OBJECTIVE The incidence of leptomeningeal disease (LMD) has increased as treatments for brain metastases (BMs) have improved and patients with metastatic disease are living longer. Sample sizes of... Show moreOBJECTIVE The incidence of leptomeningeal disease (LMD) has increased as treatments for brain metastases (BMs) have improved and patients with metastatic disease are living longer. Sample sizes of individual studies investigating LMD after surgery for BMs and its risk factors have been limited, ranging from 200 to 400 patients at risk for LMD, which only allows the use of conventional biostatistics. Here, the authors used machine learning techniques to enhance LMD prediction in a cohort of surgically treated BMs.METHODS A conditional survival forest, a Cox proportional hazards model, an extreme gradient boosting (XGBoost) classifier, an extra trees classifier, and logistic regression were trained. A synthetic minority oversampling technique (SMOTE) was used to train the models and handle the inherent class imbalance. Patients were divided into an 80:20 training and test set. Fivefold cross-validation was used on the training set for hyperparameter optimization. Patients eligible for study inclusion were adults who had consecutively undergone neurosurgical BM treatment, had been admit-ted to Brigham and Women's Hospital from January 2007 through December 2019, and had a minimum of 1 month of follow-up after neurosurgical treatment.RESULTS A total of 1054 surgically treated BM patients were included in this analysis. LMD occurred in 168 patients (15.9%) at a median of 7.05 months after BM diagnosis. The discrimination of LMD occurrence was optimal using an XGboost algorithm (area under the curve = 0.83), and the time to LMD was prognosticated evenly by the random forest algorithm and the Cox proportional hazards model (C-index = 0.76). The most important feature for both LMD clas-sification and regression was the BM proximity to the CSF space, followed by a cerebellar BM location. Lymph node metastasis of the primary tumor at BM diagnosis and a cerebellar BM location were the strongest risk factors for both LMD occurrence and time to LMD.CONCLUSIONS The outcomes of LMD patients in the BM population are predictable using SMOTE and machine learn-ing. Lymph node metastasis of the primary tumor at BM diagnosis and a cerebellar BM location were the strongest LMD risk factors. Show less
Background. Immune checkpoint inhibitors (ICI) have been a breakthrough for selected cancer patients, including those with brain metastases (BMs). Likewise, steroids have been an integral component... Show moreBackground. Immune checkpoint inhibitors (ICI) have been a breakthrough for selected cancer patients, including those with brain metastases (BMs). Likewise, steroids have been an integral component of symptomatic management of BM patients. However, clinical evidence on the interaction between ICI and steroids in BM patients is conflicting and has not adequately been summarized thus far. Hence, the aim of this study was to perform a systematic literature review and meta-analysis on the association between steroid use and overall survival (OS) in BM patients receiving ICI.Methods. A systematic literature search was performed. Pooled effect estimates were calculated using randomeffects models across included studies.Results. After screening 1145 abstracts, 15 observational studies were included. Fourteen studies reported sufficient data for meta-analysis, comprising 1102 BM patients of which 32.1% received steroids. In the steroid group, median OS ranged from 2.9 to 10.2 months. In the nonsteroid group, median OS ranged from 4.9 to 25.1 months. Pooled results demonstrated significantly worse OS (HR = 1.84, 95% CI 1.22-2.77) and systemic progression-free survival (PFS; HR = 2.00, 95% CI 1.37-2.91) in the steroid group. Stratified analysis showed a consistent effect across the melanoma subgroup; not in the lung cancer subgroup. No significant association was shown between steroid use and intracranial PFS (HR = 1.31, 95% Cl 0.42-4.07).Conclusions. Administration of steroids was associated with significantly worse OS and PFS in BM patients receiving ICI. Further research on dose, timing, and duration of steroids is needed to elucidate the cause of this association and optimize outcomes in BM patients receiving ICI. Show less
Background and purpose: Brain metastases originating from gynaecological tumours are a rare phenomenon, but have an increasing incidence due to better targeted therapies. This study aimed to... Show moreBackground and purpose: Brain metastases originating from gynaecological tumours are a rare phenomenon, but have an increasing incidence due to better targeted therapies. This study aimed to identify factors that predict survival in these patients, which can be used in creating a robust prognostic tool for shared decision making.Materials and methods: We identified a consecutive cohort of 73 patients treated for gynaecological brain metastases in two tertiary institutions. Baseline demographics, pathology and serum CA-125 were included in a multivariable Cox proportional hazards model.Results: Median overall survival in our cohort was 14.4 months, with a one-year survival of 56.4% and a two-year survival of 39.1%. Thirty-eight patients (52.1%) had ovarian carcinoma as the primary malignancy. The following factors were significantly associated with survival: age (HR 1.05 per year), CA-125 (HR 1.02 par 50 U/ml), and uterine and vulvar primary tumours (when compared to ovarian carcinoma, with HRs 3.07 and 8.70). A post-hoc analysis with primary tumour site reclassified into ovary versus non-ovary showed a HR of 0.50 for ovarian primary tumour type.Conclusion: We have found that age, pathology and CA-125 are prognostic factors for survival in patients with brain metastases from gynaecological tumours. Our findings may provide a foundation for future development of prediction models, for the benefit of both patients and physicians. (c) 2020 The Authors. Published by Elsevier B.V. on behalf of European Society for Radiotherapy and Oncology. Show less
