Identifying Unexpected Deaths in Long-Term Care Homes

被引:2
作者
Rangrej, Jagadish [1 ,2 ]
Kaufman, Sam [3 ]
Wang, Sping [1 ,2 ]
Kerem, Aidin [1 ,2 ]
Hirdes, John [4 ]
Hillmer, Michael P. [1 ,2 ,5 ]
Malikov, Kamil [1 ,2 ,5 ]
机构
[1] Ontario Minist Hlth, Capac Planning & Analyt Div, Hlth Data Sci Branch, 1075 Bay St,13th Floor, Toronto, ON M5S 2B1, Canada
[2] Ontario Minist Long Term Care, Toronto, ON, Canada
[3] Ontario Minist Attorney Gen, Corp Serv Div, Analyt & Evidence Branch, Toronto, ON, Canada
[4] Univ Waterloo, Sch Publ Hlth & Hlth Syst, Waterloo, ON, Canada
[5] Univ Toronto, Inst Hlth Policy Management & Evaluat, Toronto, ON, Canada
关键词
long-term care home; unexpected death; statistical methods; XGBoost; mixed-effect logistic regression; NURSING-HOME; MORTALITY;
D O I
10.1016/j.jamda.2021.09.025
中图分类号
R592 [老年病学]; C [社会科学总论];
学科分类号
03 ; 0303 ; 100203 ;
摘要
Objectives: Predicting unexpected deaths among long-term care (LTC) residents can provide valuable information to clinicians and policy makers. We study multiple methods to predict unexpected death, adjusting for individual and home-level factors, and to use as a step to compare mortality differences at the facility level in the future work. Design: We conducted a retrospective cohort study using Resident Assessment Instrument Minimum Data Set assessment data for all LTC residents in Ontario, Canada, from April 2017 to March 2018. Setting and Participants: All residents in Ontario long-term homes. We used data routinely collected as part of administrative reporting by health care providers to the funder: Ontario Ministry of Health and Long-Term Care. This project is a component of routine policy development to ensure safety of the LTC system residents. Methods: Logistic regression (LR), mixed-effect LR (mixLR), and a machine learning algorithm (XGBoost) were used to predict individual mortality over 5 to 95 days after the last available RAI assessment. Results: We identified 22,419 deaths in the cohort of 106,366 cases (mean age: 83.1 years; female: 67.7%; dementia: 68.8%; functional decline: 16.6%). XGBoost had superior calibration and discrimination (Cstatistic 0.837) over both mixLR (0.819) and LR (0.813). The models had high correlation in predicting death (LR-mixLR: 0.979, LR-XGBoost: 0.885, mixLR-XGBoost: 0.882). The inter-rater reliability between the models LR-mixLR and LR-XGBoost was 0.56 and 0.84, respectively. Using results in which all 3 models predicted probability of actual death of a resident at <5% yielded 210 unexpected deaths or 0.9% of the observed deaths. Conclusions and Implications: XGBoost outperformed other models, but the combination of 3 models provides a method to detect facilities with potentially higher rates of unexpected deaths while minimizing the possibility of false positives and could be useful for ongoing surveillance and quality assurance at the facility, regional, and national levels. Crown Copyright (C) 2021 Published by Elsevier Inc. on behalf of AMDA - The Society for Post-Acute and Long-Term Care Medicine.
引用
收藏
页码:1431.e21 / 1431.e28
页数:8
相关论文
共 38 条
[1]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[2]  
CIHI, DISCH ABSTR DAT MET
[3]  
CIHI, NAT AMB CAR REP SYST
[4]  
CIHI, CONTINUING CARE META
[5]  
Compute Ontario | Calculate Ontario, COVID 19 HLTH RES DA
[6]   Do report cards predict future quality? The case of skilled nursing facilities [J].
Cornell, Portia Y. ;
Grabowski, David C. ;
Norton, Edward C. ;
Rahman, Momotazur .
JOURNAL OF HEALTH ECONOMICS, 2019, 66 :208-221
[7]   Gender differences in the relation between comorbidity and mortality of patients with Alzheimer's disease [J].
Gambassi, G ;
Lapane, KL ;
Landi, F ;
Sgadari, A ;
Mor, V ;
Bernabei, R .
NEUROLOGY, 1999, 53 (03) :508-516
[8]  
Gelman A., 2007, DATA ANAL USING REGR
[9]  
Government of Ontario, 2021, LONG TERM CAR OV
[10]   Mixed-effects random forest for clustered data [J].
Hajjem, Ahlem ;
Bellavance, Francois ;
Larocque, Denis .
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2014, 84 (06) :1313-1328