Multimorbidity burden and high-cost status among patients with diabetes: evidence from longitudinal claims data in China
- 1Shanghai Institute of Infectious Disease and Biosecurity, Fudan University, Shanghai, China
- 2School of Public Health, Fudan University, Shanghai, China
Abstract
Objective: Multimorbidity is common among people with diabetes and is associated with healthcare cost concentration. This study aims to quantify multimorbidity burden and evaluates the association between multimorbidity and high-cost (HC) status.
Methods: We conducted a retrospective cohort study using longitudinal health insurance claims and chronic disease management data from 79,910 diabetic patients in eastern China. Patients in the top 10% of annual healthcare expenditures in 2019 were classified as HC. Multimorbidity was defined based on 29 chronic conditions identified through literature review and utilization thresholds. Descriptive analyses compared HC and non–high-cost (NHC) patients. Six machine learning models were developed to identify the contribution of multimorbidity to HC patients, using ROC-AUC and PR-AUC as the primary performance metrics. For the best-performing model, the Shapley additive explanation (SHAP) method was used to interpret the results.
Results: A total of 7,991 (10.0%) patients were classified as HC. HC patients had a higher multimorbidity burden than NHC patients (mean number of conditions: 8.6 vs. 6.4). Mean annual expenditure was substantially higher among HC patients ($25,903 vs. $2,490). Multimorbidity-related care accounted for 33.6% of total expenditures and was over ten times higher in HC patients. Hypertension was the most prevalent condition among HC patients (91.3%), while cerebrovascular disease sequelae generated the highest per-patient costs ($8,869). The Extreme Gradient Boosting model achieved the best performance (ROC-AUC = 0.750, PR-AUC = 0.301). SHAP analysis identified cerebrovascular disease sequelae, renal failure, chronic ischemic heart disease, cerebral infarction and osteoporosis as the most influential predictors of multimorbidity affecting HC status.
Conclusions: Multimorbidity is associated with HC status of patients with diabetes. Strengthening risk stratification and integrated management for patients with cardiovascular, cerebrovascular, renal, and skeletal diseases can help reduce healthcare costs and improve health outcomes.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s13561-026-00841-w.
Related
- The burden of multimorbidity in patients with TB–HIV: a retrospective cohort analysis
- Associations of multimorbidity burden with healthcare utilization and expenditures among individuals with diabetes in China
- Longitudinal joint trajectories of the dietary inflammatory index and physical activity and risk of incident cardiometabolic multimorbidity among women: evidence from the China Health and Nutrition Survey
- Stress-hyperglycemia ratio, frailty index, and their product in relation to incident cardiometabolic multimorbidity comprising diabetes, heart disease, and stroke: a longitudinal analysis of CHARLS
- Long COVID and Incident Multimorbidity in the United States: Evidence from a Nationally Representative Longitudinal Study.
BibTeX
@article{chen2026multimorbidity,
title = {{Multimorbidity burden and high-cost status among patients with diabetes: evidence from longitudinal claims data in China}},
author = {Xing Chen and Luying Zhang and Wen Chen},
journal = {Health Economics Review},
year = {2026},
month = aug,
doi = {10.1186/s13561-026-00841-w},
url = {https://doi.org/10.1186/s13561-026-00841-w},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Multimorbidity burden and high-cost status among patients with diabetes: evidence from longitudinal claims data in China
AU - Xing Chen
AU - Luying Zhang
AU - Wen Chen
PY - 2026
DA - 2026/08/10
JO - Health Economics Review
DO - 10.1186/s13561-026-00841-w
UR - https://doi.org/10.1186/s13561-026-00841-w
AB - Objective: Multimorbidity is common among people with diabetes and is associated with healthcare cost concentration. This study aims to quantify multimorbidity burden and evaluates the association between multimorbidity and high-cost (HC) status. Methods: We conducted a retrospective cohort study using longitudinal health insurance claims and chronic disease management data from 79,910 diabetic patients in eastern China. Patients in the top 10% of annual healthcare expenditures in 2019 were classified as HC. Multimorbidity was defined based on 29 chronic conditions identified through literature review and utilization thresholds. Descriptive analyses compared HC and non–high-cost (NHC) patients. Six machine learning models were developed to identify the contribution of multimorbidity to HC patients, using ROC-AUC and PR-AUC as the primary performance metrics. For the best-performing model, the Shapley additive explanation (SHAP) method was used to interpret the results. Results: A total of 7,991 (10.0%) patients were classified as HC. HC patients had a higher multimorbidity burden than NHC patients (mean number of conditions: 8.6 vs. 6.4). Mean annual expenditure was substantially higher among HC patients ($25,903 vs. $2,490). Multimorbidity-related care accounted for 33.6% of total expenditures and was over ten times higher in HC patients. Hypertension was the most prevalent condition among HC patients (91.3%), while cerebrovascular disease sequelae generated the highest per-patient costs ($8,869). The Extreme Gradient Boosting model achieved the best performance (ROC-AUC = 0.750, PR-AUC = 0.301). SHAP analysis identified cerebrovascular disease sequelae, renal failure, chronic ischemic heart disease, cerebral infarction and osteoporosis as the most influential predictors of multimorbidity affecting HC status. Conclusions: Multimorbidity is associated with HC status of patients with diabetes. Strengthening risk stratification and integrated management for patients with cardiovascular, cerebrovascular, renal, and skeletal diseases can help reduce healthcare costs and improve health outcomes. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s13561-026-00841-w.
SN - 2191-1991
ER -