[论文解读] Beta Thalassemia Carriers detection empowered federated Learning

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

Digital Imaging for Blood Diseases被引用 4

一句话总结

本研究提出一种基于联邦学习（FL）的模型，利用全血细胞计数（CBC）和红细胞指数检测β-地中海贫血基因携带者，准确率达到92.38%，同时保护患者数据隐私。该方法实现了去中心化、隐私保护且可扩展的筛查，与传统HPLC方法相比具有高性能和低成本优势。

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.

研究动机与目标

• 开发一种低成本、快速且准确的β-地中海贫血基因携带者检测方法，以减少传播和死亡率。
• 克服当前基于HPLC检测的局限性，包括高成本、处理时间长及设备需求高等问题。
• 通过在去中心化、本地数据上训练模型，而不共享原始患者记录，实现隐私保护的筛查。
• 利用基于CBC特征的联邦学习，提升诊断准确性和可靠性，优于现有方法。

提出的方法

• 采用联邦学习（FL）在多个医疗机构之间训练机器学习模型，无需集中化患者数据。
• 模型以全血细胞计数（CBC）和红细胞指数作为输入特征进行分类。
• 中央服务器使用FedAvg或类似聚合技术，聚合参与客户端（如医院）的本地模型更新。
• 通过在本地训练模型并仅交换模型权重而非原始数据，确保数据隐私。
• 模型根据血液学参数，训练以将个体分类为β-地中海贫血基因携带者或非携带者。
• 该方法支持在多样化医疗环境中可扩展部署，对基础设施要求极低。

实验结果

研究问题

• RQ1 联邦学习能否在保护患者隐私的前提下，利用CBC数据实现高诊断准确率检测β-地中海贫血基因携带者？
• RQ2 所提出的FL模型在准确率和可靠性方面，与传统HPLC方法及其他已发表方法相比表现如何？
• RQ3 联邦学习在多大程度上可降低大规模地贫基因携带者筛查的成本和时间？
• RQ4 联邦学习框架能否在具有去中心化数据源的真实医疗环境中有效部署？

主要发现

• 所提出的联邦学习模型在区分β-地中海贫血基因携带者与非携带者方面，分类准确率达到92.38%。
• 该模型在诊断准确率、可靠性以及数据隐私保护方面优于现有方法。
• 通过利用大多数临床环境中已有的常规CBC数据，该方法消除了对昂贵HPLC检测的需求。
• 系统实现了跨多个机构的可扩展、隐私保护的筛查，无需共享敏感患者数据。
• 联邦框架支持跨多样化医疗提供者的实时模型更新与持续学习。
• 该方法为资源有限地区的人群级地贫基因携带者筛查提供了一种切实可行的低成本替代方案。