Background Pancreatic cancer is the third leading cause of cancer-related deaths, and although pancreatectomy is currently the only curative treatment, it is associated with significant morbidity. Objective The objective of this study was to evaluate the utility of wearable telemonitoring technologies to predict treatment outcomes using patient activity metrics and machine learning. Methods In this prospective, single-center, single-cohort study, patients scheduled for pancreatectomy were provided with a wearable telemonitoring device to be worn prior to surgery. Patient clinical data were collected and all patients were evaluated using the American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator (ACS-NSQIP SRC). Machine learning models were developed to predict whether patients would have a textbook outcome and compared with the ACS-NSQIP SRC using area under the receiver operating characteristic (AUROC) curves. Results Between February 2019 and February 2020, 48 patients completed the study. Patient activity metrics were collected over an average of 27.8 days before surgery. Patients took an average of 4162.1 (SD 4052.6) steps per day and had an average heart rate of 75.6 (SD 14.8) beats per minute. Twenty-eight (58%) patients had a textbook outcome after pancreatectomy. The group of 20 (42%) patients who did not have a textbook outcome included 14 patients with severe complications and 11 patients requiring readmission. The ACS-NSQIP SRC had an AUROC curve of 0.6333 to predict failure to achieve a textbook outcome, while our model combining patient clinical characteristics and patient activity data achieved the highest performance with an AUROC curve of 0.7875. Conclusions Machine learning models outperformed ACS-NSQIP SRC estimates in predicting textbook outcomes after pancreatectomy. The highest performance was observed when machine learning models incorporated patient clinical characteristics and activity metrics.

Post-operative complications and hospital readmission are of great concern to surgical patients and health care providers. Wearable devices such as Fitbit wristbands enable long-term and non-intrusive monitoring of patients outside clinical environments. To build accurate predictive models based on wearable data, however, requires effective feature engineering to extract high-level features from time series data collected by the wearable sensors. This paper presents a pipeline for developing clinical predictive models based on wearable sensors. The core of the pipeline is a multi-level feature engineering framework for extracting high-level features from fine-grained time series data. The framework integrates a set of techniques tailored for noisy and incomplete wearable data collected in real-world clinical studies: (1) singular spectrum analysis for extracting high-level features from daily features over the course of the study; (2) a set of daily features that are resilient to missing data in wearable time series data; (3) a K-Nearest Neighbors (KNN) method for imputing short missing heart rate segments; (4) the integration of patients' clinical characteristics and wearable features. We evaluated the feature engineering approach and machine learning models in a clinical study involving 61 patients undergoing pancreatic surgery. Linear support vector machine (SVM) with integrated feature engineering achieved an AUROC of 0.8802 for predicting post-operative readmission or severe complications, which significantly outperformed the existing rule-based model used in clinical practice and other state-of-the-art feature engineering approaches.

No abstract

BACKGROUND: Rapid growth in smartphone use has expanded opportunities to use mobile health (mHealth) technology to collect real-time patient-reported and objective biometric data. These data may have important implication for personalized treatments of degenerative spine disease. However, no large-scale study has examined the feasibility and acceptability of these methods in spine surgery patients. OBJECTIVE: To evaluate the feasibility and acceptability of a multimodal preoperative mHealth assessment in patients with degenerative spine disease. METHODS: Adults undergoing elective spine surgery were provided with Fitbit trackers and sent preoperative ecological momentary assessments (EMAs) assessing pain, disability, mood, and catastrophizing 5 times daily for 3 weeks. Objective adherence rates and a subjective acceptability survey were used to evaluate feasibility of these methods. RESULTS: The 77 included participants completed an average of 82 EMAs each, with an average completion rate of 86%. Younger age and chronic pulmonary disease were significantly associated with lower EMA adherence. Seventy-two (93%) participants completed Fitbit monitoring and wore the Fitbits for an average of 247 hours each. On average, participants wore the Fitbits for at least 12 hours per day for 15 days. Only worse mood scores were independently associated with lower Fitbit adherence. Most participants endorsed positive experiences with the study protocol, including 91% who said they would be willing to complete EMAs to improve their preoperative surgical guidance. CONCLUSION: Spine fusion candidates successfully completed a preoperative multimodal mHealth assessment with high acceptability. The intensive longitudinal data collected may provide new insights that improve patient selection and treatment guidance.

No abstract