Search

The flame of converter mouth can well reflect the change of temperature and composition of molten steel in the furnace. The flame characteristics of converter mouth collected by device can well predict the smelting process of converter. Based on the flame spectrum data set of converter mouth, this paper uses the BEADS algorithm and rough set attribute reduction algorithm optimized by genetic algorithm to extract the features of 2048-dimensional wavelength data. Through the model, eight indexes that contribute greatly to temperature and carbon content are selected, which are f-507, f-520, f-839, f-1073, f-1371, f-1528, f-1727 and f-1826. The MIC coefficients of the eight indicators with temperature and carbon content are calculated, and the MIC coefficients of the variables is small, and the selected indicators are representative. There was a significant correlation between temperature and C content. In BP neural network of temperature prediction model, it is found that the prediction accuracy of the training set is 0.99, the prediction accuracy of the test set is 0.99, the prediction accuracy of the verification set is 0.99, and the prediction accuracy of the whole set is 0.99. Through statistics, it is found that the hit rate of the temperature model in the range of ± 5 K is 88.7%, and the hit rate in the range of ± 10 K is 98.4%. and the RMSE parameter analysis shows that the average prediction error is 3.85 K. In BP neural network of carbon content prediction model, it is found that the prediction accuracy of the training set is 0.99, the prediction accuracy of the test set is 0.99, the prediction accuracy of the verification set is 0.98, and the prediction accuracy of the whole set is 0.99. Through statistics, it is found that the hit rate of the carbon contents model in the range of ± 0.05% is 94.0%, and the hit rate in the range of ± 0.10% is 98.3%, and the RMSE parameter analysis shows that the average prediction error is 0.021%. Finally, the universality of the model is verified by MIV algorithm. [ABSTRACT FROM AUTHOR]

Prediction of bacteremia is a clinically important but challenging task. An artificial intelligence (AI) model has the potential to facilitate early bacteremia prediction, aiding emergency department (ED) physicians in making timely decisions and reducing unnecessary medical costs. In this study, we developed and externally validated a Bayesian neural network-based AI bacteremia prediction model (AI-BPM). We also evaluated its impact on physician predictive performance considering both AI and physician uncertainties using historical patient data. A retrospective cohort of 15,362 adult patients with blood cultures performed in the ED was used to develop the AI-BPM. The AI-BPM used structured and unstructured text data acquired during the early stage of ED visit, and provided both the point estimate and 95% confidence interval (CI) of its predictions. High AI-BPM uncertainty was defined as when the predetermined bacteremia risk threshold (5%) was included in the 95% CI of the AI-BPM prediction, and low AI-BPM uncertainty was when it was not included. In the temporal validation dataset (N = 8,188), the AI-BPM achieved area under the receiver operating characteristic curve (AUC) of 0.754 (95% CI 0.737–0.771), sensitivity of 0.917 (95% CI 0.897–0.934), and specificity of 0.340 (95% CI 0.330–0.351). In the external validation dataset (N = 7,029), the AI-BPM's AUC was 0.738 (95% CI 0.722–0.755), sensitivity was 0.927 (95% CI 0.909–0.942), and specificity was 0.319 (95% CI 0.307–0.330). The AUC of the post-AI physicians predictions (0.703, 95% CI 0.654–0.753) was significantly improved compared with that of the pre-AI predictions (0.639, 95% CI 0.585–0.693; p-value < 0.001) in the sampled dataset (N = 1,000). The AI-BPM especially improved the predictive performance of physicians in cases with high physician uncertainty (low subjective confidence) and low AI-BPM uncertainty. Our results suggest that the uncertainty of both the AI model and physicians should be considered for successful AI model implementation. [ABSTRACT FROM AUTHOR]

Prognostic models in cancer use patient demographic and tumor characteristics to predict survival and dynamic disease prognosis. Past work in breast cancer has shown that cancer detection method, screen-detected or symptom-detected, has prognostic significance. We investigate this phenomenon in the lung component of the Prostate, Lung, Colorectal, and Ovarian (PLCO) screening trial. Patients were randomized to intervention, receiving four annual chest x-rays (CXRs), or to control, receiving usual care. Patients were followed for a total of approximately 13 years. In PLCO, lung cancer detection method has independent prognostic value exceeding that of variables commonly used in lung cancer prognostic models, including sex, histology, and age. Results are robust to cohort selection and type of predictive model. These results imply that detection method should be considered when developing prognostic models in lung cancer studies, and cancer registries should routinely collect cancer detection method. [ABSTRACT FROM AUTHOR]

We compared the prediction performance of machine learning-based undiagnosed diabetes prediction models with that of traditional statistics-based prediction models. We used the 2014–2020 Korean National Health and Nutrition Examination Survey (KNHANES) (N = 32,827). The KNHANES 2014–2018 data were used as training and internal validation sets and the 2019–2020 data as external validation sets. The receiver operating characteristic curve area under the curve (AUC) was used to compare the prediction performance of the machine learning-based and the traditional statistics-based prediction models. Using sex, age, resting heart rate, and waist circumference as features, the machine learning-based model showed a higher AUC (0.788 vs. 0.740) than that of the traditional statistical-based prediction model. Using sex, age, waist circumference, family history of diabetes, hypertension, alcohol consumption, and smoking status as features, the machine learning-based prediction model showed a higher AUC (0.802 vs. 0.759) than the traditional statistical-based prediction model. The machine learning-based prediction model using features for maximum prediction performance showed a higher AUC (0.819 vs. 0.765) than the traditional statistical-based prediction model. Machine learning-based prediction models using anthropometric and lifestyle measurements may outperform the traditional statistics-based prediction models in predicting undiagnosed diabetes. [ABSTRACT FROM AUTHOR]

The development of acute kidney injury (AKI) and hepatorenal syndrome–acute kidney injury (HRS–AKI) in cirrhosis has been associated with intestinal barrier dysfunction and gut-kidney crosstalk. We use the related markers such as zonulin, lipopolysaccharides (LPS), and lipopolysaccharide-binding protein (LBP) to predict AKI and HRS–AKI in cirrhotic patients and evaluate their in vitro effects on intestinal (Caco-2) cells and renal tubular (HK-2) cells. From 2013 to 2020, we enrolled 70 cirrhotic patients and developed prediction models for AKI and HRS–AKI over a six-month period. There were 13 (18.6%) and 8 (11.4%) cirrhotic patients developed AKI and HRS–AKI. The prediction models incorporated zonulin, LPS, LBP, C-reactive protein, age, and history of hepatitis B for AKI, and zonulin, LPS, LBP, total bilirubin, and Child–Pugh score for HRS–AKI. The area under curve (AUC) for the prediction of AKI and HRS–AKI was 0.94 and 0.95, respectively. Furthermore, the conditioned medium of LPS+hrLBP pre-treated Caco-2 cells induced apoptosis, necrosis, and zonulin release in HK-2 cells, demonstrating the communication between them. This study found that zonulin, LPS, and LBP are potential practical markers for predicting AKI and HRS–AKI in cirrhotic patients, which may serve as potential targets for renal outcomes in cirrhotic patients. [ABSTRACT FROM AUTHOR]

