An online calculator using machine learning for predicting survival in pediatric patients with medulloblastoma

The intersections between neuroscience and medulloblastoma

Medulloblastoma (MB) represents the most common malignant central nervous system tumor in childhood. The nervous system plays a critical role in the progression of MB, with interactions between the nervous system and cancer significantly influencing oncogenesis, tumor growth, invasion, stemness, and metabolism. These interactions also regulate angiogenesis, metastatic dissemination, the tumor immune microenvironment, and drug resistance. Investigating the nervous system-MB axis holds promise for identifying diagnostic markers, prognostic biomarkers, and therapeutic targets. It also provides insights into the molecular mechanisms underlying MB and informs the development of novel therapeutic strategies. This review summarizes the latest advancements in understanding the interplay between the nervous system and MB, including the role of glial cells in MB and the potential of drug repurposing targeting nervous system components for MB treatment. These findings underscore promising diagnostic and therapeutic opportunities for MB management. Additionally, we outline future research directions in neurosciences that may pave the way for innovative therapeutic approaches and deepen our understanding of this complex disease.

Machine learning-based models for prediction of survival in medulloblastoma: a systematic review and meta-analysis

BACKGROUND

Medulloblastoma (MB) is the pediatric population's most frequent malignant intracranial lesions. Prognostication plays a crucial role in optimizing treatment strategy in the MB setting. Several studies have developed ML-based models to predict survival outcomes in individuals with MB. In this systematic review and meta-analysis study, we aimed to evaluate the role of ML-based models in predicting survival in MB patients.

METHOD

Literature records were retrieved on May 14th, 2024, using the relevant key terms without filters in PubMed, Embase, Scopus, and Web of Science. Records were screened according to the eligibility criteria, and the data from the included studies were extracted. The quality assessment was performed using the QUADAS-2 tool. The meta-analysis and sensitivity analysis were conducted using R software.

RESULTS

Six studies were included, with 2771 patients ranging from 46 to 1759 individuals. A total of 23 ML and DL models were developed, 20 of which were ML and three DL. Random forest (RF) was the most frequent classifier, as it was utilized in nine models, followed by support vector machine (SVM). Eight models were included in the meta-analysis. Our meta-analysis revealed a pooled AUC of 0.77 (95% CI: 0.75-0.80). In addition, the radionics-based and genomics-based models had a pooled AUC of 0.77 (95% CI: 0.76-079) and 0.76 (0.63-0.88), respectively (P = 0.77).

CONCLUSION

Our results suggested that ML-based models, especially ML algorithms, could play a vital and efficient role in the prediction of survival of patients based on radiomics and genomics.

Development and internal validation of machine learning models for personalized survival predictions in spinal cord glioma patients

BACKGROUND CONTEXT

Numerous factors have been associated with the survival outcomes in patients with spinal cord gliomas (SCG). Recognizing these specific determinants is crucial, yet it is also vital to establish a reliable and precise prognostic model for estimating individual survival outcomes.

OBJECTIVE

The objectives of this study are twofold: first, to create an array of interpretable machine learning (ML) models developed for predicting survival outcomes among SCG patients; and second, to integrate these models into an easily navigable online calculator to showcase their prospective clinical applicability.

STUDY DESIGN

This was a retrospective, population-based cohort study aiming to predict the outcomes of interest, which were binary categorical variables, in SCG patients with ML models.

PATIENT SAMPLE

The National Cancer Database (NCDB) was utilized to identify adults aged 18 years or older who were diagnosed with histologically confirmed SCGs between 2010 and 2019.

OUTCOME MEASURES

The outcomes of interest were survival outcomes at three specific time points postdiagnosis: 1, 3, and 5 years. These outcomes were formed by combining the "Vital Status" and "Last Contact or Death (Months from Diagnosis)" variables. Model performance was evaluated visually and numerically. The visual evaluation utilized receiver operating characteristic (ROC) curves, precision-recall curves (PRCs), and calibration curves. The numerical evaluation involved metrics such as sensitivity, specificity, accuracy, area under the PRC (AUPRC), area under the ROC curve (AUROC), and Brier Score.

METHODS

We employed five ML algorithms-TabPFN, CatBoost, XGBoost, LightGBM, and Random Forest-along with the Optuna library for hyperparameter optimization. The models that yielded the highest AUROC values were chosen for integration into the online calculator. To enhance the explicability of our models, we utilized SHapley Additive exPlanations (SHAP) for assessing the relative significance of predictor variables and incorporated partial dependence plots (PDPs) to delineate the influence of singular variables on the predictions made by the top performing models.

RESULTS

For the 1-year survival analysis, 4,913 patients [5.6% with 1-year mortality]; for the 3-year survival analysis, 4,027 patients (11.5% with 3-year mortality]; and for the 5-year survival analysis, 2,854 patients (20.4% with 5-year mortality) were included. The top models achieved AUROCs of 0.938 for 1-year mortality (TabPFN), 0.907 for 3-year mortality (LightGBM), and 0.902 for 5-year mortality (Random Forest). Global SHAP analyses across survival outcomes at different time points identified histology, tumor grade, age, surgery, radiotherapy, and tumor size as the most significant predictor variables for the top-performing models.

CONCLUSIONS

This study demonstrates ML techniques can develop highly accurate prognostic models for SCG patients with excellent discriminatory ability. The interactive online calculator provides a tool for assessment by physicians (https://huggingface.co/spaces/MSHS-Neurosurgery-Research/NCDB-SCG). Local interpretability informs prediction influences for a given individual. External validation across diverse datasets could further substantiate potential utility and generalizability. This robust, interpretable methodology aligns with the goals of precision medicine, establishing a foundation for continued research leveraging ML's predictive power to enhance patient counseling.