AI-Powered Disease Diagnosis: Evaluating the Effectiveness of Machine Learning Algorithms

EasyChair Preprint 15084

Abstract

The integration of Artificial Intelligence (AI) and Machine Learning (ML) in healthcare has revolutionized disease diagnosis, offering the potential for early detection, improved accuracy, and personalized treatment. This paper evaluates the effectiveness of various ML algorithms in diagnosing a wide range of diseases, including cardiovascular conditions, cancer, neurological disorders, and infectious diseases. By analyzing key supervised and unsupervised learning algorithms such as Support Vector Machines, Random Forests, Neural Networks, and K-means Clustering, this study explores their applications, strengths, and limitations in clinical settings. Evaluation metrics including accuracy, precision, recall, and AUC are used to assess the performance of these algorithms. The paper also highlights significant challenges in AI-powered diagnostics, such as data quality, interpretability of models, ethical considerations, and integration into clinical workflows. Finally, it examines the future prospects of AI in disease diagnosis, emphasizing advances in deep learning, personalized medicine, and AI-human collaborative models. The findings underscore the transformative role of AI in enhancing diagnostic efficiency while acknowledging the need for further research, ethical oversight, and regulatory frameworks to ensure safe and equitable implementation.

Keyphrases: Artificial Intelligence, Healthcare, neural networks

@booklet{EasyChair:15084,
  author    = {Ayuns Luz and David Ray},
  title     = {AI-Powered Disease Diagnosis: Evaluating the Effectiveness of Machine Learning Algorithms},
  howpublished = {EasyChair Preprint 15084},
  year      = {EasyChair, 2024}}