EUVIMEDEUVIMED entdecken
Crossref

A concept-enhanced, knowledge graph-guided framework for interpretable PCOS prediction: a case study in explainable biomedical artificial intelligence

Sudeepti Kulshrestha iD, Neeraj Kumar iD, Pulkit Verma iD, Kriti Sikri iD, Mayank Gangwar iD, Abhishek Sengupta iD, Suruchi Aggarwal iD, Priyanka Narad iD

Reproduction, Fertility and Development · 31.03.2026 · 38 (5)

DOI: 10.1071/rd25145 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Reproduction, Fertility and Development, online erschienen am 27.03.2026. Verfasst von Sudeepti Kulshrestha und 7 weiteren Autor:innen. Beteiligte Einrichtung: Informatics and Data Centre, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India. Hauptthemen laut MEDLINE: Polycystic Ovary Syndrome, Artificial Intelligence, Machine Learning. Die Arbeit nennt 47 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Context

Overcoming the disconnect between efficient Machine Learning (ML) techniques and its therapeutic applicability necessitates frameworks that provide clear, contextualized evidence.

Aims

The present work examines the efficacy of a conceptually-enhanced framework that combines biological domain expertise, knowledge graphs, and probabilistic inference with ML predictions. We employed this innovative strategy for predicting polycystic ovary syndrome (PCOS).

Methods

PCOS clinical data (541 patients) was sourced from Kaggle. Clinically relevant conceptual characteristics were developed and integrated with raw data using a knowledge graph (KG) employing TransE-based semantic proximity scoring and a Bayesian network (BN) to characterize conditional dependencies. Knowledge-driven concepts were included in subsequent ML procedures, including LazyPredict for model screening, and ensemble model construction from top 10 models based on accuracy using soft-voting ensemble classifier. Patient-specific, guideline-compliant explanations were designed to accompany all model predictions for improved interpretability. Key results The approach demonstrated robust predictive abilities, with the concept-integrated ensemble model demonstrating the strongest performance, with a five-fold stratified cross-validation accuracy of 93.65% (95% CI: 91.59–95.63%) and a ROC-AUC of 0.98 (95% CI: 0.96–1.00%). In addition to predicting accurately, the incorporation of features obtained from KG and BN significantly improved interpretability, with causal probabilities based on BN proving to be the most important feature. The framework facilitated patient-specific, concept-based interpretations consistent with clinical guidelines.

Conclusion

The integration of biomedically-relevant concepts improves the interpretability of PCOS predictions while maintaining predictive performance.

Implications

Our work proposes the use of clinician-aligned PCOS screening tools that provide transparent risk classification and informed treatment decisions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Polycystic Ovary SyndromeArtificial IntelligenceMachine LearningFemaleHumansBayes TheoremPredictive Learning ModelsPrediction AlgorithmsClassification AlgorithmsEnsemble Learning

Stichwörter der Autor:innen

artificial intelligencebayesian networksconcept representationintelligent decision supportknowledge extractionmachine learningmultimodal understandingsemantic reasoning

Autor:innen und Institutionen

  • Informatics and Data Centre, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India.
  • Division of Descriptive Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India.
  • Clinical Studies and Trials Unit, Division of Development Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India.
  • Amity Institute of Biotechnology, Amity University, Uttar Pradesh, Noida, India.
  • Division of Development Research, Indian Council of Medical Research (ICMR) Headquarters, New Delhi, India.

ORCID-Profile: Sudeepti Kulshrestha, Neeraj Kumar, Pulkit Verma, Kriti Sikri, Mayank Gangwar, Abhishek Sengupta, Suruchi Aggarwal, Priyanka Narad

Zitieren

APA

Kulshrestha, S., Kumar, N., Verma, P., Sikri, K., Gangwar, M., Sengupta, A., Aggarwal, S., & Narad, P. (2026). A concept-enhanced, knowledge graph-guided framework for interpretable PCOS prediction: a case study in explainable biomedical artificial intelligence. Reproduction, Fertility and Development, 38(5). https://doi.org/10.1071/rd25145

Vancouver

Kulshrestha S, Kumar N, Verma P, Sikri K, Gangwar M, Sengupta A, et al. A concept-enhanced, knowledge graph-guided framework for interpretable PCOS prediction: a case study in explainable biomedical artificial intelligence. Reproduction, Fertility and Development. 2026;38(5). doi:10.1071/rd25145

BibTeX
@article{Kulshrestha2026,
  author = {Kulshrestha, Sudeepti and Kumar, Neeraj and Verma, Pulkit and Sikri, Kriti and Gangwar, Mayank and Sengupta, Abhishek and Aggarwal, Suruchi and Narad, Priyanka},
  title = {A concept-enhanced, knowledge graph-guided framework for interpretable PCOS prediction: a case study in explainable biomedical artificial intelligence},
  journal = {Reproduction, Fertility and Development},
  year = {2026},
  volume = {38},
  number = {5},
  doi = {10.1071/rd25145}
}
Kostenlos starten →