ABSTRACT
The American College of Sports Medicine determined the energy consumption of daily activities and sports. Cardiac telerehabilitation (CTR) requires knowing how much energy people consume in daily life outside of cardiac rehabilitation activities. Therefore, we have investigated if the estimated values are valid in CTR. Data from two studies were incorporated. The first study measured ventilatory threshold (VT)1, VT2, and peak exercise on cardiopulmonary exercise testing (CPET) collected from 272 cardiac (risk) patients and compared them to the estimated oxygen consumption (VO2) at low-to-moderate-intense exercise (3-6 metabolic equivalents [METs]). Next, a patient-tailored application was developed to support CTR using these estimated values, and the intervention (the second study) was conducted with 24 coronary artery disease patients using this application during a CTR intervention. In the first study, VO2 at VT1, VT2 and peak exercise corresponded to 3.2 [2.8, 3.8], 4.3 [3.8, 5.3], and 5.4 [4.5, 6.2] METs, which are significantly different from the estimated VO2 at low-to-moderate-intense exercise, especially lower in older, obese, female, and post-myocardial infarction/heart failure patients. These VO2 varied considerably between patients. The telerehabilitation study did not show significant progress in peak VO2, but using the application's estimated target, 97.2% of the patients achieved their weekly target, which is a significant overestimate. The estimated and observed exercise-related energy expenditures by CPET were significantly different, resulting in an overestimation of the exercise done by the patients at home. The results can have a significant impact on the quantification of exercise dose during (tele)rehabilitation programs.
ABSTRACT
Applications using Artificial Intelligence (AI) have become commonplace and embedded in our daily lives. Much of our communication has transitioned from human-human interaction to human-technology or technology-mediated interaction. As technology is handed over control and streamlines choices and decision-making in different contexts, people are increasingly concerned about a potential threat to their autonomy. In this paper, we explore autonomy perception when interacting with AI-based applications in everyday contexts using a design fiction-based survey with 328 participants. We probed if providing users with explanations on "why" an application made certain choices or decisions influenced their perception of autonomy or reactance regarding the interaction with the applications. We also looked at changes in perception when users are aware of AI's presence in an application. In the social media context, we found that people perceived a greater reactance and lower sense of autonomy perhaps owing to the personal and identity-sensitive nature of the application context. Providing explanations on "why" in the navigation context, contributed to enhancing their autonomy perception, and reducing reactance since it influenced the users' subsequent actions based on the recommendation. We discuss our findings and the implications it has for the future development of everyday AI applications that respect human autonomy.
ABSTRACT
BACKGROUND: Telerehabilitation approaches have been successful in supporting coronary artery disease (CAD) patients to rehabilitate at home after hospital-based rehabilitation. However, on completing a telerehabilitation program, the effects are not sustained beyond the intervention period because of the lack of lifestyle adaptations. Furthermore, decline in patients' motivation lead to recurrence of disease and increased rehospitalization rates. We developed HeartHab, using persuasive design principles and personalization, to enable sustenance of rehabilitation effects beyond the intervention period. HeartHab promotes patients' understanding, motivates them to reach personalized rehabilitation goals, and helps to maintain positive lifestyle adaptations during telerehabilitation. OBJECTIVE: This study aimed to investigate the impact of the HeartHab app on patients' overall motivation, increasing physical activities, reaching exercise targets, quality of life, and modifiable risk factors in patients with CAD during telerehabilitation. The study also investigated carryover effects to determine the maintenance of effects after the conclusion of the intervention. METHODS: A total of 32 CAD patients were randomized on a 1:1 ratio to telerehabilitation or usual care. We conducted a 4-month crossover study with a crossover point at 2 months using a mixed-methods approach for evaluation. We collected qualitative data on users' motivation, user experience, and quality of life using questionnaires, semistructured interviews and context-based sentiment analysis. Quantitative data on health parameters, exercise capacity, and risk factors were gathered from blood tests and ergo-spirometry tests. Data procured during the app usage phase were compared against baseline values to assess the impact of the app on parameters such as motivation, physical activity, quality of life, and risk factors. Carryover effects were used to gather insights on the maintenance of effects. RESULTS: The qualitative data showed that 75% (21/28) of patients found the HeartHab app motivating and felt encouraged to achieve their rehabilitation targets. 84% (21/25) of patients either reached or exceeded their prescribed physical activity targets. We found positive significant effects on glycated hemoglobin (P=.01; d=1.03; 95% CI 0.24-1.82) with a mean decrease of 1.5 mg/dL and high-density lipoprotein (HDL) cholesterol (P=.04; d=0.78; 95% CI 0.02-1.55) with a mean increase of 0.61 mg/dL after patients used the HeartHab app. We observed significant carryover effects on weight, HDL cholesterol, and maximal oxygen consumption (VO2 max), indicating the maintenance of effects. CONCLUSIONS: Persuasive design techniques integrated in HeartHab and tailoring of exercise targets were effective in motivating patients to reach their telerehabilitation targets. This study demonstrated significant effects on glucose and HDL cholesterol and positive carryover effects on weight, HDL cholesterol, and VO2 max. There was also a perceived improvement in quality of life. A longer-term evaluation with more patients could possibly reveal effectiveness on other risk factors and maintenance of the positive health behavior change. TRIAL REGISTRATION: ClinicalTrials.gov NCT03102671; https://clinicaltrials.gov/ct2/show/NCT03102671 (Archived by WebCite at http://www.webcitation.org/76gzI9Pvd).
