Augmenting the Hospital Score with social risk factors to improve prediction for 30-day readmission following acute myocardial infarction
Main Article Content
Abstract
Background: Hospital Score is a well-known and validated tool for predicting readmission risk among diverse patient populations. Integrating social risk factors using natural language processing with the Hospital Score may improve its ability to predict 30-day readmissions following an acute myocardial infarction. Methods: A retrospective cohort included patients hospitalized at Vanderbilt University Medical Center between January 1, 2007, and December 31, 2016, with a primary index diagnosis of acute myocardial infarction, who were discharged alive. To supplement ascertainment of 30-day readmissions, data were linked to Center for Medicare & Medicaid Services (CMS) administrative data. Clinical notes from the cohort were extracted, and a natural language processing model was deployed, counting mentions of eight social risk factors. A logistic regression prediction model was run using the Hospital Score composite, its component variables, and the natural language processing-derived social risk factors. ROC comparison analysis was performed. Results: The cohort included 6,165 unique patients, where 4,137 (67.1%) were male, 1,020 (16.5%) were Black or other people of color, the average age was 67 years (SD:13), and the 30-day hospital readmission rate was 15.1% (N=934). The final test-set AUROCs were between 0.635 and 0.669. The model containing the Hospital Score component variables and the natural language processing-derived social risk factors obtained the highest AUROC. Discussion: Social risk factors extracted using natural language processing improved model performance when added to the Hospital Score composite. Clinicians and health systems should consider incorporating social risk factors when using the Hospital Score composite to evaluate risk for readmission among patients hospitalized for acute myocardial infarction.
Article Details
The Medical Research Archives grants authors the right to publish and reproduce the unrevised contribution in whole or in part at any time and in any form for any scholarly non-commercial purpose with the condition that all publications of the contribution include a full citation to the journal as published by the Medical Research Archives.
References
2. Burke RE, Schnipper JL, Williams MV, et al. The HOSPITAL Score Predicts Potentially Preventable 30-Day Readmissions in Conditions Targeted by the Hospital Readmissions Reduction Program. Med Care. Mar 2017;55(3):285-290. doi:10.1097/MLR.0000000000000665
3. Robinson R. The HOSPITAL score as a predictor of 30 day readmission in a retrospective study at a university affiliated community hospital. PeerJ. 2016;4:e2441. doi:10.7717/peerj.2441
4. Ibrahim AM, Koester, C., Al-Akchar, M., Tandan, N., Regmi, M. et al. HOSPITAL score, LACE index, and LACE+ index as predictors of 30-day readmission in patients with heart failure. BMJ Evidence-Based Medicine. 2020;25(5)doi:10.1136/bmjebm-2019-111271
5. Robinson R, Hudali T. The HOSPITAL score and LACE index as predictors of 30 day readmission in a retrospective study at a university-affiliated community hospital. PeerJ. 2017;5:e3137. doi:10.7717/peerj.3137
6. Su MC, Wang YJ, Chen TJ, et al. Assess the Performance and Cost-Effectiveness of LACE and HOSPITAL Re-Admission Prediction Models as a Risk Management Tool for Home Care Patients: An Evaluation Study of a Medical Center Affiliated Home Care Unit in Taiwan. Int J Environ Res Public Health. Feb 2 2020;17(3)doi:10.3390/ijerph17030927
7. Sun CH, Chou YY, Lee YS, et al. Prediction of 30-Day Readmission in Hospitalized Older Adults Using Comprehensive Geriatric Assessment and LACE Index and HOSPITAL Score. Int J Environ Res Public Health. Dec 26 2022;20(1)doi:10.3390/ijerph20010348
8. Donze JD, Williams MV, Robinson EJ, et al. International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital Readmissions. JAMA Intern Med. Apr 2016;176(4): 496-502. doi:10.1001/jamainternmed.2015.8462
9. Robinson R, Bhattarai, M., Hudali, T., Vogler, C. Predictors of 30-day hospital readmission: The direct comparisons of number of discharge medications to the HOSPITAL score and LACE index. Future Healthcare Journal. 2020;6(3):209-214.
