Yue Li

Yasser Iturria-Medina

Jo Anne Stratton

Guy Wolf

Smita Krishnaswamy

David A. Bennett

Danilo Bzdok

2024-05-17

Communications Biology (publié)

Protocol to perform integrative analysis of high-dimensional single-cell multimodal data using an interpretable deep learning technique

Manqi Zhou

Hao Zhang

Zilong Bai

Dylan Mann-Krzisnik

Yi Wang

2024-05-14

STAR Protocols (publié)

MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records

Yixuan Li

Ariane Marelli

Archer Yang

Survival models can help medical practitioners to evaluate the prognostic importance of clinical variables to patient outcomes such as morta… (voir plus)lity or hospital readmission and subsequently design personalized treatment regimes. Electronic Health Records (EHRs) hold the promise for large-scale survival analysis based on systematically recorded clinical features for each patient. However, existing survival models either do not scale to high dimensional and multi-modal EHR data or are difficult to interpret. In this study, we present a supervised topic model called MixEHR-SurG to simultaneously integrate heterogeneous EHR data and model survival hazard. Our contributions are three-folds: (1) integrating EHR topic inference with Cox proportional hazards likelihood; (2) integrating patient-specific topic hyperparameters using the PheCode concepts such that each topic can be identified with exactly one PheCode-associated phenotype; (3) multi-modal survival topic inference. This leads to a highly interpretable survival topic model that can infer PheCode-specific phenotype topics associated with patient mortality. We evaluated MixEHR-SurG using a simulated dataset and two real-world EHR datasets: the Quebec Congenital Heart Disease (CHD) data consisting of 8211 subjects with 75,187 outpatient claim records of 1767 unique ICD codes; the MIMIC-III consisting of 1458 subjects with multi-modal EHR records. Compared to the baselines, MixEHR-SurG achieved a superior dynamic AUROC for mortality prediction, with a mean AUROC score of 0.89 in the simulation dataset and a mean AUROC of 0.645 on the CHD dataset. Qualitatively, MixEHR-SurG associates severe cardiac conditions with high mortality risk among the CHD patients after the first heart failure hospitalization and critical brain injuries with increased mortality among the MIMIC-III patients after their ICU discharge. Together, the integration of the Cox proportional hazards model and EHR topic inference in MixEHR-SurG not only leads to competitive mortality prediction but also meaningful phenotype topics for in-depth survival analysis. The software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-SurG.

2024-05-01

Journal of Biomedical Informatics (publié)

Multi-ancestry polygenic risk scores using phylogenetic regularization

Elliot Layne

Shadi Zabad

Mathieu Blanchette

2024-02-17

bioRxiv (prépublication)

Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning

Ziyang Song

Qincheng Lu

He Zhu

Learning time-series representations for discriminative tasks, such as classification and regression, has been a long-standing challenge in … (voir plus)the healthcare domain. Current pre-training methods are limited in either unidirectional next-token prediction or randomly masked token prediction. We propose a novel architecture called Bidirectional Timely Generative Pre-trained Transformer (BiTimelyGPT), which pre-trains on biosignals and longitudinal clinical records by both next-token and previous-token prediction in alternating transformer layers. This pre-training task preserves original distribution and data shapes of the time-series. Additionally, the full-rank forward and backward attention matrices exhibit more expressive representation capabilities. Using biosignals and longitudinal clinical records, BiTimelyGPT demonstrates superior performance in predicting neurological functionality, disease diagnosis, and physiological signs. By visualizing the attention heatmap, we observe that the pre-trained BiTimelyGPT can identify discriminative segments from biosignal time-series sequences, even more so after fine-tuning on the task.

2024-02-14

ArXiv (prépublication)

Machine Learning Informed Diagnosis for Congenital Heart Disease in Large Claims Data Source

Ariane Marelli

Chao Li

Aihua Liu

Hanh Nguyen

Harry Moroz

James M. Brophy

Liming Guo

2024-02-01

JACC: Advances (publié)

Bidirectional Generative Pre-training for Improving Time Series Representation Learning

Ziyang Song

Qincheng Lu

Mike He Zhu

2024-01-01

arXiv.org (prépublication)

MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records

Yixuan Li

Ariane Marelli

Archer Yang

Survival models can help medical practitioners to evaluate the prognostic importance of clinical variables to patient outcomes such as morta… (voir plus)lity or hospital readmission and subsequently design personalized treatment regimes. Electronic Health Records (EHRs) hold the promise for large-scale survival analysis based on systematically recorded clinical features for each patient. However, existing survival models either do not scale to high dimensional and multi-modal EHR data or are difficult to interpret. In this study, we present a supervised topic model called MixEHR-SurG to simultaneously integrate heterogeneous EHR data and model survival hazard. Our contributions are three-folds: (1) integrating EHR topic inference with Cox proportional hazards likelihood; (2) integrating patient-specific topic hyperparameters using the PheCode concepts such that each topic can be identified with exactly one PheCode-associated phenotype; (3) multi-modal survival topic inference. This leads to a highly interpretable survival topic model that can infer PheCode-specific phenotype topics associated with patient mortality. We evaluated MixEHR-SurG using a simulated dataset and two real-world EHR datasets: the Quebec Congenital Heart Disease (CHD) data consisting of 8211 subjects with 75,187 outpatient claim records of 1767 unique ICD codes; the MIMIC-III consisting of 1458 subjects with multi-modal EHR records. Compared to the baselines, MixEHR-SurG achieved a superior dynamic AUROC for mortality prediction, with a mean AUROC score of 0.89 in the simulation dataset and a mean AUROC of 0.645 on the CHD dataset. Qualitatively, MixEHR-SurG associates severe cardiac conditions with high mortality risk among the CHD patients after the first heart failure hospitalization and critical brain injuries with increased mortality among the MIMIC-III patients after their ICU discharge. Together, the integration of the Cox proportional hazards model and EHR topic inference in MixEHR-SurG not only leads to competitive mortality prediction but also meaningful phenotype topics for in-depth survival analysis. The software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-SurG.

2023-12-20

ArXiv (prépublication)

TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare

Ziyang Song

Qincheng Lu

Hao Xu

Mike He Zhu

2023-11-29

ArXiv (prépublication)

TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare

Ziyang Song

Qincheng Lu

Hao Xu

Mike He Zhu

Motivation: Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success in Natural Language Processing a… (voir plus)nd Computer Vision domains. However, the development of PTMs on healthcare time-series data is lagging behind. This underscores the limitations of the existing transformer-based architectures, particularly their scalability to handle large-scale time series and ability to capture long-term temporal dependencies. Methods: In this study, we present Timely Generative Pre-trained Transformer (TimelyGPT). TimelyGPT employs an extrapolatable position (xPos) embedding to encode trend and periodic patterns into time-series representations. It also integrates recurrent attention and temporal convolution modules to effectively capture global-local temporal dependencies. Materials: We evaluated TimelyGPT on two large-scale healthcare time series datasets corresponding to continuous biosignals and irregularly-sampled time series, respectively: (1) the Sleep EDF dataset consisting of over 1.2 billion timesteps; (2) the longitudinal healthcare administrative database PopHR, comprising 489,000 patients randomly sampled from the Montreal population. Results: In forecasting continuous biosignals, TimelyGPT achieves accurate extrapolation up to 6,000 timesteps of body temperature during the sleep stage transition, given a short look-up window (i.e., prompt) containing only 2,000 timesteps. For irregularly-sampled time series, TimelyGPT with a proposed time-specific inference demonstrates high top recall scores in predicting future diagnoses using early diagnostic records, effectively handling irregular intervals between clinical records. Together, we envision TimelyGPT to be useful in various health domains, including long-term patient health state forecasting and patient risk trajectory prediction. Availability: The open-sourced code is available at Github.

2023-11-29

ArXiv (prépublication)

MDFD: Study of Distributed Non-IID Scenarios and Frechet Distance-Based Evaluation

Wei Wang

Mingwei Zhang

Ziwen Wu

Qianxi Chen

With the development of distributed machine learning and federated learning, the solution to the data island problem is promoted. People use… (voir plus) computer clusters to train machine learning models on data distributed in different regions. In the early stage of research, researchers usually assume that the data sets of each node are independent identically distribution (IID), but this is a strong assumption, which is challenging to meet in practical applications. Therefore, research on non-IID has become a hot spot in recent years. However, there is no uniform standard for designing and evaluating non-IID scenarios. This paper proposes a Frechet distance-independent non-IID distribution dataset metric MDFD. And we conducted experiments on different types of distributed machine-learning methods in different non-IID scenarios to verify the effectiveness of MDFD.

2023-10-08

International Conference on Information Photonics (publié)

SDWD: Style Diversity Weighted Distance Evaluates the Intra-Class Data Diversity of Distributed GANs

Wei Wang

Ziwen Wu

Mingwei Zhang

2023-10-08

2023 IEEE International Conference on Image Processing (ICIP) (publié)