EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust disease prognosis via diagnostic knowledge preservation: A sequential learning approach

Haresh Rengaraj Rajamohan iD, Yanqi Xu iD, Weicheng Zhu, Richard Kijowski, Kyunghyun Cho, Krzysztof J Geras, Narges Razavian, Cem M Deniz iD

PLOS One · 06.05.2026 · 21 (5) · e0344600

DOI: 10.1371/journal.pone.0344600 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.05.2026. Verfasst von Haresh Rengaraj Rajamohan und 7 weiteren Autor:innen. Beteiligte Einrichtung: Center for Data Science, New York University, New York, New York, United States of America. Hauptthemen laut MEDLINE: Breast Neoplasms, Alzheimer Disease, Osteoarthritis, Knee, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAMS NIH HHS, National Institute of Arthritis and Musculoskeletal and Skin Diseases.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate disease prognosis is essential for patient care but is often hindered by the scarcity of longitudinal data. This study explores deep learning training strategies that utilize large, accessible diagnostic datasets to pretrain models aimed at predicting future disease progression in knee osteoarthritis (OA), Alzheimer’s disease (AD), and breast cancer (BC). While diagnostic pretraining improves prognostic task performance, naive fine-tuning for prognosis can cause ‘catastrophic forgetting,’ where the model’s original diagnostic accuracy degrades, a significant patient safety concern in real-world settings. To address this, we propose a sequential learning strategy with experience replay. We used cohorts with knee radiographs, brain MRIs, and digital mammograms to predict 4-year structural worsening in OA, 2-year cognitive decline in AD, and 5-year cancer diagnosis in BC. Our results showed that diagnostic pretraining on larger datasets improved prognosis model performance compared to standard baselines, boosting both the Area Under the Receiver Operating Characteristic curve (AUROC) (e.g., Knee OA external: 0.770 vs 0.747; Breast Cancer: 0.874 vs 0.848) and the Area Under the Precision-Recall Curve (AUPRC) (e.g., Alzheimer’s Disease: 0.752 vs 0.683). Additionally, a sequential learning approach with experience replay achieved prognostic performance comparable to dedicated single-task models (e.g., Breast Cancer AUROC 0.876 vs 0.874) while also preserving diagnostic ability. This method maintained high diagnostic accuracy (e.g., Breast Cancer Balanced Accuracy 50.4% vs 50.9% for a dedicated diagnostic model), unlike simpler multitask methods prone to catastrophic forgetting (e.g., 37.7%). Our findings show that leveraging large diagnostic datasets is a reliable and data-efficient way to enhance prognostic models while maintaining essential diagnostic skills.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsAlzheimer DiseaseOsteoarthritis, KneeDeep LearningHumansFemalePrognosisMagnetic Resonance ImagingPredictive Learning ModelsDisease ProgressionROC Curve

Autor:innen und Institutionen

  • Center for Data Science, New York University, New York, New York, United States of America.
  • Department of Radiology, Hospital for Special Surgery, New York, New York, United States of America.
  • Department of Radiology, New York University Langone Health, New York, New York, United States of America.
  • Department of Population Health, New York University Langone Health, New York, New York, United States of America.
  • Bernard and Irene Schwartz Center for Biomedical Imaging, New York University Langone Health, New York, New York, United States of America.

ORCID-Profile: Haresh Rengaraj Rajamohan, Yanqi Xu, Cem M Deniz

Förderung

  • NIAMS NIH HHS
  • National Institute of Arthritis and Musculoskeletal and Skin Diseases

Zitieren

APA

Rajamohan, H. R., Xu, Y., Zhu, W., Kijowski, R., Cho, K., Geras, K. J., Razavian, N., & Deniz, C. M. (2026). Robust disease prognosis via diagnostic knowledge preservation: A sequential learning approach. PLOS One, 21(5), e0344600. https://doi.org/10.1371/journal.pone.0344600

Vancouver

Rajamohan HR, Xu Y, Zhu W, Kijowski R, Cho K, Geras KJ, et al. Robust disease prognosis via diagnostic knowledge preservation: A sequential learning approach. PLOS One. 2026;21(5):e0344600. doi:10.1371/journal.pone.0344600

BibTeX
@article{Rajamohan2026,
  author = {Rajamohan, Haresh Rengaraj and Xu, Yanqi and Zhu, Weicheng and Kijowski, Richard and Cho, Kyunghyun and Geras, Krzysztof J and Razavian, Narges and Deniz, Cem M},
  title = {Robust disease prognosis via diagnostic knowledge preservation: A sequential learning approach},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0344600},
  doi = {10.1371/journal.pone.0344600}
}
Kostenlos starten →