Jiarui Jin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jiarui Jin has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Shenda Hong
National Institute of Health Data Science, Peking University, Beijing, China
3 shared publications - Bo Liu
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China
2 shared publications - Guangkun Nie
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China
2 shared publications - Hongyan Li
State Key Laboratory of General Artificial Intelligence Peking University
2 shared publications - Xiaocheng Fang
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China
2 shared publications - Aaron D. Aguirre
Cardiology Division, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10877-10888
ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10877-10888
Open AccessECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11422-11431
CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11422-11431
Open AccessCausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts
- Top Cited Papers
- 26 June 2025
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 2 (7)
An Electrocardiogram Foundation Model Built on over 10 Million Recordings
Artificial intelligence (AI) has demonstrated significant potential in electrocardiogram (ECG) analysis and cardiovascular disease assessment. Recently, foundation models have played a remarkable role in advancing medical AI, bringing benefits such as efficient disease diagnosis and cross-domain knowledge transfer. The development of an ECG foundation model holds the promise of elevating AI-ECG research to new heights. However, building such a model poses several challenges, including insufficient database sample sizes and inadequate generalization across multiple domains. In addition, there is a notable performance gap between single-lead and multilead ECG analysis. We propose a general-purpose ECG foundation model (ECGFounder), which leverages real-world ECG annotations from cardiologists to broaden the diagnostic capabilities of ECG analysis. ECGFounder was built on 10,771,552 ECGs from 1,818,247 unique subjects with 150 label categories from the Harvard-Emory ECG Database, enabling comprehensive cardiovascular disease diagnosis. The model is designed to be both an effective out-of-the-box solution and easily fine-tunable for downstream tasks, maximizing usability. Importantly, we extended its application to reduced-lead ECGs, particularly single-lead ECGs. ECGFounder is therefore applicable to various downstream tasks in mobile and remote monitoring scenarios. Experimental results demonstrate that ECGFounder achieves expert-level performance on internal validation sets, with area under the receiver operating characteristic curve (AUROC) exceeding 0.95 for 80 diagnoses. It also shows strong classification performance and generalization across various diagnoses on external validation sets. When fine-tuned, ECGFounder outperforms baseline models in demographic analysis, clinical event detection, and cross-modality cardiac rhythm diagnosis, surpassing baseline methods by 3 to 5 points in the AUROC. The ECG foundation model offers an effective solution, allowing it to generalize across a wide range of tasks. By enhancing existing cardiovascular diagnostics and facilitating integration with cloud-based systems, which analyze ECG data uploaded from wearable devices, it significantly contributes to the advancement of the cardiovascular AI community and enables management of cardiac conditions. (Funded by the National Science Foundation and others.).
- 26 June 2025
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 2 (7)
Top Cited PapersAn Electrocardiogram Foundation Model Built on over 10 Million Recordings
Artificial intelligence (AI) has demonstrated significant potential in electrocardiogram (ECG) analysis and cardiovascular disease assessment. Recently, foundation models have played a remarkable role in advancing medical AI, bringing benefits such as efficient disease diagnosis and cross-domain knowledge transfer. The development of an ECG foundation model holds the promise of elevating AI-ECG research to new heights. However, building such a model poses several challenges, including insufficient database sample sizes and inadequate generalization across multiple domains. In addition, there is a notable performance gap between single-lead and multilead ECG analysis. We propose a general-purpose ECG foundation model (ECGFounder), which leverages real-world ECG annotations from cardiologists to broaden the diagnostic capabilities of ECG analysis. ECGFounder was built on 10,771,552 ECGs from 1,818,247 unique subjects with 150 label categories from the Harvard-Emory ECG Database, enabling comprehensive cardiovascular disease diagnosis. The model is designed to be both an effective out-of-the-box solution and easily fine-tunable for downstream tasks, maximizing usability. Importantly, we extended its application to reduced-lead ECGs, particularly single-lead ECGs. ECGFounder is therefore applicable to various downstream tasks in mobile and remote monitoring scenarios. Experimental results demonstrate that ECGFounder achieves expert-level performance on internal validation sets, with area under the receiver operating characteristic curve (AUROC) exceeding 0.95 for 80 diagnoses. It also shows strong classification performance and generalization across various diagnoses on external validation sets. When fine-tuned, ECGFounder outperforms baseline models in demographic analysis, clinical event detection, and cross-modality cardiac rhythm diagnosis, surpassing baseline methods by 3 to 5 points in the AUROC. The ECG foundation model offers an effective solution, allowing it to generalize across a wide range of tasks. By enhancing existing cardiovascular diagnostics and facilitating integration with cloud-based systems, which analyze ECG data uploaded from wearable devices, it significantly contributes to the advancement of the cardiovascular AI community and enables management of cardiac conditions. (Funded by the National Science Foundation and others.).
- 29 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-16
Affective EEG-Based Person Identification With Continual Learning
Electroencephalograms (EEGs) have garnered immense attention due to their security features, which are difficult to physically counterfeit in the field of person identification. Despite significant achievements in EEG-based person identification, several challenges remain: 1) how to dynamically update the model to identify an increasing number of users; 2) how to more effectively capture and reconstruct the interrelationships of features from different domains in EEG signals; and 3) how to enhance the core capabilities of the backbone network, including the acquisition of global features while mining fine-grained local features. To address these challenges, this paper proposes an affective EEG-based person identification with continual learning, enabling the model to dynamically adapt to the escalating needs of user identification. Furthermore, we developed a multi-domain coordinated attention transformer to serve as the backbone network. This backbone network combines spatial and time-frequency attention mechanisms with domain coordinated mechanisms, enabling it to adaptively capture fine-grained local features and reconstruct interactions across domains on a macro level. We validated our proposed method using the THU-EP dataset, a nine-class affective state dataset involving 80 subjects. Experimental results demonstrate that our method surpasses current advanced benchmarks. Additionally, we analyzed the impact of different affective states and frequency bands on affective EEG-based person identification and found that the neutral state and beta band had minimal impacts on the decay of accuracy in continual learning. Code is publicly available at https://github.com/JerryKingQAQ/AEEG-PI-CL.
- 29 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-16
Affective EEG-Based Person Identification With Continual Learning
Electroencephalograms (EEGs) have garnered immense attention due to their security features, which are difficult to physically counterfeit in the field of person identification. Despite significant achievements in EEG-based person identification, several challenges remain: 1) how to dynamically update the model to identify an increasing number of users; 2) how to more effectively capture and reconstruct the interrelationships of features from different domains in EEG signals; and 3) how to enhance the core capabilities of the backbone network, including the acquisition of global features while mining fine-grained local features. To address these challenges, this paper proposes an affective EEG-based person identification with continual learning, enabling the model to dynamically adapt to the escalating needs of user identification. Furthermore, we developed a multi-domain coordinated attention transformer to serve as the backbone network. This backbone network combines spatial and time-frequency attention mechanisms with domain coordinated mechanisms, enabling it to adaptively capture fine-grained local features and reconstruct interactions across domains on a macro level. We validated our proposed method using the THU-EP dataset, a nine-class affective state dataset involving 80 subjects. Experimental results demonstrate that our method surpasses current advanced benchmarks. Additionally, we analyzed the impact of different affective states and frequency bands on affective EEG-based person identification and found that the neutral state and beta band had minimal impacts on the decay of accuracy in continual learning. Code is publicly available at https://github.com/JerryKingQAQ/AEEG-PI-CL.