Application of Clinical Department–Specific AI-Assisted Coding Using Taiwan Diagnosis-Related Groups: Retrospective Validation Study
Bibliographic record
Abstract
Background: The accuracy of the ICD-10-CM (International Classification of Diseases, Tenth Revision, Clinical Modification) procedure coding system (PCS) is crucial for generating correct Taiwan diagnosis-related groups (DRGs), as coding errors can lead to financial losses for hospitals. Objective: The study aimed to determine the consistency between an artificial intelligence (AI)-assisted coding module and manual coding, as well as to identify clinical specialties suitable for implementing the developed AI-assisted coding module. Methods: This study examined the AI-assisted coding module from the perspective of health care professionals. The research period started in February 2023. The study excluded cases outside of Taiwan DRGs, those with incomplete medical records, and cases with Taiwan DRG disposals ICD-10 (International Statistical Classification of Diseases, Tenth Revision) PCS. Data collection was conducted through retrospective medical record review. The AI-assisted module was constructed using a hierarchical attention network. The verification of the Taiwan DRGs results from the AI-assisted coding model focused on the major diagnostic categories (MDCs). Statistical computations were conducted using SPSS version 19. Research variables consisted of categorical variables represented by MDC, and continuous variables were represented by the relative weight of Taiwan DRGs. Results: A total of 2632 discharge records meeting the research criteria were collected from February to April 2023. In terms of inferential statistics, κ statistics were used for MDC analysis. The infectious and parasitic diseases MDC, as well as the respiratory diseases MDC had κ values exceeding 0.8. Clinical inpatient specialties were statistically analyzed using the Wilcoxon signed rank test. There was not a difference in coding results between the 23 clinical departments, such as the Division of Cardiology, the Division of Nephrology, and the Department of Urology. Conclusions: For human coders, with the assistance of the ICD-10-CM AI-assisted coding system, work time is reduced. Additionally, strengthening knowledge in clinical documentation enables human coders to maximize their role. This positions them to become clinical documentation experts, preparing them for further career development. Future research will apply the same method to validate the ICD-10 AI-assisted coding module.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".