Multicenter machine learning model using clinical and radiomic features for prediction of postoperative residual status in meningioma

Basit Öğe Kaydı
dc.authorid0000-0002-4192-9268
dc.authorid0000-0002-4839-3347
dc.authorid0009-0002-0244-6623
dc.authorid0000-0002-7133-031X
dc.authorid0009-0000-0794-0052
dc.authorid0000-0002-5263-2793
dc.authorid0009-0008-6593-1785
dc.contributor.authorŞanlıer, Nafiye
dc.contributor.authorYüce, Murat
dc.contributor.authorSulaimanov, Umid
dc.contributor.authorIsmayilova, Gular
dc.contributor.authorHüryol, Çağın
dc.contributor.authorBozkurt, Hüseyin
dc.contributor.authorÖztürk, Öykü
dc.contributor.authorÖztürk, Fikret
dc.contributor.authorDemir, Hüseyin
dc.contributor.authorBaşkaya, Mustafa K.
dc.date.accessioned2026-09-12T12:38:05Z
dc.date.available2026-09-12T12:38:05Z
dc.date.issued2026
dc.departmentFakülteler, Tıp Fakültesi, Cerrahi Tıp Bilimleri Bölümü, Beyin ve Sinir Cerrahisi Ana Bilim Dalı
dc.description.abstractOBJECTIVE Gross-total resection is the primary surgical objective in meningioma management; however, predicting re sectability preoperatively remains challenging, particularly for meningiomas located in the skull base that exhibit complex anatomical relationships. There is a lack of validated reproducible models that integrate known anatomical factors for surgery; similarly, the value of radiomics as a stand-alone predictor is still unclear. The aim of this study was to develop a machine learning model that combines clinical and radiomic features to estimate early postoperative residual menin gioma. METHODS This retrospective multicenter study included 369 patients who underwent meningioma resection from 2020 to 2024 and had available preoperative contrast-enhanced T1-weighted MRI. Patient data from 3 centers (n = 307) were used to develop the model using leave-one-center-out cross-validation, and an independent cohort (n = 62) was used for external validation. Radiomic features were derived from manually segmented meningiomas, filtered for reproducibility, and integrated with 6 predefined clinical variables. The clinical-only, radiomics-only, and combined models were trained using 4 machine learning classifiers. Model performance was assessed through cross-validation, independent external validation, and receiver operating characteristic analysis. Formal incremental benefit analyses were performed on the common overlap external subset, with predictions available for all compared models. RESULTS Residual meningioma occurred in 23.5% of patients in the development cohort and 14.5% in the external cohort. Lesion location and venous sinus involvement were significantly associated with residual status. Following the feature selection, 2 stable radiomic texture features were retained. In external validation, the combined radiomics-clinical k-nearest neighbors model achieved the highest area under the curve (0.821), with sensitivity of 0.889, specificity of 0.706, and accuracy of 0.733. Clinical variables provided most of the predictive value, whereas radiomic features provided only limited incremental value when added to the clinical model. Decision curve analysis revealed net benefit for the combined model within a narrow range of low thresholds. CONCLUSIONS In this multicenter study, which included external validation, clinical variables provided most of the predictive value for postoperative residual meningioma. Radiomic features alone showed limited discrimination and only modest added value beyond clinical predictors. These combined models could serve as decision-support tools for preoperative risk assessment in meningioma surgery but are not yet suitable for routine stand-alone clinical use.
dc.identifier.citationŞanlıer, N., Yüce, M., Sulaimanov, U., Ismayilova, G., Hüryol, Ç., Bozkurt, H., Öztürk, Ö., Öztürk, F., Demir, H., & Başkaya, M. K. (2026). Multicenter machine learning model using clinical and radiomic features for prediction of postoperative residual status in meningioma. Neurosurgical Focus, 61(3), pp. 1-12. https://doi.org/10.3171/2026.6.FOCUS26266
dc.identifier.doi10.3171/2026.6.FOCUS26266
dc.identifier.endpage12
dc.identifier.issn1092-0684
dc.identifier.issue3
dc.identifier.pmidPMID: 42679396
dc.identifier.scopus2-s2.0-105048910799
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttps://doi.org/10.3171/2026.6.FOCUS26266
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1638
dc.identifier.volume61
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.indekslendigikaynak.otherSCI-E - Science Citation Index Expanded
dc.institutionauthorDemir, Hüseyin
dc.institutionauthorid0000-0002-5263-2793
dc.language.isoen
dc.publisherAmerican Association of Neurological Surgeons
dc.relation.ispartofNeurosurgical Focus
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectMachine Learning
dc.subjectMeningioma
dc.subjectMRI
dc.subjectPrediction
dc.subjectRadiomics
dc.subjectSurgical Resectability
dc.titleMulticenter machine learning model using clinical and radiomic features for prediction of postoperative residual status in meningioma
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Tam Metin / Full Text.pdf
Boyut:
14.17 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Cerrahi Tıp Bilimleri Bölümü Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu