Machine-learning-based cost prediction models for inpatients with mental disorders in China
Abstract 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 i...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Psychiatry |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12888-024-06358-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544365343768576 |
|---|---|
| author | Yuxuan Ma Xi Tu Xiaodong Luo Linlin Hu Chen Wang |
| author_facet | Yuxuan Ma Xi Tu Xiaodong Luo Linlin Hu Chen Wang |
| author_sort | Yuxuan Ma |
| collection | DOAJ |
| description | Abstract 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 (R2) = 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. |
| format | Article |
| id | doaj-art-7402237d958d404c8268b5605e516c9a |
| institution | Kabale University |
| issn | 1471-244X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Psychiatry |
| spelling | doaj-art-7402237d958d404c8268b5605e516c9a2025-01-12T12:34:22ZengBMCBMC Psychiatry1471-244X2025-01-0125111610.1186/s12888-024-06358-yMachine-learning-based cost prediction models for inpatients with mental disorders in ChinaYuxuan Ma0Xi Tu1Xiaodong Luo2Linlin Hu3Chen Wang4School of Health Policy and Management, Chinese Academy of Medical Sciences & Peking Union Medical CollegeSchool of Health Policy and Management, Chinese Academy of Medical Sciences & Peking Union Medical CollegeThe Second Hospital of JinhuaSchool of Health Policy and Management, Chinese Academy of Medical Sciences & Peking Union Medical CollegeChinese Academy of Medical Sciences & Peking Union Medical CollegeAbstract 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 (R2) = 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.https://doi.org/10.1186/s12888-024-06358-yMachine learningInpatients with mental disordersCost prediction |
| spellingShingle | Yuxuan Ma Xi Tu Xiaodong Luo Linlin Hu Chen Wang Machine-learning-based cost prediction models for inpatients with mental disorders in China BMC Psychiatry Machine learning Inpatients with mental disorders Cost prediction |
| title | Machine-learning-based cost prediction models for inpatients with mental disorders in China |
| title_full | Machine-learning-based cost prediction models for inpatients with mental disorders in China |
| title_fullStr | Machine-learning-based cost prediction models for inpatients with mental disorders in China |
| title_full_unstemmed | Machine-learning-based cost prediction models for inpatients with mental disorders in China |
| title_short | Machine-learning-based cost prediction models for inpatients with mental disorders in China |
| title_sort | machine learning based cost prediction models for inpatients with mental disorders in china |
| topic | Machine learning Inpatients with mental disorders Cost prediction |
| url | https://doi.org/10.1186/s12888-024-06358-y |
| work_keys_str_mv | AT yuxuanma machinelearningbasedcostpredictionmodelsforinpatientswithmentaldisordersinchina AT xitu machinelearningbasedcostpredictionmodelsforinpatientswithmentaldisordersinchina AT xiaodongluo machinelearningbasedcostpredictionmodelsforinpatientswithmentaldisordersinchina AT linlinhu machinelearningbasedcostpredictionmodelsforinpatientswithmentaldisordersinchina AT chenwang machinelearningbasedcostpredictionmodelsforinpatientswithmentaldisordersinchina |