Characterising user engagement with mHealth for chronic disease self-management and impact on machine learning performance.

Mobile Health (mHealth) has the potential to be transformative in the management of chronic conditions. Machine learning can leverage self-reported data collected with apps to predict periods of increased health risk, alert users, and signpost interventions. Despite this, mHealth must balance the treatment burden of frequent self-reporting and predictive performance and safety. Here we report how user engagement with a widely used and clinically validated mHealth app, myCOPD (designed for the self-management of Chronic Obstructive Pulmonary Disease), directly impacts the performance of a machine learning model predicting an acute worsening of condition (i.e., exacerbations). We classify how users typically engage with myCOPD, finding that 60.3% of users engage frequently, however, less frequent users can show transitional engagement (18.4%), becoming more engaged immediately ( < 21 days) before exacerbating. Machine learning performed better for users who engaged the most, however, this performance decrease can be mostly offset for less frequent users who engage more near exacerbation. We conduct interviews and focus groups with myCOPD users, highlighting digital diaries and disease acuity as key factors for engagement. Users of mHealth can feel overburdened when self-reporting data necessary for predictive modelling and confidence of recognising exacerbations is a significant barrier to accurate self-reported data. We demonstrate that users of mHealth should be encouraged to engage when they notice changes to their condition (rather than clinically defined symptoms) to achieve data that is still predictive for machine learning, while reducing the likelihood of disengagement through desensitisation.

Prediction of Chronic Obstructive Pulmonary Disease Exacerbation Events by Using Patient Self-reported Data in a Digital Health App: Statistical Evaluation and Machine Learning Approach.

BACKGROUND: Self-reporting digital apps provide a way of remotely monitoring and managing patients with chronic conditions in the community. Leveraging the data collected by these apps in prognostic models could provide increased personalization of care and reduce the burden of care for people who live with chronic conditions. This study evaluated the predictive ability of prognostic models for the prediction of acute exacerbation events in people with chronic obstructive pulmonary disease by using data self-reported to a digital health app. OBJECTIVE: The aim of this study was to evaluate if data self-reported to a digital health app can be used to predict acute exacerbation events in the near future. METHODS: This is a retrospective study evaluating the use of symptom and chronic obstructive pulmonary disease assessment test data self-reported to a digital health app (myCOPD) in predicting acute exacerbation events. We include data from 2374 patients who made 68,139 self-reports. We evaluated the degree to which the different variables self-reported to the app are predictive of exacerbation events and developed both heuristic and machine learning models to predict whether the patient will report an exacerbation event within 3 days of self-reporting to the app. The model's predictive ability was evaluated based on self-reports from an independent set of patients. RESULTS: Users self-reported symptoms, and standard chronic obstructive pulmonary disease assessment tests displayed correlation with future exacerbation events. Both a baseline model (area under the receiver operating characteristic curve [AUROC] 0.655, 95% CI 0.689-0.676) and a machine learning model (AUROC 0.727, 95% CI 0.720-0.735) showed moderate ability in predicting exacerbation events, occurring within 3 days of a given self-report. Although the baseline model obtained a fixed sensitivity and specificity of 0.551 (95% CI 0.508-0.596) and 0.759 (95% CI 0.752-0.767) respectively, the sensitivity and specificity of the machine learning model can be tuned by dichotomizing the continuous predictions it provides with different thresholds. CONCLUSIONS: Data self-reported to health care apps designed to remotely monitor patients with chronic obstructive pulmonary disease can be used to predict acute exacerbation events with moderate performance. This could increase personalization of care by allowing preemptive action to be taken to mitigate the risk of future exacerbation events.

Evidence generation for the clinical impact of myCOPD in patients with mild, moderate and newly diagnosed COPD: a randomised controlled trial.

Self-management interventions in COPD aim to improve patients' knowledge, skills and confidence to make correct decisions, thus improving health status and outcomes. myCOPD is a web-based self-management app known to improve inhaler use and exercise capacity in individuals with more severe COPD. We explored the impact of myCOPD in patients with mild-moderate or recently diagnosed COPD through a 12-week, open-label, parallel-group, randomised controlled trial of myCOPD compared with usual care. The co-primary outcomes were between-group differences in mean COPD assessment test (CAT) score at 90 days and critical inhaler errors. Key secondary outcomes were app usage and patient activation measurement (PAM) score. Sixty patients were randomised (29 myCOPD, 31 usual care). Groups were balanced for forced expiratory volume in 1 s (FEV1 % pred) but there was baseline imbalance between groups for exacerbation frequency and CAT score. There was no significant adjusted mean difference in CAT score at study completion, -1.27 (95% CI -4.47-1.92, p=0.44) lower in myCOPD. However, an increase in app use was associated with greater CAT score improvement. The odds of ≥1 critical inhaler error was lower in the myCOPD arm (adjusted OR 0.30 (95% CI 0.09-1.06, p=0.061)). The adjusted odds ratio for being in a higher PAM level at 90 days was 1.65 (95% CI 0.46-5.85) in favour of myCOPD. The small sample size and phenotypic difference between groups limited our ability to demonstrate statistically significant evidence of benefit beyond inhaler technique. However, our findings provide important insights into associations between increased app use and clinically meaningful benefit warranting further study in real world settings.

A randomised controlled feasibility trial of E-health application supported care vs usual care after exacerbation of COPD: the RESCUE trial.

Exacerbations of COPD are one of the commonest causes of admission and readmission to hospital. The role of digital interventions to support self-management in improving outcomes is uncertain. We conducted an open, randomised controlled trial of a digital health platform application (app) in 41 COPD patients recruited following hospital admission with an acute exacerbation. Subjects were randomised to either receive usual care, including a written self-management plan (n = 21), or the myCOPD app (n = 20) for 90 days. The primary efficacy outcome was recovery rate of symptoms measured by COPD assessment test (CAT) score. Exacerbations, readmission, inhaler technique quality of life and patient activation (PAM) scores were also captured by a blinded team. The app was acceptable in this care setting and was used by 17 of the 20 patients with sustained use over the study period. The treatment effect on the CAT score was 4.49 (95% CI: -8.41, -0.58) points lower in the myCOPD arm. Patients' inhaler technique improved in the digital intervention arm (101 improving to 20 critical errors) compared to usual care (100 to 72 critical errors). Exacerbations tended to be less frequent in the digital arm compared to usual care; 34 vs 18 events. Hospital readmissions risk was numerically lower in the digital intervention arm: OR for readmission 0.383 (95% CI: 0.074, 1.987; n = 35). In this feasibility study of the digital self-management platform myCOPD, the app has proven acceptable to patients to use and use has improved exacerbation recovery rates, with strong signals of lower re-exacerbation and readmission rates over 90 days. myCOPD reduced the number of critical errors in inhaler technique compared to usual care with written self-management. This provides a strong basis for further exploration of the use of app interventions in the context of recently hospitalised patients with COPD and informs the potential design of a large multi-centre trial.