predictions from multiple classifiers including the Random Forest were pooled together. Results: Our results led to almost similar areas under the Receiver Operating Characteristic curves of 0.72 (95% CI = [0.62, 0.82]), 0.80 (95% CI = [0.71, 0.89]), 0.79 (95% CI = [0.7, 0.88]) for the simple, dichotomization and hybrid approaches, respectively. These approaches were based on 6, 20, and 16 antibodies, respectively. Conclusions: The three feature selection strategies provided a better predictive performance of the outcome when compared to the previous results relying on Random Forest including all the 36 antibodies (AUC = 0.68, 95% CI = [0.57;0.79]). Given the similar predictive performance, we recommended that the three strategies should be used in conjunction in the same data set and selected according to their complexity. [ABSTRACT FROM AUTHOR]

Background: Systemic juvenile idiopathic arthritis (SJIA) is a form of childhood arthritis with clinical features such as fever, lymphadenopathy, arthritis, rash, and serositis. It seriously affects the growth and development of children and has a high rate of disability and mortality. SJIA may result from genetic, infectious, or autoimmune factors since the precise source of the disease is unknown. Our study aims to develop a genetic-based diagnostic model to explore the identification of SJIA at the genetic level. Methods: The gene expression dataset of peripheral blood mononuclear cell (PBMC) samples from SJIA was collected from the Gene Expression Omnibus (GEO) database. Then, three GEO datasets (GSE11907-GPL96, GSE8650-GPL96 and GSE13501) were merged and used as a training dataset, which included 125 SJIA samples and 92 health samples. GSE7753 was used as a validation dataset. The limma method was used to screen differentially expressed genes (DEGs). Feature selection was performed using Lasso, random forest (RF)-recursive feature elimination (RFE) and RF classifier. Results: We finally identified 4 key genes (ALDH1A1, CEACAM1, YBX3 and SLC6A8) that were essential to distinguish SJIA from healthy samples. And we combined the 4 key genes and performed a grid search as well as 10-fold cross-validation with 5 repetitions to finally identify the RF model with optimal mtry. The mean area under the curve (AUC) value for 5-fold cross-validation was greater than 0.95. The model's performance was then assessed once more using the validation dataset, and an AUC value of 0.990 was obtained. All of the above AUC values demonstrated the strong robustness of the SJIA diagnostic model. Conclusions: We successfully developed a new SJIA diagnostic model that can be used for a novel aid in the identification of SJIA. In addition, the identification of 4 key genes that may serve as potential biomarkers for SJIA provides new insights to further understand the mechanisms of SJIA. [ABSTRACT FROM AUTHOR]

Background: Metabolic syndrome (MetS) is a cluster of metabolic abnormalities (including obesity, insulin resistance, hypertension, and dyslipidemia), which can be used to identify at-risk populations for diabetes and cardiovascular diseases, the main causes of morbidity and mortality worldwide. The achievement of a simple approach for diagnosing MetS without needing biochemical tests is so valuable. The present study aimed to predict MetS using non-invasive features based on a successful random forest learning algorithm. Also, to deal with the problem of data imbalance that naturally exists in this type of data, the effect of two different data balancing approaches, including the Synthetic Minority Over-sampling Technique (SMOTE) and Random Splitting data balancing (SplitBal), on model performance is investigated. Results: The most important determinant for MetS prediction was waist circumference. Applying a random forest learning algorithm to imbalanced data, the trained models reach 86.9% and 79.4% accuracies and 37.1% and 38.2% sensitivities in men and women, respectively. However, by applying the SplitBal data balancing technique, the best results were obtained, and despite that the accuracy of the trained models decreased by 7.8% and 11.3%, but their sensitivity improved significantly to 82.3% and 73.7% in men and women, respectively. Conclusions: The random forest learning method, along with data balancing techniques, especially SplitBal, could create MetS prediction models with promising results that can be applied as a useful prognostic tool in health screening programs. [ABSTRACT FROM AUTHOR]

Background: Obesity is increasingly recognized as a grave public health concern globally. It is associated with prevalent diseases including coronary heart disease, fatty liver, type 2 diabetes, and dyslipidemia. Prior research has identified demographic, socioeconomic, lifestyle, and genetic factors as contributors to obesity. Nevertheless, the influence of occupational risk factors on obesity among workers remains under-explored. Investigating risk factors specific to steelworkers is crucial for early detection, prediction, and effective intervention, thereby safeguarding their health. Methods: This research utilized a cohort study examining health impacts on workers in an iron and steel company in Hebei Province, China. The study involved 5469 participants. By univariate analysis, multifactor analysis, and review of relevant literature, predictor variables were found. Three predictive models—XG Boost, Support Vector Machine (SVM), and Random Forest (RF)—were employed. Results: Univariate analysis and cox proportional hazard regression modeling identified age, gender, smoking and drinking habits, dietary score, physical activity, shift work, exposure to high temperatures, occupational stress, and carbon monoxide exposure as key factors in the development of obesity in steelworkers. Test results indicated accuracies of 0.819, 0.868, and 0.872 for XG Boost, SVM, and RF respectively. Precision rates were 0.571, 0.696, and 0.765, while recall rates were 0.333, 0.592, and 0.481. The models achieved AUCs of 0.849, 0.908, and 0.912, with Brier scores of 0.128, 0.105, and 0.104, log losses of 0.409, 0.349, and 0.345, and calibration-in-the-large of 0.058, 0.054, and 0.051, respectively. Among these, the Random Forest model demonstrated superior performance. Conclusions: The research indicates that obesity in steelworkers results from a combination of occupational and lifestyle factors. Of the models tested, the Random Forest model exhibited superior predictive ability, highlighting its significant practical application. [ABSTRACT FROM AUTHOR]

Purpose: With the change of lifestyle, the occurrence of coronary artery disease presents a younger trend, increasing the medical and economic burden on the family and society. To reduce the burden caused by this disease, this study applied LASSO Logistic Regression and Random Forest to establish a risk prediction model for premature coronary artery disease(PCAD) separately and compared the predictive performance of the two models. Methods: The data are obtained from 1004 patients with coronary artery disease admitted to a third-class hospital in Liaoning Province from September 2019 to December 2021. The data from 797 patients were ultimately evaluated. The dataset of 797 patients was randomly divided into the training set (569 persons) and the validation set (228 persons) scale by 7:3. The risk prediction model was established and compared by LASSO Logistic and Random Forest. Result: The two models in this study showed that hyperuricemia, chronic renal disease, carotid artery atherosclerosis were important predictors of premature coronary artery disease. A result of the AUC between the two models showed statistical difference (Z = 3.47, P < 0.05). Conclusions: Random Forest has better prediction performance for PCAD and is suitable for clinical practice. It can provide an objective reference for the early screening and diagnosis of premature coronary artery disease, guide clinical decision-making and promote disease prevention. [ABSTRACT FROM AUTHOR]

