Simulation-Based Machine Learning Approach to Classify Accelerated Biological Aging Using Telomere and Epigenetic Markers

Classification and prediction tasks are common in health research. With the increasing availability of vast health data repositories (e.g. electronic medical record databases) and advances in computing power, traditional statistical approaches are being augmented or replaced with machine learning (ML) approaches to classify and predict health outcomes. ML describes the automated process of identifying ("learning") patterns in data to perform tasks. Developing an ML model includes selecting between many ML models (e.g. decision trees, support vector machines, neural networks); model specifications such as hyperparameter tuning; and evaluation of model performance. This process is conducted repeatedly to find the model and corresponding specifications that optimize some measure of model performance. ML models can make more accurate classifications and predictions than their statistical counterparts and confer greater flexibility when modelling unstructured data or interactions between covariates; however, many ML models require larger sample sizes to achieve good classification or predictive performance and have been criticized as "black box" for their poor transparency and interpretability. ML holds potential in family medicine for risk profiling of patients' disease risk and clinical decision support to present additional information at times of uncertainty or high demand. In the future, ML approaches are positioned to become commonplace in family medicine. As such, it is important to understand the objectives that can be addressed using ML approaches and the associated techniques and limitations. This article provides a brief introduction into the use of ML approaches for classification and prediction tasks in family medicine.

Abstract: Accurate prediction of maximum scour depth (MSD) at sluice gates is critical for guaranteeing the stability and safety of hydraulic systems. Traditional empirical formulas often fail to capture the non-linear interactions between flow dynamics, sediment characteristics, and structural configurations. This study addresses these limitations by leveraging advanced machine learning (ML) techniques, specifically tree-based models, to enhance predictive accuracy. The performance of three tree-based models–Extra Trees (ERT), CatBoost (CAT), and Histogram-Based Gradient Boosting (HGB)–was examined using two hyperparameter tuning methods: Tree-Structured Parzen Estimator (TPE) and Particle Swarm Optimization (PSO). The models underwent 100 simulations to quantify uncertainty and variability in performance metrics. The results indicate that CAT_PSO (optimized with PSO) exhibits superior predictive performance compared to empirical formulas and other ML techniques. CAT_PSO achieved the highest mean CORR (correlation coefficient) of 0.9644 and mean NSE (Nash-Sutcliffe Efficiency) of 0.9272. HGB models demonstrated slightly lower performance compared to CAT and ERT, with higher variability in predictions. Further analysis explored the influence of individual input factors on model performance. The inclusion of more variables, such as tailwater depth and sediment size, generally enhanced model performance. The study also developed new empirical equations for MSD estimation by considering both multiplicative and additive models, progressively incorporating additional input features. These new formulas show improved predictive accuracy over empirical methods, though they still fall short of the performance achieved by the ML models.

DNA methylation (DNAm)-based marker of aging, referred to as 'epigenetic age' or 'DNAm age' is a highly accurate multi-tissue biomarker for aging, associated with age-related disease risk, including cancer. Breast cancer (BC), an age-associated disease, is associated with older DNAm age and epigenetic age acceleration (age accel) at tissue levels. But this raises a question on the predictability of DNAm age/age accel in BC development, emphasizing the importance of studying DNAm age in pre-diagnostic peripheral blood (PB) in BC etiology and prevention. We included postmenopausal women from the largest study cohort and prospectively investigated BC development with their pre-diagnostic DNAm in PB leukocytes (PBLs). We estimated Horvath's pan-tissue DNAm age and investigated whether DNAm age/age accel highly correlates with risk for developing subtype-specific BC and to what degree the risk is modified by hormones and lifestyle factors. DNAm age in PBLs was tightly correlated with age in this age range, and older DNAm age and epigenetic age accel were significantly associated with risk for developing overall BC and luminal subtypes. Of note, in women with bilateral oophorectomy before natural menopause experiencing shorter lifetime estrogen exposure than those with natural menopause, epigenetic age accel substantially influenced BC development, independent of obesity status and exogeneous estrogen use. Our findings contribute to better understanding of biologic aging processes that mediate BC carcinogenesis, detecting a non-invasive epigenetic aging marker that better reflects BC development, and ultimately identifying the elderly with high risk who can benefit from epigenetically targeted preventive interventions.

