Cost-Effective Deep Learning Framework for Automated Thalassemia Screening in Resource-Limited Settings
Bibliographic record
Abstract
Thalassemia is an inherited blood disorder characterized by defective globin chain synthesis, leading to reduced hemoglobin production. It is classified mainly into alpha- and beta-thalassemia. This study aims to leverage deep learning models to detect thalassemia using three methods, Multilayer Perceptron (MLP), a Residual MLP (ResMLP), and TabNet model. The dataset used was publicly available, sourced from a screening test conducted in India and had 13021 records with three study groups (normal, thalassemia and other hemoglobinopathies). After data preprocessing, feature scaling, and splitting, model performance was evaluated. Residual MLP model achieved 99.69% accuracy and 97% F1 score, which was the highest among all models. Furthermore, the multiclass MLP model has also shown comparative results with 99.62% accuracy and 96% F1 score validating the model's ability to predict thalassemia effectively. However, Tabnet model showed the highest recall of 99% but lowest accuracy and F1score of 99.19% and 92% respectively. The results indicate that the Residual MLP model outperformed other models with superior accuracy and F1 score, demonstrating its robustness in predicting thalassemia. Also, comparable results from the multiclass MLP models further validate the reliability of deep learning approaches for thalassemia screening potentially in a clinical setting
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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) | 0.002 | 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 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".