Patient Outcome Predictions Improve Operations at Hartford HealthCare.
Saved in:
| Title: | Patient Outcome Predictions Improve Operations at Hartford HealthCare. |
|---|---|
| Authors: | Na, Liangyuan (AUTHOR), Villalobos Carballo, Kimberly (AUTHOR), Pauphilet, Jean (AUTHOR), Haddad-Sisakht, Ali (AUTHOR), Kombert, Daniel (AUTHOR), Boisjoli-Langlois, Melissa (AUTHOR), Castiglione, Andrew (AUTHOR), Khalifa, Maram (AUTHOR), Hebbal, Pooja (AUTHOR), Stein, Barry (AUTHOR), Bertsimas, Dimitris (AUTHOR) |
| Source: | INFORMS Journal on Applied Analytics. May/Jun2026, Vol. 56 Issue 3, p224-242. 19p. |
| Subjects: | Discharge planning, Prognostic models, Medical care costs, Hospital administration, Death forecasting, Artificial intelligence in medicine, Prognosis, Length of stay in hospitals |
| Geographic Terms: | Hartford (Conn.) |
| Abstract: | We build and deploy machine learning models that accurately predict short- and medium-term inpatient outcomes for Hartford HealthCare, including 24–48 hour discharge, ICU transfer, mortality, and discharge disposition (AUC 76%–93%). More than 200 clinicians currently use these predictions in daily rounds, leading to earlier discharge planning, shorter length of stay (0.63 days per patient), and substantial financial benefits (between $52 and $67 million annually) for the healthcare system. Access to accurate predictions of patients' outcomes can enhance decision making within healthcare institutions. Hartford HealthCare has been collaborating with academics and consultants to predict short- and medium-term outcomes for all inpatients across their seven hospitals. We develop machine learning models that predict the probabilities of next 24-hour/48-hour discharge and intensive care unit transfers, end-of-stay mortality, and discharge dispositions. All models achieve high out-of-sample area under the receiver operating curve (75.7% – 92.5%) and are well calibrated. In addition, combining 48-hour discharge predictions with doctors' predictions simultaneously enables more patient discharges (10%–28.7%) and fewer 7-day/30-day readmissions (p < 0.001). We implement an automated pipeline that extracts data and updates predictions every morning, as well as user-friendly software and a color-coded alert system to communicate these patient-level predictions to clinical teams. Since its deployment, more than 200 doctors, nurses, and case managers across seven hospitals have been using the tool in their daily patient review process. With our tool, we find that doctors start the administrative discharge process earlier, leading to a significant reduction in the average length of stay (0.63 days per patient). We anticipate substantial financial benefits (between $52 and $67 million annually) for the healthcare system. History: This paper was refereed. Supplemental Material: The online appendix is available at https://doi.org/10.1287/inte.2024.0170. [ABSTRACT FROM AUTHOR] |
| Copyright of INFORMS Journal on Applied Analytics is the property of INFORMS: Institute for Operations Research & the Management Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | We build and deploy machine learning models that accurately predict short- and medium-term inpatient outcomes for Hartford HealthCare, including 24–48 hour discharge, ICU transfer, mortality, and discharge disposition (AUC 76%–93%). More than 200 clinicians currently use these predictions in daily rounds, leading to earlier discharge planning, shorter length of stay (0.63 days per patient), and substantial financial benefits (between $52 and $67 million annually) for the healthcare system. Access to accurate predictions of patients' outcomes can enhance decision making within healthcare institutions. Hartford HealthCare has been collaborating with academics and consultants to predict short- and medium-term outcomes for all inpatients across their seven hospitals. We develop machine learning models that predict the probabilities of next 24-hour/48-hour discharge and intensive care unit transfers, end-of-stay mortality, and discharge dispositions. All models achieve high out-of-sample area under the receiver operating curve (75.7% – 92.5%) and are well calibrated. In addition, combining 48-hour discharge predictions with doctors' predictions simultaneously enables more patient discharges (10%–28.7%) and fewer 7-day/30-day readmissions (p < 0.001). We implement an automated pipeline that extracts data and updates predictions every morning, as well as user-friendly software and a color-coded alert system to communicate these patient-level predictions to clinical teams. Since its deployment, more than 200 doctors, nurses, and case managers across seven hospitals have been using the tool in their daily patient review process. With our tool, we find that doctors start the administrative discharge process earlier, leading to a significant reduction in the average length of stay (0.63 days per patient). We anticipate substantial financial benefits (between $52 and $67 million annually) for the healthcare system. History: This paper was refereed. Supplemental Material: The online appendix is available at https://doi.org/10.1287/inte.2024.0170. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 26440865 |
| DOI: | 10.1287/inte.2024.0170 |
