Study protocol: A Chat-Based Decision Support System for a Maternal Health Journey in Assam, India (Preprint)

BACKGROUND Assam, India, exhibits the highest maternal mortality ratio in the nation (195 per 100,000 live births, nearly twice the national average), primarily due to ongoing deficiencies in access to and quality of maternal health (MH) care. Many women receive suboptimal antenatal (ANC) and postnatal care (PNC), challenges exacerbated by geographic isolation, socio-economic constraints, and limited healthcare infrastructure. Digital health innovations, notably mobile health (mHealth) interventions such as messaging platforms and chatbots, have demonstrated potential in enhancing ANC attendance and promoting facility-based deliveries in resource-constrained environments. To address these persistent challenges, the e-SAATHI (Strengthening ANC/PNC via AskNivi Tailored Health Information, Referrals, and Follow-up) project was developed to deliver personalized, stage-specific MH support using a chat-based decision system in Assam. OBJECTIVE This study assesses the acceptability, feasibility, and effectiveness of the e-SAATHI chatbot in increasing women's access to maternal health information and improving ANC and PNC service uptake across public and private facilities. Objectives include increasing ANC/PNC use (e.g., ≥4 ANC visits, timely postnatal care), promoting respectful care, and gathering insights for scaling digital health in high-burden regions. METHODS Phase 1 (0–3 months): Co-design and pilot testing aligned with WHO and national guidelines. Phase 2 (4–24 months): Enroll pregnant and postpartum women via health facilities and social media. The chatbot sends 2–3 messages weekly from 10 weeks pregnancy to 15 weeks postpartum. About 300 healthcare providers will be trained and engaged for onboarding and feedback. Phase 3 (25–36 months): Scale-up across districts, reaching 225,000 women. Data collection includes interviews, surveys, facility assessments, and chatbot analytics. Qualitative analysis will explore experiences; quantitative data (ANC completion, facility delivery, PNC follow-up, satisfaction) will compare pre- and post-intervention. Ethical approvals, informed consent, and data confidentiality are observed. RESULTS As this protocol outlines a planned intervention, final results are pending completion. The study will report changes in key maternal health indicators (including ANC attendance and institutional delivery rates) as well as user-reported outcomes (knowledge acquisition, adoption of self-care practices, and care satisfaction). Furthermore, operational feasibility—encompassing provider integration and encountered barriers such as digital literacy and connectivity issues—will be detailed. Ongoing CLA cycles are expected to capture intervention adaptations and inform optimal strategies for scale-up. CONCLUSIONS e-SAATHI offers a scalable digital approach to improve MH in high-risk settings. By delivering timely, personalized support, the chatbot may enhance health-seeking behavior and outcomes in Assam and similar low-resource areas globally. CLINICALTRIAL None