Objective: This study seeks to investigate independent risk factors affecting the prognoses of patients with bladder pain syndrome/interstitial cystitis (BPS/IC) following hydrodistention surgery and to develop a column chart model and a random forest model to help predict clinical outcomes. Method: A retrospective analysis was conducted on the clinical data of 1006 BPS/IC patients who visited the urology department of the Fifth Hospital of Shanxi Medical University (Shanxi Provincial People's Hospital) between June 2012 and June 2022. The patients were randomly divided into a model group (n = 704) and a validation group (n = 302). In the model group, logistic regression analysis was used to identify independent risk factors, which were used to construct a prognostic nomogram. The nomogram was evaluated by analyzing the area under the curve (AUC), calibration curve, and decision curve. These results were subsequently validated via consistency analysis (n = 302). And based on the random forest algorithm, we calculate the same data and construct a random forest model. Result: Multivariate logistic regression analysis revealed that age and the expression of the biomarkers CD117, P2X3R, NGF, and TrkA were independent prognostic factors for patients with BPS/IC (P < 0.05). Using these five indicators, a nomogram was developed to predict the risk factors for BPS/IC (scores ranged from 0 to 400). Based on the indicators, the nomogram demonstrated good prognostic performance (AUC = 0.982 and 95% confidence interva is 0.960–0.100). The correction curve indicated a high level of differentiation in the model, and the decision curve suggested positive clinical benefits. The random forest model has high accuracy and good calibration in predicting the prognosis of patients with interstitial cystitis after hydrodistention surgery. Conclusion: Age, CD117, P2X3R, NGF, and TrkA are independent prognostic factors for bladder pain syndrome/interstitial cystitis. The column chart model and random forest model constructed based on these indicators have good predictive performance for patient prognosis. [ABSTRACT FROM AUTHOR]

Background: Shared decision making (SDM) improves the health status of patients with chronic diseases, especially in the condition of poly-medicated patients. This study aims to find the factors associated with participation of patients with chronic diseases in SDM on medication. Methods: A total of 1,196 patients with chronic diseases were selected in Hubei Province of China using cluster sampling methods. The random forest method was applied to rank the importance of independent variables by Mean Decrease Gini and out-of- bag (OOB) curve. Multivariate logistic regression was used to explore the independent variables' effect direction and relative hazard. Results: In this study, 5.18% of patients used patient-directed decision making (PDM, a decision-making model led by patients), 37.79% of patients used SDM (a collaborative decision-making model by patients and doctors), and 57.02% of patients used doctor-directed decision making (DDM, or paternalistic decision making, a decision-making model led by doctors). The random forest analysis demonstrated that the top 5 important factors were age, education, exercise, disease course, and medication knowledge. The OOB curve showed that the error rate reached minimum when top 5 variables in importance ranking composed an optimal variable combination. In multivariate logistic regression, we chose SDM as a reference group, and identified medication knowledge (OR = 2.737, 95%CI = 1.524 ~ 4.916) as the influencing factor between PDM and SDM. Meanwhile, the influencing factors between DDM and SDM were age (OR = 0.636, 95%CI = 0.439 ~ 0.921), education (OR = 1.536, 95%CI = 1.122 ~ 2.103), exercise (OR = 1.443, 95%CI = 1.109 ~ 1.877), disease course (OR = 0.750, 95%CI = 0.584 ~ 0.964), and medication knowledge (OR = 1.446, 95%CI = 1.120 ~ 1.867). Conclusion: Most Chinese patients with chronic diseases used DDM during their medication decision-making, and some patients used PDM and SDM. The participation in SDM should be taken seriously among elderly patients with lower education levels. The SDM promotion should focus on transformation of patients' traditional perception and enhance their medication knowledge. [ABSTRACT FROM AUTHOR]

Background: Composition of the intestinal microbiota has been correlated to therapeutic efficacy of immune checkpoint inhibitors (ICI) in various cancer entities including melanoma. Prediction of the outcome of such therapy, however, is still unavailable. This prospective, non-interventional study was conducted in order to achieve an integrated assessment of the connection between a specific intestinal microbiota profile and antitumor immune response to immune checkpoint inhibitor therapy (anti-PD-1 and/or anti-CTLA-4) in melanoma patients. Methods: We assessed blood and stool samples of 29 cutaneous melanoma patients who received immune checkpoint inhibitor therapy. For functional and phenotypical immune analysis, 12-color flow cytometry and FluoroSpot assays were conducted. Gut microbiome was analyzed with shotgun metagenomics sequencing. To combine clinical, microbiome and immune variables, we applied the Random Forest algorithm. Results: A total of 29 patients was analyzed in this study, among whom 51.7% (n = 15) reached a durable clinical benefit. The Immune receptor TIGIT is significantly upregulated in T cells (p = 0.0139) and CD56high NK cells (p = 0.0037) of responders. Several bacterial taxa were associated with response (e.g. Ruminococcus torques) or failure (e.g. Barnesiella intestinihominis) to immune therapy. A combination of two microbiome features (Barnesiella intestinihominis and the Enterobacteriaceae family) and one immune feature (TIGIT+ CD56high NK cells) was able to predict response to ICI already at baseline (AUC = 0.85; 95% CI: 0.841–0.853). Conclusions: Our results reconfirm a link between intestinal microbiota and response to ICI therapy in melanoma patients and furthermore point to TIGIT as a promising target for future immunotherapies. [ABSTRACT FROM AUTHOR]

Background: Correlation metrics are widely utilized in genomics analysis and often implemented with little regard to assumptions of normality, homoscedasticity, and independence of values. This is especially true when comparing values between replicated sequencing experiments that probe chromatin accessibility, such as assays for transposase-accessible chromatin via sequencing (ATAC-seq). Such data can possess several regions across the human genome with little to no sequencing depth and are thus non-normal with a large portion of zero values. Despite distributed use in the epigenomics field, few studies have evaluated and benchmarked how correlation and association statistics behave across ATAC-seq experiments with known differences or the effects of removing specific outliers from the data. Here, we developed a computational simulation of ATAC-seq data to elucidate the behavior of correlation statistics and to compare their accuracy under set conditions of reproducibility. Results: Using these simulations, we monitored the behavior of several correlation statistics, including the Pearson's R and Spearman's ρ coefficients as well as Kendall's τ and Top–Down correlation. We also test the behavior of association measures, including the coefficient of determination R 2 , Kendall's W, and normalized mutual information. Our experiments reveal an insensitivity of most statistics, including Spearman's ρ , Kendall's τ , and Kendall's W, to increasing differences between simulated ATAC-seq replicates. The removal of co-zeros (regions lacking mapped sequenced reads) between simulated experiments greatly improves the estimates of correlation and association. After removing co-zeros, the R 2 coefficient and normalized mutual information display the best performance, having a closer one-to-one relationship with the known portion of shared, enhanced loci between simulated replicates. When comparing values between experimental ATAC-seq data using a random forest model, mutual information best predicts ATAC-seq replicate relationships. Conclusions: Collectively, this study demonstrates how measures of correlation and association can behave in epigenomics experiments. We provide improved strategies for quantifying relationships in these increasingly prevalent and important chromatin accessibility assays. [ABSTRACT FROM AUTHOR]

