An official website of the United States government
Abstract BackgroundPrognostic indices for patients with brain metastases (BM) are needed to individualize treatment and stratify clinical trials. Two frequently used tools to estimate survival in patients with BM are the recursive partitioning analysis (RPA) and the diagnosis-specific graded prognostic assessment (DS-GPA). Given recent advances in therapies and improved survival for patients with BM, this study aims to validate and analyze these 2 models in a modern cohort. MethodsPatients diagnosed with BM were identified via our institution’s Tumor Board meetings. Data were retrospectively collected from the date of diagnosis with BM. The concordance of the RPA and GPA was calculated using Harrell’s C index. A Cox proportional hazards model with backwards elimination was used to generate a parsimonious model predictive of survival. ResultsOur study consisted of 206 patients diagnosed with BM between 2010 and 2019. The RPA had a prediction performance characterized by Harrell’s C index of 0.588. The DS-GPA demonstrated a Harrell’s C index of 0.630. A Cox proportional hazards model assessing the effect of age, presence of lung, or liver metastases, and Eastern Cooperative Oncology Group (ECOG) performance status score of 3/4 on survival yielded a Harrell’s C index of 0.616. Revising the analysis with an uncategorized ECOG demonstrated a C index of 0.648. ConclusionsWe found that the performance of the RPA remains unchanged from previous validation studies a decade earlier. The DS-GPA outperformed the RPA in predicting overall survival in our modern cohort. Analyzing variables shared by the RPA and DS-GPA produced a model that performed analogously to the DS-GPA.
more »
« less
This content will become publicly available on January 1, 2027
Explainable AI for Predicting Mortality Risk in Metastatic Cancer: Retrospective Cohort Study Using the Memorial Sloan Kettering-Metastatic Dataset
BackgroundMetastatic cancer remains one of the leading causes of cancer-related mortality worldwide. Yet, the prediction of survivability in this population remains limited by heterogeneous clinical presentations and high-dimensional molecular features. Advances in machine learning (ML) provide an opportunity to integrate diverse patient- and tumor-level factors into explainable predictive ML models. Leveraging large real-world datasets and modern ML techniques can enable improved risk stratification and precision oncology. ObjectiveThis study aimed to develop and interpret ML models for predicting overall survival in patients with metastatic cancer using the Memorial Sloan Kettering-Metastatic (MSK-MET) dataset and to identify key prognostic biomarkers through explainable artificial intelligence techniques. MethodsWe performed a retrospective analysis of the MSK-MET cohort, comprising 25,775 patients across 27 tumor types. After data cleaning and balancing, 20,338 patients were included. Overall survival was defined as deceased versus living at last follow-up. Five classifiers (extreme gradient boosting [XGBoost], logistic regression, random forest, decision tree, and naive Bayes) were trained using an 80/20 stratified split and optimized via grid search with 5-fold cross-validation. Model performance was assessed using accuracy, area under the curve (AUC), precision, recall, and F1-score. Model explainability was achieved using Shapley additive explanations (SHAP). Survival analyses included Kaplan-Meier estimates, Cox proportional hazards models, and an XGBoost-Cox model for time-to-event prediction. The positive predictive value and negative predictive value were calculated at the Youden index–optimal threshold. ResultsXGBoost achieved the highest performance (accuracy=0.74; AUC=0.82), outperforming other classifiers. In survival analyses, the XGBoost-Cox model with a concordance index (C-index) of 0.70 exceeded the traditional Cox model (C-index=0.66). SHAP analysis and Cox models consistently identified metastatic site count, tumor mutational burden, fraction of genome altered, and the presence of distant liver and bone metastases as among the strongest prognostic factors, a pattern that held at both the pan-cancer level and recurrently across cancer-specific models. At the cancer-specific level, performance varied; prostate cancer achieved the highest predictive accuracy (AUC=0.88), while pancreatic cancer was notably more challenging (AUC=0.68). Kaplan-Meier analyses demonstrated marked survival separation between patients with and without metastases (80-month survival: approximately 0.80 vs 0.30). At the Youden-optimal threshold, positive predictive value and negative predictive value were approximately 70% and 80%, respectively, supporting clinical use for risk stratification. ConclusionsExplainable ML models, particularly XGBoost combined with SHAP, can strongly predict survivability in metastatic cancers while highlighting clinically meaningful features. These findings support the use of ML-based tools for patient counseling, treatment planning, and integration into precision oncology workflows. Future work should include external validation on independent cohorts, integration with electronic health records via Fast Healthcare Interoperability Resources–based dashboards, and prospective clinician-in-the-loop evaluation to assess real-world use.
