The problem with the ‘truth’: rethinking ground truth for artificial intelligence in endometriosis diagnosis
Human Reproduction · 2026
DOI: 10.1093/humrep/deag024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Human Reproduction, 2026. Verfasst von Alison Deslandes und 9 weiteren Autor:innen. Beteiligte Einrichtung: Robinson Research Institute, University of Adelaide, Adelaide, Australia. Hauptthemen laut MEDLINE: Endometriosis, Artificial Intelligence. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Government through the Medical Research Futures Fund: Primary Health Care Research Data Infrastructure Grant 2020, Medical Research Futures Fund: Primary Health Care Research Data Infrastructure, NHMRC.
Abstract (Originalsprache)
Artificial intelligence (AI) is revolutionizing how we practice medicine. In areas where we have traditionally struggled, such as diagnosing endometriosis, AI has significant potential to improve the breadth and accuracy of diagnostic services offering a great benefit to patient care. When developing AI models for diagnosis, the ‘ground truth’ refers to the reference standard used in the labelling of the data used to train the model. Conventionally, in clinical medicine, we correlate any new diagnostic tool to the established ‘gold standard’, which in the case of endometriosis is laparoscopic visualization of lesions and histological confirmation. This method however is increasingly recognized as imperfect. Acknowledgement of the limitations of surgery and recent improvements in the diagnostic capability of imaging technologies to detect endometriosis, has created a situation where endometriosis no longer has one clear ‘gold standard’ for diagnosis. In this commentary, we will explore the impact of this on AI-driven endometriosis diagnostic tools and propose novel ways this could be addressed in the context of creating ground truths for endometriosis diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Robinson Research Institute, University of Adelaide, Adelaide, Australia.
- Specialist Imaging Partners, Adelaide, Australia.
- Australian Institute for Machine Learning, University of Adelaide, Adelaide, Australia.
- Department of Obstetrics and Gynecology, McMaster University, Hamilton, Canada.
- School of Computer and Mathematical Sciences, University of Adelaide, Adelaide, Australia.
- Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom.
ORCID-Profile: Alison Deslandes, Yuan Zhang, Mathew Leonardi, Jodie Avery, George Condous, Steven Knox, M Louise Hull
Förderung
- Australian Government through the Medical Research Futures Fund: Primary Health Care Research Data Infrastructure Grant 2020
- Medical Research Futures Fund: Primary Health Care Research Data Infrastructure
- NHMRC
- Endometriosis Australia
Zitieren
APA
Deslandes, A., Zhang, Y., Leonardi, M., Chen, H. T., Carneiro, G., Avery, J., Condous, G., Knox, S., Hull, M. L., & IMAGENDO Team (2026). The problem with the ‘truth’: rethinking ground truth for artificial intelligence in endometriosis diagnosis. Human Reproduction. https://doi.org/10.1093/humrep/deag024
Vancouver
Deslandes A, Zhang Y, Leonardi M, Chen HT, Carneiro G, Avery J, et al. The problem with the ‘truth’: rethinking ground truth for artificial intelligence in endometriosis diagnosis. Human Reproduction. 2026. doi:10.1093/humrep/deag024
BibTeX
@article{Deslandes2026,
author = {Deslandes, Alison and Zhang, Yuan and Leonardi, Mathew and Chen, Hsiang-Ting and Carneiro, Gustavo and Avery, Jodie and Condous, George and Knox, Steven and Hull, M Louise and IMAGENDO Team, IMAGENDO Team},
title = {The problem with the ‘truth’: rethinking ground truth for artificial intelligence in endometriosis diagnosis},
journal = {Human Reproduction},
year = {2026},
doi = {10.1093/humrep/deag024}
}
EUVIMED