Search

In intensive care unit (ICU) patients undergoing mechanical ventilation (MV), the occurrence of difficult weaning contributes to increased ventilator-related complications, prolonged hospitalization duration, and a significant rise in healthcare costs. Therefore, early identification of influencing factors and prediction of patients at risk of difficult weaning can facilitate early intervention and preventive measures. This study aimed to strengthen airway management for ICU patients by constructing a risk prediction model with comprehensive and individualized offline programs based on machine learning techniques. This study involved the collection of data from 487 patients undergoing MV in the ICU, with a total of 36 variables recorded. The dataset was divided into a training set (70% of the data) and a test set (30% of the data). Five machine learning models, namely logistic regression, random forest, support vector machine, light gradient boosting machine, and extreme gradient boosting, were compared to predict the risk of difficult weaning in ICU patients with MV. Significant influencing factors were identified based on the results of these models, and a risk prediction model for ICU patients with MV was established. When evaluating the models using AUC (Area under the Curve of ROC) and Accuracy as performance metrics, the Random Forest algorithm exhibited the best performance among the five machine learning algorithms. The area under the operating characteristic curve for the subjects was 0.805, with an accuracy of 0.748, recall (0.888), specificity (0.767) and F1 score (0.825). This study successfully developed a risk prediction model for ICU patients with MV using a machine learning algorithm. The Random Forest algorithm demonstrated the highest prediction performance. These findings can assist clinicians in accurately assessing the risk of difficult weaning in patients and formulating effective individualized treatment plans. Ultimately, this can help reduce the risk of difficult weaning and improve the quality of life for patients. [ABSTRACT FROM AUTHOR]

Deep vein thrombosis (DVT) is a common complication in patients with lower extremity fractures. Once it occurs, it will seriously affect the quality of life and postoperative recovery of patients. Therefore, early prediction and prevention of DVT can effectively improve the prognosis of patients. This study constructed different machine learning models to explore their effectiveness in predicting DVT. Five prediction models were applied to the study, including Extreme Gradient Boosting (XGBoost) model, Logistic Regression (LR) model, RandomForest (RF) model, Multilayer Perceptron (MLP) model, and Support Vector Machine (SVM) model. Afterwards, the performance of the obtained prediction models was evaluated by area under the curve (AUC), accuracy, sensitivity, specificity, F1 score, and Kappa. The prediction performances of the models based on machine learning are as follows: XGBoost model (AUC = 0.979, accuracy = 0.931), LR model (AUC = 0.821, accuracy = 0.758), RF model (AUC = 0.970, accuracy = 0.921), MLP model (AUC = 0.830, accuracy = 0.756), SVM model (AUC = 0.713, accuracy = 0.661). On our data set, the XGBoost model has the best performance. However, the model still needs external verification research before clinical application. [ABSTRACT FROM AUTHOR]

Patients with parathyroid carcinoma (PC) are often diagnosed postoperatively, due to incomplete resection during the initial surgery, resulting in poor outcomes. The aim of our study was to investigate the pre-surgery indicators of PC and try to develop a predictive model for PC utilizing machine learning. Evaluation of pre-surgery neuropsychological function and confirmation of pathology were carried out in 133 patients with primary hyperparathyroidism in Beijing Chaoyang Hospital from December 2019 to January 2023. Patients were randomly divided into a training cohort (n = 93) and a validating cohort (n = 40). Analysis of the clinical dataset, two machine learning including the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression were utilized to develop the prediction model for PC. Logistic regression analysis was also conducted for comparison. Significant differences in elevated parathyroid hormone and decreased serum phosphorus in PC compared to (BP). The lower score of MMSE and MOCA was observed in PC and a cutoff of MMSE < 24 was the optimal threshold to stratify PC from BP (area under the curve AUC 0.699 vs 0.625). The predicted probability of PC by machine learning was similar to the observed probability in the test set, whereas the logistic model tended to overpredict the possibility of PC. The XGBoost model attained a higher AUC than the logistic algorithms and LASSO models. (0.835 vs 0.683 vs 0.607). Preoperative cognitive function may be a probable predictor for PC. The cognitive function-based prediction model based on the XGBoost algorithm outperformed LASSO and logistic regression, providing valuable preoperative assistance to surgeons in clinical decision-making for patients suspected PC. [ABSTRACT FROM AUTHOR]

