Objective: Taking inpatients with cerebral infarction as an example, the case mix scheme of TCM dominant diseases in TCM hospitals was explored to provide the data reference for better participation of TCM dominant diseases in the payment by disease in the future. Methods: The first page data of 9055 cases of inpatients with cerebral infarction in several TCM hospitals in Beijing in 2019 were extracted. The sub-node variables were determined by multiple linear regression, and incorporated into a decision tree model for case mix and calculation of the standard costs and disease weights after grouping. Results: Key factors such as gender, age, days of hospitalization, cost of consumables, hospital type and hospital level were incorporated into the decision tree model as inpatient cost sub-node variables, resulting in 19 case mixes with a more reasonable overall grouping. Conclusion: Hospitals should take measures to control the key factors affecting the hospitalization cost of patients with cerebral infarction, focus on the excess cost, develop standard cost, cost ceiling, excess cost, and disease weight, and actively explore the case mix scheme of TCM dominant diseases to provide the data reference for participation in the payment by disease.
Key words
TCM dominant diseases /
cerebral infarction /
case mix /
decision tree
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] WILM Q, HANNA R, MIKKO P, et al.Acute myocardial infarction and diagnosis-related groups: patient classification and hospital reimbursement in 11 European countries[J]. European Heart Journal, 2013(26):1972-1981A.
[2] IMAI S, YAMADA T, KASASHI K, et al.Construction of a flow chart-like risk prediction model of ganciclovir‐induced neutropaenia including severity grade: A data mining approach using decision tree[J]. Journal of Clinical Pharmacy & Therapeutics, 2019.
[3] GIBSON, CLAIRE L.Cerebral ischemic stroke: is gender important?[J]. Journal of Cerebral Blood Flow & Metabolism Official Journal of the International Society of Cerebral Blood Flow & Metabolism, 2013, 33(9):1355-1361.
[4] PELTOLA M, QUENTIN W.Diagnosis-Related Groups for Stroke in Europe: Patient Classification and Hospital Reimbursement in 11 Countries[J]. Cerebrovascular Diseases, 2013, 35(2):113.
[5] HUANG Y C.The impact factors on the cost and length of stay among acute ischemic stroke (vol 22, pg e152, 2013)[J]. Journal of Stroke and Cerebrovascular Diseases, 2014, 23(10):2936-2936.
[6] KARSTEN K, MARTIN G, THOMAS M, et al.Gender-differences in prevalence and outcome of ischemic stroke and promoting factors of atrial thrombi[J]. Artery Research, 2018, 22:68-78.
[7] BUSSE R, GEISSLER A, AAVIKSOO A, et al.Diagnosis related groups in Europe: moving towards transparency, efficiency, and quality in hospitals?[J]. BMJ, 2013, 346.
[8] MURPHY E L, COMISKEY C M.Using chi-Squared Automatic Interaction Detection (CHAID) modelling to identify groups of methadone treatment clients experiencing significantly poorer treatment outcomes[J]. Journal of Substance Abuse Treatment, 2013, 45(4):343-349.
[9] CHING-YEN K, YU L C, CHEN H C, et al.Comparison of Models for the Prediction of Medical Costs of Spinal Fusion in Taiwan Diagnosis-Related Groups by Machine Learning Algorithms[J]. Healthcare Informatics Research, 2018, 24(1):29-37.
