EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Towards an Explainable AI-Based Tool to Predict Preterm Birth

Ilias Kyparissidis Kokkinidis, Evangelos Logaras, Emmanouil S Rigas, Ioannis Tsakiridis, Themistoklis Dagklis, Antonis Billis, Panagiotis D Bamidis

Studies in Health Technology and Informatics · 2023

DOI: 10.3233/shti230207 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2023. Verfasst von Ilias Kyparissidis Kokkinidis und 6 weiteren Autor:innen. Beteiligte Einrichtung: Lab of Medical Physics and Digital Innovation, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece. Hauptthemen laut MEDLINE: Artificial Intelligence, Premature Birth. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Preterm birth (PTB) is defined as delivery occurring before 37 weeks of gestation. In this paper, Artificial Intelligence (AI)-based predictive models are adapted to accurately estimate the probability of PTB. In doing so, pregnant women’ objective results and variables extracted from the screening procedure in combination with demographics, medical history, social history, and other medical data are used. A dataset consisting of 375 pregnant women is used and a number of alternative Machine Learning (ML) algorithms are applied to predict PTB. The ensemble voting model produced the best results across all performance metrics with an area under the curve (ROC-AUC) of approximately 0.84 and a precision–recall curve (PR-AUC) of approximately 0.73. An attempt to provide clinicians with an explanation of the prediction is performed to increase trustworthiness.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligencePremature BirthInfant, NewbornPregnancyFemaleHumansAlgorithmsMachine LearningBenchmarking

Stichwörter der Autor:innen

Artificial Intelligence (AI)ClinicalDecision Support SystemsExplainable Artificial Intelligence (XAI)Machine Learning (ML)Obstetrics and Gynecology (specialty)Premature Birth

Autor:innen und Institutionen

  • Lab of Medical Physics and Digital Innovation, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece.
  • 3rd Department of Obstetrics and Gynecology, Aristotle University of Thessaloniki, Greece.

Zitieren

APA

Kyparissidis Kokkinidis, I., Logaras, E., Rigas, E. S., Tsakiridis, I., Dagklis, T., Billis, A., & Bamidis, P. D. (2023). Towards an Explainable AI-Based Tool to Predict Preterm Birth. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti230207

Vancouver

Kyparissidis Kokkinidis I, Logaras E, Rigas ES, Tsakiridis I, Dagklis T, Billis A, et al. Towards an Explainable AI-Based Tool to Predict Preterm Birth. Studies in Health Technology and Informatics. 2023. doi:10.3233/shti230207

BibTeX
@article{KyparissidisKokkinidis2023,
  author = {Kyparissidis Kokkinidis, Ilias and Logaras, Evangelos and Rigas, Emmanouil S and Tsakiridis, Ioannis and Dagklis, Themistoklis and Billis, Antonis and Bamidis, Panagiotis D},
  title = {Towards an Explainable AI-Based Tool to Predict Preterm Birth},
  journal = {Studies in Health Technology and Informatics},
  year = {2023},
  doi = {10.3233/shti230207}
}
Kostenlos starten →