Saved in:
Bibliographic Details
Main Authors: Sahil Siddique, Shahbaz Husain Khan, Tanzeer Reyaz
Format: Recurso digital
Language:
Published: Zenodo 2026
Online Access:https://doi.org/10.5281/zenodo.18679276
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901332576698368
author Sahil Siddique
Shahbaz Husain Khan
Tanzeer Reyaz
author_facet Sahil Siddique
Shahbaz Husain Khan
Tanzeer Reyaz
contents <p>The rapid growth of machine learning has significantly transformed the healthcare sector by enabling intelligent and data-driven disease prediction systems. Early and simultaneous detection of multiple diseases is essential for reducing mortality rates, improving treatment planning, and minimizing healthcare costs. This research proposes a machine learning–based framework for the prediction of three major chronic diseases heart disease, diabetes, and Parkinson’s disease using the Support Vector Machine (SVM) algorithm. The proposed system utilizes publicly available medical datasets containing demographic, clinical, and biomarker attributes. Data preprocessing, feature selection, and model optimization techniques are applied to improve prediction performance and generalization ability. SVM is selected due to its robustness, high classification accuracy, and ability to handle nonlinear relationships in medical data. Furthermore, the study extends the framework by incorporating stress detection using multimodal physiological signals from the WESAD dataset. Machine learning and deep learning techniques are employed to classify individuals based on stress levels using non-invasive biosignal data. The integration of disease prediction and stress monitoring demonstrates the feasibility of building an intelligent clinical decision support system. Experimental results show that the proposed framework can assist healthcare professionals in early diagnosis, personalized treatment planning, and population-level health monitoring. The findings highlight the potential of machine learning to improve healthcare delivery, enhance diagnostic accuracy, and support preventive medicine.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18679276
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle REAL TIME SIGN LANGUAGE DETECTION
Sahil Siddique
Shahbaz Husain Khan
Tanzeer Reyaz
<p>The rapid growth of machine learning has significantly transformed the healthcare sector by enabling intelligent and data-driven disease prediction systems. Early and simultaneous detection of multiple diseases is essential for reducing mortality rates, improving treatment planning, and minimizing healthcare costs. This research proposes a machine learning–based framework for the prediction of three major chronic diseases heart disease, diabetes, and Parkinson’s disease using the Support Vector Machine (SVM) algorithm. The proposed system utilizes publicly available medical datasets containing demographic, clinical, and biomarker attributes. Data preprocessing, feature selection, and model optimization techniques are applied to improve prediction performance and generalization ability. SVM is selected due to its robustness, high classification accuracy, and ability to handle nonlinear relationships in medical data. Furthermore, the study extends the framework by incorporating stress detection using multimodal physiological signals from the WESAD dataset. Machine learning and deep learning techniques are employed to classify individuals based on stress levels using non-invasive biosignal data. The integration of disease prediction and stress monitoring demonstrates the feasibility of building an intelligent clinical decision support system. Experimental results show that the proposed framework can assist healthcare professionals in early diagnosis, personalized treatment planning, and population-level health monitoring. The findings highlight the potential of machine learning to improve healthcare delivery, enhance diagnostic accuracy, and support preventive medicine.</p>
title REAL TIME SIGN LANGUAGE DETECTION
url https://doi.org/10.5281/zenodo.18679276