Hongyan Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hongyan Li has a total of 71 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
20 shared publications - Chenxi Sun
Harvard Medical School, Boston
7 shared publications Moxian Song
Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China
6 shared publications- Bo Liu
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China
5 shared publications Chenxi Sun
Harvard Medical School
5 shared publicationsBaofeng Zhang
Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2413-2423
ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2413-2423
Open AccessECGTwin: Personalized ECG Generation Using Controllable Diffusion Model
- 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. 11717-11727
AnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 11717-11727
Open AccessAnyPPG: An ECG-Guided PPG Foundation Model Trained on Over 100,000 Hours of Recordings for Holistic Health Profiling
- 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
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 387-395
LLM-GC: Advancing Granger Causal Discovery from Time Series with Multimodel Language Modeling
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 387-395
Open AccessLLM-GC: Advancing Granger Causal Discovery from Time Series with Multimodel Language Modeling
- Open Access
ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using \textit{Protocol-Guided Instruction Data Generation}, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with \textit{Interleaved Modality Dropout} to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present \textit{Reinforcement Learning with ECG Diagnostic Evidence Rewards} to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. Code and data are publicly available at \href{https://github.com/PKUDigitalHealth/ECG-R1}{here}, and an online platform can be accessed at \href{http://ai.heartvoice.com.cn/ECG-R1/}{here}.
Open AccessECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using \textit{Protocol-Guided Instruction Data Generation}, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with \textit{Interleaved Modality Dropout} to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present \textit{Reinforcement Learning with ECG Diagnostic Evidence Rewards} to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. Code and data are publicly available at \href{https://github.com/PKUDigitalHealth/ECG-R1}{here}, and an online platform can be accessed at \href{http://ai.heartvoice.com.cn/ECG-R1/}{here}.
- Top Cited PapersOpen Access
- 1 January 2026
- Published by American Association for the Advancement of Science (AAAS) in Health Data Science
- Vol. 6
A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data
Importance: Medical time series constitute the largest data type in electronic health records and are often irregularly sampled in real-world clinical settings. Such irregularly sampled medical time series exhibit uneven time intervals, missing observations, and heterogeneous sampling rates, posing substantial challenges for deep learning models. Highlights: In this paper, from an irregularity-aware and data-centric perspective, we categorize existing deep learning methods for irregularly sampled medical time series into missing-data-based and raw-data-based approaches. We analyze their theoretical foundations and practical implications and conduct experiments on benchmark and real-world medical datasets to compare their strengths and limitations. Conclusion: Based on these analyses, we provide practical recommendations and discuss open problems and future research directions for modeling irregularly sampled medical time series.
- 1 January 2026
- Published by American Association for the Advancement of Science (AAAS) in Health Data Science
- Vol. 6
Top Cited PapersOpen AccessA Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data
Importance: Medical time series constitute the largest data type in electronic health records and are often irregularly sampled in real-world clinical settings. Such irregularly sampled medical time series exhibit uneven time intervals, missing observations, and heterogeneous sampling rates, posing substantial challenges for deep learning models. Highlights: In this paper, from an irregularity-aware and data-centric perspective, we categorize existing deep learning methods for irregularly sampled medical time series into missing-data-based and raw-data-based approaches. We analyze their theoretical foundations and practical implications and conduct experiments on benchmark and real-world medical datasets to compare their strengths and limitations. Conclusion: Based on these analyses, we provide practical recommendations and discuss open problems and future research directions for modeling irregularly sampled medical time series.
- Open Access
Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECG
Myocardial infarction is a critical manifestation of coronary artery disease, yet detecting it from single-lead electrocardiogram (ECG) remains challenging due to limited spatial information. An intuitive idea is to convert single-lead into multiple-lead ECG for classification by pre-trained models, but generative methods optimized at the signal level in most cases leave a large latent space gap, ultimately degrading diagnostic performance. This naturally raises the question of whether latent space alignment could help. However, most prior ECG alignment methods focus on learning transformation invariance, which mismatches the goal of single-lead detection. To address this issue, we propose SelfMIS, a simple yet effective alignment learning framework to improve myocardial infarction detection from single-lead ECG. Discarding manual data augmentations, SelfMIS employs a self-cutting strategy to pair multiple-lead ECG with their corresponding single-lead segments and directly align them in the latent space. This design shifts the learning objective from pursuing transformation invariance to enriching the single-lead representation, explicitly driving the single-lead ECG encoder to learn a representation capable of inferring global cardiac context from the local signal. Experimentally, SelfMIS achieves superior performance over baseline models across nine myocardial infarction types while maintaining a simpler architecture and lower computational overhead, thereby substantiating the efficacy of direct latent space alignment. Our code and checkpoint will be publicly available after acceptance.
