{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:26:15Z","timestamp":1785432375489,"version":"3.56.0"},"reference-count":42,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82573744"],"award-info":[{"award-number":["82573744"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82473135"],"award-info":[{"award-number":["82473135"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["82573744"],"award-info":[{"award-number":["82573744"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["82473135"],"award-info":[{"award-number":["82473135"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Heilongjiang Provincial Charity Federation","award":["2021HX041"],"award-info":[{"award-number":["2021HX041"]}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"crossref","award":["PL2025H091"],"award-info":[{"award-number":["PL2025H091"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background: Gliomas are the most common primary malignant tumors of the central nervous system. Accurate preoperative grading is essential for individualized surgical planning and treatment selection; however, reliable non-invasive prediction tools integrating multimodal preoperative data remain limited. This study aimed to develop and internally validate an interpretable machine-learning model for non-invasive glioma grading. Methods: Clinical and imaging data from 400 patients with pathologically confirmed gliomas were retrospectively collected. Twenty-four preoperative variables were analyzed. The dataset was randomly divided into training and validation cohorts (7:3). Feature selection was performed using a combination of the Boruta algorithm and logistic regression analyses, followed by correlation filtering. Seventeen machine-learning algorithms were benchmarked using five-fold cross-validation, and the optimal model was evaluated in the independent validation cohort using ROC analysis, calibration assessment, precision\u2013recall curves, and decision curve analysis. Model interpretability was examined using SHAP. Results: Eight key predictors were identified, including age, focal neurological deficits, midline shift, tumor laterality, tumor lobar location, enhancing tumor volume, and MRS-derived Cho\/NAA and Cho\/Cr ratios. The Random Forest model achieved an area under the ROC curve of 0.946 (95% CI: 0.902\u20130.989) in the validation cohort. Calibration analysis demonstrated reasonable agreement between predicted and observed outcomes, and the precision\u2013recall curve yielded an average precision of 0.98. Decision curve analysis indicated net clinical benefit across relevant probability thresholds. Conclusions: A multimodal machine-learning model integrating clinical, structural imaging, and MRS-derived metabolic features was developed and internally validated for non-invasive preoperative glioma grading. The model showed good discrimination and calibration and provided individualized probability estimates, suggesting potential value for preoperative risk stratification. However, clinical deployment remains premature, and further external validation is required.<\/jats:p>","DOI":"10.3390\/cancers18081204","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T07:55:12Z","timestamp":1775807712000},"page":"1204","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Interpretable Multimodal Machine-Learning Model for Non-Invasive Preoperative Glioma Grading"],"prefix":"10.3390","volume":"18","author":[{"given":"Xianfeng","family":"Rao","sequence":"first","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Pediatric Surgery, The Sixth Affiliated Hospital of Harbin Medical University, Harbin 150023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanhao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liudong","family":"Gong","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingchun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanxi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianjun","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Spleen and Stomach Diseases, Wangjing Hospital, China Academy of Chinese Medical Sciences, Beijing 100102, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Laboratory Diagnostics, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Teng","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The First Affiliated Hospital of Harbin Medical University, Harbin 150001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"ref_1","first-page":"10","article-title":"Cancer statistics, 2025","volume":"75","author":"Siegel","year":"2025","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1038\/s41572-024-00516-y","article-title":"Glioma. Nature reviews","volume":"10","author":"Weller","year":"2024","journal-title":"Dis. Primers"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/S0140-6736(18)30990-5","article-title":"Primary brain tumours in adults","volume":"392","author":"Lapointe","year":"2018","journal-title":"Lancet"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1002\/cncr.33918","article-title":"Diagnostic, therapeutic, and prognostic implications of the 2021 World Health Organization classification of tumors of the central nervous system","volume":"128","author":"Gritsch","year":"2022","journal-title":"Cancer"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"15017","DOI":"10.1038\/nrdp.2015.17","article-title":"Glioma. Nature