Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Aug 17, 2020
Date Accepted: Feb 17, 2021
Wearable technology and machine learning predict outcomes in a prospective cohort of pancreatectomy patients
ABSTRACT
Background:
Pancreas cancer is the 3rd leading cause of cancer-related deaths and pancreatectomy is currently the only curative treatment; however, it is associated with significant morbidity. This study evaluated wearable telemonitoring technologies to predict treatment outcomes using patient activity metrics and machine learning.
Objective:
To evaluate 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 a wearable telemonitoring device to be worn prior to surgery. Patient clinical data was 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 to the ACS NSQIP - SRC using area under the receiver operating characteristics (AUROC) curves.
Results:
From February 2019 to February 2020 48 patients completed the study. Patient activity metrics were collected over an average of 27.8 days before surgery. Patients took on average 4,162.1 (SD=4,052.6) steps per day, had an average heart rate of 75.6 (SD=14.8) beats per minute. Twenty-eight (58%) patients had a Textbook Outcome. The 20 (42%) patients who did not have a Textbook Outcome included 14 with severe complications and 11 requiring readmission. 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 + Patient Activity achieved the highest performance with an AUROC curve of 0.7839.
Conclusions:
Machine learning models outperform 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.
Citation
Per the author's request the PDF is not available.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.