The behavioral and psychological symptoms of dementia (BPSD) are challenging aspects of dementia care. This study used machine learning models to predict the occurrence of BPSD among community-dwelling older adults with dementia. We included 187 older adults with dementia for model training and 35 older adults with dementia for external validation. Demographic and health data and premorbid personality traits were examined at the baseline, and actigraphy was utilized to monitor sleep and activity levels. A symptom diary tracked caregiver-perceived symptom triggers and the daily occurrence of 12 BPSD classified into seven subsyndromes. Several prediction models were also employed, including logistic regression, random forest, gradient boosting machine, and support vector machine. The random forest models revealed the highest area under the receiver operating characteristic curve (AUC) values for hyperactivity, euphoria/elation, and appetite and eating disorders; the gradient boosting machine models for psychotic and affective symptoms; and the support vector machine model showed the highest AUC. The gradient boosting machine model achieved the best performance in terms of average AUC scores across the seven subsyndromes. Caregiver-perceived triggers demonstrated higher feature importance values across the seven subsyndromes than other features. Our findings demonstrate the possibility of predicting BPSD using a machine learning approach. [ABSTRACT FROM AUTHOR]

We sought to verify the reliability of machine learning (ML) in developing diabetes prediction models by utilizing big data. To this end, we compared the reliability of gradient boosting decision tree (GBDT) and logistic regression (LR) models using data obtained from the Kokuho-database of the Osaka prefecture, Japan. To develop the models, we focused on 16 predictors from health checkup data from April 2013 to December 2014. A total of 277,651 eligible participants were studied. The prediction models were developed using a light gradient boosting machine (LightGBM), which is an effective GBDT implementation algorithm, and LR. Their reliabilities were measured based on expected calibration error (ECE), negative log-likelihood (Logloss), and reliability diagrams. Similarly, their classification accuracies were measured in the area under the curve (AUC). We further analyzed their reliabilities while changing the sample size for training. Among the 277,651 participants, 15,900 (7978 males and 7922 females) were newly diagnosed with diabetes within 3 years. LightGBM (LR) achieved an ECE of 0.0018 ± 0.00033 (0.0048 ± 0.00058), a Logloss of 0.167 ± 0.00062 (0.172 ± 0.00090), and an AUC of 0.844 ± 0.0025 (0.826 ± 0.0035). From sample size analysis, the reliability of LightGBM became higher than LR when the sample size increased more than 10 4 . Thus, we confirmed that GBDT provides a more reliable model than that of LR in the development of diabetes prediction models using big data. ML could potentially produce a highly reliable diabetes prediction model, a helpful tool for improving lifestyle and preventing diabetes. [ABSTRACT FROM AUTHOR]

HIV treatment programs face challenges in identifying patients at risk for loss-to-follow-up and uncontrolled viremia. We applied predictive machine learning algorithms to anonymised, patient-level HIV programmatic data from two districts in South Africa, 2016–2018. We developed patient risk scores for two outcomes: (1) visit attendance ≤ 28 days of the next scheduled clinic visit and (2) suppression of the next HIV viral load (VL). Demographic, clinical, behavioral and laboratory data were investigated in multiple models as predictor variables of attending the next scheduled visit and VL results at the next test. Three classification algorithms (logistical regression, random forest and AdaBoost) were evaluated for building predictive models. Data were randomly sampled on a 70/30 split into a training and test set. The training set included a balanced set of positive and negative examples from which the classification algorithm could learn. The predictor variable data from the unseen test set were given to the model, and each predicted outcome was scored against known outcomes. Finally, we estimated performance metrics for each model in terms of sensitivity, specificity, positive and negative predictive value and area under the curve (AUC). In total, 445,636 patients were included in the retention model and 363,977 in the VL model. The predictive metric (AUC) ranged from 0.69 for attendance at the next scheduled visit to 0.76 for VL suppression, suggesting that the model correctly classified whether a scheduled visit would be attended in 2 of 3 patients and whether the VL result at the next test would be suppressed in approximately 3 of 4 patients. Variables that were important predictors of both outcomes included prior late visits, number of prior VL tests, time since their last visit, number of visits on their current regimen, age, and treatment duration. For retention, the number of visits at the current facility and the details of the next appointment date were also predictors, while for VL suppression, other predictors included the range of the previous VL value. Machine learning can identify HIV patients at risk for disengagement and unsuppressed VL. Predictive modeling can improve the targeting of interventions through differentiated models of care before patients disengage from treatment programmes, increasing cost-effectiveness and improving patient outcomes. [ABSTRACT FROM AUTHOR]