10. Nguyen OK, Makam AN, Clark C, Zhang S, Das SR, Halm EA. Predicting 30-Day Hospital Readmissions in Acute Myocardial Infarction: The AMI "READMITS" (Renal Function, Elevated Brain Natriuretic Peptide, Age, Diabetes Mellitus, Nonmale Sex, Intervention with Timely Percutaneous Coronary Intervention, and Low Systolic Blood Pressure) Score. J Am Heart Assoc. Apr 17 2018;7(8)doi:10.1161/JAHA.118.008882
11. Matheny ME, Ricket I, Goodrich CA, et al. Development of Electronic Health Record-Based Prediction Models for 30-Day Readmission Risk Among Patients Hospitalized for Acute Myocardial Infarction. JAMA Netw Open. Jan 4 2021;4(1): e2035782. doi:10.1001/jamanetworkopen.2020.35782
12. Dodson JA, Hajduk AM, Murphy TE, et al. Thirty-Day Readmission Risk Model for Older Adults Hospitalized With Acute Myocardial Infarction. Circ Cardiovasc Qual Outcomes. May 2019;12(5):e005320. doi:10.1161/CIRCOUTCOMES.118.005320
13. Navathe AS, Zhong F, Lei VJ, et al. Hospital Readmission and Social Risk Factors Identified from Physician Notes. Health Serv Res. Apr 2018;53(2):1110-1136. doi:10.1111/1475-6773.12670
14. Bernheim SM, Parzynski CS, Horwitz L, et al. Accounting For Patients' Socioeconomic Status Does Not Change Hospital Readmission Rates. Health Aff (Millwood). Aug 1 2016;35(8):1461-70. doi:10.1377/hlthaff.2015.0394
15. Wasfy JH, Vijeta B., Healy Emma, Choirat C., Dominici F., Wadhera R. et al. Relative Effects of the Hospital Readmissions Reduction Program on Hospitals that Serve Poorer Patients. Medical Care. 2019;57(12):968-976. doi:10.1097/MLR.0000000000001207
16. Brown JR, Ricket IM, Reeves RM, et al. Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission? J Am Heart Assoc. Mar 24 2022:e024198. doi:10.1161/JAHA.121.024198
17. Maier C, Kapsner LA, Mate S, Prokosch HU, Kraus S. Patient Cohort Identification on Time Series Data Using the OMOP Common Data Model. Appl Clin Inform. Jan 2021;12(1):57-64. doi:10.1055/s-0040-1721481
18. Kang B, Yoon J, Kim HY, Jo SJ, Lee Y, Kam HJ. Deep-learning-based automated terminology mapping in OMOP-CDM. J Am Med Inform Assoc. Jul 14 2021;28(7):1489-1496. doi:10.1093/jamia/ocab030
19. Biedermann P, Ong R, Davydov A, et al. Standardizing registry data to the OMOP Common Data Model: experience from three pulmonary hypertension databases. BMC Med Res Methodol. Nov 2 2021;21(1):238. doi:10.1186/s12874-021-01434-3
20. Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. Jan 7 2015;350:g7594. doi:10.1136/bmj.g7594
21. Reeves R, Christensen, L., Brown, JR., Conway, M., Levis, M., Globbel, G., Shah, R., Goodrich, C., Ricket, I., Minter, F., Bohm, A., Bray, B., Matheny, M., Chapman, W. Adaptation of an NLP System to a New Healthcare Environment to Identify Social Determinants of Health. Journal of Bioinformatics. 2021;120(103851)doi:doi: 10.1016/j.jbi.2021.103851
22. Conway M, Keyhani S, Christensen L, et al. Moonstone: a novel natural language processing system for inferring social risk from clinical narratives. J Biomed Semantics. Apr 11 2019;10(1):6. doi:10.1186/s13326-019-0198-0
23. Blu Lab UoU. VA Readmissions Moonstone Workspace. https://github.com/Blulab-Utah/VAReadmissionMoonstone
24. YC Y. Multiple Imputation for Missing Data: Concepts and New Development (Version 9.0). presented at: Proceedings of the Twenty-Fifth Annual SAS Users Group International Conference; 2000;
25. Lin C, Hsu S, Lu HF, Pan LF, Yan YH. Comparison of Back-Propagation Neural Network, LACE Index and HOSPITAL Score in Predicting All-Cause Risk of 30-Day Readmission. Risk Manag Healthc Policy. 2021;14:3853-3864. doi:10.2147/RMHP.S318806
26. Linzey JR, Foshee, R.L., Srinvasan, S., Fiestan, G.O., Mossner, J.M., Gemmete, J.J., Burke, J.F., Sheehan, K.M., Rajajee, V., Pandey, A.S. The predictive value of the HOSPITAL SCORE AND LACE index for an adult neurosurgical population: A prospective Ananlysis World Neurosurgery. 2020;137:e166-e175. doi:10.1016/j.wneu.2020.01.117
27. Wasfy JH, Singal G, O'Brien C, et al. Enhancing the Prediction of 30-Day Readmission After Percutaneous Coronary Intervention Using Data Extracted by Querying of the Electronic Health Record. Circ Cardiovasc Qual Outcomes. Sep 2015;8(5):477-85. doi:10.1161/CIRCOUTCOMES.115.001855
28. Amarasingham R, Moore BJ., Tabak YP., Drazner MH, Clark CA., Zhang S., et al. An Automated Model to Identify Heart Failure Patients at Risk for 30-day Readmission or Death Using Electronic Medical Record Sata. Medical Care. 2010;48(11):981-8. doi:10.1097/MLR.0b013e3181ef60d9
29. Wray CM, Vali M, Walter LC, et al. Examining the Interfacility Variation of Social Determinants of Health in the Veterans Health Administration. Fed Pract. Jan 2021;38(1):15-19. doi:10.12788/fp.0080
30. Baker MC, Alberti PM, Tsao TY, Fluegge K, Howland RE, Haberman M. Social Determinants Matter For Hospital Readmission Policy: Insights From New York City. Health Aff (Millwood). Apr 2021;40(4):645-654. doi:10.1377/hlthaff.2020.01742
31. Zhang Y, Zhang Y, Sholle E, et al. Assessing the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission or death. PLoS One. 2020;15(6):e0235064. doi:10.1371/journal.pone.0235064
32. Chapman EN, Kaatz A, Carnes M. Physicians and implicit bias: how doctors may unwittingly perpetuate health care disparities. J Gen Intern Med. Nov 2013;28(11):1504-10. doi:10.1007/s11606-013-2441-1
33. Shah RU. We Don't Need More Data, We Need the Right Data. Circulation. Jul 21 2020;142(3):197-198. doi:10.1161/CIRCULATIONAHA.120.045968
34. Sperrin M, Martin GP, Sisk R, Peek N. Missing data should be handled differently for prediction than for description or causal explanation. J Clin Epidemiol. Sep 2020;125:183-187. doi:10.1016/j.jclinepi.2020.03.028