Advancing Accuracy in Non-invasive Hemoglobin Estimation: A Comparative Clinical Study of the Performance of the Non-invasive Anemia Detection App (NiADA)
Bibliographic record
Abstract
BACKGROUND: Anemia remains a significant global health burden, particularly in low- and middle-income countries. Traditional hemoglobin screening methods are invasive, resource-intensive, and often impractical for large-scale or repeated population-level screening. The Non-invasive Anemia Detection App (NiADA, Monere AI Private Limited, Kolkata, West Bengal, India) provides a smartphone-based, artificial intelligence (AI)-powered alternative for estimating hemoglobin levels using images of the lower palpebral conjunctiva. OBJECTIVE: This study aims to evaluate the improvement in accuracy and clinical utility of NiADA version 3 compared to NiADA version 2 in estimating hemoglobin levels and detecting anemia across diverse demographic subgroups in a tertiary care setting. MATERIALS AND METHODS: This study was conducted at NRS Medical College and Hospital, Kolkata, India, from December 2024 to January 2025. A total of 2,476 participants (ages 2-90 years) were enrolled. Trained personnel captured partial facial images, focusing on the lower eyelid, using Android smartphones running NiADA version 3. The algorithm subsequently extracted the lower palpebral conjunctiva and surrounding scleral regions for automated analysis. Images underwent preprocessing and were analyzed in real time by the AI model. Venous blood samples were collected immediately after image capture in standard ethylenediamine tetraacetic acid anticoagulant tubes, and hemoglobin levels were measured using an automated hematology analyzer. Regression and classification performance were evaluated using Bland-Altman analysis, mean bias, Lin's concordance correlation coefficient (CCC), and confusion matrices. Subgroup analyses were performed for adult males, adult females, and children. RESULTS: NiADA exhibited strong agreement with laboratory-measured hemoglobin levels across all demographic subgroups, with Pearson correlation coefficients ranging from 0.81 to 0.86, Lin's CCC between 0.80 and 0.87, and R² values spanning 0.73 to 0.76. The mean bias remained within ±0.27 g/dL across cohorts. Bland-Altman analysis showed that over 95% of predictions fell within the limits of agreement for children (-2.07 to 2.46 g/dL), females (-2.48 to 2.64 g/dL), and males (-2.51 to 3.05 g/dL). In anemia classification, NiADA achieved the highest accuracy in adult females (88.7%), followed by children (84.4%) and adult males (81.2%). Sensitivity remained consistently high across all groups (≥88%), while specificity ranged from 71.8% to 76.1%. CONCLUSIONS: NiADA version 3 demonstrates strong accuracy and reliability as a non-invasive hemoglobin estimation tool, with performance comparable to that of conventional point-of-care devices. Its smartphone-based, consumable-free workflow makes it particularly well-suited for large-scale screening and longitudinal monitoring in both clinical and community settings. These results support NiADA's integration into public health initiatives targeting anemia surveillance and prevention.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.016 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".