Search

Purpose: To determine whether a machine learning approach optimizes survival estimation for patients with symptomatic bone metastases (SBM), we developed the Bone Metastases Ensemble Trees for Survival (BMETS) to predict survival using 27 prognostic covariates. To establish its relative clinical utility, we compared BMETS with 2 simpler Cox regression models used in this setting., Methods and Materials: For 492 bone sites in 397 patients evaluated for palliative radiation therapy (RT) for SBM from January 2007 to January 2013, data for 27 clinical variables were collected. These covariates and the primary outcome of time from consultation to death were used to build BMETS using random survival forests. We then performed Cox regressions as per 2 validated models: Chow's 3-item (C-3) and Westhoff's 2-item (W-2) tools. Model performance was assessed using cross-validation procedures and measured by time-dependent area under the curve (tAUC) for all 3 models. For temporal validation, a separate data set comprised of 104 bone sites treated in 85 patients in 2018 was used to estimate tAUC from BMETS., Results: Median survival was 6.4 months. Variable importance was greatest for performance status, blood cell counts, recent systemic therapy type, and receipt of concurrent nonbone palliative RT. tAUC at 3, 6, and 12 months was 0.83, 0.81, and 0.81, respectively, suggesting excellent discrimination of BMETS across postconsultation time points. BMETS outperformed simpler models at each time, with respective tAUC at each time of 0.78, 0.76, and 0.74 for the C-3 model and 0.80, 0.78, and 0.77 for the W-2 model. For the temporal validation set, respective tAUC was similarly high at 0.86, 0.82, and 0.78., Conclusions: For patients with SBM, BMETS improved survival predictions versus simpler traditional models. Model performance was maintained when applied to a temporal validation set. To facilitate clinical use, we developed a web platform for data entry and display of BMETS-predicted survival probabilities., (Copyright © 2020 Elsevier Inc. All rights reserved.)

We propose a multi-view data analysis approach using radiomics and dosiomics (R&D) texture features for predicting acute-phase weight loss (WL) in lung cancer radiotherapy. Baseline weight of 388 patients who underwent intensity modulated radiation therapy (IMRT) was measured between one month prior to and one week after the start of IMRT. Weight change between one week and two months after the commencement of IMRT was analyzed, and dichotomized at 5% WL. Each patient had a planning CT and contours of gross tumor volume (GTV) and esophagus (ESO). A total of 355 features including clinical parameter (CP), GTV and ESO (GTV&ESO) dose-volume histogram (DVH), GTV radiomics, and GTV&ESO dosiomics features were extracted. R&D features were categorized as first- (L1), second- (L2), higher-order (L3) statistics, and three combined groups, L1 + L2, L2 + L3 and L1 + L2 + L3. Multi-view texture analysis was performed to identify optimal R&D input features. In the training set (194 earlier patients), feature selection was performed using Boruta algorithm followed by collinearity removal based on variance inflation factor. Machine-learning models were developed using Laplacian kernel support vector machine (lpSVM), deep neural network (DNN) and their averaged ensemble classifiers. Prediction performance was tested on an independent test set (194 more recent patients), and compared among seven different input conditions: CP-only, DVH-only, R&D-only, DVH + CP, R&D + CP, R&D + DVH and R&D + DVH + CP. Combined GTV L1 + L2 + L3 radiomics and GTV&ESO L3 dosiomics were identified as optimal input features, which achieved the best performance with an ensemble classifier (AUC = 0.710), having statistically significantly higher predictability compared with DVH and/or CP features (p < 0.05). When this performance was compared to that with full R&D-only features which reflect traditional single-view data, there was a statistically significant difference (p < 0.05). Using optimized multi-view R&D input features is beneficial for predicting early WL in lung cancer radiotherapy, leading to improved performance compared to using conventional DVH and/or CP features.

Big clinical data analytics as a primary component of precision medicine is discussed, identifying where these emerging tools fit in the spectrum of genomics and radiomics research. A learning health system (LHS) is conceptualized that uses clinically acquired data with machine learning to advance the initiatives of precision medicine. The LHS is comprehensive and can be used for clinical decision support, discovery, and hypothesis derivation. These developing uses can positively impact the ultimate management and therapeutic course for patients. The conceptual model for each use of clinical data, however, is different, and an overview of the implications is discussed. With advancements in technologies and culture to improve the efficiency, accuracy, and breadth of measurements of the patient condition, the concept of an LHS may be realized in precision radiation therapy., (Copyright © 2018 Elsevier Inc. All rights reserved.)

The capture of high‐quality treatment data and outcomes is necessary in order to learn from our clinical experiences with big data analytics. In radiotherapy, there are several practical challenges to overcome. Practical aspects of data collection are discussed pointing to a need for a culture change in clinical practice to one that captures structured patient‐related data in routine care in a prospective manner. Radiation dosimetry and the contoured anatomy must also be captured routinely to represent the best estimate of delivered radiation. The quality and integrity present in the data are critical which poses opportunities to introduce electronic validity checking to improve them. Similarly, data completeness and methods and technology to improve the efficiency and sufficiency of data capture can be introduced. In the manuscript, the types of clinical data are discussed including patient reports, images, biospecimens, treatments, and symptom management. With a data‐driven culture, the realization of a learning health system is possible unlocking the potential of big data and its influence on clinical decision‐making and hypothesis generation. [ABSTRACT FROM AUTHOR]

This Vision 20/20 paper considers what computational advances are likely to be implemented in clinical radiation oncology in the coming years and how the adoption of these changes might alter the practice of radiotherapy. Four main areas of likely advancement are explored: cloud computing, aggregate data analyses, parallel computation, and automation. As these developments promise both new opportunities and new risks to clinicians and patients alike, the potential benefits are weighed against the hazards associated with each advance, with special considerations regarding patient safety under new computational platforms and methodologies. While the concerns of patient safety are legitimate, the authors contend that progress toward next-generation clinical informatics systems will bring about extremely valuable developments in quality improvement initiatives, clinical efficiency, outcomes analyses, data sharing, and adaptive radiotherapy. [ABSTRACT FROM AUTHOR]