Development of Machine Learning-Based Mpox Surveillance Models in a Learning Health System

medRxiv [Preprint]. 2024 Sep 27:2024.09.25.24314318. doi: 10.1101/2024.09.25.24314318.

Abstract

We developed machine learning and deep learning models to identify mpox cases from clinical notes as part of a learning health system initiative. Lasso regression outperformed deep learning models, excelled in minimizing false positives, and may prove helpful for flagging missed or delayed diagnoses as part of continuous quality improvement.

Keywords: artificial intelligence; health equity; learning health system; machine learning; mpox.

Publication types

  • Preprint