Frequent laboratory monitoring is recommended for early identification of toxicity when initiating conventional synthetic disease-modifying antirheumatic drugs (csDMARDs). We aimed at developing a risk prediction model to individualize laboratory testing at csDMARD initiation. We identified inflammatory joint disease patients (N = 1196) initiating a csDMARD in Turku University Hospital 2013–2019. Baseline and follow-up safety monitoring results were drawn from electronic health records. For rheumatoid arthritis patients, diagnoses and csDMARD initiation/cessation dates were manually confirmed. Primary endpoint was alanine transaminase (ALT) elevation of more than twice the upper limit of normal (ULN) within 6 months after treatment initiation. Computational models for predicting incident ALT elevations were developed using Lasso Cox proportional hazards regression with stable iterative variable selection (SIVS) and were internally validated against a randomly selected test cohort (1/3 of the data) that was not used for training the models. Primary endpoint was reached in 82 patients (6.9%). Among baseline variables, Lasso model with SIVS predicted subsequent ALT elevations of > 2 × ULN using higher ALT, csDMARD other than methotrexate or sulfasalazine and psoriatic arthritis diagnosis as important predictors, with a concordance index of 0.71 in the test cohort. Respectively, at first follow-up, in addition to baseline ALT and psoriatic arthritis diagnosis, also ALT change from baseline was identified as an important predictor resulting in a test concordance index of 0.72. Our computational model predicts ALT elevations after the first follow-up test with good accuracy and can help in optimizing individual testing frequency. [ABSTRACT FROM AUTHOR]

Severe air pollution poses a significant threat to public safety and human health. Predicting future air quality conditions is crucial for implementing pollution control measures and guiding residents' activity choices. However, traditional single-module machine learning models suffer from long training times and low prediction accuracy. To improve the accuracy of air quality forecasting, this paper proposes a ISSA–LSTM model-based approach for predicting the air quality index (AQI). The model consists of three main components: random forest (RF) and mRMR, improved sparrow search algorithm (ISSA), and long short-term memory network (LSTM). Firstly, RF–mRMR is used to select the influential variables affecting AQI, thereby enhancing the model's performance. Next, ISSA algorithm is employed to optimize the hyperparameters of LSTM, further improving the model's performance. Finally, LSTM model is utilized to predict AQI concentrations. Through comparative experiments, it is demonstrated that the ISSA–LSTM model outperforms other models in terms of RMSE and R2, exhibiting higher prediction accuracy. The model's predictive performance is validated across different time steps, demonstrating minimal prediction errors. Therefore, the ISSA–LSTM model is a viable and effective approach for accurately predicting AQI. [ABSTRACT FROM AUTHOR]

Legal restrictions allow to give full control to automated vehicles for longer time periods either in restricted areas or when moving with reduced speed. Although being technically feasible for a wide range of driving scenarios, the restrictions are still in place due to the lack of a clear safety strategy. An essential step towards safety is the introduction of a self-monitoring component. In this study, a self-evaluation concept is presented which assesses a system based on a physics-defined minimum prediction horizon for state-of-the-art Deep Learning-based trajectory prediction models. Since User Experience is a key metric for car manufacturers, a further manoeuvre constraint is added to the model. We emphasize the generalizability of the presented assessment concept, however, in order to demonstrate feasibility in practical use, three specific scenarios are discussed. The results are gained with real data from publicly available driving campaigns as well as synthetically generated simulation data. Two exemplary models, a simple LSTM-based model and VectorNet, a prominent motion prediction model, are evaluated. A quantitative assessment shows a lack of training data in the public datasets for vehicle speeds > 25 m/s in order to offer safe driving above such vehicle speeds. [ABSTRACT FROM AUTHOR]

In this work, the tunneling resistivity between neighboring nanosheets in grapheme–polymer nanocomposites is expressed by a simple equation as a function of the characteristics of graphene and tunnels. This expression is obtained by connecting two advanced models for the conductivity of graphene-filled materials reflecting tunneling role and interphase area. The predictions of the applied models are linked to the tested data of several samples. The impressions of all factors on the tunneling resistivity are evaluated and interpreted using the suggested equation. The calculations of tunneling resistivity for the studied examples by the model and suggested equation demonstrate the same levels, which confirm the presented methodology. The results indicate that the tunneling resistivity decreases by super-conductive graphene, small tunneling width, numerous contacts among nanosheets and short tunneling length. [ABSTRACT FROM AUTHOR]

Post-stroke disability affects patients' lifestyles after discharge, and it is essential to predict functional recovery early in hospitalization to allow time for appropriate decisions. Previous studies reported important clinical indicators, but only a few clinical indicators were analyzed due to insufficient numbers of cases. Although review articles can exhaustively identify many prognostic factors, it remains impossible to compare the contribution of each predictor. This study aimed to determine which clinical indicators contribute more to predicting the functional independence measure (FIM) at discharge by comparing standardized coefficients. In this study, 980 participants were enrolled to build predictive models with 32 clinical indicators, including the stroke impairment assessment set (SIAS). Trunk function had the most significant standardized coefficient of 0.221. The predictive models also identified easy FIM sub-items, SIAS, and grip strength on the unaffected side as having positive standardized coefficients. As for the predictive accuracy of this model, R2 was 0.741. This is the first report that included FIM sub-items separately in post-stroke predictive models with other clinical indicators. Trunk function and easy FIM sub-items were included in the predictive model with larger positive standardized coefficients. This predictive model may predict prognosis with high accuracy, fewer clinical indicators, and less effort to predict. [ABSTRACT FROM AUTHOR]

