A novel model for predicting prolonged stay of patients with type-2 diabetes mellitus: a 13-year (2010-2022) multicenter retrospective case-control study

Juntao Tan; Zhengyu Zhang; Yuxin He; Yue Yu; Jing Zheng; Yunyu Liu; Jun Gong; Jianjun Li; Xin Wu; Shengying Zhang; Xiantian Lin; Yuxi Zhao; Xiaoxin Wu; Songjia Tang; Jingjing Chen; Wenlong Zhao

doi:10.1186/s12967-023-03959-1

A novel model for predicting prolonged stay of patients with type-2 diabetes mellitus: a 13-year (2010-2022) multicenter retrospective case-control study

J Transl Med. 2023 Feb 7;21(1):91. doi: 10.1186/s12967-023-03959-1.

Authors

Juntao Tan^#¹, Zhengyu Zhang^#², Yuxin He³, Yue Yu⁴, Jing Zheng¹, Yunyu Liu⁵, Jun Gong⁶, Jianjun Li⁷, Xin Wu⁸, Shengying Zhang⁹, Xiantian Lin¹⁰, Yuxi Zhao¹⁰, Xiaoxin Wu¹¹, Songjia Tang¹², Jingjing Chen¹³, Wenlong Zhao^{14

15}

Affiliations

¹ Operation Management Office, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, 401320, China.
² Medical Records Department, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, 310003, Zhejiang, China.
³ Department of Medical Administration, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, 401320, China.
⁴ Senior Bioinformatician Department of Quantitative Health Sciences Mayo Clinic, Rochester, MN, 55905, USA.
⁵ Medical Records Department, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400010, China.
⁶ Department of Information Center, The University Town Hospital of Chongqing Medical University, Chongqing, 401331, China.
⁷ Department of Cardiothoracic Surgery, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, 401320, China.
⁸ Department of Gastrointestinal Surgery, The Third People's Hospital of Chongqing, Chongqing Medical University, Chongqing, 400038, China.
⁹ Department of Respiratory, Yinzhou Second Hospital, Ningbo, 315153, Zhejiang, China.
¹⁰ State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Centre for Infectious Diseases, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qing Chun Road, Hangzhou, 310003, Zhejiang, China.
¹¹ State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Centre for Infectious Diseases, The First Affiliated Hospital, Zhejiang University School of Medicine, 79 Qing Chun Road, Hangzhou, 310003, Zhejiang, China. xiaoxinwu@zju.edu.cn.
¹² Plastic and Aesthetic Surgery Department, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou, 310000, Zhejiang, China. tangsj@zju.edu.cn.
¹³ Department of Digital Urban Governance, Zhejiang University City College, Hangzhou, 310015, Zhejiang, China. joyjchan@gmail.com.
¹⁴ College of Medical Informatics, Chongqing Medical University, Chongqing, 400016, China. cqzhaowl@163.com.
¹⁵ Medical Data Science Academy, Chongqing Medical University, Chongqing, 400016, China. cqzhaowl@163.com.

^# Contributed equally.

Abstract

Background: Length of stay (LOS) is an important metric for evaluating the management of inpatients. This study aimed to explore the factors impacting the LOS of inpatients with type-2 diabetes mellitus (T2DM) and develop a predictive model for the early identification of inpatients with prolonged LOS.

Methods: A 13-year multicenter retrospective study was conducted on 83,776 patients with T2DM to develop and validate a clinical predictive tool for prolonged LOS. Least absolute shrinkage and selection operator regression model and multivariable logistic regression analysis were adopted to build the risk model for prolonged LOS, and a nomogram was taken to visualize the model. Furthermore, receiver operating characteristic curves, calibration curves, and decision curve analysis and clinical impact curves were used to respectively validate the discrimination, calibration, and clinical applicability of the model.

Results: The result showed that age, cerebral infarction, antihypertensive drug use, antiplatelet and anticoagulant use, past surgical history, past medical history, smoking, drinking, and neutrophil percentage-to-albumin ratio were closely related to the prolonged LOS. Area under the curve values of the nomogram in the training, internal validation, external validation set 1, and external validation set 2 were 0.803 (95% CI [confidence interval] 0.799-0.808), 0.794 (95% CI 0.788-0.800), 0.754 (95% CI 0.739-0.770), and 0.743 (95% CI 0.722-0.763), respectively. The calibration curves indicated that the nomogram had a strong calibration. Besides, decision curve analysis, and clinical impact curves exhibited that the nomogram had favorable clinical practical value. Besides, an online interface ( https://cytjt007.shinyapps.io/prolonged_los/ ) was developed to provide convenient access for users.

Conclusion: In sum, the proposed model could predict the possible prolonged LOS of inpatients with T2DM and help the clinicians to improve efficiency in bed management.

Keywords: Nomogram; Online service; Prediction model; Prolonged stay; Type-2 diabetes mellitus.

Publication types

Multicenter Study
Research Support, Non-U.S. Gov't

MeSH terms

Albumins
Case-Control Studies
Diabetes Mellitus, Type 2*
Humans
Retrospective Studies
Risk Factors

Substances

Albumins