A 'Silent Trial' Assessing the Accuracy of Large Language Models for Assisting Community Health Workers in Low-Resource Settings

This study evaluating Large Language Models in Rwanda found that while OpenAI's o3 matched the high referral accuracy of local community health workers, Google's Gemini Flash 2.5 performed poorly, suggesting that model selection is critical and that LLMs may offer limited immediate benefit in well-established programs but could support less mature initiatives.

Shimelash, N., Rutunda, S., Menon, V. + 16 more2026-02-17📄 primary care research

Teleconferencing as an alternative to written Advice and Guidance referrals at the primary-secondary care interface: a qualitative case study

This qualitative case study suggests that teleconferencing serves as a promising alternative to written Advice and Guidance referrals by enhancing GP-specialist relationships, improving patient care continuity, and reducing unnecessary outpatient referrals, though further research is needed to confirm its cost-effectiveness and long-term sustainability.

He, S., Usher-Smith, J., Martin, G.2026-02-16📄 primary care research

Improving cardiovascular population risk in primary care: protocol for the PROSPERA cluster-randomized controlled trial of a complex multilevel intervention

The PROSPERA study is a pragmatic cluster-randomized controlled trial in the Netherlands designed to evaluate the real-world effectiveness of a multilevel intervention—comprising risk stratification, professional training, a lifestyle questionnaire, and a clinical decision support tool—in improving cardiovascular risk management outcomes among primary care patients compared to usual care.

Bongaerts, V. A. M. C., Vos, R. C., Hageman, S. H. J. + 4 more2026-02-16📄 primary care research