Nowadays, global public health crises are occurring more frequently, and accurate prediction of these diseases can reduce the burden on the healthcare system. Taking COVID-19 as an example, accurate prediction of infection can assist experts in effectively allocating medical resources and diagnosing diseases. Currently, scholars worldwide use single model approaches or epidemiology models more often to predict the outbreak trend of COVID-19, resulting in poor prediction accuracy. Although a few studies have employed ensemble models, there is still room for improvement in their performance. In addition, there are only a few models that use the laboratory results of patients to predict COVID-19 infection. To address these issues, research efforts should focus on improving disease prediction performance and expanding the use of medical disease prediction models. In this paper, we propose an innovative deep learning model Whale Optimization Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM) and Artificial Neural Network (ANN) called WOCLSA which incorporates three models ANN, CNN and LSTM. The WOCLSA model utilizes the Whale Optimization Algorithm to optimize the neuron number, dropout and batch size parameters in the integrated model of ANN, CNN and LSTM, thereby finding the global optimal solution parameters. WOCLSA employs 18 patient indicators as predictors, and compares its results with three other ensemble deep learning models. All models were validated with train-test split approaches. We evaluate and compare our proposed model and other models using accuracy, F1 score, recall, AUC and precision metrics. Through many studies and tests, our results show that our prediction models can identify patients with COVID-19 infection at the AUC of 91%, 91%, and 93% respectively. Other prediction results achieve a respectable accuracy of 92.82%, 92.79%, and 91.66% respectively, f1-score of 93.41%, 92.79%, and 92.33% respectively, precision of 93.41%, 92.79%, and 92.33% respectively, recall of 93.41%, 92.79%, and 92.33% respectively. All of these exceed 91%, surpassing those of comparable models. The execution time of WOCLSA is also an advantage. Therefore, the WOCLSA ensemble model can be used to assist in verifying laboratory research results and predict and to judge various diseases in public health events. [ABSTRACT FROM AUTHOR]

Drug response prediction is important to establish personalized medicine for cancer therapy. Model construction for predicting drug response (i.e., cell viability half-maximal inhibitory concentration [IC50]) of an individual drug by inputting pharmacogenomics in disease models remains critical. Machine learning (ML) has been predominantly applied for prediction, despite the advent of deep learning (DL). Moreover, whether DL or traditional ML models are superior for predicting cell viability IC50s has to be established. Herein, we constructed ML and DL drug response prediction models for 24 individual drugs and compared the performance of the models by employing gene expression and mutation profiles of cancer cell lines as input. We observed no significant difference in drug response prediction performance between DL and ML models for 24 drugs [root mean squared error (RMSE) ranging from 0.284 to 3.563 for DL and from 0.274 to 2.697 for ML; R2 ranging from −7.405 to 0.331 for DL and from −8.113 to 0.470 for ML]. Among the 24 individual drugs, the ridge model of panobinostat exhibited the best performance (R2 0.470 and RMSE 0.623). Thus, we selected the ridge model of panobinostat for further application of explainable artificial intelligence (XAI). Using XAI, we further identified important genomic features for panobinostat response prediction in the ridge model, suggesting the genomic features of 22 genes. Based on our findings, results for an individual drug employing both DL and ML models were comparable. Our study confirms the applicability of drug response prediction models for individual drugs. [ABSTRACT FROM AUTHOR]

This paper deals with the mathematical modeling of bacterial co-aggregation and its numerical implementation in a FEM framework. Since the concept of co-aggregation refers to the physical binding between cells of different microbial species, a system composed of two species is considered in the modeling framework. The extension of the model to an arbitrary number of species is straightforward. In addition to two-species (multi-species growth) dynamics, the transport of a nutritional substance and the extent of co-aggregation are introduced into the model as the third and fourth primary variables. A phase-field modeling approach is employed to describe the co-aggregation between the two species. The mathematical model is three-dimensional and fully based on the continuum description of the problem without any need for discrete agents which are the key elements of the individual-based modeling approach. It is shown that the use of a phase-field-based model is equivalent to a particular form of classical diffusion-reaction systems. Unlike the so-called mixture models, the evolution of each component of the multi-species system is captured thanks to the inherent capability of phase-field modeling in treating systems consisting of distinct multi-phases. The details of numerical implementation in a FEM framework are also presented. Indeed, a new multi-field user element is developed and implemented in ANSYS for this multiphysics problem. Predictions of the model are compared with the experimental observations. By that, the versatility and applicability of the model and the numerical tool are well established. [ABSTRACT FROM AUTHOR]

Primary aldosteronism (PA) is one of the most common causes of secondary hypertension and is potentially curable. However, a large number of patients still undergo persistent hypertension (PHT) after unilateral adrenal surgery. This research retrospectively studied the factors associated with this clinical difficulty and established a prediction model for the postoperative PHT; Methods: 353 patients from 2014 to 2021 with PA undergoing unilateral adrenal surgery were enrolled in this study. Clinical and biochemical characteristics were reviewed and the associating factors were examined using univariate and multivariate analysis. A nomogram-based prediction model was established correspondingly; results: 46.2% (163/190) of patients had post-surgical PHT. Multivariate analysis suggested that BMI ≥ 25, diabetes, duration of hypertension, male gender, and ARR were independent predictors of PHT after surgery. The prediction model based on the nomogram showed good discrimination ability (the C index of the training group and the validation group were 0.783 and 0.769, respectively), and the calibration curves and the Hosmer–Lemeshow test were good as well. Clinical usefulness was quantified using the decision curve analysis; This nomogram is an integration of the clinical and biochemical data of patients before surgery, and is a reliable tool with high accuracy for predicting the postoperative PHT in patients with PA. [ABSTRACT FROM AUTHOR]

Adult gaze behaviour towards naturalistic scenes is highly biased towards semantic object classes. Little is known about the ontological development of these biases, nor about group-level differences in gaze behaviour between adults and preschoolers. Here, we let preschoolers (n = 34, age 5 years) and adults (n = 42, age 18–59 years) freely view 40 complex scenes containing objects with different semantic attributes to compare their fixation behaviour. Results show that preschool children allocate a significantly smaller proportion of dwell time and first fixations on Text and instead fixate Faces, Touched objects, Hands and Bodies more. A predictive model of object fixations controlling for a range of potential confounds suggests that most of these differences can be explained by drastically reduced text salience in pre-schoolers and that this effect is independent of low-level salience. These findings are in line with a developmental attentional antagonism between text and body parts (touched objects and hands in particular), which resonates with recent findings regarding 'cortical recycling'. We discuss this and other potential mechanisms driving salience differences between children and adults. [ABSTRACT FROM AUTHOR]

In order to reveal the relationship between new urbanization and carbon emission to provide reference opinions for the construction of low-carbon urbanization, an evaluation system between new urbanization and carbon emission was constructed. Then their matching degree relationship was analyzed by coupling coordination degree model based on the data from 2012 to 2021 in Anhui Province, and their development trend from 2023 to 2032 was predicted by gray prediction model. The results show that: (1) New urbanization and carbon emission have the co-trend effect, and the consistency of core impact factors is relatively significant. Among them, the level of new urbanization increases from 0.058 in 2012 to 0.699 in 2021 and carbon emission development increases from 0.023 in 2012 to 0.165 in 2021, which both showing an upward trend. Meanwhile, social urbanization and population carbon emission are the core influencing factors. (2) The coupling coordination degree between new urbanization and carbon emission is low, but the synergy trend is optimistic and there is a large room for improvement. Among them, the coupling coordination coefficient of the coupling system rises from 0.136 in 2012 to 1.412 in 2021 (antagonistic phase), and then reaches 0.820 by 2032 (highly coordinated phase) by forecast. It shows that their current development is unbalanced, but the development trend is good, and there is a chance for improvement. This paper deepens the understanding of the logical correlation between new urbanization and carbon emission, and the following views are formed: (1) Low-carbon development is still the mainstream of new urbanization; (2) The coordination development of new urbanization and carbon emission reduction should be strengthened. [ABSTRACT FROM AUTHOR]

