Could a mobile app with artificial intelligence built into the program be helpful for patients?
As I often say in the clinic that the brick and mortar clinic rates 3-star, but as soon as I walk in we reach 5-star rating. As I read more and more about various technologies being created to help provide do-it-yourself or self-care management solutions, I admittedly feel a tad threatened. Although I know what I do isn't necessarily rocket science, it stings just a little bit thinking that technology just might replace me.
As I read this particular study, I focused on "artificial intelligence." When a product truly has artificial intelligence, the product is continually learning and making decisions based on boatloads of data. This particular product, from what I am interpreting, seems to have a decision algorithm within it based on guidelines and professional expertise. The questions asked within the app to determine the output. The questions focus on: present condition, history, past treatment, 24-hour pattern, drug history, and social history. From my perspective the artificial intelligence kicks in more strongly every 14 days as the app user is reassessed.
So, what is missing in the app? Based on the study, I'm not sure if a differential diagnosis occurred. I don't believe it is reasonable to believe that every person who has persistent pain just needs exercise to improve the condition. Granted, the app does have a disclaimer that the app does not replace medical services.
For the last 12 weeks I have been participating in a group strengthening program at the local YMCA. Interesting to me, the instructor seems more focused on designing changes versus focusing on the quality of the performance of the exercise. As I watch others performing the exercises, what I see missing is good form and appropriate recruitment of muscles to perform the activity. After some sessions, some of the participants mention back or shoulder pain - and I know the reason is because the instructor provides very little guidance on the amount of resistance for each participant nor cues to ensure the exercise is performed safely. From this experience, I truly do wonder if a do-it-yourself self-management without any face-to-face time or supervision will actually provide the intended results.
I can appreciate the fact that this study was basically really looking at the feasibility of an app for these people. The findings indicate that those in the study did receive and appreciate educational material. Those in the study also increased their exercise levels. Pain level also reduced. The study has limitations that there is no comparison group.
I'm crossing my fingers and hoping that apps don't replace 5-star me!
You'll find the abstract to the recent study below.
Chronic musculoskeletal neck and back pain are disabling conditions among adults. Use of technology has been suggested as an alternative way to increase adherence to exercise therapy, which may improve clinical outcomes.
The aim was to investigate the self-perceived benefits of an artificial intelligence (AI)-embedded mobile app to self-manage chronic neck and back pain.
A total of 161 participants responded to the invitation. The evaluation questionnaire included 14 questions that were intended to explore if using the AI rehabilitation system may (1) increase time spent on therapeutic exercise, (2) affect pain level (assessed by the 0-10 Numerical Pain Rating Scale), and (3) reduce the need for other interventions.
An increase in time spent on therapeutic exercise per day was observed. The median Numerical Pain Rating Scale scores were 6 (interquartile range [IQR] 5-8) before and 4 (IQR 3-6) after using the AI-embedded mobile app (95% CI 1.18-1.81). A 3-point reduction was reported by the participants who used the AI-embedded mobile app for more than 6 months. Reduction in the usage of other interventions while using the AI-embedded mobile app was also reported.
This study demonstrated the positive self-perceived beneficiary effect of using the AI-embedded mobile app to provide a personalized therapeutic exercise program. The positive results suggest that it at least warrants further study to investigate the physiological effect of the AI-embedded mobile app and how it compares with routine clinical care.
JMIR Mhealth Uhealth. 2018 Nov 26;6(11):e198. doi: 10.2196/mhealth.8127.