Redirigiendo al acceso original de articulo en 24 segundos...
Inicio  /  Informatics  /  Vol: 10 Par: 2 (2023)  /  Artículo
ARTÍCULO
TITULO

Development and Internal Validation of an Interpretable Machine Learning Model to Predict Readmissions in a United States Healthcare System

Amanda L. Luo    
Akshay Ravi    
Simone Arvisais-Anhalt    
Anoop N. Muniyappa    
Xinran Liu and Shan Wang    

Resumen

(1) One in four hospital readmissions is potentially preventable. Machine learning (ML) models have been developed to predict hospital readmissions and risk-stratify patients, but thus far they have been limited in clinical applicability, timeliness, and generalizability. (2) Methods: Using deidentified clinical data from the University of California, San Francisco (UCSF) between January 2016 and November 2021, we developed and compared four supervised ML models (logistic regression, random forest, gradient boosting, and XGBoost) to predict 30-day readmissions for adults admitted to a UCSF hospital. (3) Results: Of 147,358 inpatient encounters, 20,747 (13.9%) patients were readmitted within 30 days of discharge. The final model selected was XGBoost, which had an area under the receiver operating characteristic curve of 0.783 and an area under the precision-recall curve of 0.434. The most important features by Shapley Additive Explanations were days since last admission, discharge department, and inpatient length of stay. (4) Conclusions: We developed and internally validated a supervised ML model to predict 30-day readmissions in a US-based healthcare system. This model has several advantages including state-of-the-art performance metrics, the use of clinical data, the use of features available within 24 h of discharge, and generalizability to multiple disease states.

 Artículos similares

       
 
George Tzoumakis, Konstantinos Fotopoulos and George Lampeas    
Future liquid hydrogen-powered aircraft requires the design and optimization of a large number of systems and subsystems, with cryogenic tanks being one of the largest and most critical. Considering previous space applications, these tanks are usually st... ver más
Revista: Aerospace

 
Zikang Jin, Zonghan Yu, Fanshuo Meng, Wei Zhang, Jingzhi Cui, Xiaolong He, Yuedi Lei and Omer Musa    
The parametric design method is widely utilized in the preliminary design stage for hypersonic vehicles; it ensures the fast iteration of configuration, generation, and optimization. This study proposes a novel parametric method for a wide-range, wing-mo... ver más
Revista: Aerospace

 
Isehaq Al-Huseini, Maryam Al-Ismaili, Ammar Boudaka and Srinivasa Rao Sirasanagandla    
Vascular calcification is calcium deposition occurring in the wall of blood vessels, leading to mechanical stress and rupture due to a loss of elasticity and the hardening of the vessel wall. The role of the Transient Receptor Channel Vanilloid 4 (TRPV4)... ver más
Revista: Applied Sciences

 
Yongzhen Zhang, Yanbo Hui, Ying Zhou, Juanjuan Liu, Ju Gao, Xiaoliang Wang, Baiwei Wang, Mengqi Xie and Haonan Hou    
Moldy corn produces aflatoxin and gibberellin, which can have adverse effects on human health if consumed. Mold is a significant factor that affects the safe storage of corn. If not detected and controlled in a timely manner, it will result in substantia... ver más
Revista: Applied Sciences

 
Luka Crnogorac, Suzana Lutovac, Rade Tokalic, Milo? Gligoric and Zoran Gligoric    
Relatively large deformations of the steel arch support in underground coal mines in the Republic of Serbia present one of the main problems for achieving the planned production of coal. Monitoring of the critical sections of the steel arch support in th... ver más
Revista: Applied Sciences