There have been multiple attempts to predict the expression of the genes based on the sequence, epigenetics, and various other factors. To improve those predictions, we have decided to investigate adding protein-specific 3D interactions that play a significant role in the condensation of the chromatin structure in the cell nucleus. To achieve this, we have used the architecture of one of the state-of-the-art algorithms, ExPecto, and investigated the changes in the model metrics upon adding the spatially relevant data. We have used ChIA-PET interactions that are mediated by cohesin (24 cell lines), CTCF (4 cell lines), and RNAPOL2 (4 cell lines). As the output of the study, we have developed the Spatial Gene Expression (SpEx) algorithm that shows statistically significant improvements in most cell lines. We have compared ourselves to the baseline ExPecto model, which obtained a 0.82 Spearman's rank correlation coefficient (SCC) score, and 0.85, which is reported by newer Enformer were able to obtain the average correlation score of 0.83. However, in some cases (e.g. RNAPOL2 on GM12878), our improvement reached 0.04, and in some cases (e.g. RNAPOL2 on H1), we reached an SCC of 0.86. [ABSTRACT FROM AUTHOR]

Models predicting individual body weights over time clarify patient expectations in weight loss programs. The accuracy of two commonly used weight prediction models in community living people is unclear. All eligible people entering a weight management program between 1992 and 2015 were included. Patients' diet was 1200 kcal/day for week 0 followed by 900 kcal/day for weeks 1–7 and were excluded from the analysis if they were nonadherent. We generated expected weights using the National Institutes of Health Body Weight Planner (NIH-BWP) and the Pennington Biomedical Research Center Weight Loss Predictor (PBRC-WLP). 3703 adherent people were included (mean age 46 years, 72.6% women, mean [SD] weight 262.3 pounds [54.2], mean [SD] BMI 42.4 [7.6]). Mean (SD) relative body weight differences (100*[observed−expected]/expected) for NIH-BWP and PBRC-WLP models was − 1.5% (3.8) and − 2.9% (3.2), respectively. At week 7, mean squared error with NIH-BWP (98.8, 83%CI 89.7–108.8) was significantly lower than that with PBRC-WLP (117.7, 83%CI 112.4–123.4). Notable variation in relative weight difference were seen (for NIH-BWP, 5th–95th percentile was − 6.2%, + 3.7%; Δ 9.9%). During the first 7 weeks of a weight loss program, both weight prediction models returned expected weights that were very close to observed values with the NIH-BWP being more accurate. However, notable variability between expected and observed weights in individual patients were seen. Clinicians can monitor patients in weight loss programs by comparing their progress with these data. [ABSTRACT FROM AUTHOR]

DNA loop extrusion by structural-maintenance-of-chromosome (SMC) complexes has emerged as a primary organizing principle for chromosomes. The mechanism by which SMC motor proteins extrude DNA loops is still unresolved and much debated. The ring-like structure of SMC complexes prompted multiple models where the extruded DNA is topologically or pseudotopologically entrapped within the ring during loop extrusion. However, recent experiments showed the passage of roadblocks much bigger than the SMC ring size, suggesting a nontopological mechanism. Recently, attempts were made to reconcile the observed passage of large roadblocks with a pseudotopological mechanism. Here we examine the predictions of these pseudotopological models and find that they are not consistent with new experimental data on SMC roadblock encounters. Particularly, these models predict the formation of two loops and that roadblocks will reside near the stem of the loop upon encounter—both in contrast to experimental observations. Overall, the experimental data reinforce the notion of a nontopological mechanism for extrusion of DNA. [ABSTRACT FROM AUTHOR]

Korea is showing the fastest trend in the world in population aging; there is a high interest in the elderly population nationwide. Among the common chronic diseases, the elderly tends to have a high incidence of depression. That said, it has been vital to focus on preventing depression in the elderly in advance. Hence, this study aims to select the factors related to depression in low-income seniors identified in previous studies and to develop a prediction model. In this study, 2975 elderly people from low-income families were extracted using the 13th-year data of the Korea Welfare Panel Study (2018). Decision trees, logistic regression, neural networks, and random forest were applied to develop a predictive model among the numerous data mining techniques. In addition, the wrapper's stepwise backward elimination, which finds the optimal model by removing the least relevant factors, was applied. The evaluation of the model was confirmed via accuracy. It was verified that the final prediction model, in the case of a decision tree, showed the highest predictive power with an accuracy of 97.3%. Second, psychological factors, leisure life satisfaction, social support, subjective health awareness, and family support ranked higher than demographic factors influencing depression. Based on the results, an approach focused on psychological support is much needed to manage depression in low-income seniors. As predicting depression in the elderly varies on numerous influencing factors, using a decision tree may be beneficial to establish a firm prediction model to identify vital factors causing depression in the elderly population. [ABSTRACT FROM AUTHOR]

Since the beginning of the COVID-19 pandemic, new and non-invasive digital technologies such as artificial intelligence (AI) had been introduced for mortality prediction of COVID-19 patients. The prognostic performances of the machine learning (ML)-based models for predicting clinical outcomes of COVID-19 patients had been mainly evaluated using demographics, risk factors, clinical manifestations, and laboratory results. There is a lack of information about the prognostic role of imaging manifestations in combination with demographics, clinical manifestations, and laboratory predictors. The purpose of the present study is to develop an efficient ML prognostic model based on a more comprehensive dataset including chest CT severity score (CT-SS). Fifty-five primary features in six main classes were retrospectively reviewed for 6854 suspected cases. The independence test of Chi-square was used to determine the most important features in the mortality prediction of COVID-19 patients. The most relevant predictors were used to train and test ML algorithms. The predictive models were developed using eight ML algorithms including the J48 decision tree (J48), support vector machine (SVM), multi-layer perceptron (MLP), k-nearest neighbourhood (k-NN), Naïve Bayes (NB), logistic regression (LR), random forest (RF), and eXtreme gradient boosting (XGBoost). The performances of the predictive models were evaluated using accuracy, precision, sensitivity, specificity, and area under the ROC curve (AUC) metrics. After applying the exclusion criteria, a total of 815 positive RT-PCR patients were the final sample size, where 54.85% of the patients were male and the mean age of the study population was 57.22 ± 16.76 years. The RF algorithm with an accuracy of 97.2%, the sensitivity of 100%, a precision of 94.8%, specificity of 94.5%, F1-score of 97.3%, and AUC of 99.9% had the best performance. Other ML algorithms with AUC ranging from 81.2 to 93.9% had also good prediction performances in predicting COVID-19 mortality. Results showed that timely and accurate risk stratification of COVID-19 patients could be performed using ML-based predictive models fed by routine data. The proposed algorithm with the more comprehensive dataset including CT-SS could efficiently predict the mortality of COVID-19 patients. This could lead to promptly targeting high-risk patients on admission, the optimal use of hospital resources, and an increased probability of survival of patients. [ABSTRACT FROM AUTHOR]