Background: The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure. Methods: The data in this paper were selected from patients with chronic heart failure who were hospitalized at the First Affiliated Hospital of Kunming Medical University, from 2017 to 2019 with cardiac function class III-IV. The dataset was explored using six different machine learning models, including logistic regression, naive Bayes, random forest classifier, extreme gradient boost, K-nearest neighbor, and decision tree. Finally, interpretable methods based on machine learning, such as SHAP value, permutation importance, and partial dependence plots, were used to estimate the 3-year all-cause mortality risk and produce individual interpretations of the model's conclusions. Result: In this paper, random forest was identified as the optimal aools lgorithm for this dataset. We also incorporated relevant machine learning interpretable tand techniques to improve disease prognosis, including permutation importance, PDP plots and SHAP values for analysis. From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure. Conclusion: The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. Machine learning in combination with permutation importance, PDP plots, and the SHAP value could offer a clear explanation of individual risk prediction and give doctors an intuitive knowledge of the functions of important model components. [ABSTRACT FROM AUTHOR]

The development of novel treatments for Progressive Supranuclear Palsy (PSP) is hindered by a knowledge gap of the impact of neurodegenerative neuropathology on brain structure and function. The current standard practice for measuring postmortem tau histology is semi-quantitative assessment, which is prone to inter-rater variability, time-consuming and difficult to scale. We developed and optimized a tau aggregate type-specific quantification pipeline for cortical and subcortical regions, in human brain donors with PSP. We quantified 4 tau objects ('neurofibrillary tangles', 'coiled bodies', 'tufted astrocytes', and 'tau fragments') using a probabilistic random forest machine learning classifier. The tau pipeline achieved high classification performance (F1-score > 0.90), comparable to neuropathologist inter-rater reliability in the held-out test set. Using 240 AT8 slides from 32 postmortem brains, the tau burden was correlated against the PSP pathology staging scheme using Spearman's rank correlation. We assessed whether clinical severity (PSP rating scale, PSPRS) score reflects neuropathological severity inferred from PSP stage and tau burden using Bayesian linear mixed regression. Tufted astrocyte density in cortical regions and coiled body density in subcortical regions showed the highest correlation to PSP stage (r = 0.62 and r = 0.38, respectively). Using traditional manual staging, only PSP patients in stage 6, not earlier stages, had significantly higher clinical severity than stage 2. Cortical tau density and neurofibrillary tangle density in subcortical regions correlated with clinical severity. Overall, our data indicate the potential for highly accurate digital tau aggregate type-specific quantification for neurodegenerative tauopathies; and the importance of studying tau aggregate type-specific burden in different brain regions as opposed to overall tau, to gain insights into the pathogenesis and progression of tauopathies. [ABSTRACT FROM AUTHOR]

Introduction: Plasmode simulations are a type of simulations that use real data to determine the synthetic data-generating equations. Such simulations thus allow evaluating statistical methods under realistic conditions. As far as we know, no plasmode algorithm has been proposed for simulating longitudinal data. In this paper, we propose a longitudinal plasmode framework to generate realistic data with both a time-varying exposure and time-varying covariates. This work was motivated by the objective of comparing different methods for estimating the causal effect of a cumulative exposure to psychosocial stressors at work over time. Methods: We developed two longitudinal plasmode algorithms: a parametric and a nonparametric algorithms. Data from the PROspective Québec (PROQ) Study on Work and Health were used as an input to generate data with the proposed plasmode algorithms. We evaluated the performance of multiple estimators of the parameters of marginal structural models (MSMs): inverse probability of treatment weighting, g-computation and targeted maximum likelihood estimation. These estimators were also compared to standard regression approaches with either adjustment for baseline covariates only or with adjustment for both baseline and time-varying covariates. Results: Standard regression methods were susceptible to yield biased estimates with confidence intervals having coverage probability lower than their nominal level. The bias was much lower and coverage of confidence intervals was much closer to the nominal level when considering MSMs. Among MSM estimators, g-computation overall produced the best results relative to bias, root mean squared error and coverage of confidence intervals. No method produced unbiased estimates with adequate coverage for all parameters in the more realistic nonparametric plasmode simulation. Conclusion: The proposed longitudinal plasmode algorithms can be important methodological tools for evaluating and comparing analytical methods in realistic simulation scenarios. To facilitate the use of these algorithms, we provide R functions on GitHub. We also recommend using MSMs when estimating the effect of cumulative exposure to psychosocial stressors at work. [ABSTRACT FROM AUTHOR]

Background: Lodging or stem bending decreases wheat yield quality and quantity. Thus, the traits reflected in early lodging wheat are helpful for early monitoring to some extent. In order to identify the superior genotypes and compare multiple linear regression (MLR) with support vector regression (SVR), artificial neural network (ANN), and random forest regression (RF) for predicting lodging in Iranian wheat accessions, a total of 228 wheat accessions were cultivated under field conditions in an alpha-lattice experiment, randomized incomplete block design, with two replications in two cropping seasons (2018–2019 and 2019–2020). To measure traits, a total of 20 plants were isolated from each plot and were measured using image processing. Results: The lodging score index (LS) had the highest positive correlation with plant height (r = 0.78**), Number of nodes (r = 0.71**), and internode length 1 (r = 0.70**). Genotypes were classified into four groups based on heat map output. The most lodging-resistant genotypes showed a lodging index of zero or close to zero. The findings revealed that the RF algorithm provided a more accurate estimate (R2 = 0.887 and RMSE = 0.091 for training data and R2 = 0.768 and RMSE = 0.124 for testing data) of wheat lodging than the ANN and SVR algorithms, and its robustness was as good as ANN but better than SVR. Conclusion: Overall, it seems that the RF model can provide a helpful predictive and exploratory tool to estimate wheat lodging in the field. This work can contribute to the adoption of managerial approaches for precise and non-destructive monitoring of lodging. [ABSTRACT FROM AUTHOR]

Background: Even for an experienced neurophysiologist, it is challenging to look at a single graph of an unlabeled motor evoked potential (MEP) and identify the corresponding muscle. We demonstrate that supervised machine learning (ML) can successfully perform this task. Methods: Intraoperative MEP data from supratentorial surgery on 36 patients was included for the classification task with 4 muscles: Extensor digitorum (EXT), abductor pollicis brevis (APB), tibialis anterior (TA) and abductor hallucis (AH). Three different supervised ML classifiers (random forest (RF), k-nearest neighbors (kNN) and logistic regression (LogReg)) were trained and tested on either raw or compressed data. Patient data was classified considering either all 4 muscles simultaneously, 2 muscles within the same extremity (EXT versus APB), or 2 muscles from different extremities (EXT versus TA). Results: In all cases, RF classifiers performed best and kNN second best. The highest performances were achieved on raw data (4 muscles 83%, EXT versus APB 89%, EXT versus TA 97% accuracy). Conclusions: Standard ML methods show surprisingly high performance on a classification task with intraoperative MEP signals. This study illustrates the power and challenges of standard ML algorithms when handling intraoperative signals and may lead to intraoperative safety improvements. [ABSTRACT FROM AUTHOR]