reviews","volume":"1","author":"Weller","year":"2015","journal-title":"Dis. Primers"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.semcancer.2017.11.010","article-title":"Glioma epigenetics: From subclassification to novel treatment options","volume":"51","author":"Gusyatiner","year":"2018","journal-title":"Semin. Cancer Biol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e13060","DOI":"10.1111\/bpa.13060","article-title":"The 2021 WHO Classification of Tumors of the Central Nervous System: An update on pediatric low-grade gliomas and glioneuronal tumors","volume":"32","author":"Bale","year":"2022","journal-title":"Brain Pathol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1805","DOI":"10.1093\/neuonc\/noae107","article-title":"The biological significance of tumor grade, age, enhancement, and extent of resection in IDH-mutant gliomas: How should they inform treatment decisions in the era of IDH inhibitors?","volume":"26","author":"French","year":"2024","journal-title":"Neuro-Oncology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1158\/1078-0432.CCR-23-1180","article-title":"Tumor Volume Growth Rates and Doubling Times during Active Surveillance of IDH-mutant Low-Grade Glioma","volume":"30","author":"Bhatia","year":"2024","journal-title":"Clin. Cancer Res. Off. J. Am. Assoc. Cancer Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1186\/s13046-016-0404-1","article-title":"Brain stereotactic biopsy flow cytometry for central nervous system lymphoma characterization: Advantages and pitfalls","volume":"35","author":"Cordone","year":"2016","journal-title":"J. Exp. Clin. Cancer Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1007\/s00330-024-11140-5","article-title":"Preoperative prediction of diffuse glioma type and grade in adults: A gadolinium-free MRI-based decision tree","volume":"35","author":"Azizova","year":"2025","journal-title":"Eur. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1002\/jmri.26265","article-title":"Radiomics Nomogram Building from Multiparametric MRI to Predict Grade in Patients with Glioma: A Cohort Study","volume":"49","author":"Wang","year":"2019","journal-title":"J. Magn. Reson. Imaging JMRI"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1007\/s00234-018-2091-4","article-title":"Radiomics features to distinguish glioblastoma from primary central nervous system lymphoma on multi-parametric MRI","volume":"60","author":"Kim","year":"2018","journal-title":"Neuroradiology"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e1383","DOI":"10.1016\/j.crad.2024.08.005","article-title":"Magnetic resonance imaging (MRI)-based intratumoral and peritumoral radiomics for prognosis prediction in glioma patients","volume":"79","author":"Gao","year":"2024","journal-title":"Clin. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, L., Zhang, C., Wang, Z., Wang, Y., Guo, Y., Qi, C., You, G., Zhang, Z., Fan, X., and Jiang, T. (2023). Development of an integrated predictive model for postoperative glioma-related epilepsy using gene-signature and clinical data. BMC Cancer, 23.","DOI":"10.1186\/s12885-022-10385-x"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"13371","DOI":"10.1038\/s41598-025-87632-1","article-title":"Magnetic resonance spectroscopy guided radiotherapy boost for patients with glioblastoma","volume":"15","author":"Xu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1093\/neuonc\/noab106","article-title":"The 2021 WHO Classification of Tumors of the Central Nervous System: A summary","volume":"23","author":"Louis","year":"2021","journal-title":"Neuro-Oncology"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2986","DOI":"10.1007\/s00330-023-10343-6","article-title":"Amide proton transfer-weighted imaging and derived radiomics in the classification of adult-type diffuse gliomas","volume":"34","author":"Wu","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2805","DOI":"10.1097\/JS9.0000000000003668","article-title":"Current concerns and future directions of large language model ChatGPT in medicine: A machine-learning-driven global-scale bibliometric analysis","volume":"2","author":"Guo","year":"2026","journal-title":"Int. J. Surg."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"fcae372","DOI":"10.1093\/braincomms\/fcae372","article-title":"Enhanced MRI-based brain tumour classification with a novel Pix2pix generative adversarial network augmentation framework","volume":"6","author":"Onakpojeruo","year":"2024","journal-title":"Brain Commun."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Onakpojeruo, E.P., Mustapha, M.T., Ozsahin, D.U., and Ozsahin, I. (2024). A Comparative Analysis of the Novel Conditional Deep Convolutional Neural Network Model, Using Conditional Deep Convolutional Generative Adversarial Network-Generated Synthetic and Augmented Brain Tumor Datasets for Image Classification. Brain Sci., 14.","DOI":"10.3390\/brainsci14060559"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"ref_24","first-page":"1033","article-title":"Clinical prediction models for young febrile infants at the emergency department: An international validation study","volume":"103","author":"Gomez","year":"2018","journal-title":"Arch. Dis. Child."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.21037\/tp-23-269","article-title":"Risk factors and predictive models for early recurrent intussusception in children: A retrospective cohort study","volume":"12","author":"Yang","year":"2023","journal-title":"Transl. Pediatr."