Better Care Pathways: AI Qualitative Analysis in Healthcare

According to the PLoS ONE SYNC-RF study protocol, AI qualitative analysis in healthcare can support the structured synthesis of interviews, surveys, facility assessments, and literature when researchers maintain human oversight. The protocol examines how referral and follow-up systems affect continuity of care for people living with multiple long-term conditions in India.

• The SYNC-RF programme, published on November 3, 2026, uses three linked phases: a systematic review, a district-level mixed-methods assessment, and development of an integrated referral and follow-up model.
• The study plans to assess 20 Primary Health Centres, with 10 rural and 10 urban facilities, together with linked Community Health Centres and a district hospital.
• The patient survey target is 600 adults aged 30 years and above with two or more chronic conditions, with referral completion assessed within 30 days.
• The qualitative component plans approximately 10 interviews each with patients, caregivers, and healthcare providers, plus 4 to 6 interviews with state or district health officials.
• The protocol states that qualitative data will be analyzed through reflexive thematic analysis, while quantitative and qualitative findings will be integrated through triangulation and a joint display matrix.

The SYNC-RF protocol uses sequential, multistage mixed methods to understand referral and follow-up for multiple long-term conditions in an Indian district. According to the PLoS ONE protocol, Phase 1 synthesizes global evidence, Phase 2 combines facility assessment, patient surveying, and in-depth interviews, and Phase 3 develops and refines the SYNC-RF model through expert consultation.

The protocol defines multiple long-term conditions as the coexistence of two or more chronic conditions and identifies fragmented referrals, weak counter-referral communication, and inadequate follow-up as research problems. The protocol describes referrals as often informal or poorly documented and states that missing follow-up can contribute to missed appointments, duplicated services, and delayed treatment.

The qualitative study will include patients with multiple long-term conditions, caregivers, healthcare providers, and health officials. According to the protocol, interviews are expected to last 30 to 45 minutes, will be conducted in English or a local language, and will be audio-recorded with consent.

The protocol says that transcripts will be read repeatedly, coded with deductive and inductive codes, grouped into sub-themes and broader themes, and discussed within the research team. The authors describe this purpose as generating “context-specific evidence on gaps, barriers, and enabling factors affecting referral and follow-up for MLTC care.”

AI qualitative analysis can assist these steps by accelerating transcription review, suggesting consistent code labels, clustering similar excerpts, and making comparisons across patient, caregiver, provider, and policymaker interviews. Researchers must still review the source excerpts, assess cultural and translation nuance, and make the final thematic decisions.

The SYNC-RF protocol demonstrates how healthcare researchers can combine systematic evidence, facility data, patient surveys, and stakeholder interviews to study continuity of care for multiple long-term conditions. AI qualitative analysis can make that evidence base easier to search, compare, and synthesize, but human researchers must retain control over interpretation and ethical decisions. A structured platform can help teams move from raw transcripts to defensible themes and cross-segment insights more efficiently. Try Evidano for free to analyze qualitative documents and survey responses in one research workspace.