Figure - available from: Quality of Life Research
This content is subject to copyright. Terms and conditions apply.
Source publication
Purpose
The Patient-Reported Outcomes Measurement Information System® (PROMIS)-16 assesses the same multi-item domains but does not include the pain intensity item in the PROMIS-29. We evaluate how well physical and mental health summary scores estimated from the PROMIS-16 reproduce those estimated using the PROMIS-29.
Methods
An evaluation of dat...
Citations
... These scales may be monitored with the help of AI as seen in other patient reported outcome measurement scores. 9 AI-powered chatbots may also improve treatment plans and offer immediate access to information. 10 Utilizing AI in pain management can improve patient care by alleviating anxieties, promoting adherence, and facilitating a relationship between patients and physicians. ...
Artificial Intelligence (AI) has the potential to optimize personalized treatment tools and enhance clinical decision-making. However, biases in AI, arising from sex, race, socioeconomic status (SES), and statistical methods, can exacerbate disparities in pain management. This narrative review examines these biases and proposes strategies to mitigate them. A comprehensive literature search across databases such as PubMed, Google Scholar, and PsycINFO focused on AI applications in pain management and sources of biases. Sex and racial biases often stem from societal stereotypes, underrepresentation of females, overrepresentation of European ancestry patients in clinical trials, and unequal access to treatment caused by systemic racism, leading to inaccurate pain assessments and misrepresentation in clinical data. SES biases reflect differential access to healthcare resources and incomplete data for lower SES individuals, resulting in larger prediction errors. Statistical biases, including sampling and measurement biases, further affect the reliability of AI algorithms. To ensure equitable healthcare delivery, this review recommends employing specific fairness-aware techniques such as reweighting algorithms, adversarial debiasing, and other methods that adjust training data to minimize bias. Additionally, leveraging diverse perspectives—including insights from patients, clinicians, policymakers, and interdisciplinary collaborators—can enhance the development of fair and interpretable AI systems. Continuous monitoring and inclusive collaboration are essential for addressing biases and harnessing AI’s potential to improve pain management outcomes across diverse populations.
Purpose
This longitudinal study evaluates whether the Patient-Reported Outcomes Measurement and Information System (PROMIS)-16 domains capture average change over time comparable to the PROMIS-29 + 2 and have similar associations with change in overall health rating and two disability indices.
Methods
Data were collected using Amazon’s Mechanical Turk at baseline, 3 months, and 6 months among individuals reporting chronic low back pain. The analytic sample includes respondents who completed baseline and at least one follow-up assessment (N = 1137). We estimated latent growth models for eight PROMIS domains and compared growth parameters between the PROMIS-16 and PROMIS 29 + 2 with a z-test. Additionally, for each domain, random intercept and slope scores for individuals were computed for the PROMIS-29 + 2 and PROMIS-16 and correlated to estimate concordance. Using growth parameters for physical function and pain interference, we predicted average change in the Oswestry Disability Index (ODI), Roland Morris Disability Questionnaire (RMDQ), the overall health rating, and compared regression coefficients between the PROMIS-16 and PROMIS 29 + 2.
Results
All growth models fit the data well. Intercept and slope parameters were statistically comparable (p’s > 0.05) in magnitude across all domains between the PROMIS-16 and PROMIS-29 + 2. Correlations between random intercept and slope scores for individuals across domains were high. Additionally, the regression coefficients between slopes for pain interference and physical function and ODI, RMDQ, and overall health rating were statistically comparable (p’s > 0.05) between the PROMIS-16 and PROMIS 29 + 2.
Conclusion
Results provide between-level support for the longitudinal and predictive validity of the PROMIS-16. Similar average baseline scores and changes over time were observed between PROMIS-16 and PROMIS-29 + 2. Further, average change estimates comparably predicted average change in distal outcomes. This work provides evidence supporting the utility of the PROMIS-16 as a viable, short-profile option for use in clinical and research settings.
