TY - JOUR
T1 - Prognostic models for progression-free survival in atypical meningioma
T2 - Comparison of machine learning-based approach and the COX model in an Asian multicenter study
AU - Kim, Dowook
AU - Kim, Yeseul
AU - Sung, Wonmo
AU - Kim, In Ah
AU - Cho, Jaeho
AU - Lee, Joo Ho
AU - Grassberger, Clemens
AU - Byun, Hwa Kyung
AU - Chang, Won Ick
AU - Ren, Leihao
AU - Gong, Ye
AU - Wee, Chan Woo
AU - Hua, Lingyang
AU - Yoon, Hong In
N1 - Publisher Copyright:
© 2024 Elsevier B.V.
PY - 2025/2
Y1 - 2025/2
N2 - Background and purpose: Atypical meningiomas are prevalent intracranial tumors with varied prognoses and recurrence rates. The role of adjuvant radiotherapy (ART) in atypical meningiomas remains debated. This study aimed to develop and validate a prognostic model incorporating machine learning techniques and clinical factors to predict progression-free survival (PFS) in patients with atypical meningiomas and assess the impact of ART. Materials and methods: A retrospective review of 669 patients from five institutions in Korea and China was conducted. Cox proportional hazards, gradient boosting machine, and random survival forest models were employed for comparative analysis, utilizing both internal and external validation sets. Model performance was assessed using Harrell's concordance index and permutation feature importance. Results: Of 581 eligible patients, age, post-operative platelet count, performance status, Simpson grade, and ART were identified as significant prognostic factors across all models. In the ART subgroup, age and tumor size were the top prognostic indicators. The Cox model outperformed other methods, achieving a training C-index of 0.73 (95 % CI: 0.72–0.73) and an external validation C-index of 0.74 (95 % CI: 0.73–0.74). The model effectively stratified patients into risk categories, revealing a differential impact of ART: low-risk patients in the active surveillance group showed a 5.6 % improvement in 5-year PFS with predicted ART addition, compared to a 15.9 % improvement in the high-risk group. Conclusion: This multicenter study offers a validated prognostic model for atypical meningiomas, highlighting the need for tailored treatment plans. The model's ability to stratify patients into risk categories for PFS provides a valuable tool for clinical decision-making, potentially optimizing patient outcomes.
AB - Background and purpose: Atypical meningiomas are prevalent intracranial tumors with varied prognoses and recurrence rates. The role of adjuvant radiotherapy (ART) in atypical meningiomas remains debated. This study aimed to develop and validate a prognostic model incorporating machine learning techniques and clinical factors to predict progression-free survival (PFS) in patients with atypical meningiomas and assess the impact of ART. Materials and methods: A retrospective review of 669 patients from five institutions in Korea and China was conducted. Cox proportional hazards, gradient boosting machine, and random survival forest models were employed for comparative analysis, utilizing both internal and external validation sets. Model performance was assessed using Harrell's concordance index and permutation feature importance. Results: Of 581 eligible patients, age, post-operative platelet count, performance status, Simpson grade, and ART were identified as significant prognostic factors across all models. In the ART subgroup, age and tumor size were the top prognostic indicators. The Cox model outperformed other methods, achieving a training C-index of 0.73 (95 % CI: 0.72–0.73) and an external validation C-index of 0.74 (95 % CI: 0.73–0.74). The model effectively stratified patients into risk categories, revealing a differential impact of ART: low-risk patients in the active surveillance group showed a 5.6 % improvement in 5-year PFS with predicted ART addition, compared to a 15.9 % improvement in the high-risk group. Conclusion: This multicenter study offers a validated prognostic model for atypical meningiomas, highlighting the need for tailored treatment plans. The model's ability to stratify patients into risk categories for PFS provides a valuable tool for clinical decision-making, potentially optimizing patient outcomes.
KW - Adjuvant radiotherapy
KW - Atypical meningioma
KW - Machine learning
KW - Prognostic model
KW - Progression-free survival
UR - http://www.scopus.com/inward/record.url?scp=85212646802&partnerID=8YFLogxK
U2 - 10.1016/j.radonc.2024.110695
DO - 10.1016/j.radonc.2024.110695
M3 - Article
AN - SCOPUS:85212646802
SN - 0167-8140
VL - 203
JO - Radiotherapy and Oncology
JF - Radiotherapy and Oncology
M1 - 110695
ER -