Evaluation of the Clinical Impact of a Smartphone Application for Cataract Detection
Bibliographic record
Abstract
Background Approximately 10 million people in India suffer from bilateral blindness, with cataracts accounting for roughly 70% of these cases. However, there is a severe scarcity of ophthalmologists in India (12,000 across the country), which makes routine cataract screening very difficult, particularly in rural areas. To tackle this problem, we investigated the use of an artificial intelligence (AI)-based application for cataract screening at All India Institute of Medical Sciences (AIIMS), Bibinagar, that can be used by nursing officers and other healthcare professionals as a primary screening tool. Ophthalmologists from AIIMS Bibinagar additionally validate the results of this application. Purpose The aim of this study was to assess the clinical performance of a smartphone-based cataract screening application that uses an AI module to identify cataracts in photos taken with the device's camera. The study compared the application's results with diagnoses made by ophthalmologists using a slit lamp. Methods At AIIMS Bibinagar, 495 patients participated in a prospective clinical trial. The AI-based screening solution examined smartphone images that were taken in accordance with a set protocol to identify whether cataracts were present. The results of the application were then compared with the diagnoses made by ophthalmologists based on slit-lamp tests. Results The study included 990 eye images. The AI screening application demonstrated an overall accuracy of 90.01% for cataract detection. Specific metrics include a sensitivity of 89.50%, specificity of 89.73%, precision of 91.43%, and an F1 score of 90.36%. The positive predictive value (PPV) was approximately 91.3%, based on 485 true positives and 46 false positives. The negative predictive value (NPV) was approximately 87.6%, based on 402 true negatives and 57 false negatives. Conclusions The smartphone-based cataract screening application proves to be an effective tool for community-level cataract screening in remote areas where access to expensive equipment and specialized ophthalmic care is limited. Its high accuracy and efficiency make it a valuable option for low-resource settings and suitable for home screening, particularly in the post-COVID era.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".