more »
« less
- Award ID(s):
- 2201583
- PAR ID:
- 10659460
- Publisher / Repository:
- JMIR Publications
- Date Published:
- Journal Name:
- JMIR Cancer
- Volume:
- 12
- ISSN:
- 2369-1999
- Page Range / eLocation ID:
- e74196
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Neoantigens are derived from tumor-specific somatic mutations. Neoantigen-based synthesized peptides have been under clinical investigation to boost cancer immunotherapy efficacy. The promising results prompt us to further elucidate the effect of neoantigen expression on patient survival in breast cancer. We applied Kaplan–Meier survival and multivariable Cox regression models to evaluate the effect of neoantigen expression and its interaction with T-cell activation on overall survival in a cohort of 729 breast cancer patients. Pearson’s chi-squared tests were used to assess the relationships between neoantigen expression and clinical pathological variables. Spearman correlation analysis was conducted to identify correlations between neoantigen expression, mutation load, and DNA repair gene expression. ERCC1, XPA, and XPC were negatively associated with neoantigen expression, while BLM, BRCA2, MSH2, XRCC2, RAD51, CHEK1, and CHEK2 were positively associated with neoantigen expression. Based on the multivariable Cox proportional hazard model, patients with a high level of neoantigen expression and activated T-cell status showed improved overall survival. Similarly, in the T-cell exhaustion and progesterone receptor (PR) positive subgroups, patients with a high level of neoantigen expression showed prolonged survival. In contrast, there was no significant difference in the T-cell activation and PR negative subgroups. In conclusion, neoantigens may serve as immunogenic agents for immunotherapy in breast cancer.more » « less
-
Abstract ObjectiveLeverage electronic health record (EHR) audit logs to develop a machine learning (ML) model that predicts which notes a clinician wants to review when seeing oncology patients. Materials and MethodsWe trained logistic regression models using note metadata and a Term Frequency Inverse Document Frequency (TF-IDF) text representation. We evaluated performance with precision, recall, F1, AUC, and a clinical qualitative assessment. ResultsThe metadata only model achieved an AUC 0.930 and the metadata and TF-IDF model an AUC 0.937. Qualitative assessment revealed a need for better text representation and to further customize predictions for the user. DiscussionOur model effectively surfaces the top 10 notes a clinician wants to review when seeing an oncology patient. Further studies can characterize different types of clinician users and better tailor the task for different care settings. ConclusionEHR audit logs can provide important relevance data for training ML models that assist with note-writing in the oncology setting.more » « less
-
Abstract BackgroundOropharyngeal cancer (OPC) exhibits varying responses to chemoradiation therapy, making treatment outcome prediction challenging. Traditional imaging‐based methods often fail to capture the spatial heterogeneity within tumors, which influences treatment resistance and disease progression. Advances in modeling techniques allow for more nuanced analysis of this heterogeneity, identifying distinct tumor regions, or habitats, that drive patient outcomes. PurposeTo interrogate the association between treatment‐induced changes in spatial heterogeneity and chemoradiation resistance of oropharyngeal cancer (OPC) based on a novel tumor habitat analysis. MethodsA mathematical model was used to estimate tumor time dynamics of patients with OPC based on the applied analysis of partial differential equations. The position and momentum of each voxel was propagated according to Fokker‐Planck dynamics, that is, a common model in statistical mechanics. The boundary conditions of the Fokker‐Planck equation were solved based on pre‐ and intra‐treatment (i.e., after 2 weeks of therapy)18F‐FDG‐PET SUV images of patients (n = 56) undergoing definitive (chemo)radiation for OPC as part of a previously conducted prospective clinical trial. Tumor‐specific time dynamics, measured based on