Use of a physical activity monitor to track perioperative activity of radical cystectomy patients. Our first glimpse at what our patients are doing before and after surgery.

PURPOSE: To optimize recovery after radical cystectomy (RC), providers stress the importance of ambulation and adequate rest. However, little is known about the activity and sleep habits of patients undergoing RC. Therefore, we utilized a wearable physical activity monitor (PAM) in the perioperative period to provide the first objective data on physical activity and sleep habits for RC patients. MATERIALS AND METHODS: We prospectively identified patients ≥60 years old with planned RC. Participants completed a 4-week prehabilitation exercise program prior to surgery. They wore a PAM for 7-day intervals: at baseline, after prehabilitation, at postoperative day (POD) 30 and POD90. We tracked physical activity via metabolic equivalents (METs). METs were categorized by intensity: light (MET 1.5-<3), moderate (MET 3-<6), and vigorous (MET ≥6). We calculated daily step totals. We tracked hours slept and number of sleep awakenings. We correlated activity and sleep with self-reported quality of life (QOL). RESULTS: Forty-two patients completed prehabilitation and RC. Moderate intensity exercise decreased at POD30 (61 minutes/d at baseline, 30 minutes/d at POD30, P = 0.005). Physical activity did not significantly differ for light or vigorous activity at any timepoint. RC did not significantly affect sleep. Sleep and physical activity were associated with mental and physical QOL, respectively. CONCLUSIONS: This is the first study utilizing patient-worn monitors in RC to track physical activity and sleep. This study gives patients and providers a better understanding of postcystectomy recovery expectations. With these results in mind, interventions may be implemented to optimize activity and sleep in the perioperative period.

Machine Learning Applications in Head and Neck Radiation Oncology: Lessons From Open-Source Radiomics Challenges.

Radiomics leverages existing image datasets to provide non-visible data extraction via image post-processing, with the aim of identifying prognostic, and predictive imaging features at a sub-region of interest level. However, the application of radiomics is hampered by several challenges such as lack of image acquisition/analysis method standardization, impeding generalizability. As of yet, radiomics remains intriguing, but not clinically validated. We aimed to test the feasibility of a non-custom-constructed platform for disseminating existing large, standardized databases across institutions for promoting radiomics studies. Hence, University of Texas MD Anderson Cancer Center organized two public radiomics challenges in head and neck radiation oncology domain. This was done in conjunction with MICCAI 2016 satellite symposium using Kaggle-in-Class, a machine-learning and predictive analytics platform. We drew on clinical data matched to radiomics data derived from diagnostic contrast-enhanced computed tomography (CECT) images in a dataset of 315 patients with oropharyngeal cancer. Contestants were tasked to develop models for (i) classifying patients according to their human papillomavirus status, or (ii) predicting local tumor recurrence, following radiotherapy. Data were split into training, and test sets. Seventeen teams from various professional domains participated in one or both of the challenges. This review paper was based on the contestants' feedback; provided by 8 contestants only (47%). Six contestants (75%) incorporated extracted radiomics features into their predictive model building, either alone (n = 5; 62.5%), as was the case with the winner of the "HPV" challenge, or in conjunction with matched clinical attributes (n = 2; 25%). Only 23% of contestants, notably, including the winner of the "local recurrence" challenge, built their model relying solely on clinical data. In addition to the value of the integration of machine learning into clinical decision-making, our experience sheds light on challenges in sharing and directing existing datasets toward clinical applications of radiomics, including hyper-dimensionality of the clinical/imaging data attributes. Our experience may help guide researchers to create a framework for sharing and reuse of already published data that we believe will ultimately accelerate the pace of clinical applications of radiomics; both in challenge or clinical settings.