To examine heterogeneous trajectories of 8-year gait speed among patients with symptomatic knee osteoarthritis (KOA) and to develop a nomogram prediction model. We analyzed data from the Osteoarthritis Initiative (OAI) assessed at baseline and follow-up over 8 years (n = 1289). Gait speed was measured by the 20-m walk test. The gait speed trajectories among patients with KOA were explored by latent class growth analysis. A nomogram prediction model was created based on multivariable logistic regression. Three gait speed trajectories were identified: the fast gait speed group (30.4%), moderate gait speed group (50.5%) and slow gait speed group (19.1%). Age ≥ 60 years, female, non-white, nonmarried, annual income < $50,000, obesity, depressive symptoms, comorbidity and WOMAC pain score ≥ 5 were risk factors for the slow gait trajectory. The area under the ROC curve of the prediction model was 0.775 (95% CI 0.742–0.808). In the external validation cohort, the AUC was 0.773 (95% CI 0.697–0.848). Heterogeneous trajectories existed in the gait speed of patients with KOA and could be predicted by multiple factors. Risk factors should be earlier identified, and targeted intervention should be carried out to improve physical function of KOA patients. [ABSTRACT FROM AUTHOR]

Large Scale Natural Draft Cooling Tower has become a hot topic in China because it is an important part of the nuclear power plant, and its environmental impacts include shading, solar energy loss, water deposition and salt deposition. In China, there is no built large-scale natural draft cooling tower of nuclear power plant. Therefore, model prediction becomes an effective way to solve this problem. This paper introduces the basic principles and structure of SACTI (Seasonal and Annual Cooling Tower Impact) model. SACTI is a cooling tower assessment model developed by Argonne National Laboratory, USA. A comparative case study between China's Pengze Nuclear Power Plant and the US Amos Power Plant is also presented. Calculations were carried out for the Pengze and Amos power plants, and the results showed that the maximum value of salt deposition at the Pengze plant was about 166.5 kg/(km2-month) at a distance of 800 m from the cooling tower. The maximum value of salt deposition at the Amos plant was about 92.85 kg/(km2-month) at a distance of 600 m from the cooling tower. Conclusions show that the research work can provide a useful solution in future work, the simulation results of the SACTI model have a potential mean in the absence of monitoring data. This research provides a way to generate simulation data through SACTI program in the design process of nuclear power plant cooling tower, and designers can use these data to determine how the cooling tower will affect the natural environment and manage within an appropriate range to reduce the impact on the environment. [ABSTRACT FROM AUTHOR]

Resolving practical non-identifiability of computational models typically requires either additional data or non-algorithmic model reduction, which frequently results in models containing parameters lacking direct interpretation. Here, instead of reducing models, we explore an alternative, Bayesian approach, and quantify the predictive power of non-identifiable models. We considered an example biochemical signalling cascade model as well as its mechanical analogue. For these models, we demonstrated that by measuring a single variable in response to a properly chosen stimulation protocol, the dimensionality of the parameter space is reduced, which allows for predicting the measured variable's trajectory in response to different stimulation protocols even if all model parameters remain unidentified. Moreover, one can predict how such a trajectory will transform in the case of a multiplicative change of an arbitrary model parameter. Successive measurements of remaining variables further reduce the dimensionality of the parameter space and enable new predictions. We analysed potential pitfalls of the proposed approach that can arise when the investigated model is oversimplified, incorrect, or when the training protocol is inadequate. The main advantage of the suggested iterative approach is that the predictive power of the model can be assessed and practically utilised at each step. [ABSTRACT FROM AUTHOR]

Early postoperative mortality risk prediction is crucial for clinical management of gastric cancer. This study aims to predict 90-day mortality in gastric cancer patients undergoing gastrectomy using automated machine learning (AutoML), optimize models for preoperative prediction, and identify factors influential in prediction. National Cancer Database was used to identify stage I–III gastric cancer patients undergoing gastrectomy between 2004 and 2016. 26 features were used to train predictive models using H2O.ai AutoML. Performance on validation cohort was measured. In 39,108 patients, 90-day mortality rate was 8.8%. The highest performing model was an ensemble (AUC = 0.77); older age, nodal ratio, and length of inpatient stay (LOS) following surgery were most influential for prediction. Removing the latter two parameters decreased model performance (AUC 0.71). For optimizing models for preoperative use, models were developed to first predict node ratio or LOS, and these predicted values were inputted for 90-day mortality prediction (AUC of 0.73–0.74). AutoML performed well in predicting 90-day mortality in a larger cohort of gastric cancer patients that underwent gastrectomy. These models can be implemented preoperatively to inform prognostication and patient selection for surgery. Our study supports broader evaluation and application of AutoML to guide surgical oncologic care. [ABSTRACT FROM AUTHOR]

This study aims to evaluate the specific characteristics of various multileaf collimator (MLC) position errors that are correlated with the indices using dose distribution. The dose distribution was investigated using the gamma, structural similarity, and dosiomics indices. Cases from the American Association of Physicists in Medicine Task Group 119 were planned, and systematic and random MLC position errors were simulated. The indices were obtained from distribution maps and statistically significant indices were selected. The final model was determined when all values of the area under the curve, accuracy, precision, sensitivity, and specificity were higher than 0.8 (p < 0.05). The dose–volume histogram (DVH) relative percentage difference between the error-free and error datasets was examined to investigate clinical relations. Seven multivariate predictive models were finalized. The common significant dosiomics indices (GLCM Energy and GLRLM_LRHGE) can characterize the MLC position error. In addition, the finalized logistic regression model for MLC position error prediction showed excellent performance with AUC > 0.9. Furthermore, the results of the DVH were related to dosiomics analysis in that it reflects the characteristics of the MLC position error. It was also shown that dosiomics analysis could provide important information on localized dose-distribution differences in addition to DVH information. [ABSTRACT FROM AUTHOR]

