EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Post-Operative Medium- and Long-Term Endocrine Outcomes in Patients with Non-Functioning Pituitary Adenomas—Machine Learning Analysis

Ziad Hussein, Robert W Slack, Hani J Marcus iD, Evangelos B Mazomenos iD, Stephanie E Baldeweg

Cancers · 16.05.2023 · 15 (10) · 2771

DOI: 10.3390/cancers15102771 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 16.05.2023. Verfasst von Ziad Hussein und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diabetes & Endocrinology, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield S10 2JF, UK. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome/EPSRC Centre for Interventional and Surgical Sciences, UCLH/UCL Biomedical Research Centre.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Post-operative endocrine outcomes in patients with non-functioning pituitary adenoma (NFPA) are variable. The aim of this study was to use machine learning (ML) models to better predict medium- and long-term post-operative hypopituitarism in patients with NFPAs. We included data from 383 patients who underwent surgery with or without radiotherapy for NFPAs, with a follow-up period between 6 months and 15 years. ML models, including k-nearest neighbour (KNN), support vector machine (SVM), and decision tree models, showed a superior ability to predict panhypopituitarism compared with non-parametric statistical modelling (mean accuracy: 0.89; mean AUC-ROC: 0.79), with SVM achieving the highest performance (mean accuracy: 0.94; mean AUC-ROC: 0.88). Pre-operative endocrine function was the strongest feature for predicting panhypopituitarism within 1 year post-operatively, while endocrine outcomes at 1 year post-operatively supported strong predictions of panhypopituitarism at 5 and 10 years post-operatively. Other features found to contribute to panhypopituitarism prediction were age, volume of tumour, and the use of radiotherapy. In conclusion, our study demonstrates that ML models show potential in predicting post-operative panhypopituitarism in the medium and long term in patients with NFPM. Future work will include incorporating additional, more granular data, including imaging and operative video data, across multiple centres.

Schlagwörter

Stichwörter der Autor:innen

decision treehypopituitarismknnlogistic regressionmachine learningnon-functioning pituitary adenomapanhypopituitarismsvm

Autor:innen und Institutionen

  • Department of Diabetes & Endocrinology, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield S10 2JF, UK.
  • Department of Diabetes & Endocrinology, University College London Hospital, London NW1 2BU, UK.
  • Centre for Obesity & Metabolism, Department of Experimental & Translational Medicine, Division of Medicine, University College London, London WC1N 3BG, UK.
  • Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London W1W 7TY, UK.
  • Department of Medical Physics and Biomedical Engineering, University College London, London WC1E 6BT, UK.
  • Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London NW1 2BU, UK.

ORCID-Profile: Hani J Marcus, Evangelos B Mazomenos

Förderung

  • Wellcome/EPSRC Centre for Interventional and Surgical Sciences
  • UCLH/UCL Biomedical Research Centre

Zitieren

APA

Hussein, Z., Slack, R. W., Marcus, H. J., Mazomenos, E. B., & Baldeweg, S. E. (2023). Post-Operative Medium- and Long-Term Endocrine Outcomes in Patients with Non-Functioning Pituitary Adenomas—Machine Learning Analysis. Cancers, 15(10), 2771. https://doi.org/10.3390/cancers15102771

Vancouver

Hussein Z, Slack RW, Marcus HJ, Mazomenos EB, Baldeweg SE. Post-Operative Medium- and Long-Term Endocrine Outcomes in Patients with Non-Functioning Pituitary Adenomas—Machine Learning Analysis. Cancers. 2023;15(10):2771. doi:10.3390/cancers15102771

BibTeX
@article{Hussein2023,
  author = {Hussein, Ziad and Slack, Robert W and Marcus, Hani J and Mazomenos, Evangelos B and Baldeweg, Stephanie E},
  title = {Post-Operative Medium- and Long-Term Endocrine Outcomes in Patients with Non-Functioning Pituitary Adenomas—Machine Learning Analysis},
  journal = {Cancers},
  year = {2023},
  volume = {15},
  number = {10},
  pages = {2771},
  doi = {10.3390/cancers15102771}
}
Kostenlos starten →