the solution of the Fokker‐Planck equation, were generated for each patient. Tumor habitats (i.e., non‐overlapping subregions of the primary tumor) were identified by measuring vector similarity in voxel‐level time dynamics through a fuzzy c‐means clustering algorithm. The robustness of our habitat construction method was quantified using a mean silhouette metric to measure intra‐habitat variability. Fifty‐four habitat‐specific radiomic texture features were extracted from pre‐treatment SUV images and normalized by habitat volume. Univariate Kaplan‐Meier analyses were implemented as a feature selection method, where statistically significant features (p < 0.05, log‐rank) were used to construct a multivariate Cox proportional‐hazards model. Parameters from the resulting Cox model were then used to construct a risk score for each patient, based on habitat‐specific radiomic expression. The patient cohort was stratified by median risk score value and association with recurrence‐free survival (RFS) was evaluated via log‐rank tests. ResultsDynamic tumor habitat analysis partitioned the gross disease of each patient into three spatial subregions. Voxels within each habitat suggested differential response rates in different compartments of the tumor. The minimum mean silhouette value was 0.57 and maximum mean silhouette value was 0.8, where values above 0.7 indicated strong intra‐habitat consistency and values between 0.5 and 0.7 indicated reasonable intra‐habitat consistency. Nine radiomic texture features (three GLRLM, two GLCOM, and three GLSZM) and SUVmax were found to be prognostically significant and were used to build the multivariate Cox model. The resulting risk score was associated with RFS (p = 0.032). By contrast, potential confounding factors (primary tumor volume and mean SUV) were not significantly associated with RFS (p = 0.286 andp = 0.231, respectively). ConclusionWe interrogated spatial heterogeneity of oropharyngeal tumors through the application of a novel algorithm to identify spatial habitats on SUV images. Our habitat construction technique was shown to be robust and habitat‐specific feature spaces revealed distinct underlying radiomic expression patterns. Radiomic features were extracted from dynamic habitats and used to build a risk score which demonstrated prognostic value.more » « less
-
Objective: Evaluate the effectiveness of machine learning tools that incorporate spatial information such as disease location and lymph node metastatic patterns-of-spread, for prediction of survival and toxicity in HPV+ oropharyngeal cancer (OPC). Materials & methods: 675 HPV+ OPC patients that were treated at MD Anderson Cancer Center between 2005 and 2013 with curative intent IMRT were retrospectively collected under IRB approval. Risk stratifications incorporating patient radiometric data and lymph node metastasis patterns via an anatomically-adjacent representation with hierarchical clustering were identified. These clusterings were combined into a 3-level patient stratification and included along with other known clinical features in a Cox model for predicting survival outcomes, and logistic regression for toxicity, using independent subsets for training and validation. Results: Four groups were identified and combined into a 3-level stratification. The inclusion of patient stratifications in predictive models for 5-yr Overall survival (OS), 5-year recurrence free survival, (RFS) and Radiation-associated dysphagia (RAD) consistently improved model performance measured using the area under the curve (AUC). Test set AUC improvements over models with clinical covariates, was 9 % for predicting OS, and 18 % for predicting RFS, and 7 % for predicting RAD. For models with both clinical and AJCC covariates, AUC improvement was 7 %, 9 %, and 2 % for OS, RFS, and RAD, respectively. Conclusion: Including data-driven patient stratifications considerably improve prognosis for survival and toxicity outcomes over the performance achieved by clinical staging and clinical covariates alone. These stratifications generalize well to across cohorts, and sufficient information for reproducing these clusters is included.more » « less
