Junyi Gao

Junyi Gao

Auto-generated profile, based on publicly available information

Junyi Gao

University of Edinburgh, Edinburgh, United Kingdom and Health Data Research UK, London, United Kingdom

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

2 June 2025 in eClinicalMedicine
Verified
Journal Article
Open access
DTDaira Trusinska
Daira Trusinska
BLBohee Lee
Bohee Lee
SFSohail Ferdous
Sohail Ferdous
HKHarley H.Y. Kwok
Harley H.Y. Kwok
BGBecky Gordon
Becky Gordon
TSTing Shi
Ting Shi
In clinical trials, recently introduced respiratory syncytial virus (RSV) immunisation products have shown high efficacy in preventing severe RSV outcomes. Implementing successful immunisation programmes is however key to realising these benefits in real-world settings. We aimed to investigate uptake of the long-acting monoclonal antibody nirsevimab, the RSV maternal vaccine, and RSV vaccines for older adults in countries where immunisation programmes have been introduced, and to explore how uptake varies between countries and population subgroups. In this systematic review and meta-analysis, we carried out four monthly searches in Medline, Embase, and Global Health databases for studies reporting uptake of nirsevimab, the RSV maternal vaccine, and RSV vaccines for older adults. We included population-based studies published between December 1, 2022 and February 5, 2025. Two independent reviewers screened studies, extracted data, and completed a risk of bias assessment using the Joanna Briggs Institute (JBI) Critical Appraisal Tools. We assessed uptake stratified by country and socio-demographic and clinical subgroups. Meta-analyses were conducted using random-effects modelling. PROSPERO registration number: CRD42025643585. We screened a total of 1267 studies, 43 of which met the inclusion criteria reporting data on over 1.38 million individuals from six countries. Nirsevimab uptake data were reported in 34 studies: 16 from Spain, eight from the United States, seven from France, one with combined data from Andorra and Spain, and one from each of Italy and Luxembourg. Our pooled estimates showed that nirsevimab uptake on population level was 90.1% (95% confidence interval (CI): 86.4–92.9) in Spain and 51.2% (95% CI: 29.3–72.7) in the United States during the 2023/24 RSV season. Uptake data for the RSV maternal vaccine and RSV vaccines for older adults were reported in five and eight studies, respectively, all from the United States. Meta-analysis showed population-level uptake of 30.5% (95% CI: 20.6–42.6) and 18.2% (95% CI: 10.8–28.9), respectively. Uptake varied across subgroups. Uptake of nirsevimab varied substantially between the countries that have implemented infant RSV immunisation programmes. Despite the limited number of studies and the lack of more accurate data at national level the low uptake estimates for RSV maternal vaccine and RSV vaccines for older adults are concerning. National, clinical, and public health initiatives are needed to increase uptake of RSV immunisation products and ensure maximum benefit to people currently at risk of severe RSV outcomes. 10.13039/501100023699 Health Data Research UK , Inflammation and Immunity Driver Programme.


7 March 2024 in Patterns
Verified
Journal Article
Open access
JGJunyi Gao
Junyi Gao
YZYinghao Zhu
Yinghao Zhu
WWWenqing Wang
Wenqing Wang
ZWZixiang Wang
Zixiang Wang
GDGuiying Dong
Guiying Dong
LMLiantao Ma
Liantao Ma
The COVID-19 pandemic highlighted the need for predictive deep-learning models in health care. However, practical prediction task design, fair comparison, and model selection for clinical applications remain a challenge. To address this, we introduce and evaluate two new prediction tasks—outcome-specific length-of-stay and early-mortality prediction for COVID-19 patients in intensive care—which better reflect clinical realities. We developed evaluation metrics, model adaptation designs, and open-source data preprocessing pipelines for these tasks while also evaluating 18 predictive models, including clinical scoring methods and traditional machine-learning, basic deep-learning, and advanced deep-learning models, tailored for electronic health record (EHR) data. Benchmarking results from two real-world COVID-19 EHR datasets are provided, and all results and trained models have been released on an online platform for use by clinicians and researchers. Our efforts contribute to the advancement of deep-learning and machine-learning research in pandemic predictive modeling.

4 August 2023
Verified
Conference Paper
Open access
CYChaoqi Yang
Chaoqi Yang
ZWZhenbang Wu
Zhenbang Wu
PJPatrick Jiang
Patrick Jiang
ZLZhen Lin
Zhen Lin
JGJunyi Gao
Junyi Gao
JSJimeng Sun
Jimeng Sun
Deep learning (DL) has emerged as a promising tool in healthcare applications. However, the reproducibility of many studies in this field is limited by the lack of accessible code implementations and standard benchmarks. To address the issue, we create PyHealth, a comprehensive library to build, deploy, and validate DL pipelines for healthcare applications. PyHealth supports various data modalities, including electronic health records (EHRs), physiological signals, medical images, and clinical text. It offers various advanced DL models and maintains comprehensive medical knowledge systems. The library is designed to support both DL researchers and clinical data scientists. Upon the time of writing, PyHealth has received 633 stars, 130 forks, and 15k+ downloads in total on GitHub. This tutorial will provide an overview of PyHealth, present different modules, and showcase their functionality through hands-on demos. Participants can follow along and gain hands-on experience on the Google Colab platform during the session.

29 May 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
JGJunyi Gao
Junyi Gao
JHJoerg Heintz
Joerg Heintz
CMChristina Mack
Christina Mack
LGLucas Glass
Lucas Glass
ACAdam Cross
Adam Cross
JSJimeng Sun
Jimeng Sun
In this work, we aim to accurately predict the number of hospitalizations during the COVID-19 pandemic by developing a spatiotemporal prediction model. We propose HOIST, an Ising dynamics-based deep learning model for spatiotemporal COVID-19 hospitalization prediction. By drawing the analogy between locations and lattice sites in statistical mechanics, we use the Ising dynamics to guide the model to extract and utilize spatial relationships across locations and model the complex influence of granular information from real-world clinical evidence. By leveraging rich linked databases, including insurance claims, census information, and hospital resource usage data across the U.S., we evaluate the HOIST model on the large-scale spatiotemporal COVID-19 hospitalization prediction task for 2299 counties in the U.S. In the 4-week hospitalization prediction task, HOIST achieves 368.7 mean absolute error, 0.6 $${R}^{2}$$ R 2 and 0.89 concordance correlation coefficient score on average. Our detailed number needed to treat (NNT) and cost analysis suggest that future COVID-19 vaccination efforts may be most impactful in rural areas. This model may serve as a resource for future county and state-level vaccination efforts.