Background: Rapid identification of high-risk polytrauma patients is crucial for early intervention and improved outcomes. This study aimed to develop and validate machine learning models for predicting 72 h mortality in adult polytrauma patients using readily available clinical parameters. Methods: A retrospective analysis was conducted on polytrauma patients from the Dryad database and our institution. Missing values pertinent to eligible individuals within the Dryad database were compensated for through the k-nearest neighbor algorithm, subsequently randomizing them into training and internal validation factions on a 7:3 ratio. The patients of our institution functioned as external validation cohorts. The predictive efficacy of random forest (RF), neural network, and XGBoost models was assessed through an exhaustive suite of performance indicators. The SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were engaged to explain the supreme-performing model. Conclusively, restricted cubic spline analysis and multivariate logistic regression were employed as sensitivity analyses to verify the robustness of the findings. Results: Parameters including age, body mass index, Glasgow Coma Scale, Injury Severity Score, pH, base excess, and lactate emerged as pivotal predictors of 72 h mortality. The RF model exhibited unparalleled performance, boasting an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% confidence interval [CI] 0.84–0.89), an area under the precision-recall curve (AUPRC) of 0.67 (95% CI 0.61–0.73), and an accuracy of 0.83 (95% CI 0.81–0.86) in the internal validation cohort, paralleled by an AUROC of 0.98 (95% CI 0.97–0.99), an AUPRC of 0.88 (95% CI 0.83–0.93), and an accuracy of 0.97 (95% CI 0.96–0.98) in the external validation cohort. It provided the highest net benefit in the decision curve analysis in relation to the other models. The outcomes of the sensitivity examinations were congruent with those inferred from SHAP and LIME. Conclusions: The RF model exhibited the best performance in predicting 72 h mortality in adult polytrauma patients and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making. [ABSTRACT FROM AUTHOR]

Random Forests are a powerful and frequently applied Machine Learning tool. The permutation variable importance (VIMP) has been proposed to improve the explainability of such a pure prediction model. It describes the expected increase in prediction error after randomly permuting a variable and disturbing its association with the outcome. However, VIMPs measure a variable's marginal influence only, that can make its interpretation difficult or even misleading. In the present work we address the general need for improving the explainability of prediction models by exploring VIMPs in the presence of correlated variables. In particular, we propose to use a variable's residual information for investigating if its permutation importance partially or totally originates from correlated predictors. Hypotheses tests are derived by a resampling algorithm that can further support results by providing test decisions and p-values. In simulation studies we show that the proposed test controls type I error rates. When applying the methods to a Random Forest analysis of post-transplant survival after kidney transplantation, the importance of kidney donor quality for predicting post-transplant survival is shown to be high. However, the transplant allocation policy introduces correlations with other well-known predictors, which raises the concern that the importance of kidney donor quality may simply originate from these predictors. By using the proposed method, this concern is addressed and it is demonstrated that kidney donor quality plays an important role in post-transplant survival, regardless of correlations with other predictors. [ABSTRACT FROM AUTHOR]

Background: Cancer subtype classification is helpful for personalized cancer treatment. Although, some approaches have been developed to classifying caner subtype based on high dimensional gene expression data, it is difficult to obtain satisfactory classification results. Meanwhile, some cancers have been well studied and classified to some subtypes, which are adopt by most researchers. Hence, this priori knowledge is significant for further identifying new meaningful subtypes. Results: In this paper, we present a combined parallel random forest and autoencoder approach for cancer subtype identification based on high dimensional gene expression data, ForestSubtype. ForestSubtype first adopts the parallel RF and the priori knowledge of cancer subtype to train a module and extract significant candidate features. Second, ForestSubtype uses a random forest as the base module and ten parallel random forests to compute each feature weight and rank them separately. Then, the intersection of the features with the larger weights output by the ten parallel random forests is taken as our subsequent candidate features. Third, ForestSubtype uses an autoencoder to condenses the selected features into a two-dimensional data. Fourth, ForestSubtype utilizes k-means++ to obtain new cancer subtype identification results. In this paper, the breast cancer gene expression data obtained from The Cancer Genome Atlas are used for training and validation, and an independent breast cancer dataset from the Molecular Taxonomy of Breast Cancer International Consortium is used for testing. Additionally, we use two other cancer datasets for validating the generalizability of ForestSubtype. ForestSubtype outperforms the other two methods in terms of the distribution of clusters, internal and external metric results. The open-source code is available at https://github.com/lffyd/ForestSubtype. Conclusions: Our work shows that the combination of high-dimensional gene expression data and parallel random forests and autoencoder, guided by a priori knowledge, can identify new subtypes more effectively than existing methods of cancer subtype classification. [ABSTRACT FROM AUTHOR]

Background: Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) displays significant potential for applications in cancer research, especially in tumor typing and subtyping. Lung cancer is the primary cause of tumor-related deaths, where the most lethal entities are adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). Distinguishing between these two common subtypes is crucial for therapy decisions and successful patient management. Results: We propose a new algebraic topological framework, which obtains intrinsic information from MALDI data and transforms it to reflect topological persistence. Our framework offers two main advantages. Firstly, topological persistence aids in distinguishing the signal from noise. Secondly, it compresses the MALDI data, saving storage space and optimizes computational time for subsequent classification tasks. We present an algorithm that efficiently implements our topological framework, relying on a single tuning parameter. Afterwards, logistic regression and random forest classifiers are employed on the extracted persistence features, thereby accomplishing an automated tumor (sub-)typing process. To demonstrate the competitiveness of our proposed framework, we conduct experiments on a real-world MALDI dataset using cross-validation. Furthermore, we showcase the effectiveness of the single denoising parameter by evaluating its performance on synthetic MALDI images with varying levels of noise. Conclusion: Our empirical experiments demonstrate that the proposed algebraic topological framework successfully captures and leverages the intrinsic spectral information from MALDI data, leading to competitive results in classifying lung cancer subtypes. Moreover, the framework's ability to be fine-tuned for denoising highlights its versatility and potential for enhancing data analysis in MALDI applications. [ABSTRACT FROM AUTHOR]

