Electronic Health Record
Electronic health records (EHRs) are digital repositories of patient medical information, aiming to improve healthcare efficiency and quality. Current research focuses on enhancing EHR utility through advanced natural language processing (NLP) techniques, including transformer-based models and graph neural networks, to improve data extraction, analysis, and prediction of patient outcomes. These efforts address challenges like data security, interoperability, and the need for efficient clinical decision support systems, ultimately impacting patient care, research, and administrative workflows. The development of robust and reliable methods for processing and analyzing EHR data is a key area of ongoing investigation.
Papers
Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges
Hiba Ahsan, Denis Jered McInerney, Jisoo Kim, Christopher Potter, Geoffrey Young, Silvio Amir, Byron C. Wallace
PRISM: Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration for EHR Data Sparsity Mitigation
Yinghao Zhu, Zixiang Wang, Long He, Shiyun Xie, Xiaochen Zheng, Liantao Ma, Chengwei Pan
Contrastive Learning of Temporal Distinctiveness for Survival Analysis in Electronic Health Records
Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Bin Liu, Mei Liu, Zijun Yao
Considerations for health care institutions training large language models on electronic health records
Weipeng Zhou, Danielle Bitterman, Majid Afshar, Timothy A. Miller
From Military to Healthcare: Adopting and Expanding Ethical Principles for Generative Artificial Intelligence
David Oniani, Jordan Hilsman, Yifan Peng, COL, Ronald K. Poropatich, COL Jeremy C. Pamplin, LTC Gary L. Legault, Yanshan Wang
Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke
Qizhang Feng, Jiayi Yuan, Forhan Bin Emdad, Karim Hanna, Xia Hu, Zhe He