P-107 - AI-powered Personalized Pain Management: Evaluating the Clinical Efficacy of Paindrainer® in Enhancing Daily Function and Reducing Pain Interference

Abstract Title:
AI-powered Personalized Pain Management: Evaluating the Clinical Efficacy of Paindrainer^® in Enhancing Daily Function and Reducing Pain Interference



Background:
The fundamental goal of pain rehabilitation processes is to optimize a patient’s self-rated quality of life through the ability to adapt and respond to changes, thereby minimizing pain and distress ^[1]. Novel approaches to self-management of pain care that promote long-lasting behavioral changes must therefore be tailored to each person’s experience ^[2]. The CDC´s Clinical Practice Guideline for Prescribing Opioids for Chronic Pain emphasizes an individualized, patient-centric approach for treating chronic pain ^[3]. However, most treatment options are based on population-based validations and are lacking a truly patient-centric approach. Core self-management skills, such as self-monitoring of symptoms, goal setting and planning, are important in the pain rehabilitation process, where psychological flexibility is an essential component ^[4–6]. However, implementing new skills, finding pain triggers and protectors, and use this knowledge for behavioral changes, are difficult, partly since the human brain is incapable of handling more than four variables at the same time ^[7], whereas everyday life consists of many more.


Core self-management skills are crucial, but implementing new skills can be challenging. AI can aid in managing complex variables and support personalized, gradual behavioral changes. A comprehensive, user-friendly digital platform that guides patients in self-management and lifestyle modifications is consequently desirable.


Purpose/Objectives:
The study aim was to investigate how a neural network powered, 360° patient-centric, digital self-management tool that promotes behavioral change, such as increased physical activity and practicing phasing, affects the daily functions in adults with chronic back and neck pain.



Methods:
Eligible subjects (n=41) were enrolled in a 12-week prospective, multicenter, single-arm, open-label study and instructed to use the digital coach daily. The AI engine worked with each individual patient and was trained by the first initial loggings.


After 7 loggings the subjects obtain individual daily plans for optimal activity balance and how to gradually modify activities to achieve increased physical function and alleviate pain.

Primary outcome was a change in Patient-Reported Outcomes Measurement Information Systems (PROMIS) scores for pain interference. Secondary outcomes were changes in PROMIS physical function, anxiety, depression, pain intensity scores, pain catastrophizing scale (PCS) scores and CPAQ-8.





Results:
In the study, 41 participants completed the 6-week questionnaires, and 34 completed the 12-week questionnaires. Measures included pain interference, physical function, anxiety, depression, pain intensity, pain catastrophizing, and work capacity.





The primary outcome, assessed by the PROMIS 6a pain interference scale, showed a significant reduction from baseline at both 6 weeks (p < 0.0001) and 12 weeks (p = 0.020). The mean T-score decreased from 61.5 to 57.6 at 6 weeks and to 59.1 at 12 weeks. Overall, 73.8% of subjects experienced a decrease in T-score, with 57.5% achieving the empirical defined minimally important difference (MID) of -2.4. In the responding group, the decrease in T-score was -8.5 at 6 weeks and -7.4 at 12 weeks.





PROMIS physical function scores also improved significantly, with mean T-scores increasing from 39.9 to 41.9 at 6 weeks and to 41.8 at 12 weeks. The MID for physical function, defined as an increase of 1.9 in T-score, was achieved by 72.5% of subjects. Additionally, pain intensity decreased, with mean pain scores dropping from 5.6 to 4.4 at 6 weeks and to 4.1 at 12 weeks.


A pre- to post-intervention improvement in depression score was also statistically significant, observed in 100% of subjects, as was the improvement in anxiety scores, evident in 81.3% of the subjects. PCS mean scores was also significantly decreased at 12 weeks as well as an increase in activity engagement as measured by CPAQ-8.





The change in work capacity was also assessed by analyzing logged primary data. The average daily minutes of logged work increased for 50% of subjects, with 15% showing no change and 35% showing a decrease. The proportion of this subgroup had increased their working period by over one hour (range 60-320 minutes) was 69%.


Conclusions/Implications for future research and/or clinical care:
This study underscores the need for personalized approaches to chronic pain management, given its profound impact on individuals and society. Current treatments often lack long-term effectiveness and may carry risks such as opioid use and access to comprehensive pain management remains limited for many patients.





Technological advanced tools like Paindrainer offers promise for individualized pain care, where real-time monitoring of symptoms creates guidance tailored to each person's unique needs. This approach also aligns with the principles of ACT, emphasizing acceptance and commitment to valued activities rather than symptom reduction alone.





The study demonstrates significant improvements exceed clinically meaningful thresholds over all measured parameters for a majority of the patients, suggesting a holistic impact on the pain. It also highlights the transformative potential of AI-powered tools in revolutionizing personalized pain care. By prioritizing individual experiences and leveraging technological innovation, we can advance towards more effective, accessible, and patient-centric pain management solutions.



References:
1. Wade DT. What is rehabilitation? An empirical investigation leading to an evidence-based description. Vol. 34, Clinical Rehabilitation. SAGE Publications Ltd; 2020571–83.


2. Institute of Medicine (U.S.). Committee on Advancing Pain Research C. Relieving Pain in America : a Blueprint for Transforming Prevention, Care, Education, and Research. National Academies Press; 2011.


3. Dowell D, Ragan KR, Jones CM, Baldwin GT, Chou R. Prescribing Opioids for Pain — The New CDC Clinical Practice Guideline. New England Journal of Medicine 2022;387(22):2011–3.


4. Keefe FJ, Rumble ME, Scipio CD, Giordano LA, Perri LCM. Psychological aspects of persistent pain: Current state of the science. Vol. 5, Journal of Pain. Churchill Livingstone Inc.; 2004195–211.


5. Devan H, Farmery D, Peebles L, Grainger R. Evaluation of Self-Management Support Functions in Apps for People With Persistent Pain: Systematic Review. Vol. 7, JMIR mHealth and uHealth. JMIR Publications Inc.; 2019.


6. Jackson T, Wang Y, Wang Y, Fan H. Self-efficacy and chronic pain outcomes: A meta-analytic review. Vol. 15, Journal of Pain. Churchill Livingstone Inc.; 2014800–14.


7. Halford GS, Baker R, McCredden JE, Bain JD. How many variables can humans process? Psychol Sci 2005;16(1):70–6.