Background: Diabetes is associated with high morbidity, mortality and quality-of-life impairment in patients. In China, the number of people suffering from diabetes ranks first in the world. Gansu Province is located in northwest China and is an economically underdeveloped region of China. By analyzing the level of health service utilization of people with diabetes in Gansu Province, the degree of equity in health service utilization and its influencing factors were studied to provide scientific data to support the promotion of health equity for people with diabetes and the introduction of relevant policies by relevant authorities. Methods: A sample of 282 people with diabetes who were 15 years old and above was chosen by multi-stage stratified sampling method. A structured questionnaire survey was conducted via face-to-face interviews. Random forest and logistic regression analysis were used to demonstrate the effects of the explanatory variables on health seeking behaviors from predisposing, enabling and need variables. The concentration index was used to indicate the equity of health service utilization across households of different economic levels. Results: The outpatient rate for the diabetic population surveyed was 92.91%, with 99.87% of urban patients, higher than the 90.39% of rural patients. The average number of hospital days per person was 3.18 days, with 5.03 days per person in urban areas, which was higher than the 2.51 days per person in rural areas. The study showed that the factors most likely to influence patients to seek outpatient services were frequency of taking diabetic medication, whether or not they were contracted to a household doctor, and living environment; the top three factors most likely to influence patients with diabetes to seek inpatient services were number of non-communicable chronic disease, self-assessment of health status, medical insurance. The concentration index for outpatient service utilization and inpatient service utilization were − 0.241 and 0.107, respectively, indicating that outpatient services were concentrated on patients at lower income levels and patients at higher income levels tended to favor inpatient services. Conclusion: This study found that the low level of health care resources available to people with diabetes, whose health status is suboptimal, makes it difficult to meet their health needs. Patients' health conditions, comorbidities of people with diabetes, and the level of protection were still important factors that hindered the use of health services. It is necessary to promote the rational use of health services by diabetic patients and further improve the corresponding policies to achieve the goal of chronic disease prevention and control in "Health China 2030". [ABSTRACT FROM AUTHOR]

Background: Polypharmacy (PP) is increasingly common in Iran, and contributes to the substantial burden of drug-related morbidity, increasing the potential for drug interactions and potentially inappropriate medications. Machine learning algorithms (ML) can be employed as an alternative solution for the prediction of PP. Therefore, our study aimed to compare several ML algorithms to predict the PP using the health insurance claims data and choose the best-performing algorithm as a predictive tool for decision-making. Methods: This population-based cross-sectional study was performed between April 2021 and March 2022. After feature selection, information about 550 thousand patients were obtained from National Center for Health Insurance Research (NCHIR). Afterwards, several ML algorithms were trained to predict PP. Finally, to assess the models' performance, the metrics derived from the confusion matrix were calculated. Results: The study sample comprised 554 133 adults with a median (IQR) age of 51 years (40 – 62) that nested in 27 cities within the Khuzestan province of Iran. Most of the patients were female (62.5%), married (63.5%), and employed (83.2%) during the last year. The prevalence of PP in all populations was about 36.0%. After performing the feature selection, out of 23 features, the number of prescriptions, Insurance coverage for prescription drugs, and hypertension were found as the top three predictors. Experimental results showed that Random Forest (RF) performed better than other ML algorithms with recall, specificity, accuracy, precision and F1-score of 63.92%, 89.92%, 79.99%, 63.92% and 63.92% respectively. Conclusion: It was found that ML provides a reasonable level of accuracy in predicting polypharmacy. Therefore, the prediction models based on ML, especially the RF algorithm, performed better than other methods for predicting PP in Iranian people in terms of the performance criteria. [ABSTRACT FROM AUTHOR]

Background: Machine learning tools such as random forests provide important opportunities for modeling large, complex modern data generated in medicine. Unfortunately, when it comes to understanding why machine learning models are predictive, applied research continues to rely on 'out of bag' (OOB) variable importance metrics (VIMPs) that are known to have considerable shortcomings within the statistics community. After explaining the limitations of OOB VIMPs – including bias towards correlated features and limited interpretability – we describe a modern approach called 'knockoff VIMPs' and explain its advantages. Methods: We first evaluate current VIMP practices through an in-depth literature review of 50 recent random forest manuscripts. Next, we recommend organized and interpretable strategies for analysis with knockoff VIMPs, including computing them for groups of features and considering multiple model performance metrics. To demonstrate methods, we develop a random forest to predict 5-year incident stroke in the Sleep Heart Health Study and compare results based on OOB and knockoff VIMPs. Results: Nearly all papers in the literature review contained substantial limitations in their use of VIMPs. In our demonstration, using OOB VIMPs for individual variables suggested two highly correlated lung function variables (forced expiratory volume, forced vital capacity) as the best predictors of incident stroke, followed by age and height. Using an organized analytic approach that considered knockoff VIMPs of both groups of features and individual features, the largest contributions to model sensitivity were medications (especially cardiovascular) and measured medical risk factors, while the largest contributions to model specificity were age, diastolic blood pressure, self-reported medical risk factors, polysomnography features, and pack-years of smoking. Thus, we reach very different conclusions about stroke risk factors using OOB VIMPs versus knockoff VIMPs. Conclusions: The near-ubiquitous reliance on OOB VIMPs may provide misleading results for researchers who use such methods to guide their research. Given the rapid pace of scientific inquiry using machine learning, it is essential to bring modern knockoff VIMPs that are interpretable and unbiased into widespread applied practice to steer researchers using random forest machine learning toward more meaningful results. [ABSTRACT FROM AUTHOR]

Background: Diabetic kidney disease (DKD) is a severe complication of diabetes. Currently, no effective measures are available to reduce the risk of DKD progression. This study aimed to establish a weighted risk model to determine DKD progression and provide effective treatment strategies. Methods: This was a hospital-based, cross-sectional study. A total of 1104 patients with DKD were included in this study. The random forest method was used to develop weighted risk models to assess DKD progression. Receiver operating characteristic curves were used to validate the models and calculate the optimal cutoff values for important risk factors. Results: We developed potent weighted risk models to evaluate DKD progression. The top six risk factors for DKD progression to chronic kidney disease were hemoglobin, hemoglobin A1c (HbA1c), serum uric acid (SUA), plasma fibrinogen, serum albumin, and neutrophil percentage. The top six risk factors for determining DKD progression to dialysis were hemoglobin, HbA1c, neutrophil percentage, serum albumin, duration of diabetes, and plasma fibrinogen level. Furthermore, the optimal cutoff values of hemoglobin and HbA1c for determining DKD progression were 112 g/L and 7.2%, respectively. Conclusion: We developed potent weighted risk models for DKD progression that can be employed to formulate precise therapeutic strategies. Monitoring and controlling combined risk factors and prioritizing interventions for key risk factors may help reduce the risk of DKD progression. [ABSTRACT FROM AUTHOR]

Background: Polypharmacy (PP) is increasingly common in Iran, and contributes to the substantial burden of drug-related morbidity, increasing the potential for drug interactions and potentially inappropriate medications. Machine learning algorithms (ML) can be employed as an alternative solution for the prediction of PP. Therefore, our study aimed to compare several ML algorithms to predict the PP using the health insurance claims data and choose the best-performing algorithm as a predictive tool for decision-making. Methods: This population-based cross-sectional study was performed between April 2021 and March 2022. After feature selection, information about 550 thousand patients were obtained from National Center for Health Insurance Research (NCHIR). Afterwards, several ML algorithms were trained to predict PP. Finally, to assess the models' performance, the metrics derived from the confusion matrix were calculated. Results: The study sample comprised 554 133 adults with a median (IQR) age of 51 years (40 – 62) that nested in 27 cities within the Khuzestan province of Iran. Most of the patients were female (62.5%), married (63.5%), and employed (83.2%) during the last year. The prevalence of PP in all populations was about 36.0%. After performing the feature selection, out of 23 features, the number of prescriptions, Insurance coverage for prescription drugs, and hypertension were found as the top three predictors. Experimental results showed that Random Forest (RF) performed better than other ML algorithms with recall, specificity, accuracy, precision and F1-score of 63.92%, 89.92%, 79.99%, 63.92% and 63.92% respectively. Conclusion: It was found that ML provides a reasonable level of accuracy in predicting polypharmacy. Therefore, the prediction models based on ML, especially the RF algorithm, performed better than other methods for predicting PP in Iranian people in terms of the performance criteria. [ABSTRACT FROM AUTHOR]

