Background Although many pain-related smartphone apps exist, little attention has been given to understanding how these apps are used over time and what factors contribute to greater compliance and patient engagement. Objective This retrospective analysis was designed to help identify factors that predicted the benefits and future use of a smartphone pain app among patients with chronic pain. Methods An app designed for both Android and iOS devices was developed by Brigham and Women’s Hospital Pain Management Center (BWH-PMC) for users with chronic pain to assess and monitor pain and communicate with their providers. The pain app offered chronic pain assessment, push notification reminders and communication, personalized goal setting, relaxation sound files, topics of interest with psychological and medical pain management strategies, and line graphs from daily assessments. BWH-PMC recruited 253 patients with chronic pain over time to use the pain app. All subjects completed baseline measures and were asked to record their progress every day using push notification daily assessments. After 3 months, participants completed follow-up questionnaires and answered satisfaction questions. We defined the number of completed daily assessments as a measure of patient engagement with the pain app. Results The average age of participants was 51.5 years (SD 13.7, range 18-92), 72.8% (182/253) were female, and 36.8% (78/212) reported the low back as their primary pain site. The number of daily assessments ranged from 1 to 426 (average 62.0, SD 49.9). The app was easy to introduce among patients, and it was well accepted. Those who completed more daily assessments (greater patient engagement) throughout the study were more likely to report higher pain intensity, more activity interference, and greater disability and were generally overweight compared with others. Patients with higher engagement with the app rated the app as offering greater benefit in coping with their pain and expressed more willingness to use the app in the future (P<.05) compared with patients showing lower engagement. Patients completing a small number of daily assessments reported less pain intensity, less daily activity interference, and less pain-related disability on average and were less likely to use the two-way messaging than those who were more engaged with the pain app (P<.05). Conclusions Patients with chronic pain who appeared to manage their pain better were less likely to report benefits of a smartphone pain app designed for chronic pain management. They demonstrated lower patient engagement in reporting their daily progress, in part, owing to the perceived burden of regularly using an app without a perceived benefit. An intrinsically different pain app designed and targeted for individuals based on early identification of user characteristics and adapted for each individual would likely improve compliance and app-related patient engagement.

BackGrOunD: In response to the growing incidence of opioid dependence, guidelines have been created, and new treatments are being developed to assist physicians in treating dependence and withdrawal of opioids.

BACKGROUND Although many pain-related smartphone apps exist, little attention has been given to understanding how these apps are used over time and what factors contribute to greater compliance and patient engagement. OBJECTIVE This retrospective analysis was designed to help identify factors that predicted the benefits and future use of a smartphone pain app among patients with chronic pain. METHODS An app designed for both Android and iOS devices was developed by Brigham and Women’s Hospital Pain Management Center (BWH-PMC) for users with chronic pain to assess and monitor pain and communicate with their providers. The pain app offered chronic pain assessment, push notification reminders and communication, personalized goal setting, relaxation sound files, topics of interest with psychological and medical pain management strategies, and line graphs from daily assessments. BWH-PMC recruited 253 patients with chronic pain over time to use the pain app. All subjects completed baseline measures and were asked to record their progress every day using push notification daily assessments. After 3 months, participants completed follow-up questionnaires and answered satisfaction questions. We defined the number of completed daily assessments as a measure of patient engagement with the pain app. RESULTS The average age of participants was 51.5 years (SD 13.7, range 18-92), 72.8% (182/253) were female, and 36.8% (78/212) reported the low back as their primary pain site. The number of daily assessments ranged from 1 to 426 (average 62.0, SD 49.9). The app was easy to introduce among patients, and it was well accepted. Those who completed more daily assessments (greater patient engagement) throughout the study were more likely to report higher pain intensity, more activity interference, and greater disability and were generally overweight compared with others. Patients with higher engagement with the app rated the app as offering greater benefit in coping with their pain and expressed more willingness to use the app in the future (<i>P</i>&lt;.05) compared with patients showing lower engagement. Patients completing a small number of daily assessments reported less pain intensity, less daily activity interference, and less pain-related disability on average and were less likely to use the two-way messaging than those who were more engaged with the pain app (<i>P</i>&lt;.05). CONCLUSIONS Patients with chronic pain who appeared to manage their pain better were less likely to report benefits of a smartphone pain app designed for chronic pain management. They demonstrated lower patient engagement in reporting their daily progress, in part, owing to the perceived burden of regularly using an app without a perceived benefit. An intrinsically different pain app designed and targeted for individuals based on early identification of user characteristics and adapted for each individual would likely improve compliance and app-related patient engagement.

Objective To estimate the risk of a patient with osteoarthritis (OA) developing chronic opioid use (COU) within 1 year of a new opioid prescription by using electronic health record (EHR) data and predictive models. Methods We used EHR data from 13 health care organizations to identify patients with OA with an opioid prescription between March 1, 2017 and February 28, 2019 and no record of opioid use in the prior 6 months. We evaluated 4 machine learning models to estimate patients’ risk of COU (≥3 prescriptions ≥84 days, maximum gap ≤60 days). We also estimated the transportability of models to organizations outside the training set. Results The cohort consisted of 33,894 patients with OA, of whom 2,925 (8.6%) developed COU within 1 year. All models demonstrated good discrimination, with the best‐performing model (random forest) achieving an area under the receiver operating characteristic curve (AUC) of 0.728 (95% CI 0.711–0.745), but the simplest regression model performed nearly as well (AUC 0.717 [95% CI 0.699–0.734]). Predicted risk deciles spanned a range of 2% risk for the 10th percentile to 18% risk for the 90th percentile for well‐calibrated models. Models showed highly variable discrimination across organizations (AUC 0.571–0.842). Conclusions We found that EHR‐based predictive models could estimate the risk of future COU among patients with OA to help inform care decisions. Black‐box methods did not have significant advantages over more interpretable models. Care should be taken when extending all models into organizations not included in model training because of a high variability in performance across held‐out organizations.