EUVIMEDEUVIMED entdecken
Multizentrische Studie

A supervised machine learning approach for predicting the need for postsurgical intervention in acromegaly

Yuki Shinya, Abdul Karim Ghaith, Sukwoo Hong, Justine S Herndon, Sandhya R Palit, Dana Erickson, Irina Bancos, Miguel Saez-Alegre, Ramin A Morshed, Carlos Pinheiro Neto, Fredric B Meyer, John L D Atkinson und 1 weitere

Neurosurgical Focus · 2025

DOI: 10.3171/2025.4.focus2597 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Neurosurgical Focus, 2025. Verfasst von Yuki Shinya und 12 weiteren Autor:innen. Beteiligte Einrichtung: 1Department of Neurologic Surgery, Mayo Clinic, Rochester, Minnesota. Hauptthemen laut MEDLINE: Acromegaly, Supervised Machine Learning, Growth Hormone-Secreting Pituitary Adenoma, Adenoma. Die Arbeit nennt 30 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE Patients with growth hormone (GH)–secreting pituitary adenomas (PAs) experience various symptoms and comorbidities, which can ultimately lead to increased mortality. This study aimed to develop and validate a machine learning (ML) model for predicting long-term outcomes in patients with GH-secreting PAs following endonasal transsphenoidal surgery (ETS). METHODS The authors conducted a retrospective three-institution cohort study that included patients with GH-secreting PAs treated with ETS between 2013 and 2023. Clinical, radiological, and biochemical data were collected. The main outcome of interest was the intervention-free rate (IFR) after primary ETS. Supervised ML algorithms, including decision trees and random forests, were developed to predict the IFR. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC) and Shapley Additive Explanations (SHAP) values. RESULTS The median follow-up for 100 patients with GH-secreting PAs (53% female) was 64 months (range 1–130 months). Additional intervention for persistent or recurrent acromegaly was required in 32% of patients. Following primary ETS alone, the 3-year IFR was 70% and the 5-year IFR was 67%. Multiple ML models were developed and evaluated using AUROCs. The decision tree analysis achieved an accuracy of 81% and emphasized the importance of both gross-total resection (GTR) and patient age in determining the long-term IFR. To better understand the factors that contributed to model performance, SHAP analysis was applied to the best-performing model. The SHAP dependence plots showed that key factors associated with a longer IFR included tumor size < 9 mm, GTR, patient age > 65 years, and Knosp grade 0. CONCLUSIONS This ML model offers a more nuanced and potentially more accurate approach to identify patients more likely to develop recurrent or persistent acromegaly following primary ETS and require additional treatment. Following external validation, this ML model could improve personalized treatment planning and follow-up strategies and enhance patient care and resource allocation in clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AcromegalySupervised Machine LearningGrowth Hormone-Secreting Pituitary AdenomaAdenomaMachine LearningHumansFemaleMaleMiddle AgedRetrospective StudiesAdultAgedTreatment OutcomeCohort StudiesFollow-Up Studies

Stichwörter der Autor:innen

acromegalylong-term outcomesmachine learningoutcome predictionpituitary adenomas

Autor:innen und Institutionen

  • 1Department of Neurologic Surgery, Mayo Clinic, Rochester, Minnesota.
  • 2Department of Neurosurgery, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan.
  • 3Department of Medicine, Division of Endocrinology, Diabetes, and Nutrition, Mayo Clinic, Rochester, Minnesota; and.
  • 4Department of Otolaryngology-Head and Neck Surgery, Mayo Clinic, Rochester, Minnesota.

Zitieren

APA

Shinya, Y., Ghaith, A. K., Hong, S., Herndon, J. S., Palit, S. R., Erickson, D., Bancos, I., Saez-Alegre, M., Morshed, R. A., Pinheiro Neto, C., Meyer, F. B., Atkinson, J. L. D., & Van Gompel, J. J. (2025). A supervised machine learning approach for predicting the need for postsurgical intervention in acromegaly. Neurosurgical Focus. https://doi.org/10.3171/2025.4.focus2597

Vancouver

Shinya Y, Ghaith AK, Hong S, Herndon JS, Palit SR, Erickson D, et al. A supervised machine learning approach for predicting the need for postsurgical intervention in acromegaly. Neurosurgical Focus. 2025. doi:10.3171/2025.4.focus2597

BibTeX
@article{Shinya2025,
  author = {Shinya, Yuki and Ghaith, Abdul Karim and Hong, Sukwoo and Herndon, Justine S and Palit, Sandhya R and Erickson, Dana and Bancos, Irina and Saez-Alegre, Miguel and Morshed, Ramin A and Pinheiro Neto, Carlos and Meyer, Fredric B and Atkinson, John L D and Van Gompel, Jamie J},
  title = {A supervised machine learning approach for predicting the need for postsurgical intervention in acromegaly},
  journal = {Neurosurgical Focus},
  year = {2025},
  doi = {10.3171/2025.4.focus2597}
}
Kostenlos starten →