[Paper Review] Beta Thalassemia Carriers detection empowered federated Learning

Muhammad Shoaib Farooq, Hafiz Ali Younas|arXiv (Cornell University)|Jun 2, 2023

Digital Imaging for Blood Diseases4 citations

TL;DR

This study proposes a federated learning (FL)-based model to detect beta-thalassemia carriers using complete blood count (CBC) and red blood cell indices, achieving 92.38% accuracy while preserving patient data privacy. The approach enables decentralized, privacy-preserving, and scalable screening with high performance and low cost compared to traditional HPLC methods.

ABSTRACT

Thalassemia is a group of inherited blood disorders that happen when hemoglobin, the protein in red blood cells that carries oxygen, is not made enough. It is found all over the body and is needed for survival. If both parents have thalassemia, a child's chance of getting it increases. Genetic counselling and early diagnosis are essential for treating thalassemia and stopping it from being passed on to future generations. It may be hard for healthcare professionals to differentiate between people with thalassemia carriers and those without. The current blood tests for beta thalassemia carriers are too expensive, take too long, and require too much screening equipment. The World Health Organization says there is a high death rate for people with thalassemia. Therefore, it is essential to find thalassemia carriers to act quickly. High-performance liquid chromatography (HPLC), the standard test method, has problems such as cost, time, and equipment needs. So, there must be a quick and cheap way to find people carrying the thalassemia gene. Using federated learning (FL) techniques, this study shows a new way to find people with the beta-thalassemia gene. FL allows data to be collected and processed on-site while following privacy rules, making it an excellent choice for sensitive health data. Researchers used FL to train a model for beta-thalassemia carriers by looking at the complete blood count results and red blood cell indices. The model was 92.38 % accurate at telling the difference between beta-thalassemia carriers and people who did not have the disease. The proposed FL model is better than other published methods in terms of how well it works, how reliable it is, and how private it is. This research shows a promising, quick, accurate, and low-cost way to find thalassemia carriers and opens the door for screening them on a large scale.

Motivation & Objective

• To develop a low-cost, fast, and accurate method for detecting beta-thalassemia carriers to reduce transmission and mortality.
• To overcome limitations of current HPLC-based testing, including high cost, long processing time, and equipment demands.
• To enable privacy-preserving screening by training models on decentralized, on-site data without sharing raw patient records.
• To improve diagnostic accuracy and reliability over existing methods using federated learning with CBC-derived features.

Proposed method

• Federated learning (FL) is employed to train a machine learning model across multiple healthcare institutions without centralizing patient data.
• The model uses complete blood count (CBC) and red blood cell indices as input features for classification.
• A central server aggregates local model updates from participating clients (e.g., hospitals) using FedAvg or similar aggregation techniques.
• The system ensures data privacy by training models locally and only exchanging model weights, not raw data.
• The model is trained to classify individuals as beta-thalassemia carriers or non-carriers based on hematological parameters.
• The approach supports scalable deployment across diverse healthcare settings with minimal infrastructure requirements.

Experimental results

Research questions

• RQ1 Can federated learning achieve high diagnostic accuracy in detecting beta-thalassemia carriers using CBC data while preserving patient privacy?
• RQ2 How does the performance of the proposed FL model compare to conventional HPLC and other published methods in terms of accuracy and reliability?
• RQ3 To what extent can federated learning reduce the cost and time of large-scale thalassemia carrier screening?
• RQ4 Can the FL framework be effectively deployed in real-world healthcare settings with decentralized data sources?

Key findings

• The proposed federated learning model achieved a classification accuracy of 92.38% in distinguishing beta-thalassemia carriers from non-carriers.
• The model outperforms existing methods in terms of diagnostic accuracy, reliability, and data privacy protection.
• The approach eliminates the need for expensive HPLC testing by leveraging routine CBC data available in most clinical settings.
• The system enables scalable, privacy-preserving screening across multiple institutions without sharing sensitive patient data.
• The federated framework supports real-time model updates and continuous learning across diverse healthcare providers.
• The method presents a viable, low-cost alternative for population-wide thalassemia carrier screening in resource-limited regions.