Medical-AI trial: smartphone photo of the inner eyelid + AI to detect anemia non-invasively (NiADA / AnemiAI) vs. blood draw (3,000 participants) (NCT07678762)
A multicenter prospective study evaluating the diagnostic accuracy of NiADA, an app that photographs the lower eyelid conjunctiva with a smartphone and uses AI to estimate hemoglobin and detect anemia non-invasively, compared with the standard venous blood draw. Sensitivity and specificity are the primary endpoints. Target 3,000.
Trial overview (primary data)
- StatusActive, not recruiting
- ConditionsAnemia (Diagnosis), Anemia
- InterventionsDEVICE: AnemIA App
- SponsorFabio Biscegli Jatene
- Target enrollment3,000 participants
- Period2026-03-02 〜 2026-12-31
Key points
- An accuracy evaluation of NiADA, which photographs the lower eyelid conjunctiva by smartphone and uses AI to estimate hemoglobin and detect anemia non-invasively.
- The reference is the standard venous blood draw; the app result is compared with a draw taken within four hours.
- Primary endpoints are the sensitivity and specificity of anemia detection; multicenter, prospective, target 3,000.
- Anemia is easily missed and has a large impact on surgical, vulnerable, and underserved populations.
- Aimed at rapid screening where a blood draw and lab are unavailable; an accuracy stage, not an establishment of effectiveness.
Anemia is a shortage of hemoglobin in the blood that causes fatigue and shortness of breath, with an especially large impact on people undergoing surgery or with limited access to care. Though common, it is easily missed because confirmation requires a blood draw and a laboratory.
The NiADA app that this study evaluates tries to replace that confirmation non-invasively: it photographs the color of the inner lower eyelid (the palpebral conjunctiva) with a smartphone camera and uses AI to estimate hemoglobin from the image.
Per the registry summary, the study is multicenter and prospective: a trained healthcare professional photographs the lower conjunctiva with a smartphone camera and records the app (NiADA) estimate on the spot. That result is then compared with a standard venous blood draw performed within four hours to evaluate the diagnostic accuracy of the app. The primary endpoints are the sensitivity and specificity of anemia detection. The target is 3,000 participants, run as a researcher-initiated study.
Conjunctival pallor has long been a clue to anemia, but the judgment is subjective and variable. If a smartphone image and AI can turn it into a number, anemia might be flagged quickly even where a blood draw and laboratory are unavailable, with potential use in resource-limited areas and in home or preoperative screening.
That said, this study is an accuracy evaluation against the blood-draw standard; it does not establish the effectiveness of the app or replacement of blood testing.
Why it matters
Non-invasive screening via smartphone image plus AI is an area expected to enable early detection where a blood draw and lab are unavailable. It has potential in resource-limited areas and home or preoperative settings, and offers a window into how such accuracy is validated (this trial is an accuracy evaluation, not an establishment of effectiveness).
FAQ
Why photograph the inner eyelid (conjunctiva)?
Can the app diagnose anemia without a blood draw?
Sources (primary)
Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.
- ClinicalTrials.gov (study record, original)
- NCT ID: NCT07678762