Open AccessSelf-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECG
Myocardial infarction is a critical manifestation of coronary artery disease, yet detecting it from single-lead electrocardiogram (ECG) remains challenging due to limited spatial information. An intuitive idea is to convert single-lead into multiple-lead ECG for classification by pre-trained models, but generative methods optimized at the signal level in most cases leave a large latent space gap, ultimately degrading diagnostic performance. This naturally raises the question of whether latent space alignment could help. However, most prior ECG alignment methods focus on learning transformation invariance, which mismatches the goal of single-lead detection. To address this issue, we propose SelfMIS, a simple yet effective alignment learning framework to improve myocardial infarction detection from single-lead ECG. Discarding manual data augmentations, SelfMIS employs a self-cutting strategy to pair multiple-lead ECG with their corresponding single-lead segments and directly align them in the latent space. This design shifts the learning objective from pursuing transformation invariance to enriching the single-lead representation, explicitly driving the single-lead ECG encoder to learn a representation capable of inferring global cardiac context from the local signal. Experimentally, SelfMIS achieves superior performance over baseline models across nine myocardial infarction types while maintaining a simpler architecture and lower computational overhead, thereby substantiating the efficacy of direct latent space alignment. Our code and checkpoint will be publicly available after acceptance.
- Open Access
UniECG: Understanding and Generating ECG in One Unified Model
Recent unified models such as GPT-5 have achieved encouraging progress on vision-language tasks. However, these unified models typically fail to correctly understand ECG signals and provide accurate medical diagnoses, nor can they correctly generate ECG signals. To address these limitations, we propose UniECG, the first unified model for ECG capable of concurrently performing evidence-based ECG interpretation and text-conditioned ECG generation tasks. Through a decoupled two-stage training approach, the model first learns evidence-based interpretation skills (ECG-to-Text), and then injects ECG generation capabilities (Text-to-ECG) via latent space alignment. UniECG can autonomously choose to interpret or generate an ECG based on user input, significantly extending the capability boundaries of current ECG models. Our code and checkpoints will be made publicly available at https://github.com/PKUDigitalHealth/UniECG upon acceptance.
Open AccessUniECG: Understanding and Generating ECG in One Unified Model
Recent unified models such as GPT-5 have achieved encouraging progress on vision-language tasks. However, these unified models typically fail to correctly understand ECG signals and provide accurate medical diagnoses, nor can they correctly generate ECG signals. To address these limitations, we propose UniECG, the first unified model for ECG capable of concurrently performing evidence-based ECG interpretation and text-conditioned ECG generation tasks. Through a decoupled two-stage training approach, the model first learns evidence-based interpretation skills (ECG-to-Text), and then injects ECG generation capabilities (Text-to-ECG) via latent space alignment. UniECG can autonomously choose to interpret or generate an ECG based on user input, significantly extending the capability boundaries of current ECG models. Our code and checkpoints will be made publicly available at https://github.com/PKUDigitalHealth/UniECG upon acceptance.
- Open Access
Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model
Electrocardiogram (ECG) is essential for the clinical diagnosis of arrhythmias and other heart diseases, but deep learning methods based on ECG often face limitations due to the need for high-quality annotations. Although previous ECG self-supervised learning (eSSL) methods have made significant progress in representation learning from unannotated ECG data, they typically treat ECG signals as ordinary time-series data, segmenting the signals using fixed-size and fixed-step time windows, which often ignore the form and rhythm characteristics and latent semantic relationships in ECG signals. In this work, we introduce a novel perspective on ECG signals, treating heartbeats as words and rhythms as sentences. Based on this perspective, we first designed the QRS-Tokenizer, which generates semantically meaningful ECG sentences from the raw ECG signals. Building on these, we then propose HeartLang, a novel self-supervised learning framework for ECG language processing, learning general representations at form and rhythm levels. Additionally, we construct the largest heartbeat-based ECG vocabulary to date, which will further advance the development of ECG language processing. We evaluated HeartLang across six public ECG datasets, where it demonstrated robust competitiveness against other eSSL methods. Our data and code are publicly available at https://github.com/PKUDigitalHealth/HeartLang.
Open AccessReading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model
Electrocardiogram (ECG) is essential for the clinical diagnosis of arrhythmias and other heart diseases, but deep learning methods based on ECG often face limitations due to the need for high-quality annotations. Although previous ECG self-supervised learning (eSSL) methods have made significant progress in representation learning from unannotated ECG data, they typically treat ECG signals as ordinary time-series data, segmenting the signals using fixed-size and fixed-step time windows, which often ignore the form and rhythm characteristics and latent semantic relationships in ECG signals. In this work, we introduce a novel perspective on ECG signals, treating heartbeats as words and rhythms as sentences. Based on this perspective, we first designed the QRS-Tokenizer, which generates semantically meaningful ECG sentences from the raw ECG signals. Building on these, we then propose HeartLang, a novel self-supervised learning framework for ECG language processing, learning general representations at form and rhythm levels. Additionally, we construct the largest heartbeat-based ECG vocabulary to date, which will further advance the development of ECG language processing. We evaluated HeartLang across six public ECG datasets, where it demonstrated robust competitiveness against other eSSL methods. Our data and code are publicly available at https://github.com/PKUDigitalHealth/HeartLang.