For proper design and operation of biomass‐based energy systems, it is important to determine the higher heating value (HHV) of biomass. In this paper, two machine learning (ML) approaches, namely extra trees (ET) and least squares support vector machine (LSSVM), are used to predict the value of HHV associated with biofuels. The data required for HHV calculation, including proximate and ultimate analyses datasets, were collected from the literature. The performances of these two ML approaches for predicting biomass HHV were then compared with other smart models available in the literature. Even though the available empirical models can predict the biomass HHV with acceptable precision, it was found that our proposed ML techniques have a superior performance based on the error analysis; the proposed approaches also consider all key biomass characteristics in the developed models. In addition, the ET model proved to be slightly more accurate compared to the LSSVM model. Additionally, the developed proximate‐based ET model showed better performance compared to the ultimate‐based ET model. The most influential parameters in the developed ET models for the proximate and ultimate approaches were determined to be ash fraction and carbon fraction, respectively. Finally, it was concluded that the smart modelling techniques can be utilized as a robust and reliable alternative predictive methodology to replace direct laboratory measurement of the biomass HHV.

The design of this system shows the efficient prediction of heart diseases by the implementation of machine learning multiple classifiers algorithm. The UCI Heart Disease Dataset is used, while the data preprocessing involves filling missing values, encoding of categorical values, scaling of features, and selection of important features. Three machine learning classifiers, namely Random Forest Classifier, Gradient Boosting Classifier, and Logistic Regression are implemented. The implementation involves training the machine learning models using the RandomizedSearchCV technique and cross-validation technique. The evaluation of the model's performance is done using measures such as ACCURACY, PRECISION, RECALL, and F1-SCORE. A fair comparison is conducted to select the best performing model automatically using accuracy. Results show that the Random Forest model performed the best with an accuracy of 81.67%, compared to the rest of the models. Evaluation of feature importance shows key clinical features that significantly contribute to the accuracy. Keywords— Heart Disease Prediction, Machine Learning, Random Forest, Gradient Boosting, Logistic Regression, Feature Selection, Classification, Healthcare Analytics, UCI Dataset, Predictive Modeling

Background Current heart failure guidelines emphasize the importance of timely detection of subclinical left ventricular (LV) remodelling and dysfunction for more precise risk stratification of asymptomatic subjects. Both LV diastolic dysfunction (LVDD) and LV hypertrophy (LVH) as assessed by echocardiography are known independent prognostic markers of future cardiovascular events in the community. However, selective screening strategies of individuals at risk who would benefit most from in-depth cardiac phenotyping are lacking. Purpose We assess the utility of several Machine Learning (ML) classifiers built on clinical and biochemical features for detecting subclinical LV abnormalities. Methods We included 1407 participants (mean age, 51 years, 51% women) randomly recruited from the general population. We used echocardiographic parameters reflecting LV diastolic function and structure to define LV abnormalities (LVDD, n=239; LVH, n=135). After that four supervised ML algorithms (Random Forest (RF), Gradient Boosting (GD), Stochastic Gradient Descent (SGD) and Support Vector Machines (SV)) were built based on routine clinical, hemodynamic and laboratory data (features; n=61) to categorize LVDD and LVH (two prediction tasks). We applied a 10-fold stratified cross-validation set-up. Results ML classifiers exhibited a high area under the ROC (AUC) for predicting LVDD with values between 88.5% and 93.1% (Figure, left panel). Age, BMI, different components of blood pressure, antihypertensive treatment, routine biomarkers such as serum electrolytes, creatinine, blood sugar, leptin, uric acid, lipid profile, as well as blood cell counts were the top selected features for predicting LVDD. Prediction AUC of ML algorithms for detection of LVH was somewhat lower than for LVDD and ranged from 72.5% to 78.7% (Figure, right panel). The top selected features for LVH classifier were similar to those of LVDD, but also included social class, serum gamma-glutamyl transferase, fasting insulin, plasma renin activity and cortisol. ROC curves (sensitivity-1-specificity) Conclusions ML algorithms combining routinely measured clinical and laboratory data have shown high accuracy of LVDD and LVH prediction. These ML classifiers might be useful to preselect individuals at risk for further in depth echocardiographic examination, monitoring and implementation of preventive strategies in order to delay transition to disease symptoms.

Accurately predicting thermophysical properties across various physical states is essential for both industrial and scientific applications. However, experimental data often exhibit variability and noise, requiring robust modeling approaches. In this work, we employ machine learning (ML) techniques to predict methane's thermophysical properties in liquid, vapor, and supercritical phases, including isobaric and isochoric heat capacities, density, specific volume, Joule-Thomson coefficients, enthalpies, sound speed, and shear viscosities, applying an approach recently developed [ACS Eng. Au 5, 226 (2025)10.1021/acsengineeringau.5c00001]. We explore various ML algorithms, including Adaptive Boosting, Bagging, Decision Trees, Extra Trees, Gradient Boosting, Histogram-based Gradient Boosting Regression Tree, K-Nearest Neighbors, Light Gradient Boosting Machine, Nu-Support Vector Regression, Random Forest, Extreme Gradient Boosting, and Artificial Neural Networks. The ML models, which use raw experimental data without removing outliers, produce predictions that are closer to those obtained from the equations of state (EOS) employed by the National Institute of Standards and Technology than to the same raw experimental data used as input for developing the EOS. These results highlight ML's potential to identify and generalize complex patterns, smooth inherent noise, and manage the variability of different thermophysical properties. They indicate that ML models, particularly Extra Trees and Gradient Boosting, can offer a scalable alternative for thermophysical property predictions, offering consistency and efficiency over traditional methods. Although our approach does not eliminate preprocessing, it demonstrates that ML can effectively manage noisy data independently, offering a more efficient and cost-effective alternative to conventional pre- and postprocessing techniques.

