Publications

Telehealth became a new norm in healthcare following the COVID-19 pandemic. This study evaluates the relationship between state telehealth payment parity legislation and health service utilization among insured workers in commercial insurance plans, finding that payment parity significantly increased telehealth visits and total outpatient visits without reducing in-person care.

State-level telehealth payment parity laws require equal reimbursement for telehealth and in-person visits. This study evaluates how payment parity affected utilization of disease-specific recommended care and emergency department services among insured patients with chronic mental health disorders and cardiometabolic risks, finding significant increases in psychotherapy visits and reductions in ED visits for mental health.

Generative artificial intelligence (AI) can exhibit biases, compromise data privacy, misinterpret prompts that are adversarial attacks, and produce hallucinations. Despite the potential of generative AI for many applications in digital health, practitioners must understand these tools and their limitations. This scoping review pays particular attention to the challenges with generative AI technologies in medical settings and surveys potential solutions. Using PubMed, we identified a total of 120 articles published by March 2024, which reference and evaluate generative AI in medicine, from which we synthesized themes and suggestions for future work. After first discussing general background on generative AI, we focus on collecting and presenting 6 challenges key for digital health practitioners and specific measures that can be taken to mitigate these challenges. Overall, bias, privacy, hallucination, and regulatory compliance were frequently considered, while other concerns around generative AI, such as overreliance on text models, adversarial misprompting, and jailbreaking, are not commonly evaluated in the current literature.

A comprehensive, collective approach to navigating the challenges of bias, privacy, and ethical considerations presented by the use of artificial intelligence in health care will require robust frameworks, continuous learning, and a commitment to equity. The insights and discussions presented in this issue are a testament to the ongoing efforts in North Carolina and beyond to find a balance between innovation with responsibility, ensuring that AI can deliver on its promise to enhance outcomes.

Infectious disease surveillance is difficult in many low- and middle-income countries. Information market (IM)–based participatory surveillance is a crowdsourcing method that encourages individuals to actively report health symptoms and observed trends by trading web-based virtual "stocks" with payoffs tied to a future event. This study aims to assess the feasibility and acceptability of a tailored IM surveillance system to monitor population-level COVID-19 outcomes in Accra, Ghana. We designed and evaluated a prediction markets IM system from October to December 2021 using a mixed methods study approach. Using an IM system for disease surveillance is feasible and acceptable in Ghana. This approach shows promise as a cost-effective source of information on disease trends in low- and middle-income countries where surveillance is underdeveloped.

Clinical decision support systems must balance comprehensive information with cognitive load. This paper introduces Dynamic Information Sub-Selection (DISS), a method for optimizing which information to present to clinicians during decision-making. DISS uses machine learning to dynamically select the most decision-relevant information, reducing cognitive burden while maintaining or improving diagnostic accuracy.

Telemedicine has experienced rapid growth as an alternative care venue, particularly in China where it has become increasingly integrated into the healthcare system. This study develops and applies innovative approaches to measure care quality in China's telemedicine market, providing evidence on provider behavior and patient outcomes in virtual care settings.

Telemedicine has expanded access to care for sensitive health conditions including sexually transmitted infections. Using standardized patients, this study evaluates the quality of telemedicine consultations for STIs in China, examining diagnostic accuracy, treatment recommendations, and patient communication.

Mobile health (mHealth) interventions offer promising approaches for diabetes management in resource-limited settings. This cluster randomized controlled trial evaluates the effectiveness of an mHealth-supported healthy future programme for improving type 2 diabetes outcomes among patients in Nairobi, Kenya.

Digital technologies offer new opportunities for community engagement in clinical trials research. This paper reviews digital approaches to enhancing community participation, examining how social media, mobile apps, and online platforms can improve recruitment, retention, and meaningful involvement of community stakeholders in research.

Digital health kiosks offer potential to improve healthcare access in rural areas. This study evaluates a village-based digital health kiosk program in rural China through two cluster-randomized controlled trials, examining effects on care quality, utilization, and health outcomes in underserved communities.

Telemedicine offers potential to address healthcare access disparities in rural areas. This qualitative study explores the factors influencing the adoption and use of telemedicine services among primary care physicians and patients in rural China, identifying barriers and facilitators to implementation.

Digital network-based methods may enhance peer distribution of HIV self-testing kits. This three-arm randomized controlled trial evaluated whether monetary incentives and peer referral could improve secondary distribution of HIV self-testing among men who have sex with men in China, finding that both interventions significantly increased testing uptake and reached first-time testers.

Objective: To examine the responsiveness of primary care providers to pro-social and financial incentives to participate in a learning collaborative for the treatment of opioid use disorder (OUD). Study setting: We conducted a statewide experiment in North Carolina from January 2019 to November 2019 to expand access to support for providers learning to treat opioid use disorder using different types of messaging and incentives. Study design: We randomly assigned 15,835 primary care providers (physicians, nurse practitioners, and physician assistants) in North Carolina to receive one of four letters recruiting providers to participate in an online learning collaborative. Principal findings: We found a 47.5% greater response rate when pro-social messaging was included compared to when it was not.

This study uses standardized patients (actors trained to portray patients with specific symptoms) to measure the quality of tuberculosis care provided by village clinicians and township health center physicians in rural China. The study reveals significant gaps in care quality and highlights the challenges of integrating infectious disease detection into primary care systems in low-resource settings.

Mobile health interventions including text message reminders can improve adherence to health interventions. This cluster-randomized controlled trial evaluated the impact of SMS reminders on caregivers' adherence to a home fortification program for preventing childhood anemia in rural western China, demonstrating significant improvements in supplement use.