Running live at AIIMS Patna. A three-stage CNN pipeline reads a urine dipstick from a smartphone camera — 90%+ accuracy vs lab, 70–80% lower cost per test. APIIC + NIDHI-DST funded · CDSCO TRL 4→6 · HIPAA-aligned architecture · WHO IMCI-aligned · transferable to any LMIC or academic clinical network.
The mobile app captures the dipstick image under standardised LED lighting. Stage 1 CNN on-device detects the strip. EXIF metadata is stripped. A TLS 1.3 upload goes to ap-south-1. Stage 2 segmentation runs in the secure cloud. Stage 3 classification (NEG / 1+ / 2+ / 3+ / 4+) returns with confidence. BLE BP/weight streams in parallel. The REDCap clinical CRF stores results anonymised by 6-digit PIN.
android · ios app + bluetooth bp cuff
↓ tls 1.3
stage 1 detection → stage 2 segmentation → stage 3 classification
↓
confidence floor · pin anonymisation
↓
redcap crf · ap-south-1 only
Smartphone-based AI urine dipstick + IoT vitals for children with nephrotic syndrome. Validated with the paediatrics team at AIIMS Patna. APIIC + NIDHI-DST funded. 90%+ accuracy vs lab, 70–80% cost cut, TRL 4→6.
Read the case →Two to three weeks. $6K–$12K. A written scorecard with topology recommendation, cost ranges, and remediation plan. No commitment to build.