A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers
© 2018 by The Society for Healthcare Epidemiology of America. All rights reserved. OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press (CUP)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/133418 |
| _version_ | 1826211696561094656 |
|---|---|
| author | Oh, Jeeheh Makar, Maggie Fusco, Christopher McCaffrey, Robert Rao, Krishna Ryan, Erin E Washer, Laraine West, Lauren R Young, Vincent B Guttag, John Hooper, David C Shenoy, Erica S Wiens, Jenna |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Oh, Jeeheh Makar, Maggie Fusco, Christopher McCaffrey, Robert Rao, Krishna Ryan, Erin E Washer, Laraine West, Lauren R Young, Vincent B Guttag, John Hooper, David C Shenoy, Erica S Wiens, Jenna |
| author_sort | Oh, Jeeheh |
| collection | MIT |
| description | © 2018 by The Society for Healthcare Epidemiology of America. All rights reserved. OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH). METHODS We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital. RESULTS Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80-0.84) and 0.75 ( 95% CI, 0.73-0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities. CONCLUSION A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies. Infect Control Hosp Epidemiol 2018;39:425-433 |
| first_indexed | 2024-09-23T15:10:04Z |
| format | Article |
| id | mit-1721.1/133418 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:10:04Z |
| publishDate | 2021 |
| publisher | Cambridge University Press (CUP) |
| record_format | dspace |
| spelling | mit-1721.1/1334182023-03-02T16:02:35Z A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers Oh, Jeeheh Makar, Maggie Fusco, Christopher McCaffrey, Robert Rao, Krishna Ryan, Erin E Washer, Laraine West, Lauren R Young, Vincent B Guttag, John Hooper, David C Shenoy, Erica S Wiens, Jenna Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science © 2018 by The Society for Healthcare Epidemiology of America. All rights reserved. OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH). METHODS We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital. RESULTS Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80-0.84) and 0.75 ( 95% CI, 0.73-0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities. CONCLUSION A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies. Infect Control Hosp Epidemiol 2018;39:425-433 2021-10-27T19:52:46Z 2021-10-27T19:52:46Z 2018 2019-05-30T14:29:09Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/133418 en 10.1017/ICE.2018.16 Infection Control and Hospital Epidemiology Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Cambridge University Press (CUP) PMC |
| spellingShingle | Oh, Jeeheh Makar, Maggie Fusco, Christopher McCaffrey, Robert Rao, Krishna Ryan, Erin E Washer, Laraine West, Lauren R Young, Vincent B Guttag, John Hooper, David C Shenoy, Erica S Wiens, Jenna A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers |
| title | A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers |
| title_full | A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers |
| title_fullStr | A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers |
| title_full_unstemmed | A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers |
| title_short | A Generalizable, Data-Driven Approach to Predict Daily Risk of Clostridium difficile Infection at Two Large Academic Health Centers |
| title_sort | generalizable data driven approach to predict daily risk of clostridium difficile infection at two large academic health centers |
| url | https://hdl.handle.net/1721.1/133418 |
| work_keys_str_mv | AT ohjeeheh ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT makarmaggie ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT fuscochristopher ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT mccaffreyrobert ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT raokrishna ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT ryanerine ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT washerlaraine ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT westlaurenr ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT youngvincentb ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT guttagjohn ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT hooperdavidc ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT shenoyericas ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT wiensjenna ageneralizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT ohjeeheh generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT makarmaggie generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT fuscochristopher generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT mccaffreyrobert generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT raokrishna generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT ryanerine generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT washerlaraine generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT westlaurenr generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT youngvincentb generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT guttagjohn generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT hooperdavidc generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT shenoyericas generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters AT wiensjenna generalizabledatadrivenapproachtopredictdailyriskofclostridiumdifficileinfectionattwolargeacademichealthcenters |