EUVIMEDEUVIMED entdecken
Open Access

Beyond black-box models: explainable AI for embryo ploidy prediction and patient-centric consultation

Thi-My-Trang Luong, Nguyen-Tuong Ho, Yuh-Ming Hwu, Shyr-Yeu Lin, Jason Yen-Ping Ho, Ruey-Sheng Wang, Yi-Xuan Lee, Shun-Jen Tan, Yi-Rong Lee, Yung-Ling Huang, Yi-Ching Hsu, Nguyen-Quoc-Khanh Le und 1 weitere

Journal of Assisted Reproduction and Genetics · 2024

DOI: 10.1007/s10815-024-03178-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Assisted Reproduction and Genetics, 2024. Verfasst von Thi-My-Trang Luong und 12 weiteren Autor:innen. Beteiligte Einrichtung: International Master Program in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan. Hauptthemen laut MEDLINE: Ploidies, Artificial Intelligence. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To determine if an explainable artificial intelligence (XAI) model enhances the accuracy and transparency of predicting embryo ploidy status based on embryonic characteristics and clinical data. METHODS: This retrospective study utilized a dataset of 1908 blastocyst embryos. The dataset includes ploidy status, morphokinetic features, morphology grades, and 11 clinical variables. Six machine learning (ML) models including Random Forest (RF), Linear Discriminant Analysis (LDA), Logistic Regression (LR), Support Vector Machine (SVM), AdaBoost (ADA), and Light Gradient-Boosting Machine (LGBM) were trained to predict ploidy status probabilities across three distinct datasets: high-grade embryos (HGE, n = 1107), low-grade embryos (LGE, n = 364), and all-grade embryos (AGE, n = 1471). The model's performance was interpreted using XAI, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) techniques. RESULTS: The mean maternal age was 38.5 ± 3.85 years. The Random Forest (RF) model exhibited superior performance compared to the other five ML models, achieving an accuracy of 0.749 and an AUC of 0.808 for AGE. In the external test set, the RF model achieved an accuracy of 0.714 and an AUC of 0.750 (95% CI, 0.702-0.796). SHAP's feature impact analysis highlighted that maternal age, paternal age, time to blastocyst (tB), and day 5 morphology grade significantly impacted the predictive model. In addition, LIME offered specific case-ploidy prediction probabilities, revealing the model's assigned values for each variable within a finite range. CONCLUSION: The model highlights the potential of using XAI algorithms to enhance ploidy prediction, optimize embryo selection as patient-centric consultation, and provides reliability and transparent insights into the decision-making process.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PloidiesArtificial IntelligenceHumansFemaleAdultPregnancyBlastocystRetrospective StudiesEmbryo TransferPreimplantation DiagnosisMachine LearningFertilization in VitroReferral and ConsultationMaternal AgeSupport Vector Machine

Stichwörter der Autor:innen

Embryo selectionExplainable artificial intelligenceMachine learningPloidy predictionPreimplantation genetic testing

Autor:innen und Institutionen

  • International Master Program in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.
  • AIBioMed Research Group, Taipei Medical University, Taipei, Taiwan.
  • Taipei Fertility Centre, Taipei, Taiwan.
  • IVFMD, My Duc Hospital, Ho Chi Minh, Vietnam.
  • AIBioMed Research Group, Taipei Medical University, Taipei, Taiwan. khanhlee@tmu.edu.tw.
  • Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan. khanhlee@tmu.edu.tw.

Zitieren

APA

Luong, T. M., Ho, N. T., Hwu, Y. M., Lin, S. Y., Ho, J. Y., Wang, R. S., Lee, Y. X., Tan, S. J., Lee, Y. R., Huang, Y. L., Hsu, Y. C., Le, N. Q., & Tzeng, C. R. (2024). Beyond black-box models: explainable AI for embryo ploidy prediction and patient-centric consultation. Journal of Assisted Reproduction and Genetics. https://doi.org/10.1007/s10815-024-03178-7

Vancouver

Luong TM, Ho NT, Hwu YM, Lin SY, Ho JY, Wang RS, et al. Beyond black-box models: explainable AI for embryo ploidy prediction and patient-centric consultation. Journal of Assisted Reproduction and Genetics. 2024. doi:10.1007/s10815-024-03178-7

BibTeX
@article{Luong2024,
  author = {Luong, Thi-My-Trang and Ho, Nguyen-Tuong and Hwu, Yuh-Ming and Lin, Shyr-Yeu and Ho, Jason Yen-Ping and Wang, Ruey-Sheng and Lee, Yi-Xuan and Tan, Shun-Jen and Lee, Yi-Rong and Huang, Yung-Ling and Hsu, Yi-Ching and Le, Nguyen-Quoc-Khanh and Tzeng, Chii-Ruey},
  title = {Beyond black-box models: explainable AI for embryo ploidy prediction and patient-centric consultation},
  journal = {Journal of Assisted Reproduction and Genetics},
  year = {2024},
  doi = {10.1007/s10815-024-03178-7}
}
Kostenlos starten →