Post-acute care(PAC)residents in nursing homes(NHs)are recently hospitalized patients with medi-cally complex diagnoses,ranging from severe orthopedic injuries to cardiovascular diseases.A major role of NHs is to maximize restoration of PAC residents during their NH stays with desirable discharge outcomes,such as higher community discharge likelihood and lower re/hospitaliza-tion risk.Accurate prediction of the PAC residents'length-of-stay(LOS)with multiple discharge dispositions(e.g.,community discharge and re/hospitalization)will allow NH management groups to stratify NH residents based on their individualized risk in realizing personalized and resi-dent-centered NH care delivery.Due to the highly hetero-geneous health conditions of PAC residents and their multiple types of correlated discharge dispositions,devel-oping an accurate prediction model becomes challenging.Existing predictive analytics methods,such as distribution-/regression-based methods and machine learning methods,either fail to incorporate varied individual characteristics comprehensively or ignore multiple discharge dispositions.In this work,a data-driven predictive analytics approach is considered to jointly predict the individualized re/hospital-ization risk and community discharge likelihood over time in the presence of varied residents'characteristics.A sam-pling algorithm is further developed to generate accurate predictive samples for a heterogeneous population of PAC residents in an NH and facilitate facility-level performance evaluation.A real case study using large-scale NH data is provided to demonstrate the superior prediction perfor-mance of the proposed work at individual and facility levels through comprehensive comparison with a large number of existing prediction methods as benchmarks.The developed analytics tools will allow NH management groups to identify the most at-risk residents by providing them with more proactive and focused care to improve resident outcomes.

Nazmus SAKIB;Xuxue SUN;Nan KONG;Chris MASTERSON;Hongdao MENG;Kelly SMITH;Mingyang LI

Department of Industrial and Management Systems Engineering,University of South Florida,Tampa,FL 33620,USA;College of Media Engineering,Communication University of Zhejiang,Hangzhou 310019,China;Weldon School of Biomedical Engineering,Purdue University,West Lafayette,IN 47907,USA;Greystone Health Network,Tampa,FL 33610,USA;School of Aging Studies,University of South Florida,Tampa,FL 33620,USA

工程管理前沿（英文版）

[1]Nazmus SAKIB;Xuxue SUN;Nan KONG;Chris MASTERSON;Hongdao MENG;Kelly SMITH;Mingyang LI-.Heterogeneous length-of-stay modeling of post-acute care residents in the nursing home with competing discharge dispositions)[J].工程管理前沿（英文版）,2022(04):577-591

dispositions,NHs,hospitaliza

Heterogeneous,length,modeling,post,acute,care,residents,nursing,competing,discharge,Post,PAC,homes,recently,hospitalized,patients,medi,cally,complex,diagnoses,ranging,from,severe,orthopedic,injuries,cardiovascular,diseases,major,role,maximize,restoration,during,their,stays,desirable,outcomes,such,higher,community,likelihood,lower,risk,Accurate,prediction,LOS,multiple,hospitalization,will,allow,management,groups,stratify,individualized,realizing,personalized,centered,delivery,Due,highly,health,conditions,types,correlated,oping,accurate,becomes,challenging,Existing,predictive,analytics,methods,distribution,regression,machine,learning,either,fail,incorporate,varied,characteristics,comprehensively,ignore,In,this,work,data,driven,approach,considered,jointly,over,presence,pling,algorithm,further,developed,generate,samples,heterogeneous,population,facilitate,facility,performance,evaluation,case,study,using,large,scale,provided,demonstrate,superior,proposed,levels,through,comparison,number,existing,benchmarks,tools,identify,most,by,providing,them,more,proactive,focused,improve

0.472696