Electronic Health Record-Based Machine Learning for Risk Prediction and Deployment into Clinical Workflows

Supervised Approaches to Risk Prediction

Shung DL, Chan CE, You K, Nakamura S, Saarinen T, Zheng NS, Simonov M, Li DK, Tsay C, Kawamura Y, Shen M, Hsiao A, Sekhon J*, Laine L*. Validation of an Electronic Health Record-Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding. Gastroenterology. 2024 Jul 5:S0016-5085(24)05183-7.

Shung D, Huang J, Castro E, Tay JK, Simonov M, Laine L, Batra R, Krishnaswamy S. Neural network predicts need for red blood cell transfusion for patients with acute gastrointestinal bleeding admitted to the intensive care unit. Nature Scientific Reports 2021; 11, 8827.

Shung DL, Au B, Taylor RA, Tay JK, Laursen SB, Stanley AJ, Dalton HR, Ngu J, Schultz M, and Laine L. Validation of a machine learning model that outperforms clinical risk scoring systems for upper gastrointestinal bleeding. Gastroenterology. 2020 Jan;158(1):160-167. doi: 10.1053/j.gastro.2019.09.009. Epub 2019 Sep 25.

Phenotyping

Shung D, Tsay C, Laine L, Chang D, Li F, Thomas P, Partridge C, Simonov M, Hsiao A, Tay JK, Taylor A. Early Identification of Patients with Acute Gastrointestinal Bleeding in the Emergency Department using Electronic Health Record Phenotyping. Journal of Gastroenterology and Hepatology. 2020; 36 (6), 1590-1597

GutGPT: An Integrated Generative AI product for Clinical Decision Support

Rajashekar N, Shin Y, Pu Y, Chung S, You K, Giuffre M, Chan C, Saarinen T, Hsiao A, Sekhon J, Wong A, Evans L, Kizilcec R, Laine L, Mccall T, Shung DL. 2024. Human-Algorithmic Interaction Using a Large Language Model-Augmented Artificial Intelligence Clinical Decision Support System. In Proceedings of the Computer Human Interaction Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 442, 1–20. https://doi.org/10.1145/3613904.3642024

Chan, C., You, K., Chung, S., Giuffrè, M., Saarinen, T., Rajashekar, N., Pu, Y., Shin, Y.E., Laine, L., Wong, A., Kizilcec, R., Sekhon J., Shung DL. 2023. Assessing the Usability of GutGPT: A Simulation Study of an AI Clinical Decision Support System for Gastrointestinal Bleeding Risk. Machine Learning for Health at NeurIPS 2023. arXiv preprint arXiv:2312.10072.

Large Language Models in Medicine & Human-Algorithmic Interaction

LLMs and Clinical Use

Giuffrè M, Kresevic S, You K, Dupont J, Huebner J, Grimshaw AA, Shung DL. Systematic review: The use of large language models as medical chatbots in digestive diseases. Alimentary Pharmacology and Therapeutics. 2024; 00: 1–23. https://doi.org/10.1111/apt.18058

Kresevic, S., Giuffrè, M., Ajcevic, M. Croce L, Shung DL. Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. Nature Digital Medicine. 7, 102 (2024). https://doi.org/10.1038/s41746-024-01091-y

Giuffrè M, Kresevic S, Pugliese N, You K, Shung DL. Optimizing large language models in digestive disease: strategies and challenges to improve clinical outcomes. Liver International. 2024; 00: 1-11. doi:10.1111/liv.15974

Human-Algorithmic Interaction

Alur, R.; Laine, L.; Li, D. K.; Raghavan, M.; Shah, D.; and Shung, D. 2023. Auditing for Human Expertise. Spotlight Designation. Neural Information Processing Systems (NeurIPS) 2023. arXiv preprint arXiv:2306.01646.

Kizilcec R, Shung D, Sung JJY. Chapter 10 - Human-machine interaction: AI-assisted medicine, instead of AI-driven medicine. Artificial Intelligence in Medicine; Academic Press 2024: 131-140. https://doi.org/10.1016/B978-0-323-95068-8.00010-8.

