Impact of Social Determinants of Health and Demographics on Refill Requests by Medicare Patients Using a Conversational Artificial Intelligence Text Messaging Solution: Cross-Sectional Study

Abstract

BackgroundNonadherence among patients with chronic disease continues to be a significant concern, and the use of text message refill reminders has been effective in improving adherence. However, questions remain about how differences in patient characteristics and demographics might influence the likelihood of refill using this channel.ObjectiveThe aim of this study was to evaluate the efficacy of an SMS-based refill reminder solution using conversational artificial intelligence (AI; an automated system that mimics human conversations) with a large Medicare patient population and to explore the association and impact of patient demographics (age, gender, race/ethnicity, language) and social determinants of health on successful engagement with the solution to improve refill adherence.MethodsThe study targeted 99,217 patients with chronic disease, median age of 71 years, for medication refill using the mPulse Mobile interactive SMS text messaging solution from December 2016 to February 2019. All patients were partially adherent or nonadherent Medicare Part D members of Kaiser Permanente, Southern California, a large integrated health plan. Patients received SMS reminders in English or Spanish and used simple numeric or text responses to validate their identity, view their medication, and complete a refill request. The refill requests were processed by Kaiser Permanente pharmacists and support staff, and refills were picked up at the pharmacy or mailed to patients. Descriptive statistics and predictive analytics were used to examine the patient population and their refill behavior. Qualitative text analysis was used to evaluate quality of conversational AI.ResultsOver the course of the study, 273,356 refill reminders requests were sent to 99,217 patients, resulting in 47,552 refill requests (17.40%). This was consistent with earlier pilot study findings. Of those who requested a refill, 54.81% (26,062/47,552) did so within 2 hours of the reminder. There was a strong inverse relationship (r10=−0.93) between social determinants of health and refill requests. Spanish speakers (5149/48,156, 10.69%) had significantly lower refill request rates compared with English speakers (42,389/225,060, 18.83%; X21 [n=273,216]=1829.2; P<.001). There were also significantly different rates of refill requests by age band (X26 [n=268,793]=1460.3; P<.001), with younger patients requesting refills at a higher rate. Finally, the vast majority (284,598/307,484, 92.23%) of patient responses were handled using conversational AI.ConclusionsMultiple factors impacted refill request rates, including a strong association between social determinants of health and refill rates. The findings suggest that higher refill requests are linked to language, race/ethnicity, age, and social determinants of health, and that English speakers, whites, those younger than 75 years, and those with lower social determinants of health barriers are significantly more likely to request a refill via SMS. A neural network–based predictive model with an accuracy level of 7...

A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects

“…Of the 82 studies, 80% used survey data (n = 66), followed by text (n = 11) and map and image (n = 4) data. Conway et al used text in electronic health records to extract social risk factors ( Conway et al, 2019 ), Robson and Boray combined data mining and prediction algorithms to predict the length of stay in the hospital ( Robson and Boray, 2019 ), Prayaga et al evaluated the efficacy of sending text message reminders to Medicare patients ( Prayaga et al, 2019 ), and Crossley et al used natural language processing to identify health literacy in patients with diabetes ( Crossley et al, 2020 ). Larkin ( Larkin & Hystad, 2019 ) used a map (e.g., Google Street View) with deep convolutional neural networks to estimate environmental exposures using images.…”

“…Clinical studies can be defined by the study setting (e.g., within the hospital) and the situation of an interaction with a doctor but not by clinical outcomes. To give an example, we considered the study of Prayaga et al as eligible even though it used clinical data, because it focused on SDH ( Prayaga et al, 2019 ). We included peer-reviewed publications to include only reliable evidence, and we did not include conference abstracts, letters, or notes.…”

“…Violence prevention and poverty-reduction measures would likely improve childhood cognitive outcomes. ( Prayaga et al, 2019 ) 2019 To evaluate the efficacy of an SMS-based refill reminder solution using conversational artificial intelligence Data curation, Prediction Text United States 273356 Medication refill request Neural network multilayer perceptron There are sharp differences in the likelihood to reply to a refill reminder and complete a refill request via SMS based on demographic and socioeconomic factors. We found a strong association between refill request rates and patient language, age, race/ethnicity, and SDOH levels, and these differences may contribute to health disparities and impact health outcomes in Medicare patients.…”

Including Social and Behavioral Determinants in Predictive Models: Trends, Challenges, and Opportunities

“…Similarly, SBDH-oriented predictive models using newer applications of machine learning techniques have shown varying levels of performance in predictions. A neural network predictive model that incorporates SBDH was found to identify, with 78% accuracy, over two-third of the Medicare patients in their sample who would not respond to automated medication refill requests and may benefit from targeted outreach [ 45 ]. Seligman et al [ 46 ] applied linear regression and different machine learning techniques to predict systolic blood pressure, BMI, waist circumference, and telomere length using SBDH variables of gender, income, wealth, education, public benefits, family structure, and health behaviors.…”

Mobile Fotonovelas Within a Text Message Outreach: An Innovative Tool to Build Health Literacy and Influence Behaviors in Response to the COVID-19 Pandemic

“…The mPulse Mobile platform delivers text messages to patients and members on behalf of health care companies. The platform consists of several components that collectively enable companies to interactively engage with their end users about appointments, refills, gaps in care, or other health-related topics [ 22 ]. This was our first use of a mobile fotonovela to share important health information to address health beliefs, build self-efficacy, and influence health behaviors.…”