AnemiaVision: Non-Invasive Anemia Detection via Smartphone Imagery Using EfficientNet-B3 with TrivialAugmentWide, Mixup Augmentation, and Persistent Patient History Management

2026-04-24

AI Summary

This study addresses the challenge of anemia underdiagnosis in low-resource settings due to limited access to laboratory testing by proposing a non-invasive screening system based on smartphone-captured images. The system analyzes photographs of the palpebral conjunctiva and nail beds using an EfficientNet-B3 backbone enhanced with TrivialAugmentWide, RandomErasing, Mixup data augmentation, cosine annealing learning rate scheduling, and an efficient classification head. Evaluated on a validation set, it achieves 96.2% accuracy, 0.98 AUC-ROC, and 96% sensitivity—substantially outperforming baseline models (44.9%). Key innovations include an accuracy-prioritized early stopping strategy, a zero-data-loss automated database migration architecture, and integrated patient history management. The backend, implemented in Flask and deployed on the Render platform, enables rapid frontline anemia screening in rural areas.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Non-convex Optimization

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Anemia affects over one billion people globally and remains severely under-diagnosed in low-resource regions where laboratory blood tests are inaccessible. This paper presents AnemiaVision, an end-to-end web-based system for non-invasive anemia screening from smartphone photographs of the palpebral conjunctiva and fingernail beds. The proposed pipeline fine-tunes a pre-trained EfficientNet-B3 backbone with a redesigned three-layer classifier head incorporating BatchNorm, GELU activations, and high-rate Dropout (0.45/0.35). Training employs four orthogonal accuracy-boosting techniques: TrivialAugmentWide for policy-free image augmentation, RandomErasing for spatial regularisation, Mixup (alpha=0.2) for inter-class smoothing, and cosine-annealing scheduling with linear warmup. Early stopping is governed by peak validation accuracy rather than validation loss to prevent premature termination on high-variance epochs. The deployed Flask application integrates persistent patient-history management backed by PostgreSQL on Render, with an automated database-migration entrypoint ensuring zero data loss across redeploys. Ablation experiments demonstrate that accuracy-first early stopping contributes +1.6% and Mixup contributes +2.8% to final validation accuracy. Overall, the proposed system achieves a validation accuracy of 96.2% and AUC-ROC of 0.98, compared with 44.9% validation accuracy and AUC-ROC of 0.58 from the three-epoch CPU-only baseline. Sensitivity for the anemic class reaches 0.96, making the system suitable as a first-line screening tool for community health workers in rural settings. The system is publicly accessible and source code is openly available.

Problem

• anemia
• non-invasive detection
• low-resource settings
• under-diagnosis
• smartphone-based screening

Innovation

• EfficientNet-B3
• TrivialAugmentWide
• Mixup
• accuracy-first early stopping
• persistent patient history