Background: High-volume tertiary centers face significant challenges in Neisseria gonorrhoeae (NG) control due to "stigma-driven non-disclosure" and "counseling fatigue." NG also acts as a potent biological catalyst for HIV and other STIs, particularly in resource-constrained environments. We evaluated the SHAPE (Sexual Health Awareness, Promotion, and Evaluation) protocol, a multi-modular digital interface designed to optimize the NG care cascade through automated triage and AI-driven health promotion.
Methods: A prospective implementation study (N=100) was conducted at an apex STI center in New Delhi. The SHAPE framework utilized a QR-facilitated interface integrating: (1) Digital Triage: Discreet capture of urethral discharge symptoms and behavioral risk markers; (2) Clinical optimization: Real-time data summaries facilitating targeted screening for NG and common co-infections (Syphilis/HIV); (3) AI-Led Stewardship: Standardized modules on NG treatment adherence and antimicrobial resistance (AMR); and (4) e-Partner Notification (ePN): An anonymous referral system for presumptive treatment. Success was measured via the validated STD-KQ and partner recruitment rates.
Results: The digital protocol demonstrated superior diagnostic fidelity; 86% of participants disclosed high-risk behaviors overriding stigma-led non-disclosure during routine verbal history taking. (p < 0.05). The framework identified a 22% increase in suspected co-infections compared to routine care. Clinical literacy showed marked improvement: the mean STD-KQ score rose from a baseline of 11.6 ± 4.2 to 23.4 ± 2.8 (p < 0.05). Partner engagement was robust, with 82% index cases utilizing ePN, facilitating the clinical presentation of 1.6 partners per index patient. The follow-up adherence also increased from routine to 78%.
Conclusion: The SHAPE protocol demonstrates that digital anonymity is a potent catalyst for honest disclosure and effective partner management in NG control. By standardizing screening, counseling and antimicrobial stewardship with leveraging help of AI, this model could be beneficial for achieving WHO 2030 targets in resource-constrained settings.