JEEVHITAA -- An End-to-End HCAI System to Support Collective Care

TL;DR

JEEVHITAA tackles the collective-care deficit in mobile health by treating care circles as the unit of design and embedding role-aware, auditable coordination into an end-to-end platform. It integrates a cross-platform Flutter client, on-device canonical ontology with versioned profiles, encrypted local and cloud stores, and a dual retrieval-augmented LLM pipeline for insights and verification, all under fine-grained, time-bounded access controls. Through ontology-driven synthetic simulations and broad vendor compatibility tests, the approach demonstrates robust summary fidelity, provenance accuracy, and secure information flows, with a four-week feasibility pilot indicating practical usability and safety. The work offers a practical blueprint for privacy-preserving multi-actor health coordination and lays groundwork for longitudinal deployments to evaluate real-world effectiveness of relationship-aware credibility support.

Abstract

Current mobile health platforms are predominantly individual-centric and lack the necessary primitives for coordinated, auditable, multi-actor workflows. However, in many settings worldwide, health decisions are enacted by multi-actor care networks rather than single users. We present JEEVHITAA, an Android/Flutter system that provides context-sensitive, role-aware sharing and verifiable information flows for care circles. JEEVHITAA ingests platform and device data (via Google Health Connect and BLE connectors), constructs multi-layer user profiles from sensor streams and tiered onboarding, and enforces fine-grained, time-bounded access control across permissioned care graphs. Data are end-to-end encrypted in local stores and during peer sync (Firebase), and provisions are made for document capture by camera or upload as PDF. An integrated retrieval-augmented LLM pipeline (i) produces structured, role-targeted summaries and action plans, (ii) enables users to gather advanced insights on health reports, and (iii) performs evidence-grounded user-relevant verification of arbitrary health content, returning provenance, confidence scores, and source citations. We describe the system architecture, connector abstractions, and security primitives, and evaluate robustness and compatibility using synthetic, ontology-driven simulations and vendor compatibility tests. Finally, we outline plans for longitudinal in-the-wild deployments to measure system performance, the correctness of access control, and the real-world effectiveness of relationship-aware credibility support.

Figures (4)

• Figure 1: Sample figma prototype.
• Figure 2: End-to-end architecture of JEEVHITAA
• Figure 3: Android Interface - Profile, Sharing Controls Flow, Care Circles, and Shared Summary.
• Figure 4: Android Interface - AI Assistance and Health Information Verification Engine.