Background: Self-perceived general health (SPGH) is a general health indicator commonly used in epidemiological research and is associated with a wide range of exposures from different domains. However, most studies on SPGH only investigated a limited set of exposures and did not take the entire external exposome into account. We aimed to develop predictive models for SPGH based on exposome datasets using machine learning techniques and identify the most important predictors of poor SPGH status. Methods: Random forest (RF) was used on two datasets based on personal characteristics from the 2012 and 2016 editions of the Dutch national health survey, enriched with environmental and neighborhood characteristics. Model performance was determined using the area under the curve (AUC) score. The most important predictors were identified using a variable importance procedure and individual effects of exposures using partial dependence and accumulated local effect plots. The final 2012 dataset contained information on 199,840 individuals and 81 variables, whereas the final 2016 dataset had 244,557 individuals with 91 variables. Results: Our RF models had overall good predictive performance (2012: AUC = 0.864 (CI: 0.852–0.876); 2016: AUC = 0.890 (CI: 0.883–0.896)) and the most important predictors were "Control of own life", "Physical activity", "Loneliness" and "Making ends meet". Subjects who felt insufficiently in control of their own life, scored high on the De Jong-Gierveld loneliness scale or had difficulty in making ends meet were more likely to have poor SPGH status, whereas increased physical activity per week reduced the probability of poor SPGH. We observed associations between some neighborhood and environmental characteristics, but these variables did not contribute to the overall predictive strength of the models. Conclusions: This study identified that within an external exposome dataset, the most important predictors for SPGH status are related to mental wellbeing, physical exercise, loneliness, and financial status. [ABSTRACT FROM AUTHOR]

Background: Epilepsy is a neurological disorder that is usually detected by electroencephalogram (EEG) signals. Since manual examination of epilepsy seizures is a laborious and time-consuming process, lots of automatic epilepsy detection algorithms have been proposed. However, most of the available classification algorithms for epilepsy EEG signals adopted a single feature extraction, in turn to result in low classification accuracy. Although a small account of studies have carried out feature fusion, the computational efficiency is reduced due to too many features, because there are also some poor features that interfere with the classification results. Methods: In order to solve the above problems, an automatic recognition method of epilepsy EEG signals based on feature fusion and selection is proposed in this paper. Firstly, the Approximate Entropy (ApEn), Fuzzy Entropy (FuzzyEn), Sample Entropy (SampEn), and Standard Deviation (STD) mixed features of the subband obtained by the Discrete Wavelet Transform (DWT) decomposition of EEG signals are extracted. Secondly, the random forest algorithm is used for feature selection. Finally, the Convolutional Neural Network (CNN) is used to classify epilepsy EEG signals. Results: The empirical evaluation of the presented algorithm is performed on the benchmark Bonn EEG datasets and New Delhi datasets. In the interictal and ictal classification tasks of Bonn datasets, the proposed model achieves an accuracy of 99.9%, a sensitivity of 100%, a precision of 99.81%, and a specificity of 99.8%. For the interictal-ictal case of New Delhi datasets, the proposed model achieves a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a precision of 100%. Conclusion: The proposed model can effectively realize the high-precision automatic detection and classification of epilepsy EEG signals. This model can provide high-precision automatic detection capability for clinical epilepsy EEG detection. We hope to provide positive implications for the prediction of seizure EEG. [ABSTRACT FROM AUTHOR]

Background: Polypharmacy (PP) is increasingly common in Iran, and contributes to the substantial burden of drug-related morbidity, increasing the potential for drug interactions and potentially inappropriate medications. Machine learning algorithms (ML) can be employed as an alternative solution for the prediction of PP. Therefore, our study aimed to compare several ML algorithms to predict the PP using the health insurance claims data and choose the best-performing algorithm as a predictive tool for decision-making. Methods: This population-based cross-sectional study was performed between April 2021 and March 2022. After feature selection, information about 550 thousand patients were obtained from National Center for Health Insurance Research (NCHIR). Afterwards, several ML algorithms were trained to predict PP. Finally, to assess the models' performance, the metrics derived from the confusion matrix were calculated. Results: The study sample comprised 554 133 adults with a median (IQR) age of 51 years (40 – 62) that nested in 27 cities within the Khuzestan province of Iran. Most of the patients were female (62.5%), married (63.5%), and employed (83.2%) during the last year. The prevalence of PP in all populations was about 36.0%. After performing the feature selection, out of 23 features, the number of prescriptions, Insurance coverage for prescription drugs, and hypertension were found as the top three predictors. Experimental results showed that Random Forest (RF) performed better than other ML algorithms with recall, specificity, accuracy, precision and F1-score of 63.92%, 89.92%, 79.99%, 63.92% and 63.92% respectively. Conclusion: It was found that ML provides a reasonable level of accuracy in predicting polypharmacy. Therefore, the prediction models based on ML, especially the RF algorithm, performed better than other methods for predicting PP in Iranian people in terms of the performance criteria. [ABSTRACT FROM AUTHOR]

Background: Polycyclic aromatic hydrocarbon (PAH) contamination has been a worldwide environmental issue because of its impact on ecosystems and human health. Biodegradation plays an important role in PAH removal in natural environments. To date, many PAH-degrading strains and degradation genes have been reported. However, a comprehensive PAH-degrading gene database is still lacking, hindering a deep understanding of PAH degraders in the era of big data. Furthermore, the relationships between the PAH-catabolic genotype and phenotype remain unclear. Results: Here, we established a bacterial PAH-degrading gene database and explored PAH biodegradation capability via a genome-function relationship approach. The investigation of functional genes in the experimentally verified PAH degraders indicated that genes encoding hydratase-aldolase could serve as a biomarker for preliminarily identifying potential degraders. Additionally, a genome-centric interpretation of PAH-degrading genes was performed in the public genome database, demonstrating that they were ubiquitous in Proteobacteria and Actinobacteria. Meanwhile, the global phylogenetic distribution was generally consistent with the culture-based evidence. Notably, a few strains affiliated with the genera without any previously known PAH degraders (Hyphomonas, Hoeflea, Henriciella, Saccharomonospora, Sciscionella, Tepidiphilus, and Xenophilus) also bore a complete PAH-catabolic gene cluster, implying their potential of PAH biodegradation. Moreover, a random forest analysis was applied to predict the PAH-degrading trait in the complete genome database, revealing 28 newly predicted PAH degraders, of which nine strains encoded a complete PAH-catabolic pathway. Conclusions: Our results established a comprehensive PAH-degrading gene database and a genome-function relationship approach, which revealed several potential novel PAH-degrader lineages. Importantly, this genome-centric and function-oriented approach can overcome the bottleneck of conventional cultivation-based biodegradation research and substantially expand our current knowledge on the potential degraders of environmental pollutants. [ABSTRACT FROM AUTHOR]

