MétaCan
Menu
Back to cohort
Record W4404893442 · doi:10.2196/59961

Application of Clinical Department–Specific AI-Assisted Coding Using Taiwan Diagnosis-Related Groups: Retrospective Validation Study

2024· article· en· W4404893442 on OpenAlexvenueno aff
An-Tai Lu, Chong-Sin Liou, Chia-Hsin Lai, Bo-Tsz Shian, Ming-Ta Li, Chih-Yen Sun, Hao-Yun Kao, Hong-Jie Dai, Ming‐Ju Tsai

Bibliographic record

VenueJMIR Human Factors · 2024
Typearticle
Languageen
FieldHealth Professions
TopicMedical Coding and Health Information
Canadian institutionsnot available
Fundersnot available
KeywordsPreprintComputer scienceCoding (social sciences)Artificial intelligenceMachine learningWorld Wide WebStatisticsMathematics

Abstract

fetched live from OpenAlex

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.013
metaresearch head score (Gemma)0.031
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.013
Threshold uncertainty score0.071

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0130.031
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.344
GPT teacher head0.546
Teacher spread0.202 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Human FactorsSame topicMedical Coding and Health InformationFrench-language works237,207