AI Diagnostic Assistant (AIDA): A Predictive Model for Diagnoses from Health Records in Clinical Decision Support Systems
Abstract
Clinical Decision Support Systems (CDSS) play an increasingly important role in medical diagnostics. We present AI Diagnostic Assistant (AIDA), a real-time predictive model designed to assist doctors in interpreting patient conditions. AIDA analyzes electronic health records (EHR), including medical history, laboratory results, and complaints, to suggest potential diagnoses from 95 common conditions before the doctor makes the final decision. The model acts as a verification and backup tool, ensuring that no critical details are overlooked. Trained on 1.5 million patient records and validated on a dataset curated by a panel of experts, AIDA proves trustworthy as a diagnosis-making assistant (87.7% accuracy compared to 91.7% accuracy among doctors). Integrated into a megapolis-wide CDSS, AIDA has assisted doctors in over 3 million real-world diagnoses to date.
Cite
Text
Umerenkov et al. "AI Diagnostic Assistant (AIDA): A Predictive Model for Diagnoses from Health Records in Clinical Decision Support Systems." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/1098Markdown
[Umerenkov et al. "AI Diagnostic Assistant (AIDA): A Predictive Model for Diagnoses from Health Records in Clinical Decision Support Systems." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/umerenkov2025ijcai-ai/) doi:10.24963/IJCAI.2025/1098BibTeX
@inproceedings{umerenkov2025ijcai-ai,
title = {{AI Diagnostic Assistant (AIDA): A Predictive Model for Diagnoses from Health Records in Clinical Decision Support Systems}},
author = {Umerenkov, Dmitriy and Nesterov, Alexandr and Shaposhnikov, Vladimir and Abramov, Ruslan and Romanenko, Nikolay and Kokh, Vladimir and Kirina, Marina and Abrosimov, Anton and Dylov, Dmitry V. and Oseledets, Ivan V.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2025},
pages = {9880-9889},
doi = {10.24963/IJCAI.2025/1098},
url = {https://mlanthology.org/ijcai/2025/umerenkov2025ijcai-ai/}
}