Federated learning for predicting clinical outcomes in patients with COVID-19

By I. Dayan, Holger R. Roth, Aoxiao Zhong, A. Harouni, Amilcare Gentili, A. Abidin, Andrew Liu, Anthony B. Costa, Bradford J. Wood, Chien-Sung Tsai and 89 more. 2021

736 citations recorded by the source corpus.

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site’s data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare. Federated learning, a method for training artificial intelligence algorithms that protects data privacy, was used to predict future oxygen requirements of symptomatic patients with COVID-19 using data from 20 different institutes across the globe.

Subfields: Artificial Intelligence, Health Informatics, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mingxia Liu
2. Philip S. Yu
3. P. Heng
4. Bo Du
5. Qi-Yan Dou
6. Lichao Sun
7. Dacheng Tao
8. Qiang Yang

In Health Informatics

1. Philip S. Yu
2. Qiang Yang
3. Han Yu
4. Stephen Seung-Yeob Baek
5. Qi-Yan Dou
6. Lichao Sun

In Radiology, Nuclear Medicine and Imaging

1. P. Heng
2. Qi-Yan Dou
3. Cheng Chen
4. Zhen Fang
5. Klaus Hermann Maier-Hein
6. Craig K. Jones
7. Dacheng Tao
8. Bo Du

Citations in the corpus

• Federated Class-Incremental Learning (2022, methodology): “To better coma prehend the FCIL problem, we here use COVID-19 diagnosis among different hospitals as a possible example [6].”
• Federated learning for medical image analysis: A survey (2023, methodology): “The first way is to directly use databases from different medical sites/centers (Li et al., 2020d; Dayan et al., 2021).”
• FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction (2022, background): “Recently, FL has become a hot research topic [3, 8, 11].”
• Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, background): “Federated learning has drawn increasing attention in both academia and industry owing to its potential utility in large-scale applications [48, 85, 185], which has been widely explored in the fields of healthcare [39, 178, 214], medical analysis [54, 97], and data security [205], etc.”
• Multimodal biomedical AI (2022, neutral): “168 ).”
• Decentralized Federated Learning: A Survey and Perspective (2023, methodology): “Researchers employed FL to aggregate data from 20 institutes worldwide to train a universal model to predict clinical outcomes of COVID-19 patients [30].”
• Federated learning enables big data for rare cancer boundary detection (2022, background): “…is what sets this study apart from current literature, since it dealt with a multi-parametric multi-class problem with reference standards that require expert clinicians following an involved manual annotation protocol, rather than recording a categorical entry from medical records 30,51 .”
• Towards Personalized Federated Learning (2021, background): “This is especially relevant in the healthcare industry where medical data are highly sensitive and they are often collected and reside across different healthcare institutions [1]–[4].”
• Communication-efficient federated learning via knowledge distillation (2021, neutral): “Federated learning is a recent technique to learn intelligent models from decentralized private data 4 , which has been widely used in various applications that involve privacy-sensitive data such as intelligent healthcare 9,10 , personalized recommendation 11 , and mobile keyboard prediction 12 .”