David Buckeridge

2025-02-17

The International Journal of Behavioral Nutrition and Physical Activity (publié)

Extrapolatable Transformer Pre-training for Ultra Long Time-Series Forecasting

Ziyang Song

Qincheng Lu

Hao Xu

Mike He Zhu

2024-12-16

Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (publié)

arxiv.org

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.

2024-11-25

Proceedings of the 9th Machine Learning for Healthcare Conference (publié)

proceedings.mlr.press

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

Ziyang Song

Qincheng Lu

Mike He Zhu

2024-11-25

Proceedings of the 9th Machine Learning for Healthcare Conference (publié)

proceedings.mlr.press

arxiv.org

Evaluating the effectiveness of the Smart About Meds (SAM) mobile application among patients discharged from hospital: protocol of a randomised controlled trial

Robyn Tamblyn

Bettina Habib

Daniala L Weir

Elizaveta Frolova

Rolan Alattar

Jessica Rogozinsky

Caroline Beauchamp

Rosalba Pupo

Susan J Bartlett

Emily McDonald

2024-11-24

BMJ Open (publié)

MixEHR-Nest: Identifying Subphenotypes within Electronic Health Records through Hierarchical Guided-Topic Modeling

Ruohan Wang

Zilong Wang

Ziyang Song

Automatic subphenotyping from electronic health records (EHRs)provides numerous opportunities to understand diseases with unique subgroups a… (voir plus)nd enhance personalized medicine for patients. However, existing machine learning algorithms either focus on specific diseases for better interpretability or produce coarse-grained phenotype topics without considering nuanced disease patterns. In this study, we propose a guided topic model, MixEHR-Nest, to infer sub-phenotype topics from thousands of disease using multi-modal EHR data. Specifically, MixEHR-Nest detects multiple subtopics from each phenotype topic, whose prior is guided by the expert-curated phenotype concepts such as Phenotype Codes (PheCodes) or Clinical Classification Software (CCS) codes. We evaluated MixEHR-Nest on two EHR datasets: (1) the MIMIC-III dataset consisting of over 38 thousand patients from intensive care unit (ICU) from Beth Israel Deaconess Medical Center (BIDMC) in Boston, USA; (2) the healthcare administrative database PopHR, comprising 1.3 million patients from Montreal, Canada. Experimental results demonstrate that MixEHR-Nest can identify subphenotypes with distinct patterns within each phenotype, which are predictive for disease progression and severity. Consequently, MixEHR-Nest distinguishes between type 1 and type 2 diabetes by inferring subphenotypes using CCS codes, which do not differentiate these two subtype concepts. Additionally, MixEHR-Nest not only improved the prediction accuracy of short-term mortality of ICU patients and initial insulin treatment in diabetic patients but also revealed the contributions of subphenotypes. For longitudinal analysis, MixEHR-Nest identified subphenotypes of distinct age prevalence under the same phenotypes, such as asthma, leukemia, epilepsy, and depression. The MixEHR-Nest software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-Nest.

2024-10-17

ArXiv (prépublication)

arxiv.org

TrajGPT: Healthcare Time-Series Representation Learning for Trajectory Prediction

Ziyang Song

Qincheng Lu

Mike He Zhu

In many domains, such as healthcare, time-series data is irregularly sampled with varying intervals between observations. This creates chall… (voir plus)enges for classical time-series models that require equally spaced data. To address this, we propose a novel time-series Transformer called **Trajectory Generative Pre-trained Transformer (TrajGPT)**. It introduces a data-dependent decay mechanism that adaptively forgets irrelevant information based on clinical context. By interpreting TrajGPT as ordinary differential equations (ODEs), our approach captures continuous dynamics from sparse and irregular time-series data. Experimental results show that TrajGPT, with its time-specific inference approach, accurately predicts trajectories without requiring task-specific fine-tuning.

