Machine-learning-based cost prediction models for inpatients with mental disorders in China

Background Mental disorders are increasingly prevalent, leading to increased medical expenditures. To refine the reimbursement of medical costs for inpatients with mental disorders by health insurance, an accurate prediction model is essential. Per-diem payment is a common internationally implemente...

Full description

Saved in:
Bibliographic Details
Published in:BMC psychiatry Vol. 25; no. 1; pp. 33 - 16
Main Authors: Ma, Yuxuan, Tu, Xi, Luo, Xiaodong, Hu, Linlin, Wang, Chen
Format: Journal Article
Language:English
Published: London BioMed Central 09.01.2025
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Activities of daily living
Adult
Aged
Algorithms
Analysis
Call for papers - Psycho-Oncology
Care and treatment
China
Classification
Cost prediction
Demographic aspects
Diagnosis
Female
Health care expenditures
Health insurance
Hospitalization - economics
Humans
Inpatient care
Inpatients
Inpatients with mental disorders
Learning algorithms
Machine Learning
Male
Medical care, Cost of
Medicine
Medicine & Public Health
Mental depression
Mental disorders
Mental Disorders - economics
Mental illness
Methods
Middle Aged
Patients
Prediction models
Prevalence studies (Epidemiology)
Psychiatry
Psychotherapy
Resource allocation
Young Adult
China
Inpatients with mental disorders
Cost prediction
Machine learning
ISSN:1471-244X, 1471-244X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Mental disorders are increasingly prevalent, leading to increased medical expenditures. To refine the reimbursement of medical costs for inpatients with mental disorders by health insurance, an accurate prediction model is essential. Per-diem payment is a common internationally implemented payment method for medical insurance of inpatients with mental disorders, necessitating the exploration of advanced machine learning methods for predicting the average daily hospitalization costs (ADHC) based on the characteristics of inpatients with mental disorders. Methods We used data including demographic information, clinical/functional characteristics, institutional features, and cost information of 5070 hospitalized patients with mental disorders in Jinhua, China, and employed six algorithms to predict ADHC. Performance of these six algorithms was evaluated through 5- old cross-validation combined with bootstrap method to select the most suitable algorithm and identify key factors influencing ADHC. Results The random forest (RF) model demonstrated better performance (R-squared (R 2 ) = 0.6417 (95% CI, 0.6236–0.6611), root-mean-square error (RMSE) = 0.2398 (95% CI, 0.2252–0.2553), mean-absolute error (MAE) = 0.1677 (95% CI, 0.1626–0.1735), mean-absolute-percentage error (MAPE) = 0.0295 (95% CI, 0.0287–0.0304)). According to feature importance ranking, models incorporating top 11 factors (> 0.01) demonstrated comparable performance to those encompassing all variables. Top four factors (> 0.05) were level of medical institution, age, functional classification, and cognitive classification. Notably, level of medical institutions was the most significant factor across all primary models. Higher medical institutions level, patients below 20 and above 75 years old, lower functional classification, and lower cognitive classification are associated with increased ADHC. Conclusions Machine learning algorithms, particularly RF algorithm, enhance accuracy of predicting ADHC for mental health patients. The findings of this study provide evidence for setting up more reasonable insurance payment standards for inpatients with mental disorders and support resource allocation in clinical practice.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-244X
1471-244X
DOI:10.1186/s12888-024-06358-y