Better Care Insights: AI Qualitative Analysis in Healthcare

The SYNC-RF study protocol in PLoS ONE proposes a three-phase mixed-methods programme to understand referral and follow-up for people living with multiple long-term conditions in India. The protocol uses qualitative interviews, reflexive thematic analysis, facility assessments, and a patient survey to inform an integrated care model.

• According to the SYNC-RF protocol published on November 3, 2026, the research has three phases: a systematic review, a district-level mixed-methods assessment, and development of the SYNC-RF referral and follow-up model.
• According to the protocol, the district assessment includes 20 Primary Health Centres, divided into 10 rural and 10 urban facilities.
• According to the protocol, the patient survey will recruit 600 adults aged 30 years and above who have two or more chronic conditions.
• According to the protocol, 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.
• According to the protocol, the research programme is expected to complete final integration, analysis, and reporting by the end of 2027.

The SYNC-RF protocol combines global evidence, local health-system measurement, and stakeholder experience to design a context-specific referral model. The authors describe the approach as a sequential, multistage mixed-methods design in which a systematic review informs a district assessment, and the integrated evidence then informs model development.

According to the protocol, the qualitative work will use semi-structured, in-depth interviews with adults living with multiple long-term conditions, caregivers, healthcare providers, and health officials. Interviews are expected to last 30 to 45 minutes, will be audio-recorded with consent, and will be conducted in English or the local language.

According to the protocol, researchers will transcribe interviews verbatim, translate local-language transcripts into English where necessary, retain original-language versions, and use reflexive thematic analysis. The analysis will combine deductive codes based on the study objectives with inductive codes emerging from participant accounts.

The authors state that the qualitative and quantitative findings will be integrated through a joint display matrix. The matrix will identify convergence, complementarity, and divergence between facility data, patient survey results, and stakeholder interviews rather than automatically treating one evidence source as more authoritative.

The SYNC-RF protocol describes its intended output as an “evidence-informed model that is contextually relevant, feasible, and suitable for subsequent feasibility and acceptability testing.” The statement describes a proposed research contribution, not an evaluated clinical intervention.

AI qualitative analysis can help healthcare research teams organize large volumes of interview and document data, while researchers retain responsibility for interpretation, reflexivity, and ethical judgment. The SYNC-RF protocol is a useful example because its design requires comparison across patients, caregivers, providers, officials, facilities, and evidence sources.

• Transcript preparation becomes more manageable when researchers must process interviews in English and local languages, while original-language transcripts remain available for checking meaning and cultural nuance.
• Thematic analysis becomes easier to audit when researchers preserve a visible path from transcript excerpts to codes, sub-themes, broader themes, and model requirements.
• Cross-segment analysis can compare patient, caregiver, provider, and policymaker accounts without losing the distinct perspective of each stakeholder group.
• Joint-display preparation can connect qualitative themes with quantitative indicators such as referral completion, counter-referral, follow-up within 30 days, and referral turnaround time.
• Divergence analysis can identify where patient accounts differ from provider descriptions, which the SYNC-RF protocol treats as an important finding rather than an error to be removed.

The SYNC-RF authors describe the goal of integration as identifying “areas of convergence, complementarity, and divergence.” AI can accelerate the organization and retrieval of evidence for that task, but healthcare researchers should review source excerpts, translation choices, coding decisions, and interpretations before using findings in policy or service design.

Healthcare research teams should also treat AI-assisted analysis as non-diagnostic and research-focused. The protocol received ethics approval from the Centre for Chronic Disease Control in New Delhi and the University of Leicester, and the protocol requires informed consent for participant involvement.

The SYNC-RF protocol demonstrates how healthcare researchers can combine qualitative interviews, facility assessments, patient surveys, and systematic review evidence to study continuity of care for multiple long-term conditions. AI qualitative analysis can reduce the manual burden of organizing multilingual transcripts, comparing stakeholder segments, and tracing themes into a mixed-methods model, while researchers remain accountable for interpretation and ethics. The protocol is still a plan as of November 3, 2026, so its proposed SYNC-RF model and expected outcomes require future implementation and evaluation. Research teams that want a structured way to analyze interviews, surveys, and healthcare documents can try Evidano for free.