Differentiating tuberculous pleural effusion (TPE) from non-tuberculosis pleural effusion remains a challenge in clinical practice. This study aimed to develop and externally validate a novel prediction model using the peripheral blood tuberculous infection of T cells spot test (T-SPOT.TB) to assess the probability of TPE in patients with unexplained pleural effusion. Patients with pleural effusion and confirmed etiology were included in this study. A retrospective derivation population was used to develop and internally validate the predictive model. Clinical, radiological, and laboratory features were collected, and important predictors were selected using the least absolute shrinkage and selection operator. The prediction model, presented as a web calculator, was developed using multivariable logistic regression. The predictive performance of the model was evaluated for discrimination and calibration and verified in an independent validation population. The developed prediction model included age, positive T-SPOT.TB result, logarithm of the ratio of mononuclear cells to multiple nuclear cells in pleural effusion (lnRMMPE), and adenosine deaminase in pleural effusion ≥ 40 U/L. The model demonstrated good discrimination [with area under the curve of 0.837 and 0.903, respectively] and calibration (with a Brier score of 0.159 and 0.119, respectively) in both the derivation population and the validation population. Using a cutoff value of 60%, the sensitivity and specificity for identifying TPE were 70% and 88%, respectively, in the derivation population, and 77% and 92%, respectively, in the validation population. A novel predictive model based on T-SPOT.TB was developed and externally validated, demonstrating good diagnostic performance in identifying TPE. [ABSTRACT FROM AUTHOR]

We aimed to assess the added predictive performance that free-text Dutch consultation notes provide in detecting colorectal cancer in primary care, in comparison to currently used models. We developed, evaluated and compared three prediction models for colorectal cancer (CRC) in a large primary care database with 60,641 patients. The prediction model with both known predictive features and free-text data (with TabTxt AUROC: 0.823) performs statistically significantly better (p < 0.05) than the other two models with only tabular (as used nowadays) and text data, respectively (AUROC Tab: 0.767; Txt: 0.797). The specificity of the two models that use demographics and known CRC features (with specificity Tab: 0.321; TabTxt: 0.335) are higher than that of the model with only free-text (specificity Txt: 0.234). The Txt and, to a lesser degree, TabTxt model are well calibrated, while the Tab model shows slight underprediction at both tails. As expected with an outcome prevalence below 0.01, all models show much uncalibrated predictions in the extreme upper tail (top 1%). Free-text consultation notes show promising results to improve the predictive performance over established prediction models that only use structured features. Clinical future implications for our CRC use case include that such improvement may help lowering the number of referrals for suspected CRC to medical specialists. [ABSTRACT FROM AUTHOR]

Soft materials that can demonstrate on demand reconfigurability and changing compliance are highly sought after as actuator materials in many fields such as soft robotics and biotechnology. Whilst there are numerous proof of concept materials and devices, rigorous predictive models of deformation have not been well-established or widely adopted. In this paper, we discuss programming complex three-dimensional deformations of a soft intrinsically anisotropic material by controlling the orientation of the contractile units and/or direction of the applied electric field. Programming is achieved by patterning contractile units and/or selectively activating spatial regions. A new constitutive model is derived to describe the soft intrinsic anisotropy of soft materials. The model is developed within a continuum mechanics framework using an invariant-based formulation. Computational implementation allows us to simulate the complex three-dimensional shape response when activated by electric field. Several examples of the achievable Gauss-curved surfaces are demonstrated. Our computational analysis introduces a mechanics-based framework for design when considering soft morphing materials with intrinsic anisotropy, and is meant to inspire the development of new soft active materials. [ABSTRACT FROM AUTHOR]

Robust dynamic cardiac magnetic resonance imaging (MRI) has been a long-standing endeavor—as real-time imaging can provide information on the temporal signatures of disease we currently cannot assess—with the past decade seeing remarkable advances in acceleration using compressed sensing (CS) and artificial intelligence (AI). However, substantial limitations to real-time imaging remain and reconstruction quality is not always guaranteed. To improve reconstruction fidelity in dynamic cardiac MRI, we propose a novel predictive signal model that uses a priori statistics to adaptively predict temporal cardiac dynamics. By using a small training set obtained from the same patient, the new signal model can achieve robust dynamic cardiac MRI in the presence of irregular cardiac rhythm. Evaluation on simulated irregular cardiac dynamics and prospectively undersampled clinical cardiac MRI data demonstrate improved reconstruction quality for two reconstruction frameworks: Kalman filter and CS. The predictive model also works with different undersampling patterns (cartesian, radial, spiral) and can serve as a versatile foundation for robust dynamic cardiac MRI. [ABSTRACT FROM AUTHOR]

Young children are increasingly exposed to an obesogenic environment through increased intake of processed food and decreased physical activity. Mothers' perceptions of obesity and parenting styles influence children's abilities to maintain a healthy weight. This study developed a prediction model for childhood obesity in 10-year-olds, and identify relevant risk factors using a machine learning method. Data on 1185 children and their mothers were obtained from the Korean National Panel Study. A prediction model for obesity was developed based on ten factors related to children (gender, eating habits, activity, and previous body mass index) and their mothers (education level, self-esteem, and body mass index). These factors were selected based on the least absolute shrinkage and selection operator. The prediction model was validated with an Area Under the Receiver Operator Characteristic Curve of 0.82 and an accuracy of 76%. Other than body mass index for both children and mothers, significant risk factors for childhood obesity were less physical activity among children and higher self-esteem among mothers. This study adds new evidence demonstrating that maternal self-esteem is related to children's body mass index. Future studies are needed to develop effective strategies for screening young children at risk for obesity, along with their mothers. [ABSTRACT FROM AUTHOR]

The association between the embryo quality, clinical characteristics, miRNAs (secreted by blastocysts in the culture medium) and pregnancy outcomes has been well-established. Studies on prediction models for pregnancy outcome, using clinical characteristics and miRNA expression, are limited. We aimed to establish the prediction model for prediction of pregnancy outcome of woman after a fresh cycle of Day 5 single blastocyst transfer (Day 5 SBT) based on clinical data and miRNA expression. A total of 86 women, 50 with successful pregnancy and 36 with pregnancy failure after fresh cycle of Day 5 SBT, were enrolled in this study. All samples were divided into training set and test set (3:1). Based on clinical index statistics of enrolled population and miRNA expression, the prediction model was constructed, followed by validation of the prediction model. Four clinical indicators, female age, sperm DNA fragmentation index, anti-mullerian hormone, estradiol, can be used as independent predictors of pregnancy failure after fresh cycle of Day 5 SBT. Three miRNAs (hsa-miR-199a-3p, hsa-miR-199a-5p and hsa-miR-99a-5p) had a potential diagnostic value for pregnancy failure after Day 5 SBT. The predictive effect of model combining 4 clinical indicators and 3 miRNAs (area under the receiver operating characteristic curve, AUC = 0.853) was better than models combining single 4 clinical indicators (AUC = 0.755) or 3 miRNAs (AUC = 0.713). Based on 4 clinical indicators and 3 miRNAs, a novel model to predict pregnancy outcome in woman after fresh cycle of Day 5 SBT has been developed and validated. The predictive model may be valuable for clinicians to make the optimal clinical decision and patient selection. [ABSTRACT FROM AUTHOR]

The underground pipeline network in the city is so intertwined that the concealed excavation of a metro station inevitably leads to a series of underground pipelines, causing settlement deformation and further risk of leakage. The existing theoretical methods for analysing settlement deformation are mostly for circular chambers, whereas metro stations have a nearly square cross-sectional form and different construction methods are very different, which have a greater impact on the deformation of the overlying pipelines. In this paper, based on the random medium theory and Peck's formula, the improved random medium model for predicting ground deformation is modified, the correction coefficients λ and η for the influence of different construction methods are proposed, the prediction model of underground pipeline deformation under different construction methods is obtained, and the numerical models of four work methods commonly used in urban tunnel construction: pillar hole method, side hole method, middle hole method and Pile-Beam-Arch (PBA) method are constructed through simulation, and the mathematical analysis software was used to fit the results to the model and obtain the range of correction coefficients λ and η for each of the four methods, and the accuracy and applicability of the theoretical model was verified by combining with actual engineering cases. The influence on the overlying pipes is in descending order: side hole method, pillar hole method, middle hole method and PBA method. The theoretical model provided in this paper for predicting the deformation of pipes in any overlying strata of the tunnel is well suited to the actual project and has a high degree of correlation with the measured results. [ABSTRACT FROM AUTHOR]

To ensure the safety and stability of the shield tunnel construction process, the ground settlement induced by the shield construction needs to be effectively predicted. In this paper, a prediction method combining empirical mode decomposition (EMD), chaotic adaptive sparrow search algorithm (CASSA), and extreme learning machine (ELM) is proposed. First, the EMD is used to decompose the settlement sequence into trend vectors and fluctuation vectors to fully extract the effective information of the sequence; Second, the sparrow search algorithm is improved by introducing Cubic chaotic mapping to initialize the population and adaptive factor to optimize the searcher's position formula, and the chaotic adaptive sparrow search algorithm is proposed; Finally, the CASSA-ELM prediction model is constructed by using CASSA to find the optimal values of weights and thresholds in the extreme learning machine. The fluctuation components and trend components decomposed by EMD are predicted one by one, and the prediction results are superimposed and reconstructed to obtain the predicted final settlement. Taking a shield interval in Jiangsu, China as an example, the meta-heuristic algorithm-optimized ELM model improves the prediction accuracy by 10.70% compared with the traditional ELM model. The combined EMD-CASSA-ELM prediction model can greatly improve the accuracy and speed of surface settlement prediction, and provide a new means for safety monitoring in shield tunnel construction. Intelligent prediction methods can predict surface subsidence more automatically and quickly, becoming a new development trend. [ABSTRACT FROM AUTHOR]

Understanding the load-carrying capacity of circular concrete-filled steel tube (CCFST) columns is crucial for designing CCFST structures. However, traditional empirical formulas often yield inconsistent results for the same scenario, causing confusion for decision makers. Additionally, simple regression analysis is unable to accurately predict the complex mapping relationship between input and output variables. To address these limitations, this paper proposes an ensemble model that incorporates multiple input features, such as component geometry and material properties, to predict CCFST load capacity. The model is trained and tested on two datasets comprising 1305 tests on CCFST columns under concentric loading and 499 tests under eccentric loading. The results demonstrate that the proposed ensemble model outperforms conventional support vector regression and random forest models in terms of the determination coefficient (R2) and error metrics (MAE, RMSE, and MAPE). Moreover, a feature analysis based on the Shapley additive interpretation (SHAP) technique indicates that column diameter is the most critical factor affecting compressive strength. Other important factors include tube thickness, yield strength of steel tube, and concrete compressive strength, all of which have a positive effect on load capacity. Conversely, an increase in column length or eccentricity leads to a decrease in load capacity. These findings can provide useful insights and guidance for the design of CCFST columns. [ABSTRACT FROM AUTHOR]

To investigate whether the combination scheme of deep learning score (DL-score) and radiomics can improve preoperative diagnosis in the presence of micropapillary/solid (MPP/SOL) patterns in lung adenocarcinoma (ADC). A retrospective cohort of 514 confirmed pathologically lung ADC in 512 patients after surgery was enrolled. The clinicoradiographic model (model 1) and radiomics model (model 2) were developed with logistic regression. The deep learning model (model 3) was constructed based on the deep learning score (DL-score). The combine model (model 4) was based on DL-score and R-score and clinicoradiographic variables. The performance of these models was evaluated with area under the receiver operating characteristic curve (AUC) and compared using DeLong's test internally and externally. The prediction nomogram was plotted, and clinical utility depicted with decision curve. The performance of model 1, model 2, model 3 and model 4 was supported by AUCs of 0.848, 0.896, 0.906, 0.921 in the Internal validation set, that of 0.700, 0.801, 0.730, 0.827 in external validation set, respectively. These models existed statistical significance in internal validation (model 4 vs model 3, P = 0.016; model 4 vs model 1, P = 0.009, respectively) and external validation (model 4 vs model 2, P = 0.036; model 4 vs model 3, P = 0.047; model 4 vs model 1, P = 0.016, respectively). The decision curve analysis (DCA) demonstrated that model 4 predicting the lung ADC with MPP/SOL structure would be more beneficial than the model 1and model 3 but comparable with the model 2. The combined model can improve preoperative diagnosis in the presence of MPP/SOL pattern in lung ADC in clinical practice. [ABSTRACT FROM AUTHOR]

Drug repurposing is an active area of research that aims to decrease the cost and time of drug development. Most of those efforts are primarily concerned with the prediction of drug-target interactions. Many evaluation models, from matrix factorization to more cutting-edge deep neural networks, have come to the scene to identify such relations. Some predictive models are devoted to the prediction's quality, and others are devoted to the efficiency of the predictive models, e.g., embedding generation. In this work, we propose new representations of drugs and targets useful for more prediction and analysis. Using these representations, we propose two inductive, deep network models of IEDTI and DEDTI for drug-target interaction prediction. Both of them use the accumulation of new representations. The IEDTI takes advantage of triplet and maps the input accumulated similarity features into meaningful embedding corresponding vectors. Then, it applies a deep predictive model to each drug-target pair to evaluate their interaction. The DEDTI directly uses the accumulated similarity feature vectors of drugs and targets and applies a predictive model on each pair to identify their interactions. We have done a comprehensive simulation on the DTINet dataset as well as gold standard datasets, and the results show that DEDTI outperforms IEDTI and the state-of-the-art models. In addition, we conduct a docking study on new predicted interactions between two drug-target pairs, and the results confirm acceptable drug-target binding affinity between both predicted pairs. [ABSTRACT FROM AUTHOR]

