EUVIMEDEUVIMED entdecken
Crossref

Complaint Driven Clinical Guidance and ICD Chapter Suggestion: An AI‐Based Text Classification Tool

Anday Duru iD, Eftal Sehirli iD, Muhammed Kamil Turan iD, Emrullah Demiral iD, Mehmet Tankul iD, Mehmet Coskun

Journal of Evaluation in Clinical Practice · 2026-12 · 32 (8)

DOI: 10.1111/jep.70711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Evaluation in Clinical Practice, online erschienen am 03.11.2026. Verfasst von Anday Duru und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Karabük University, Engineering and Natural Sciences Faculty, Karabük, Türkiye. Hauptthemen laut MEDLINE: International Classification of Diseases, Electronic Health Records, Artificial Intelligence. Die Arbeit nennt 49 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rationale, Aims and Objectives Accurate routing of patients to appropriate clinical departments is essential for timely diagnosis, effective treatment, and efficient use of hospital resources. However, hospital statistics and feedback from patients and healthcare staff indicate that many patients select clinics that are not appropriate for their presenting complaints. This mismatch unnecessarily occupies appointment slots, limits access to appropriate care, and increases the operational burden on healthcare systems. To address this problem, a complaint‐driven clinical guidance framework was developed to map patient complaints to suitable clinical departments and corresponding International Classification of Diseases (ICD) chapters.

Method

A 7‐year electronic health record dataset comprising 1,795,645 patient complaints was used to train and evaluate conventional machine learning algorithms and BERT‐based language models. The final classification tasks included 15 clinical departments for department recommendation and 12 ICD chapters for suggestion.

Results

For clinical department recommendation, Turkish BERT achieved the best performance, with a mean accuracy of 92.02%, precision of 92.91%, and F1‐score of 92.08%. McNemar's test confirmed that its improvement over multilingual BERT‐based alternatives was statistically significant. Error analysis indicated that most department‐level misclassifications occurred between clinically related or symptomatically overlapping departments, including Internal Medicine–Cardiology, Neurosurgery and Physical Therapy, and Cardiovascular Surgery–Cardiology. For ICD chapter suggestion, Turkish BERT achieved the best performance among the evaluated models, with a top‐1 accuracy of 66.7%, top‐3 accuracy of 82.9%, top‐5 accuracy of 85.4%.

Conclusion

Although exact ICD chapter prediction remained challenging, the substantially higher top‐3 and top‐5 accuracies indicate that the model may be useful for generating ranked candidate ICD chapters. Confusion analysis showed that errors were mainly concentrated between clinically overlapping ICD chapters, particularly neoplasms/blood and immune disorders, endocrine/metabolic diseases, circulatory system diseases, and symptom‐based chapters. These findings suggest that artificial intelligence‐based systems can effectively support clinical department recommendation to improve hospital workflow efficiency, whereas ICD chapter suggestion may serve as a preliminary ranked decision‐support tool.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

International Classification of DiseasesElectronic Health RecordsArtificial IntelligenceHumansMachine LearningClassification AlgorithmsAlgorithms

Stichwörter der Autor:innen

artificial intelligence (AI)classificationclinical guidanceelectronic health recordsinternational classification of diseases (ICD)

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Karabük University, Engineering and Natural Sciences Faculty, Karabük, Türkiye.
  • Department of Computer Engineering, Karabük University, Computing and Information Sciences Faculty, Karabük, Türkiye.
  • Department of Medical Biology, Karabük University, Medicine Faculty, Karabük, Türkiye.
  • Department of Software Engineering, Karabük University, Computing and Information Sciences Faculty, Karabük, Türkiye.
  • Department of Medical Services and Techniques, Karabük University, Vocational School of Health Services, Karabük, Türkiye.
  • Department of Dialysis, Medikar Private Hospital, Karabük, Türkiye.

ORCID-Profile: Anday Duru, Eftal Sehirli, Muhammed Kamil Turan, Emrullah Demiral, Mehmet Tankul

Zitieren

APA

Duru, A., Sehirli, E., Turan, M. K., Demiral, E., Tankul, M., & Coskun, M. (2026). Complaint Driven Clinical Guidance and ICD Chapter Suggestion: An AI‐Based Text Classification Tool. Journal of Evaluation in Clinical Practice, 32(8). https://doi.org/10.1111/jep.70711

Vancouver

Duru A, Sehirli E, Turan MK, Demiral E, Tankul M, Coskun M. Complaint Driven Clinical Guidance and ICD Chapter Suggestion: An AI‐Based Text Classification Tool. Journal of Evaluation in Clinical Practice. 2026;32(8). doi:10.1111/jep.70711

BibTeX
@article{Duru2026,
  author = {Duru, Anday and Sehirli, Eftal and Turan, Muhammed Kamil and Demiral, Emrullah and Tankul, Mehmet and Coskun, Mehmet},
  title = {Complaint Driven Clinical Guidance and ICD Chapter Suggestion: An AI‐Based Text Classification Tool},
  journal = {Journal of Evaluation in Clinical Practice},
  year = {2026},
  volume = {32},
  number = {8},
  doi = {10.1111/jep.70711}
}
Kostenlos starten →