Personalized prediction of local control after stereotactic radiosurgery for craniopharyngioma: a…

AI / informaticsJournal of neuro-oncology· Jul 2026

Personalized prediction of local control after stereotactic radiosurgery for craniopharyngioma: a multicenter machine learning survival model.

Jheremy S Reyes, Constantinos G Hadjipanayis, Kenneth Bernstein … Ajay Niranjan

Stereotactic & FunctionalAI / informaticsPrognosisQ2IF 3.2

Machine learning model predicted local control after radiosurgery for craniopharyngioma with high accuracy

Personalized prediction of local control after stereotactic radiosurgery for craniopharyngioma: a multicenter machine learning survival model.

Jheremy S Reyes … Ajay Niranjan

Journal of neuro-oncology · Jul 2026 · Q2 in Neurology

Background

Stereotactic radiosurgery (stereotactic radiosurgery) is used in selected patients with craniopharyngioma, yet counseling and follow-up planning often rely on population-level local control rates rather than individualized expectations over time.

Purpose

To develop and internally validate a multicenter survival model to predict imaging-defined time to progression after stereotactic radiosurgery for craniopharyngioma.

Methods

We analyzed a multicenter IRRF registry of stereotactic radiosurgery-treated craniopharyngioma patients.

n = 277 patients

Results

model ranked patients' progression risk correctly, 1.0 would be perfect

AUC 0.93 (95% CI 0.89 to 0.97)

null 0

0.89

0.97

CI excludes the null - significant

More results

Time-dependent AUC was 0.895 (95% CI 0.828-0.959) at 12 months, 0.897 (95% CI 0.833-0.952) at 24 months, and 0.934 (95% CI 0.889-0.969) at 60 months.

Integrated Brier score (0-60 months) was 0.050 with favorable calibration.

“

Conclusion · 1 of 2

A multicenter machine learning survival model can provide individualized, well-calibrated estimates of local control over time after stereotactic radiosurgery for craniopharyngioma to support non-prescriptive decision support.

Conclusion · 2 of 2

CLINICAL TRIAL NUMBER: Not applicable.

Personalized prediction of local control after stereotactic radiosurgery for craniopharyngioma: a multicenter machine learning survival model.

Personalized prediction of local control after stereotactic radiosurgery for craniopharyngioma: a multicenter machine learning survival model.

Related papers