Abstract

Introduction

The integration of Artificial Intelligence (AI) into telemedicine represents a transformative advancement in the delivery of remote healthcare services. In rural communities of Nepal, geographical difficulties have deprived many adequate health facilities. To address this problem, this paper explores the synergistic potential of AI to enhance telemedicine by improving diagnostic accuracy, personalizing patient care, and optimizing healthcare resource management.

Methods:

The proposed framework incorporates machine learning techniques in telemedicine. The survey was conducted in a remote village and data were collected from 250 people. Data consist of different parameters, such as age, alcohol consumption, coughing, chest pain, and shortness of breath. The paper compares and examines machine learning algorithms, such as Naive Bayes, Support Vector, and Random Forest, to predict lung cancer disease. The result is evaluated using accuracy and k-fold cross-validation.

Results:

The result shows that Random Forest exhibits higher accuracy (95.4%) and Naive Bayes exhibits lower accuracy (76.2%). The finding shows that people in their 50s, 60s, or 70s who consume more alcohol have the highest chances of having lung cancer.

Conclusions: By providing a comparison among different machine learning techniques, this paper aims to inform healthcare professionals, policymakers, and technologists about the critical role of AI in shaping the future of telemedicine and to offer actionable insights for effectively integrating these machine learning technologies. With this, the people of remote villages will benefit and the diagnosis will be simplified. However, there are limitations to data privacy and misinformation. In the future, new techniques such as deep learning neural networks and big data techniques can be integrated into telemedicine with image processing capabilities to enhance the role of AI in telemedicine.

Keywords: artificial intelligence(AI); telemedicine; remote healthcare; health data integration; health records; rural community