Preoperative and postoperative prediction of long-term meningioma outcomes

Abstract

BackgroundMeningiomas are stratified according to tumor grade and extent of resection, often in isolation of other clinical variables. Here, we use machine learning (ML) to integrate demographic, clinical, radiographic and pathologic data to develop predictive models for meningioma outcomes.Methods and findingsWe developed a comprehensive database containing information from 235 patients who underwent surgery for 257 meningiomas at a single institution from 1990 to 2015. The median follow-up was 4.3 years, and resection specimens were re-evaluated according to current diagnostic criteria, revealing 128 WHO grade I, 104 grade II and 25 grade III meningiomas. A series of ML algorithms were trained and tuned by nested resampling to create models based on preoperative features, conventional postoperative features, or both. We compared different algorithms’ accuracy as well as the unique insights they offered into the data. Machine learning models restricted to preoperative information, such as patient demographics and radiographic features, had similar accuracy for predicting local failure (AUC = 0.74) or overall survival (AUC = 0.68) as models based on meningioma grade and extent of resection (AUC = 0.73 and AUC = 0.72, respectively). Integrated models incorporating all available demographic, clinical, radiographic and pathologic data provided the most accurate estimates (AUC = 0.78 and AUC = 0.74, respectively). From these models, we developed decision trees and nomograms to estimate the risks of local failure or overall survival for meningioma patients.ConclusionsClinical information has been historically underutilized in the prediction of meningioma outcomes. Predictive models trained on preoperative clinical data perform comparably to conventional models trained on meningioma grade and extent of resection. Combination of all available information can help stratify meningioma patients more accurately.

Machine learning for radiation outcome modeling and prediction

“…ML algorithms intend to develop data‐driven models by fitting parameters using the collected clinical and dosimetric data . For structured dataset, ML approaches have already been employed for several treatment sites such as lung, prostate, head & neck cancer, or meningioma . In all cases, many different ML algorithms, such as linear regression, artificial neural network (ANN), support vector machine (SVM), BNs, DT, RFs, or gradient boosting machine (GBM), have been explored.…”

“…Decision trees are constructed using recursive partitioning analysis to optimize successive dichotomisation of input variables. The resulted tree‐like structure had been used to augment prediction of the classic Lyman NTCP, pneumonitis, 10,34 chest wall pain, salvage high‐dose‐rate brachytherapy (sHDRB) and meningioma . An advantage of DTs is that they are highly interpretable.…”

“…Since it uses weighted versions of all cases to derive splits at each point in the tree, it can be advantageous for relatively small datasets. MediBoost has been used to predict both pneumonitis and biochemical failure after sHDRB surpassing RF performance in some cases but not all …”

“…It uses gradient boosting, a way to improve any ML model by iteratively training new models that specialize on the weak points of the previous ones. GBMs have been used in radiotherapy to predict radiation‐induced pneumonitis and meningioma local failure . A version of GBM, XGBoost, consistently wins most Kaggle competitions that involve structured data today .…”

“…Recently, there is a tremendous increase in the use of ML in different areas of radiation oncology, such as treatment planning optimization, segmentation, radiation physics quality assurance, contouring or image‐guided radiotherapy . In this paper, we focus on ML for radiation outcome modeling …”