2024-10-10

NeurIPS.cc/2024/Workshop/TSALM (publié)

openreview.net

TrajGPT: Healthcare Time-Series Representation Learning for Trajectory Prediction

Ziyang Song

Qincheng Lu

Mike He Zhu

2024-10-10

NeurIPS.cc/2024/Workshop/TSALM (publié)

openreview.net

TrajGPT: Irregular Time-Series Representation Learning for Health Trajectory Analysis

Ziyang Song

Qincheng Lu

Mike He Zhu

2024-10-03

ArXiv (prépublication)

openreview.net

Correction: Economic evaluation of the effect of needle and syringe programs on skin, soft tissue, and vascular infections in people who inject drugs: a microsimulation modelling approach

Jihoon Lim

W Alton Russell

Mariam El-Sheikh

Dimitra Panagiotoglou

2024-09-09

Harm Reduction Journal (publié)

Development of a Framework for Establishing 'Gold Standard' Outbreak Data from Submitted SARS-CoV-2 Genome Samples

Yannan Shen

Russell Steele

Submitted genomic data for respiratory viruses reflect the emergence and spread of new variants. Although delays in submission limit the uti… (voir plus)lity of these data for prospective surveillance, they may be useful for evaluating other surveillance sources. However, few studies have investigated the use of these data for evaluating aberration detection in surveillance systems. Our study used a Bayesian online change point detection algorithm (BOCP) to detect increases in the number of submitted genome samples as a means of establishing 'gold standard' dates of outbreak onset in multiple countries. We compared models using different data transformations and parameter values. BOCP detected change points that were not sensitive to different parameter settings. We also found data transformations were essential prior to change point detection. Our study presents a framework for using global genomic submission data to develop 'gold standard' dates about the onset of outbreaks due to new viral variants.

2024-08-22

Medical Informatics Europe (publié)

Canada's provincial COVID-19 pandemic modelling efforts: A review of mathematical models and their impacts on the responses.

Yiqing Xia

Jorge Luis Flores Anato

Caroline Colijin

Naveed Janjua

Mike Irvine

Tyler Williamson

Marie B. Varughese

Michael Li

Nathaniel D. Osgood

David J. D. Earn

Beate Sander

Lauren E. Cipriano

Kumar Murty

Fanyu Xiu

Arnaud Godin

Amy Hurford

Sharmistha Mishra

Mathieu Maheu-Giroux

SETTING Mathematical modelling played an important role in the public health response to COVID-19 in Canada. Variability in epidemic traject… (voir plus)ories, modelling approaches, and data infrastructure across provinces provides a unique opportunity to understand the factors that shaped modelling strategies. INTERVENTION Provinces implemented stringent pandemic interventions to mitigate SARS-CoV-2 transmission, considering evidence from epidemic models. This study aimed to summarize provincial COVID-19 modelling efforts. We identified modelling teams working with provincial decision-makers, through referrals and membership in Canadian modelling networks. Information on models, data sources, and knowledge translation were abstracted using standardized instruments. OUTCOMES We obtained information from six provinces. For provinces with sustained community transmission, initial modelling efforts focused on projecting epidemic trajectories and healthcare demands, and evaluating impacts of proposed interventions. In provinces with low community transmission, models emphasized quantifying importation risks. Most of the models were compartmental and deterministic, with projection horizons of a few weeks. Models were updated regularly or replaced by new ones, adapting to changing local epidemic dynamics, pathogen characteristics, vaccines, and requests from public health. Surveillance datasets for cases, hospitalizations and deaths, and serological studies were the main data sources for model calibration. Access to data for modelling and the structure for knowledge translation differed markedly between provinces. IMPLICATION Provincial modelling efforts during the COVID-19 pandemic were tailored to local contexts and modulated by available resources. Strengthening Canadian modelling capacity, developing and sustaining collaborations between modellers and governments, and ensuring earlier access to linked and timely surveillance data could help improve pandemic preparedness.

2024-07-25

Canadian journal of public health (publié)