RESUMEN
BACKGROUND: International Classification of Diseases codes are widely used to describe diagnosis information, but manual coding relies heavily on human interpretation, which can be expensive, time consuming, and prone to errors. With the transition from the International Classification of Diseases, Ninth Revision, to the International Classification of Diseases, Tenth Revision (ICD-10), the coding process has become more complex, highlighting the need for automated approaches to enhance coding efficiency and accuracy. Inaccurate coding can result in substantial financial losses for hospitals, and a precise assessment of outcomes generated by a natural language processing (NLP)-driven autocoding system thus assumes a critical role in safeguarding the accuracy of the Taiwan diagnosis related groups (Tw-DRGs). OBJECTIVE: This study aims to evaluate the feasibility of applying an International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM), autocoding system that can automatically determine diagnoses and codes based on free-text discharge summaries to facilitate the assessment of Tw-DRGs, specifically principal diagnosis and major diagnostic categories (MDCs). METHODS: By using the patient discharge summaries from Kaohsiung Medical University Chung-Ho Memorial Hospital (KMUCHH) from April 2019 to December 2020 as a reference data set we developed artificial intelligence (AI)-assisted ICD-10-CM coding systems based on deep learning models. We constructed a web-based user interface for the AI-assisted coding system and deployed the system to the workflow of the certified coding specialists (CCSs) of KMUCHH. The data used for the assessment of Tw-DRGs were manually curated by a CCS with the principal diagnosis and MDC was determined from discharge summaries collected at KMUCHH from February 2023 to April 2023. RESULTS: Both the reference data set and real hospital data were used to assess performance in determining ICD-10-CM coding, principal diagnosis, and MDC for Tw-DRGs. Among all methods, the GPT-2 (OpenAI)-based model achieved the highest F1-score, 0.667 (F1-score 0.851 for the top 50 codes), on the KMUCHH test set and a slightly lower F1-score, 0.621, in real hospital data. Cohen κ evaluation for the agreement of MDC between the models and the CCS revealed that the overall average κ value for GPT-2 (κ=0.714) was approximately 12.2 percentage points higher than that of the hierarchy attention network (κ=0.592). GPT-2 demonstrated superior agreement with the CCS across 6 categories of MDC, with an average κ value of approximately 0.869 (SD 0.033), underscoring the effectiveness of the developed AI-assisted coding system in supporting the work of CCSs. CONCLUSIONS: An NLP-driven AI-assisted coding system can assist CCSs in ICD-10-CM coding by offering coding references via a user interface, demonstrating the potential to reduce the manual workload and expedite Tw-DRG assessment. Consistency in performance affirmed the effectiveness of the system in supporting CCSs in ICD-10-CM coding and the judgment of Tw-DRGs.
RESUMEN
BACKGROUND: This study centered on differences in medical costs, using the Taiwan diagnosis-related groups (Tw-DRGs) on medical resource utilization in inguinal hernia repair (IHR) in hospitals with different ownership to provide suitable reference information for hospital administrators. METHODS: The 2010-2011 data for three hospitals under different ownership were extracted from the Taiwan National Health Insurance claims database. A retrospective method was applied to analyze the age, sex, length of stay, diagnosis and surgical procedure code, and the change in financial risk of medical costs in IHR cases after introduction of Tw-DRGs. The study calculated the cost using Tw-DRG payment principles, and compared it with estimated inpatient medical costs calculated using the fee-for-service policy. RESULTS: There were 723 IHR cases satisfying the Tw-DRGs criteria. Cost control in the medical care corporation hospital (US$764.2/case) was more efficient than that in the public hospital (US$902.7/case) or nonprofit proprietary hospital (US$817.1/case) surveyed in this study. For IHR, anesthesiologists in the public hospital preferred to use general anesthesia (86%), while those in the two other hospitals tended to administer spinal anesthesia. We also discovered the difference in anesthesia cost was high, at US$80.2/case on average. CONCLUSIONS: Because the Tw-DRG-based reimbursement system produces varying hospital costs, hospital administrators should establish a financial risk assessment system as early as possible to improve healthcare quality and financial management efficiency. This would then benefit the hospital, patient, and Bureau of National Health Insurance.