Developing an artificial intelligence-based headache diagnostic model and its utility for non-specialists’ diagnostic accuracy
Cephalalgia · 2023-05 · 43 (5) · 033310242311569
DOI: 10.1177/03331024231156925 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cephalalgia, online erschienen am 18.04.2023. Verfasst von Masahito Katsuki und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosurgery, Itoigawa General Hospital, Niigata, Japan. Hauptthemen laut MEDLINE: Artificial Intelligence, Headache. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Background
Misdiagnoses of headache disorders are a serious issue. Therefore, we developed an artificial intelligence-based headache diagnosis model using a large questionnaire database in a specialized headache hospital.
Methods
Phase 1: We developed an artificial intelligence model based on a retrospective investigation of 4000 patients (2800 training and 1200 test dataset) diagnosed by headache specialists. Phase 2: The model’s efficacy and accuracy were validated. Five non-headache specialists first diagnosed headaches in 50 patients, who were then re-diagnosed using AI. The ground truth was the diagnosis by headache specialists. The diagnostic performance and concordance rates between headache specialists and non-specialists with or without artificial intelligence were evaluated.
Results
Phase 1: The model’s macro-average accuracy, sensitivity (recall), specificity, precision, and F values were 76.25%, 56.26%, 92.16%, 61.24%, and 56.88%, respectively, for the test dataset. Phase 2: Five non-specialists diagnosed headaches without artificial intelligence with 46% overall accuracy and 0.212 kappa for the ground truth. The statistically improved values with artificial intelligence were 83.20% and 0.678, respectively. Other diagnostic indexes were also improved.
Conclusions
Artificial intelligence improved the non-specialist diagnostic performance. Given the model’s limitations based on the data from a single center and the low diagnostic accuracy for secondary headaches, further data collection and validation are needed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurosurgery, Itoigawa General Hospital, Niigata, Japan.
- Department of Neurology, Saitama Neuropsychiatric Institute, Saitama, Japan.
- Headache Center and Department of Neurology, Tominaga Hospital, Osaka, Japan.
- Department of Neurology, Osaka Saiseikai Nakatsu Hospital, Osaka, Japan.
- Department of Plastic Surgery, Osaka Metropolitan University, Osaka, Japan.
- Department of Clinical Training, St. Luke's International Hospital, Tokyo, Japan.
ORCID-Profile: Masahito Katsuki, Shoji Kikui, Daisuke Danno
Zitieren
APA
Katsuki, M., Shimazu, T., Kikui, S., Danno, D., Miyahara, J., Takeshima, R., Takeshima, E., Shimazu, Y., Nakashima, T., Matsuo, M., & Takeshima, T. (2023). Developing an artificial intelligence-based headache diagnostic model and its utility for non-specialists’ diagnostic accuracy. Cephalalgia, 43(5), 033310242311569. https://doi.org/10.1177/03331024231156925
Vancouver
Katsuki M, Shimazu T, Kikui S, Danno D, Miyahara J, Takeshima R, et al. Developing an artificial intelligence-based headache diagnostic model and its utility for non-specialists’ diagnostic accuracy. Cephalalgia. 2023;43(5):033310242311569. doi:10.1177/03331024231156925
BibTeX
@article{Katsuki2023,
author = {Katsuki, Masahito and Shimazu, Tomokazu and Kikui, Shoji and Danno, Daisuke and Miyahara, Junichi and Takeshima, Ryusaku and Takeshima, Eriko and Shimazu, Yuki and Nakashima, Takahiro and Matsuo, Mitsuhiro and Takeshima, Takao},
title = {Developing an artificial intelligence-based headache diagnostic model and its utility for non-specialists’ diagnostic accuracy},
journal = {Cephalalgia},
year = {2023},
volume = {43},
number = {5},
pages = {033310242311569},
doi = {10.1177/03331024231156925}
}
EUVIMED