Background: This study aimed to develop and externally validate prediction models of spinal surgery outcomes based on a retrospective review of a prospective clinical database, uniquely comparing multivariate regression and random forest (machine learning) approaches, and identifying the most important predictors. Methods: Outcomes were change in back and leg pain intensity and Core Outcome Measures Index (COMI) from baseline to the last available postoperative follow-up (3–24 months), defined as minimal clinically important change (MCID) and continuous change score. Eligible patients underwent lumbar spine surgery for degenerative pathology between 2011 and 2021. Data were split by surgery date into development (N = 2691) and validation (N = 1616) sets for temporal external validation. Multivariate logistic and linear regression, and random forest classification and regression models, were fit to the development data and validated on the external data. Results: All models demonstrated good calibration in the validation data. Discrimination ability (area under the curve) for MCID ranged from 0.63 (COMI) to 0.72 (back pain) in regression, and from 0.62 (COMI) to 0.68 (back pain) in random forests. The explained variation in continuous change scores spanned 16%-28% in linear, and 15%-25% in random forests regression. The most important predictors included age, baseline scores on the respective outcome measures, type of degenerative pathology, previous spinal surgeries, smoking status, morbidity, and duration of hospital stay. Conclusions: The developed models appear robust and generalisable across different outcomes and modelling approaches but produced only borderline acceptable discrimination ability, suggesting the need to assess further prognostic factors. External validation showed no advantage of the random forest approach. [ABSTRACT FROM AUTHOR]

Objective: To investigate the relationship between physical activity and the severity of menopausal symptoms in middle-aged women in northwest China. Methods: This was a cross-sectional online survey study. Using a snowball sampling method, 468 women aged 45 to 60 were recruited from northwest China and their demographic information was collected. The modified Kupperman Menopausal Index scale and International Physical Activity Questionnaire short form were used in this study. Random forest was used to rank the importance of variables and select the optimal combination. The direction and relative risk (odds ratio value) of selected variables were further explained with an ordinal logistic regression model. Results: The prevalence of menopausal syndromes was 74.8% and more than one-half of the participants had moderate or severe symptoms (54.3%). The Mantel-Haenszel linear-by-linear chi-square test showed a strong and negative correlation between physical activity level and the severity of menopausal symptoms (P < 0.001). Random forest demonstrated that the physical activity level was the most significant variable associated with the severity of menopausal symptoms. Multiple random forest regressions showed that the out-of-bag error rate reaches the minimum when the top 4 variables (physical activity level, menopausal status, perceived health status, and parity) in the importance ranking form an optimal variable combination. Ordinal logistic regression analysis showed that a higher physical activity level and a satisfactory perceived health status might be protective factors for menopausal symptoms (odds ratio (OR) < 1, P < 0.001); whereas perimenopausal or postmenopausal status and 2 parities might be risk factors for menopausal symptoms (OR > 1, P < 0.001). Conclusions: There is a strong negative correlation between physical activity and the severity of menopausal symptoms. The results have a clinical implication that the menopausal symptoms may be improved by the moderate-to-high level physical activity in the lives of middle-aged women. [ABSTRACT FROM AUTHOR]

Background: Using texture features derived from contrast-enhanced computed tomography (CT) combined with general imaging features as well as clinical information to predict treatment response and survival in patients with hepatocellular carcinoma (HCC) who received transarterial chemoembolization (TACE) treatment. Methods: From January 2014 to November 2022, 289 patients with HCC who underwent TACE were retrospectively reviewed. Their clinical information was documented. Their treatment-naïve contrast-enhanced CTs were retrieved and reviewed by two independent radiologists. Four general imaging features were evaluated. Texture features were extracted based on the regions of interest (ROIs) drawn on the slice with the largest axial diameter of all lesions using Pyradiomics v3.0.1. After excluding features with low reproducibility and low predictive value, the remaining features were selected for further analyses. The data were randomly divided in a ratio of 8:2 for model training and testing. Random forest classifiers were built to predict patient response to TACE treatment. Random survival forest models were constructed to predict overall survival (OS) and progress-free survival (PFS). Results: We retrospectively evaluated 289 patients (55.4 ± 12.4 years old) with HCC treated with TACE. Twenty features, including 2 clinical features (ALT and AFP levels), 1 general imaging feature (presence or absence of portal vein thrombus) and 17 texture features, were included in model construction. The random forest classifier achieved an area under the curve (AUC) of 0.947 with an accuracy of 89.5% for predicting treatment response. The random survival forest showed good predictive performance with out-of-bag error rate of 0.347 (0.374) and a continuous ranked probability score (CRPS) of 0.170 (0.067) for the prediction of OS (PFS). Conclusions: Random forest algorithm based on texture features combined with general imaging features and clinical information is a robust method for predicting prognosis in patients with HCC treated with TACE, which may help avoid additional examinations and assist in treatment planning. [ABSTRACT FROM AUTHOR]

Background: Acute oral toxicity of drug candidates can lead to drug development failure; thus, predicting the acute oral toxicity of small compounds is important for successful drug development. However, evaluation of the acute oral toxicity of small compounds considered in the early stages of drug discovery is limited because of cost and time. Here, we developed a computational framework, PredAOT, that predicts the acute oral toxicity of small compounds in mice and rats. Methods: PredAOT is based on multiple random forest models for the accurate prediction of acute oral toxicity. A total of 6226 and 6238 compounds evaluated in mice and rats, respectively, were used to train the models. Results: PredAOT has the advantage of predicting acute oral toxicity in mice and rats simultaneously, and its prediction performance is similar to or better than that of existing tools. Conclusion: PredAOT will be a useful tool for the quick and accurate prediction of the acute oral toxicity of small compounds in mice and rats during drug development. [ABSTRACT FROM AUTHOR]

Background: Ponerine ants are almost exclusively predatory and comprise many of the largest known ant species. Within this clade, the genus Neoponera is among the most conspicuous Neotropical predators. We describe the first fossil member of this lineage: a worker preserved in Miocene-age Dominican amber from Hispaniola. Results: Neoponera vejestoria sp. nov. demonstrates a clear case of local extinction—there are no known extant Neoponera species in the Greater Antilles. The species is attributable to an extant and well-defined species group in the genus, which suggests the group is older than previously estimated. Through CT scan reconstruction and linear morphometrics, we reconstruct the morphospace of extant and fossil ants to evaluate the history and evolution of predatory taxa in this island system. Conclusions: The fossil attests to a shift in insular ecological community structure since the Miocene. The largest predatory taxa have undergone extinction on the island, but their extant relatives persist throughout the Neotropics. Neoponera vejestoria sp. nov. is larger than all other predatory ant workers known from Hispaniola, extant or extinct. Our results empirically demonstrate the loss of a functional niche associated with body size, which is a trait long hypothesized to be related to extinction risk. [ABSTRACT FROM AUTHOR]