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1056\/NEJMoa043330","article-title":"Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma","volume":"352","author":"Stupp","year":"2005","journal-title":"N. Engl. J. Med."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Obrador, E., Moreno-Murciano, P., Oriol-Caballo, M., L\u00f3pez-Blanch, R., Pineda, B., Guti\u00e9rrez-Arroyo, J.L., Loras, A., Gonzalez-Bonet, L.G., Martinez-Cadenas, C., and Estrela, J.M. (2024). Glioblastoma Therapy: Past, Present and Future. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25052529"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1002\/jmri.29567","article-title":"Assessment of Tumor Cell Invasion and Radiotherapy Response in Experimental Glioma by Magnetic Resonance Elastography","volume":"61","author":"Heuer","year":"2025","journal-title":"J. Magn. Reson. Imaging JMRI"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5171","DOI":"10.21037\/qims-22-145","article-title":"Incorporating multiple magnetic resonance diffusion models to differentiate low- and high-grade adult gliomas: A machine learning approach","volume":"12","author":"Xu","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Du, P., Liu, X., Wu, X., Chen, J., Cao, A., and Geng, D. (2023). Predicting Histopathological Grading of Adult Gliomas Based on Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model. Brain Sci., 13.","DOI":"10.3390\/brainsci13060912"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1002\/mp.15648","article-title":"Glioma grading prediction using multiparametric magnetic resonance imaging-based radiomics combined with proton magnetic resonance spectroscopy and diffusion tensor imaging","volume":"49","author":"Lin","year":"2022","journal-title":"Med. Phys."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1080\/01616412.2018.1497271","article-title":"Preoperative neutrophil-lymphocyte ratio correlated with glioma grading and glioblastoma survival","volume":"40","author":"Weng","year":"2018","journal-title":"Neurol. Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.3390\/diagnostics14222569","article-title":"Multimodal MRI and (1)H-MRS for Preoperative Stratification of High-Risk Molecular Subtype in Adult-Type Diffuse Gliomas","volume":"14","author":"Han","year":"2024","journal-title":"Diagnostics"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.ijrobp.2014.05.014","article-title":"3-Dimensional magnetic resonance spectroscopic imaging at 3 Tesla for early response assessment of glioblastoma patients during external beam radiation therapy","volume":"90","author":"Muruganandham","year":"2014","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"29258","DOI":"10.1038\/s41598-024-80610-z","article-title":"1H-MRS parameters in non-enhancing peritumoral regions can predict the recurrence of glioblastoma","volume":"14","author":"Lu","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"102327","DOI":"10.1016\/j.suronc.2025.102327","article-title":"Risk factors for postoperative malignant progression of lower-grade gliomas: A systematic review and meta-analysis","volume":"64","author":"Ge","year":"2025","journal-title":"Surg. Oncol."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ohmura, K., Tomita, H., and Hara, A. (2023). Peritumoral Edema in Gliomas: A Review of Mechanisms and Management. Biomedicines, 11.","DOI":"10.3390\/biomedicines11102731"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"190","DOI":"10.3171\/jns.2001.95.2.0190","article-title":"A multivariate analysis of 416 patients with glioblastoma multiforme: Prognosis, extent of resection, and survival","volume":"95","author":"Lacroix","year":"2001","journal-title":"J. Neurosurg."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"467","DOI":"10.3171\/jns.2003.99.3.0467","article-title":"Survival following surgery and prognostic factors for recently diagnosed malignant glioma: Data from the Glioma Outcomes Project","volume":"99","author":"Laws","year":"2003","journal-title":"J. Neurosurg."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Houskamp, E.J., Skorich, E.L., Mackie, M.A., and Tate, M.C. (2025). Impact of High-Grade Glioma Lesion Location on Preoperative Neuropsychological Deficits. Cancers, 17.","DOI":"10.3390\/cancers17172775"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"39280","DOI":"10.1038\/s41598-025-23098-5","article-title":"Impact of gliomas in different brain hemispheres on anxiety and the prognosis of neurosurgical patients","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1007\/s11060-025-05144-4","article-title":"Anatomical distribution and prognostic heterogeneity in glioma: Unique clinical features of occipital glioblastoma","volume":"175","author":"Zhao","year":"2025","journal-title":"J. Neuro-Oncol."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/8\/1204\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T08:32:23Z","timestamp":1779784343000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/8\/1204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":42,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["cancers18081204"],"URL":"https:\/\/doi.org\/10.3390\/cancers18081204","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]}}}