Search

BackgroundPhysical frailty is an important issue in aging societies. Three models of physical frailty assessment, the 5-Item fatigue, resistance, ambulation, illness and loss of weight (FRAIL); Cardiovascular Health Study (CHS); and Study of Osteoporotic Fractures (SOF) indices, have been regularly used in clinical and research studies. However, no previous studies have investigated the predictive ability of machine learning (ML) for physical frailty assessment. The aim was to use two ML algorithms, random forest (RF) and extreme gradient boosting (XGBoost), to predict these three physical frailty assessment models.Materials and methodsQuestionnaires regarding demographic characteristics, lifestyle habits, living environment, and physical frailty assessment were answered by 445 participants aged 60 years and above. The RF and XGBoost algorithms were used to assess their scores for the three physical frailty indices. Furthermore, feature importance and Shapley additive explanations (SHAP) were used to determine the important physical frailty factors.ResultsThe XGBoost algorithm obtained higher accuracy for predicting the three physical frailty indices; the areas under the curve obtained by the XGBoost algorithm for the 5-Item FRAIL, CHS, and SOF indices were 0.84. 0.79, and 0.69, respectively. The feature importance and SHAP of the XGBoost algorithm revealed that systolic blood pressure, diastolic blood pressure, age, and body mass index play important roles in all three physical frailty models.ConclusionThe XGBoost algorithm has a more accurate predictive rate than RF across all three physical frailty assessments. Thus, ML can be a useful tool for the early detection of physical frailty.

Abstract Purpose  The objective of this investigation was to yield a generalized in silico model to quantitatively predict CYP2A6-substrates/inhibitors interactions to facilitate drug discovery. Methods  The newly invented pharmacophore ensemble/support vector machine (PhE/SVM) scheme was employed to generate the prediction model based on the data compiled from the literature. Results  The predictions by the PhE/SVM model are in good agreement with the experimental observations for those molecules in the training set (n = 24, r 2 = 0.94, q 2 = 0.85, RMSE = 0.30) and the test set (n = 9, r 2 = 0.96, RMSE = 0.29). In addition, this in silico model performed equally well for those molecules in the external validation sets, namely one set of benzene and naphthalene derivatives (n = 45, r 2 = 0.81, RMSE = 0.46) and one set of amine neurotransmitters (n = 4, r 2 = 0.98, RMSE = 0.32). Furthermore, when compared with crystal structures, the calculated results are consistent with the published CYP2A6-substrate co-complex structure and the plasticity nature of CYP2A6 is also revealed. Conclusions  This PhE/SVM model is an accurate and robust model and can be utilized for predicting interactions with CYP2A6, high-throughput screening and data mining to facilitate drug discovery. [ABSTRACT FROM AUTHOR]