Aug 2026· Journal of Intelligent Decision Making and Information Science· 0 citations· 20 references
TL;DR
A multi-model framework using wearable sensor data to improve early disease risk prediction and support timely clinical decisions enables more robust and interpretable disease risk predictions and supports health monitoring, early clinical interventions as well as evidence-based clinical and healthcare decisions.
Abstract
Disease risk can be predicted and clinical decisions can be made early based on wearable sensor data of physiological and behavioral parameters. However, patterns in wearable data of disease development are mostly non-linear, time-dependent, and influenced by individual health variations. Therefore, it is challenging to get reliable results with a single machine learning model for disease risk prediction. This study introduces a multi-model framework using wearable sensor data to improve early disease risk prediction and support timely clinical decisions. First, the data is processed using a data cleaning, normalization, missing value handling, feature extraction and class balancing. Then, a variety of predictors such as Support Vector Machine, Random Forest, Extreme Gradient Boosting and Long Short-Term Memory networks are trained and tested. The prediction probabilities of the single models are integrated in a stacking-approach. An intelligent decision making component classifies users into different disease risk categories (low, moderate, high) based on predicted probabilities and on clinical decision making thresholds. The framework is complemented by Explainable AI to identify the most influential physiological parameters for individual user risk scores. Performance is measured by accuracy, precision, recall, F1-score, area under ROC curve, sensitivity, specificity and by calibration. In comparison to individual machine learning models, the proposed multi-model framework enables more robust and interpretable disease risk predictions and supports health monitoring, early clinical interventions as well as evidence-based clinical and healthcare decisions.
Experimental results demonstrate that Machine Learning techniques can effectively predict disease occurrence with high accuracy, thereby assisting healthcare professionals in early diagnosis and treatment planning.
Sunidhi, Mothe Rahul, M. Kumar et al.· International Journal for Re...· 0 citations
This paper proposes a machine learning–based multi-disease prediction system that integrates disease-specific classifiers within a unified, real-time clinical decision-support platform. The framework employs Support Vector Machine (RBF) for diabetes prediction, Support Vector Machine (linear) for heart disease, Decision Tree for chronic kidney disease (CKD), and Logistic Regression for cancer prediction, with each classifier selected according to the statistical characteristics of its respective dataset. The system is implemented using a Streamlit-based web interface, enabling efficient real-time prediction with interpretable outputs. Experimental evaluation demonstrates strong predictive performance, achieving accuracies ranging from 85.71% to 94.30% and AUC-ROC values between 0.91 and 0.97 across the four disease modules, representing a 7.2 percentage-point improvement over comparable unified prediction systems reported in the literature. The modular architecture provides scalability, low computational complexity, and rapid inference, making it suitable for pre-diagnostic screening in clinical environments. The proposed framework offers an effective and practical solution for early chronic disease detection while supporting future expansion. Planned enhancements include the integration of deep learning models for medical imaging and electronic health records, Explainable Artificial Intelligence (XAI) techniques such as SHAP and LIME, wearable and IoT-based continuous health monitoring, federated learning for privacy-preserving distributed model training, and prospective clinical validation through hospital information system integration. These developments are expected to improve prediction accuracy, interpretability, scalability, and clinical applicability for next-generation intelligent healthcare systems.
Chandrasekar.M, Y. S, Adithiyaa K.B· 2026 International Conferenc...· 0 citations
Diabetes has become a health problem worldwide. It often goes unnoticed until it causes health issues. Finding diabetes early using a lot of health and personal data can help reduce the diseases impact and healthcare costs. This study proposes a machine learning system for diabetes prediction. This system uses techniques to prepare data select important features handle unequal class distributions and combine multiple models. It is designed to process types of data from Electronic Health Records (EHRs) lifestyle factors and clinical measurements efficiently. Multiple machine learning models, for example tree-based classifiers, simple linear models and combined models are. Tested. Cross-validation is used to ensure the models are reliable and can be scaled up. The prediction of diabetes mellitus is based on identifying factors, so the importance analysis of characteristics is used to find the most influential predictors of diabetes. Oversampling of medical data involves the use of oversampling to overcome the problem of class distributions. The findings indicate that the given approach is more accurate, precise, possesses higher recall and F1-score, as well as ROC-AUC, compared to other models. This developed system offers an understandable solution for assessing diabetes risk early. It can be used in healthcare screening systems and clinical decision-support platforms for diabetes mellitus.
Thatikonda Krishna Kalyan Gupta, Oruganti Yashwanth Reddy, I. S et al.· 2026 International Conferenc...· 0 citations
The problem of early detection of cardiovascular risk is still a powerful challenge because the interplay of physiological, behavioral, and clinical factors involved in cardiac conditions is rather complex. In many health care settings, risk analysis is usually put aside until the symptoms have worsened, which limits the possibility of taking timely action. The current paper presents a proposed intelligent clinical decision-support system that employs monitored machine-learning methods to measure cardiovascular risk based on traditional clinical measures. The proposed system does not rely on the disconnected parameters of the medical condition of a patient but rather asks multidimensional patient data to reveal the non-linear relationship that is often missed by conventional diagnostic tools. The framework also involves systematic data cleaning, feature- relevance analysis, and model optimisation to enhance predictive consistency. Several classification algorithms such as tree based classification algorithms and probabilistic classification algorithms are considered to provide reliability and generalization. The deployment architecture is lightweight, which supports real-time risk scoring, making the system suitable in practice clinical environment. Reconfiguring ordinary clinical information into actionable risk insights, the suggested approach also lies at the core of early-stage intervention, enhancing the effectiveness of the diagnostic process and progressing the creation of data-driven intelligent health-care systems.
M. Menaka, R. C. Kumar, Nathella Adithya Ram et al.· International Conference on...· 0 citations
The paper presents the framework that mediates between optimization methods and predictive modeling to provide valuable information on the next generation of data-driven cardiovascular diagnostics to provide valuable information on the next generation of data-driven cardiovascular diagnostics.
Shamal Salunkhe, Smita Bharne, P. Patil et al.· International Research Journ...· 0 citations
There is an urgent need for explainable, clinically validated and standardised ML frameworks to translate predictive models into routine healthcare practice and improve early detection of cardiovascular disease.
Hanna Rasheed, Arya.K.R Arya.K.R, Ashida.K.A Ashida.K.A· International Journal of Tec...· 0 citations