Multimodal machine learning for predicting perioperative safety indicators in spinal surgery.

BackgroundNearly 20% of pregnancies in patients with Systemic lupus erythematosus (SLE) result in an adverse pregnancy outcome (APO); early identification of women with SLE who are at high risk of...

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

Ever since the introduction of Bitcoin, cryptocurrencies have attracted interest from many due to their potential for appreciation. They have also been stigmatized for their volatility, low correlation with traditional assets, and uncertain regulatory conditions. Nevertheless, many cryptocurrencies still attract the attention of major players in finance. As in the management of a portfolio of other assets, there is a need to regularly rebalance the portfolio to optimize returns across different time horizons. This study evaluates four machine learning models, Logistic Regression, Decision Tree, K-Nearest Neighbors, and Gradient Boosting, for identifying optimal cryptocurrency rebalancing decisions. Using a momentum-based approach with a 30-day forward window, the models are trained to classify assets as hold or rebalance based on future price movement. Our approach is based on feature engineering and hyperparameter tuning. Results show that tree-based models, such as Decision Tree and Gradient Boosting, demonstrate superior classification performance in identifying optimal rebalancing moments. However, the study also highlights the limitations of using historical data exclusively without referring to other external factors such as market sentiment and regulatory changes. Overall, the study makes a contribution to the field of cryptocurrency portfolio management by providing one of the first comparative evaluations of multiple ML architectures for cryptocurrency rebalancing decisions, demonstrating the potential of machine learning to improve portfolio management in highly volatile markets.

Machine learning (ML) methods have shown great potential in predicting colorectal cancer (CRC) survival. However, the ML models introduced thus far have mainly focused on binary outcomes and have not considered the time-to-event nature of this type of modeling. This study aims to evaluate the performance of ML approaches for modeling time-to-event survival data and develop transparent models for predicting CRC-specific survival. The data set used in this retrospective cohort study contains information on patients who were newly diagnosed with CRC between December 28, 2012, and December 27, 2019, at West China Hospital, Sichuan University. We assessed the performance of 6 representative ML models, including random survival forest (RSF), gradient boosting machine (GBM), DeepSurv, DeepHit, neural net-extended time-dependent Cox (or Cox-Time), and neural multitask logistic regression (N-MTLR) in predicting CRC-specific survival. Multiple imputation by chained equations method was applied to handle missing values in variables. Multivariable analysis and clinical experience were used to select significant features associated with CRC survival. Model performance was evaluated in stratified 5-fold cross-validation repeated 5 times by using the time-dependent concordance index, integrated Brier score, calibration curves, and decision curves. The SHapley Additive exPlanations method was applied to calculate feature importance. A total of 2157 patients with CRC were included in this study. Among the 6 time-to-event ML models, the DeepHit model exhibited the best discriminative ability (time-dependent concordance index 0.789, 95% CI 0.779-0.799) and the RSF model produced better-calibrated survival estimates (integrated Brier score 0.096, 95% CI 0.094-0.099), but these are not statistically significant. Additionally, the RSF, GBM, DeepSurv, Cox-Time, and N-MTLR models have comparable predictive accuracy to the Cox Proportional Hazards model in terms of discrimination and calibration. The calibration curves showed that all the ML models exhibited good 5-year survival calibration. The decision curves for CRC-specific survival at 5 years showed that all the ML models, especially RSF, had higher net benefits than default strategies of treating all or no patients at a range of clinically reasonable risk thresholds. The SHapley Additive exPlanations method revealed that R0 resection, tumor-node-metastasis staging, and the number of positive lymph nodes were important factors for 5-year CRC-specific survival. This study showed the potential of applying time-to-event ML predictive algorithms to help predict CRC-specific survival. The RSF, GBM, Cox-Time, and N-MTLR algorithms could provide nonparametric alternatives to the Cox Proportional Hazards model in estimating the survival probability of patients with CRC. The transparent time-to-event ML models help clinicians to more accurately predict the survival rate for these patients and improve patient outcomes by enabling personalized treatment plans that are informed by explainable ML models.