Methods Development

Sakai S, Shung D,* Sekhon J*. Enhancing Collaborative Medical Outcomes through Private Synthetic Hypercube Augmentation: PriSHA. AAAI 2024 Spring Symposium on Clinical Foundation Models. 2024

Tong A*, Huguet G*, Shung D*, Natik A, Kuchroo M, Lajoie G, Wolf G, Krishnaswamy S. Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance. 47th International Conference on Acoustics, Speech, & Signal Processing (ICASSP), Singapore, May 2022.  (Oral Presentation)

Gerasimiuk M*, Shung D*, Tong A, Stanley A, Schultz M, Ngu J, Laine L, Wolf G, Krishnaswamy S. MURAL: An unsupervised random forest-based embedding for electronic health record data.  Institute of Electrical and Electronics Engineers International Conference on Big Data: Healthcare Special Session (virtual) 2021. (Oral Presentation)

Kuchroo, M., Huang, J., Wong, P., Grenier J, Shung D et al. Multiscale PHATE identifies multimodal signatures of COVID-19. Nature Biotechnology 40, 681–691 (2022). https://doi.org/10.1038/s41587-021-01186-x

Clinical Research in Acute Gastrointestinal Bleeding

Shung DL*, Li DK*, You K, Hung KW, Laine L, Hughes ML. Adoption of a gastroenterology hospitalist model and the impact on inpatient endoscopic practice volume: a controlled interrupted time-series analysis. iGIE 2024. https://doi.org/10.1016/j.igie.2024.04.008.

Shung DL, Laine L. Review article: Upper gastrointestinal bleeding – review of current evidence and implications for management. Alimentary Pharmacology and Therapeutics. 2024; 59: 1062–1081. https://doi.org/10.1111/apt.17949

Zheng NS, Tsay C, Laine L, Shung DL. Trends in characteristics, management, and outcomes of patients presenting with gastrointestinal bleeding to emergency departments in the United States from 2006 to 2019. Alimentary Pharmacology and Therapeutics. 2022; 00: 1– 13. https://doi.org/10.1111/apt.17238

Li DK, Laine L, Shung DL. Trends in Upper Gastrointestinal Bleeding in Patients on Primary Prevention Aspirin: A Nationwide Emergency Department Sample Analysis, 2016-2020. American Journal of Medicine. 2023 Sep 9:S0002-9343(23)00542-9.

Shung DL, Lin JK, Laine L. Achieving Value by Risk Stratification with Machine Learning Model or Clinical Risk Score in Acute Upper Gastrointestinal Bleeding: A Cost Minimization Analysis. American Journal of Gastroenterology. 2023 Sep 27.

Rodriguez NJ, Zheng N, Mezzacappa C, Canavan M, Laine L, Shung D. Disparities in Access to Endoscopy for Patients with Upper Gastrointestinal Bleeding Presenting to Emergency Departments. Gastroenterology. 2022 Oct 10:S0016-5085(22)01157-X.

Shung D, Simonov M, Gentry M, Au B, Laine L. Machine Learning to Predict Outcomes in Patients with Acute Gastrointestinal Bleeding: A Systematic Review. Digestive Diseases and Sciences. 2019 May; 64(8):2078–2087

Tsay C, Shung DL, Stemmer Frumento K, Laine L. Early Colonoscopy Does Not Improve Outcome in Lower Gastrointestinal Bleeding: Systematic Review of Randomized Trials. Clinical Gastroenterology and Hepatology. 2019 Dec 13.

Machine Learning Interventions & Commentaries

Plana D*, Shung DL*, Grimshaw AA, Saraf A, Sung JJY, Kann BH. Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review. JAMA Network Open. 2022;5(9):e2233946. doi:10.1001/jamanetworkopen.2022.33946

Shung DL From Tool to Team Member: A Second Set of Eyes for Polyp Detection. Annals of Internal Medicine.2023;176:1271-1272. [Epub 29 August 2023]. doi:10.7326/M23-2022

Giuffrè, M., Shung, D.L. Harnessing the power of synthetic data in healthcare: innovation, application, and privacy. Nature Digital Medicine. 6, 186 (2023). https://doi.org/10.1038/s41746-023-00927-3

Shung, D. L., and Sung, J. J. Y. (2021) Challenges of developing artificial intelligence-assisted tools for clinical medicine. Journal of Gastroenterology and Hepatology, 36: 295–298. https://doi.org/10.1111/jgh.15378.

Shung, D. L. (2021) Advancing care for acute gastrointestinal bleeding using artificial intelligence. Journal of Gastroenterology and Hepatology, 36: 273–278. https://doi.org/10.1111/jgh.15372.