Background: Mild cognitive impairment (MCI) has been thought of as the transitional stage between normal ageing and Alzheimer's disease, involving substantial changes in brain grey matter structures. As most previous studies have focused on single regions (e.g. the hippocampus) and their changes during MCI development and reversion, the relationship between grey matter covariance among distributed brain regions and clinical development and reversion of MCI remains unclear. Methods: With samples from two independent studies (155 from the Beijing Aging Brain Rejuvenation Initiative and 286 from the Alzheimer's Disease Neuroimaging Initiative), grey matter covariance of default, frontoparietal, and hippocampal networks were identified by seed-based partial least square analyses, and random forest models were applied to predict the progression from normal cognition to MCI (N-t-M) and the reversion from MCI to normal cognition (M-t-N). Results: With varying degrees, the grey matter covariance in the three networks could predict N-t-M progression (AUC = 0.692–0.792) and M-t-N reversion (AUC = 0.701–0.809). Further analyses indicated that the hippocampus has emerged as an important region in reversion prediction within all three brain networks, and even though the hippocampus itself could predict the clinical reversion of M-t-N, the grey matter covariance showed higher prediction accuracy for early progression of N-t-M. Conclusions: Our findings are the first to report grey matter covariance changes in MCI development and reversion and highlight the necessity of including grey matter covariance changes along with hippocampal degeneration in the early detection of MCI and Alzheimer's disease. [ABSTRACT FROM AUTHOR]

Background: There is increasing interest in clinical prediction models for rare outcomes such as suicide, psychiatric hospitalizations, and opioid overdose. Accurate model validation is needed to guide model selection and decisions about whether and how prediction models should be used. Split-sample estimation and validation of clinical prediction models, in which data are divided into training and testing sets, may reduce predictive accuracy and precision of validation. Using all data for estimation and validation increases sample size for both procedures, but validation must account for overfitting, or optimism. Our study compared split-sample and entire-sample methods for estimating and validating a suicide prediction model. Methods: We compared performance of random forest models estimated in a sample of 9,610,318 mental health visits ("entire-sample") and in a 50% subset ("split-sample") as evaluated in a prospective validation sample of 3,754,137 visits. We assessed optimism of three internal validation approaches: for the split-sample prediction model, validation in the held-out testing set and, for the entire-sample model, cross-validation and bootstrap optimism correction. Results: The split-sample and entire-sample prediction models showed similar prospective performance; the area under the curve, AUC, and 95% confidence interval was 0.81 (0.77–0.85) for both. Performance estimates evaluated in the testing set for the split-sample model (AUC = 0.85 [0.82–0.87]) and via cross-validation for the entire-sample model (AUC = 0.83 [0.81–0.85]) accurately reflected prospective performance. Validation of the entire-sample model with bootstrap optimism correction overestimated prospective performance (AUC = 0.88 [0.86–0.89]). Measures of classification accuracy, including sensitivity and positive predictive value at the 99th, 95th, 90th, and 75th percentiles of the risk score distribution, indicated similar conclusions: bootstrap optimism correction overestimated classification accuracy in the prospective validation set. Conclusions: While previous literature demonstrated the validity of bootstrap optimism correction for parametric models in small samples, this approach did not accurately validate performance of a rare-event prediction model estimated with random forests in a large clinical dataset. Cross-validation of prediction models estimated with all available data provides accurate independent validation while maximizing sample size. [ABSTRACT FROM AUTHOR]

Background: In individuals or animals suffering from genetic or acquired diseases, it is important to identify which clinical or phenotypic variables can be used to discriminate between disease and non-disease states, the response to treatments or sexual dimorphism. However, the data often suffers from low number of samples, high number of variables or unbalanced experimental designs. Moreover, several parameters can be recorded in the same test. Thus, correlations should be assessed, and a more complex statistical framework is necessary for the analysis. Packages already exist that provide analysis tools, but they are not found together, rendering the decision method and implementation difficult for non-statisticians. Result: We present Gdaphen, a fast joint-pipeline allowing the identification of most important qualitative and quantitative predictor variables to discriminate between genotypes, treatments, or sex. Gdaphen takes as input behavioral/clinical data and uses a Multiple Factor Analysis (MFA) to deal with groups of variables recorded from the same individuals or anonymize genotype-based recordings. Gdaphen uses as optimized input the non-correlated variables with 30% correlation or higher on the MFA-Principal Component Analysis (PCA), increasing the discriminative power and the classifier's predictive model efficiency. Gdaphen can determine the strongest variables that predict gene dosage effects thanks to the General Linear Model (GLM)-based classifiers or determine the most discriminative not linear distributed variables thanks to Random Forest (RF) implementation. Moreover, Gdaphen provides the efficacy of each classifier and several visualization options to fully understand and support the results as easily readable plots ready to be included in publications. We demonstrate Gdaphen capabilities on several datasets and provide easily followable vignettes. Conclusions: Gdaphen makes the analysis of phenotypic data much easier for medical or preclinical behavioral researchers, providing an integrated framework to perform: (1) pre-processing steps as data imputation or anonymization; (2) a full statistical assessment to identify which variables are the most important discriminators; and (3) state of the art visualizations ready for publication to support the conclusions of the analyses. Gdaphen is open-source and freely available at https://github.com/munizmom/gdaphen, together with vignettes, documentation for the functions and examples to guide you in each own implementation. [ABSTRACT FROM AUTHOR]

Background: The use of machine learning has the potential to estimate the probability of a second classification event more accurately than traditional statistical methods, and few previous studies on predicting new fractures after osteoporotic vertebral compression fractures (OVCFs) have focussed on this point. The aim of this study was to explore whether several different machine learning models could produce better predictions than logistic regression models and to select an optimal model. Methods: A retrospective analysis of 529 patients who underwent percutaneous kyphoplasty (PKP) for OVCFs at our institution between June 2017 and June 2020 was performed. The patient data were used to create machine learning (including decision trees (DT), random forests (RF), support vector machines (SVM), gradient boosting machines (GBM), neural networks (NNET), and regularized discriminant analysis (RDA)) and logistic regression models (LR) to estimate the probability of new fractures occurring after surgery. The dataset was divided into a training set (75%) and a test set (25%), and machine learning models were built in the training set after ten cross-validations, after which each model was evaluated in the test set, and model performance was assessed by comparing the area under the curve (AUC) of each model. Results: Among the six machine learning algorithms, except that the AUC of DT [0.775 (95% CI 0.728–0.822)] was lower than that of LR [0.831 (95% CI 0.783–0.878)], RA [0.953 (95% CI 0.927–0.980)], GBM [0.941 (95% CI 0.911–0.971)], SVM [0.869 (95% CI 0.827–0.910), NNET [0.869 (95% CI 0.826–0.912)], and RDA [0.890 (95% CI 0.851–0.929)] were all better than LR. Conclusions: For prediction of the probability of new fracture after PKP, machine learning algorithms outperformed logistic regression, with random forest having the strongest predictive power. Highlights: Machine learning significantly outperformed logistic regression models in predicting new fractures after osteoporotic vertebral compression fractures. The random forest model performs best among these machine learning models. [ABSTRACT FROM AUTHOR]