Revolutionizing disease detection and revealing hidden patterns

[ad_1]

Researchers have developed a machine learning approach to identify potential disease subtypes, significantly improving disease classification and treatment strategies. The model, which achieved an AUC ROC of 89.4%, discovered 515 previously unannotated disease subtypes, demonstrating the potential for more precise and personalized medical treatments.

Researchers at the Hebrew University of Jerusalem have developed a machine learning approach to identify potential disease subtypes, significantly improving the field of disease classification and treatment strategies. The study, led by PhD student Dan Ofer and Professor Michal Linial of the Department of Biological Chemistry at the Hebrew University’s Institute of Life Sciences, marks a significant advance in the use of artificial intelligence in medical research.

Distinguishing diseases into distinct subtypes is essential for accurate study and effective treatment strategies. The Open Targets platform integrates biomedical, genetic, and biochemical datasets to support disease ontologies, classifications, and potential genetic targets. However, many disease annotations remain incomplete, often requiring extensive intervention by medical experts. This challenge is particularly important for rare and orphan diseases, where resources are limited.

The study presents a novel machine learning approach to identify diseases with potential subtypes. Using the large database of approximately 23,000 diseases documented in the Open Targets platform, they derived novel features to predict diseases with subtypes using direct evidence. Machine learning models were then applied to analyze feature importance and evaluate predictive performance, thereby discovering known and novel disease subtypes.

The model achieved an impressive 89.4% ROC area under the receiver operating characteristic curve for identifying known disease subtypes. The integration of pre-trained deep learning language models further improved the model’s performance. Notably, the research identified 515 disease candidates that were predicted to have previously unannotated subtypes, opening up new insights into disease classification.

“This project demonstrates the incredible potential of machine learning to expand our understanding of complex diseases,” said Dan Ofer. “By leveraging advanced models, we can uncover patterns and subtypes that were previously hidden, contributing to more precise and personalized treatments.”

This innovative methodology enables a robust and scalable approach to improve knowledge-based annotations and provides a comprehensive assessment of disease ontology levels. “We are excited about the potential of our machine learning approach to revolutionize disease classification,” said Professor Michal Linial. “Our results can contribute significantly to personalized medicine, offering new perspectives for therapeutic development.”

/Public dissemination. This content from the original organization/authors may be of a point-in-time nature and edited for clarity, style, and length. Mirage.News takes no institutional position or bias, and all views, positions, and conclusions expressed herein are solely those of the author(s). See the full story here.

Leave a Comment