An accurate prediction of major adverse events after percutaneous coronary intervention (PCI) improves clinical decisions and specific interventions. To determine whether machine learning (ML) techniques predict peri-PCI adverse events [acute kidney injury (AKI), bleeding, and in-hospital mortality] with better discrimination or calibration than the National Cardiovascular Data Registry (NCDR-CathPCI) risk scores, we developed logistic regression and gradient descent boosting (XGBoost) models for each outcome using data from a prospective, all-comer, multicenter registry that enrolled consecutive coronary artery disease patients undergoing PCI in Japan between 2008 and 2020. The NCDR-CathPCI risk scores demonstrated good discrimination for each outcome (C-statistics of 0.82, 0.76, and 0.95 for AKI, bleeding, and in-hospital mortality) with considerable calibration. Compared with the NCDR-CathPCI risk scores, the XGBoost models modestly improved discrimination for AKI and bleeding (C-statistics of 0.84 in AKI, and 0.79 in bleeding) but not for in-hospital mortality (C-statistics of 0.96). The calibration plot demonstrated that the XGBoost model overestimated the risk for in-hospital mortality in low-risk patients. All of the original NCDR-CathPCI risk scores for adverse periprocedural events showed adequate discrimination and calibration within our cohort. When using the ML-based technique, however, the improvement in the overall risk prediction was minimal. [ABSTRACT FROM AUTHOR]

In this study, we aimed to propose a novel diabetes index for the risk classification based on machine learning techniques with a high accuracy for diabetes mellitus. Upon analyzing their demographic and biochemical data, we classified the 2013–16 Korea National Health and Nutrition Examination Survey (KNHANES), the 2017–18 KNHANES, and the Korean Genome and Epidemiology Study (KoGES), as the derivation, internal validation, and external validation sets, respectively. We constructed a new diabetes index using logistic regression (LR) and calculated the probability of diabetes in the validation sets. We used the area under the receiver operating characteristic curve (AUROC) and Cox regression analysis to measure the performance of the internal and external validation sets, respectively. We constructed a gender-specific diabetes prediction model, having a resultant AUROC of 0.93 and 0.94 for men and women, respectively. Based on this probability, we classified participants into five groups and analyzed cumulative incidence from the KoGES dataset. Group 5 demonstrated significantly worse outcomes than those in other groups. Our novel model for predicting diabetes, based on two large-scale population-based cohort studies, showed high sensitivity and selectivity. Therefore, our diabetes index can be used to classify individuals at high risk of diabetes. [ABSTRACT FROM AUTHOR]

Increasing recognition of anatomical obstruction has resulted in a large variety of sleep surgeries to improve anatomic collapse of obstructive sleep apnea (OSA) and the prediction of whether sleep surgery will have successful outcome is very important. The aim of this study is to assess a machine learning-based clinical model that predict the success rate of sleep surgery in OSA subjects. The predicted success rate from machine learning and the predicted subjective surgical outcome from the physician were compared with the actual success rate in 163 male dominated-OSA subjects. Predicted success rate of sleep surgery from machine learning models based on sleep parameters and endoscopic findings of upper airway demonstrated higher accuracy than subjective predicted value of sleep surgeon. The gradient boosting model showed the best performance to predict the surgical success that is evaluated by pre- and post-operative polysomnography or home sleep apnea testing among the logistic regression and three machine learning models, and the accuracy of gradient boosting model (0.708) was significantly higher than logistic regression model (0.542). Our data demonstrate that the data mining-driven prediction such as gradient boosting exhibited higher accuracy for prediction of surgical outcome and we can provide accurate information on surgical outcomes before surgery to OSA subjects using machine learning models. [ABSTRACT FROM AUTHOR]