While cognitive behavioral therapy has shown efficacy in treating stress-related disorders, such as adjustment disorder and exhaustion disorder, knowledge about factors contributing to treatment response is limited. Improved identification of such factors could enhance assessment procedures and treatment strategies. In addition, evaluating how traditional prediction methods and machine learning can complement each other may help bridge gaps in understanding and predicting treatment response. This study aims to (1) evaluate putative predictors of treatment response in patients with stress-related disorders using traditional prediction methods and (2) model treatment outcomes using a machine learning approach. This design combines the interpretability of traditional methods with the ability of machine learning to identify complex patterns. We will analyze data from a randomized controlled trial comparing 2 internet-delivered treatments, cognitive behavioral therapy versus an active control treatment, for patients diagnosed with adjustment disorder or exhaustion disorder (N=300). Prediction models will be based on pooled data from both treatment arms due to the limited sample size and lack of knowledge on predictors of treatment effects. Putative predictors include sociodemographic and clinical information, clinician-assessed data, self-rated symptoms, and cognitive test scores. The primary outcome of interest is responder status on the Perceived Stress Scale-10, evaluated based on the reliable change index posttreatment. For the traditional approach, univariate logistic regressions will be conducted for each predictor, followed by an ablation study for significant predictors. For the machine learning approach, 4 classifiers (logistic regression with elastic net, random forest, support vector machine, and AdaBoost) will be trained and evaluated. The dataset will be split into training (70%) and testing (30%) sets. Hyperparameter tuning will be conducted using 5-fold cross-validation with randomized search. Model performance will be assessed using balanced accuracy, precision, recall, and area under the curve. All data were collected between April 2021 and September 2022. We hypothesize that key predictors will include younger age, education level, baseline symptom severity, treatment credibility, and history of sickness absence. We anticipate that the machine learning models will outperform a dummy model predicting the majority class and achieve a balanced accuracy of ≥67%, thus indicating clinical usefulness. This study will contribute to the limited research on predictors of treatment outcome in stress-related disorders. The findings could support the development of more personalized and effective treatments for individuals diagnosed with adjustment disorder or exhaustion disorder, potentially improving clinical practice and patient outcomes. If successful, this dual approach may encourage future studies with larger datasets and the implementation of machine learning models in clinical settings, ultimately enhancing precision in mental health care. DERR1-10.2196/65790.

In-hospital cardiac arrest (IHCA) in the emergency department (ED) is not uncommon but often fatal. Using the machine learning (ML) approach, we sought to predict ED-based IHCA (EDCA) in patients presenting to the ED based on triage data. We retrieved 733,398 ED records from a tertiary teaching hospital over a 7year period (Jan. 1, 2009-Dec. 31, 2015). We included only adult patients (≥ 18y) and excluded cases presenting as out-of-hospital cardiac arrest. Primary outcome (EDCA) was identified via a resuscitation code. Patient demographics, triage data, and structured chief complaints (CCs), were extracted. Stratified split was used to divide the dataset into the training and testing cohort at a 3-to-1 ratio. Three supervised ML models were trained and performances were evaluated and compared to the National Early Warning Score 2 (NEWS2) and logistic regression (LR) model by the area under the receiver operating characteristic curve (AUC). We included 316,465 adult ED records for analysis. Of them, 636 (0.2%) developed EDCA. Of the constructed ML models, Random Forest outperformed the others with the best AUC result (0.931, 95% CI 0.911-0.949), followed by Gradient Boosting (0.930, 95% CI 0.909-0.948) and Extra Trees classifier (0.915, 95% CI 0.892-0.936). Although the differences between each of ML models and LR (AUC: 0.905, 95% CI 0.882-0.926) were not significant, all constructed ML models performed significantly better than using the NEWS2 scoring system (AUC 0.678, 95% CI 0.635-0.722). Our ML models showed excellent discriminatory performance to identify EDCA based only on the triage information. This ML approach has the potential to reduce unexpected resuscitation events if successfully implemented in the ED information system.

The triage of patients in the Emergency Department (ED) plays a critical role in determining the urgency and type of treatment that shall be administered. Therefore, an accurate prediction system for patient triage can be very helpful. This study aims to develop a Machine Learning (ML) classification model to predict triage decisions for patients admitted to the ED at UNS Hospital. Several classification models were evaluated, including Naïve Bayes (NB), Decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). To assess model performance, multiple metrics were employed: accuracy, precision, recall, F1-score, and the confusion matrix. Following an initial evaluation, hyperparameter tuning was conducted on the selected best-performing model to identify the optimal combination of parameters for improved predictive performance. RF emerged as the best-performing model for triage prediction. The parameters tuned included the number of estimators, criterion, maximum features, and maximum depth, using a 5-fold cross-validation strategy. The optimal parameter values were found to be 900 estimators, 'entropy' for the criterion, 'log2' for max features, and a maximum depth of 40. The results of this study demonstrate that hyperparameter tuning can significantly enhance model performance, reducing recall errors, improving the F1-score, and decreasing the number of mispredictions.