Participants in this arm receive a nurse-led primary care consultation supported by a large language model (LLM)-based clinical decision support tool. During the consultation, a trained nurse conducts routine history taking and clinical assessment and engages in a multi-turn interaction with the LLM via a digital interface to support differential diagnosis, clinical reasoning, and evidence-based treatment and follow-up planning. The nurse may ask additional questions of the patient based on LLM prompts. The final clinical recommendations are generated collaboratively by the nurse using the LLM outputs and documented as a treatment plan. This arm evaluates whether AI-assisted nurse-led care can deliver clinical quality comparable to standard physician-led care in primary health settings.

The doctor consultation represents standard-of-care clinical management that is already known and accepted to be effective for diagnosing and treating the study conditions. It is an active clinical intervention, not a placebo, sham, or no-intervention arm, and it serves as the comparator against the experimental nurse + LLM intervention.

A nurse-led primary care consultation supported by a large language model-based clinical decision support tool. The nurse uses the AI tool during the patient encounter to support clinical reasoning, differential diagnosis, and evidence-based treatment and follow-up planning.

This outcome assesses the quality of clinical care by comparing AI-assisted, nurse-led consultations with standard physician-led consultations. For patients with hypertension or diabetes mellitus, clinical quality is measured using a clinical management rubric with a raw score range of -2 to 7, assessing data review, complication screening, medication adherence, counseling, and treatment planning, with penalties for inappropriate counseling or treatment. For patients presenting with fever, breathlessness, or musculoskeletal pain, clinical quality is measured using a clinical reasoning rubric with a raw score range of -5 to 10, assessing differential diagnoses, final diagnosis, and next steps, with negative scores for harmful recommendations. Consultations are audio recorded, de-identified, and scored by blinded physicians. Higher scores indicate better alignment with evidence-based, context-appropriate care.

Composite patient experience score derived from an 9-item Likert-scale exit survey adapted from the WHO Health System Responsiveness framework and PSQ-18. Items assess communication, understanding, dignity/respect, trust in AI use, and overall satisfaction. Responses are scored 1-5 per item and averaged to generate a composite score (range 1-5), with higher scores indicating more positive experience.