RESUMO
BACKGROUND: Though several nomograms exist, machine learning (ML) approaches might improve prediction of pathologic stage in patients with prostate cancer. To develop ML models to predict pathologic stage that outperform existing nomograms that use readily available clinicopathologic variables. METHODS: Patients with prostate adenocarcinoma who underwent surgery were identified in the National Cancer Database. Seven ML models were trained to predict organ-confined (OC) disease, extracapsular extension, seminal vesicle invasion (SVI), and lymph node involvement (LNI). Model performance was measured using area under the curve (AUC) on a holdout testing data set. Clinical utility was evaluated using decision curve analysis (DCA). Performance metrics were confirmed on an external validation data set. RESULTS: The ML-based extreme gradient boosted trees model achieved the best performance with an AUC of 0.744, 0.749, 0.816, 0.811 for the OC, ECE, SVI, and LNI models, respectively. The MSK nomograms achieved an AUC of 0.708, 0.742, 0.806, 0.802 for the OC, ECE, SVI, and LNI models, respectively. These models also performed the best on DCA. Findings were consistent on both a holdout internal validation data set as well as an external validation data set. CONCLUSIONS: Our ML models better predicted pathologic stage relative to existing nomograms at predicting pathologic stage. Accurate prediction of pathologic stage can help oncologists and patients determine optimal definitive treatment options for patients with prostate cancer.
RESUMO
Background: Total Marrow and Lymphoid Irradiation (TMLI) is a promising component of the preparative regimen for hematopoietic cell transplantation in patients with high-risk acute myeloid leukemia (AML) and acute lymphoid leukemia (ALL). Extramedullary (EM) relapse after TMLI is comparable to TBI and non-TBI conditioning regimens. This study evaluates outcomes of patients treated with radiotherapy (RT) with EM relapse previously treated with TMLI. Methods: A retrospective analysis of five prospective TMLI trials was performed. TMLI targeted bones and major lymphoid tissues using image-guided tomotherapy, with total dose ranging from 12 to 20 Gy. EM recurrences were treated at the discretion of the hematologist and radiation oncologist using RT ± chemotherapy. Descriptive statistics and survival analysis were then performed on this cohort. Results: In total, 254 patients with refractory or relapsed AML or ALL were treated with TMLI at our institution. Twenty-one patients were identified as receiving at least one subsequent course of radiation. A total of 67 relapse sites (median=2 sites/patient, range=1-16) were treated. Eleven relapsed patients were initially treated with curative intent. Following the initial course of subsequent RT, 1-year, 3-year and 5-year estimates of OS were 47.6%, 32.7% and 16.3%, respectively. OS was significantly better in patients treated with curative intent, with median OS of 50.7 months vs 1.6 months (p<0.001). 1-year, 3-year and 5-year estimates of PFS were 23.8%, 14.3% and 14.3%, respectively. PFS was significantly better in patients treated with curative intent, with median PFS of 6.6 months vs 1.3 months (p<0.001). Following RT, 86.6% of the sites had durable local control. Conclusions: RT is an effective modality to treat EM relapse in patients with acute leukemia who relapse after HCT achieving high levels of local control. In patients with limited relapse amenable to curative intent, radiation confers favorable long-term survival. Radiation as salvage treatment for EM relapse after HCT warrants further evaluation.
RESUMO
Background and Objective: Machine learning (ML) models are increasingly being utilized in oncology research for use in the clinic. However, while more complicated models may provide improvements in predictive or prognostic power, a hurdle to their adoption are limits of model interpretability, wherein the inner workings can be perceived as a "black box". Explainable artificial intelligence (XAI) frameworks including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) are novel, model-agnostic approaches that aim to provide insight into the inner workings of the "black box" by producing quantitative visualizations of how model predictions are calculated. In doing so, XAI can transform complicated ML models into easily understandable charts and interpretable sets of rules, which can give providers with an intuitive understanding of the knowledge generated, thus facilitating the deployment of such models in routine clinical workflows. Methods: We performed a comprehensive, non-systematic review of the latest literature to define use cases of model-agnostic XAI frameworks in oncologic research. The examined database was PubMed/MEDLINE. The last search was run on May 1, 2022. Key Content and Findings: In this review, we identified several fields in oncology research where ML models and XAI were utilized to improve interpretability, including prognostication, diagnosis, radiomics, pathology, treatment selection, radiation treatment workflows, and epidemiology. Within these fields, XAI facilitates determination of feature importance in the overall model, visualization of relationships and/or interactions, evaluation of how individual predictions are produced, feature selection, identification of prognostic and/or predictive thresholds, and overall confidence in the models, among other benefits. These examples provide a basis for future work to expand on, which can facilitate adoption in the clinic when the complexity of such modeling would otherwise be prohibitive. Conclusions: Model-agnostic XAI frameworks offer an intuitive and effective means of describing oncology ML models, with applications including prognostication and determination of optimal treatment regimens. Using such frameworks presents an opportunity to improve understanding of ML models, which is a critical step to their adoption in the clinic.