Recycled aggregate concrete (RAC) has become a popular building material due to its eco-friendly features, but the difficulty in predicting the crack resistance of RAC is increasingly impeding its application. In this study, splitting tensile strength is adopted to describe the crack resistance ability of RAC, and physics-assisted machine learning (ML) methods are used to construct the predictive models for the splitting tensile strength of RAC. The results show that the AdaBoost model has excellent predictive performance with the help of the Firefly algorithm, and physical assistance plays a remarkable role in selecting features and verifying the ML models. Due to the limit in data size and the generalizability of the model, the dataset should be supplemented with more representative data, and an algorithm for small sample sizes could be studied in the future. [ABSTRACT FROM AUTHOR]

The time point of the most precise predictor of hepatocellular carcinoma (HCC) development after viral eradication with direct-acting antiviral (DAA) therapy is unclear. In this study we developed a scoring system that can accurately predict the occurrence of HCC using data from the optimal time point. A total of 1683 chronic hepatitis C patients without HCC who achieved sustained virological response (SVR) with DAA therapy were split into a training set (999 patients) and a validation set (684 patients). The most accurate predictive scoring system to estimate HCC incidence was developed using each of the factors at baseline, end of treatment, and SVR at 12 weeks (SVR12). Multivariate analysis identified diabetes, the fibrosis-4 (FIB-4) index, and the α-fetoprotein level as independent factors at SVR12 that contributed to HCC development. A prediction model was constructed with these factors that ranged from 0 to 6 points. No HCC was observed in the low-risk group. Five-year cumulative incidence rates of HCC were 1.9% in the intermediate-risk group and 15.3% in the high-risk group. The prediction model at SVR12 most accurately predicted HCC development compared with other time points. This simple scoring system combining factors at SVR12 can accurately evaluate HCC risk after DAA treatment. [ABSTRACT FROM AUTHOR]

Few existing efforts to predict childhood obesity have included risk factors across the prenatal and early infancy periods, despite evidence that the first 1000 days is critical for obesity prevention. In this study, we employed machine learning techniques to understand the influence of factors in the first 1000 days on body mass index (BMI) values during childhood. We used LASSO regression to identify 13 features in addition to historical weight, height, and BMI that were relevant to childhood obesity. We then developed prediction models based on support vector regression with fivefold cross validation, estimating BMI for three time periods: 30–36 (N = 4204), 36–42 (N = 4130), and 42–48 (N = 2880) months. Our models were developed using 80% of the patients from each period. When tested on the remaining 20% of the patients, the models predicted children's BMI with high accuracy (mean average error [standard deviation] = 0.96[0.02] at 30–36 months, 0.98 [0.03] at 36–42 months, and 1.00 [0.02] at 42–48 months) and can be used to support clinical and public health efforts focused on obesity prevention in early life. [ABSTRACT FROM AUTHOR]

The global COVID-19 pandemic brought considerable public and policy attention to the field of infectious disease modelling. A major hurdle that modellers must overcome, particularly when models are used to develop policy, is quantifying the uncertainty in a model's predictions. By including the most recent available data in a model, the quality of its predictions can be improved and uncertainties reduced. This paper adapts an existing, large-scale, individual-based COVID-19 model to explore the benefits of updating the model in pseudo-real time. We use Approximate Bayesian Computation (ABC) to dynamically recalibrate the model's parameter values as new data emerge. ABC offers advantages over alternative calibration methods by providing information about the uncertainty associated with particular parameter values and the resulting COVID-19 predictions through posterior distributions. Analysing such distributions is crucial in fully understanding a model and its outputs. We find that forecasts of future disease infection rates are improved substantially by incorporating up-to-date observations and that the uncertainty in forecasts drops considerably in later simulation windows (as the model is provided with additional data). This is an important outcome because the uncertainty in model predictions is often overlooked when models are used in policy. [ABSTRACT FROM AUTHOR]

This study is a simple illustration of the benefit of averaging over cohorts, rather than developing a prediction model from a single cohort. We show that models trained on data from multiple cohorts can perform significantly better in new settings than models based on the same amount of training data but from just a single cohort. Although this concept seems simple and obvious, no current prediction model development guidelines recommend such an approach. [ABSTRACT FROM AUTHOR]

The actual 5-year survival rates for Gynecological Endometrioid Adenocarcinoma with Squamous Differentiation (GE-ASqD) are rarely reported. The purpose of this study was to evaluate how histological subtypes affected long-term survivors of GE-ASqD (> 5 years). We conducted a retrospective analysis of patients diagnosed GE-ASqD from the Surveillance, Epidemiology, and End Results database (2004–2015). In order to conduct the studies, we employed the chi-square test, univariate cox regression, and multivariate cox proportional hazards model. A total of 1131 patients with GE-ASqD were included in the survival study from 2004 to 2015 after applying the inclusion and exclusion criteria and the sample randomly split into a training set and a test set at a ratio of 7:3. Five machine learning algorithms were trained based on nine clinical variables to predict the 5-year overall survival. The AUC of the training group for the LR, Decision Tree, forest, Gbdt, and gbm algorithms were 0.809, 0.336, 0.841, 0.823, and 0.856 respectively. The AUC of the testing group was 0.779, 0.738, 0.753, 0.767 and 0.734, respectively. The calibration curves confirmed good performance of the five machine learning algorithms. Finally, five algorithms were combined to create a machine learning model that forecasts the 5-year overall survival rate of patients with GE-ASqD. [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]

The present study tests the accuracy of four models in estimating the hourly air temperatures in different agroecological regions of the country during two major crop seasons, kharif and rabi, by taking daily maximum and minimum temperatures as input. These methods that are being used in different crop growth simulation models were selected from the literature. To adjust the biases of estimated hourly temperature, three bias correction methods (Linear regression, Linear scaling and Quantile mapping) were used. When compared with the observed data, the estimated hourly temperature, after bias correction, is reasonably close to the observed during both kharif and rabi seasons. The bias-corrected Soygro model exhibited its good performance at 14 locations, followed by the WAVE model and Temperature models at 8 and 6 locations, respectively during the kharif season. In the case of rabi season, the bias-corrected Temperature model appears to be accurate at more locations (21), followed by WAVE and Soygro models at 4 and 2 locations, respectively. The pooled data analysis showed the least error between estimated (uncorrected and bias-corrected) and observed hourly temperature from 04 to 08 h during kharif season while it was 03 to 08 h during the rabi season. The results of the present study indicated that Soygro and Temperature models estimated hourly temperature with better accuracy at a majority of the locations situated in the agroecological regions representing different climates and soil types. Though the WAVE model worked well at some of the locations, estimation by the PL model was not up to the mark in both kharif and rabi seasons. Hence, Soygro and Temperature models can be used to estimate hourly temperature data during both kharif and rabi seasons, after the bias correction by the Linear Regression method. We believe that the application of the study would facilitate the usage of hourly temperature data instead of daily data which in turn improves the precision in predicting phenological events and bud dormancy breaks, chilling hour requirement etc. [ABSTRACT FROM AUTHOR]