Brian Chen
MSc Student
School of Computing
Queen's University
Member Between September 2019 - Present
Biography
Brian is a Master's student in the School of Computing at Queen's University. Previously, he graduated from the combined program in computer science and health information science at the University of Victoria in 2018. Brian's current research focuses on applying machine learning techniques to clinical and hospital data, including prediction of adverse events in the ICU using vital signs and biological waveforms.
Brian is a Master's student in the School of Computing at Queen's University. Previously, he graduated from the combined program in computer science and health information science at the University of Victoria in 2018. Brian's current research focuses on applying machine learning techniques to clinical and hospital data, including prediction of adverse events in the ICU using vital signs and biological waveforms.
Publications
2021
Chen, Brian; Javadi, Golara; Jamzad, Amoon; Hamilton, Alexander; Sibley, Stephanie; Maslove, David; Laird, Philip; and Parvin Mousavi,
Detecting Atrial Fibrillation in ICU Telemetry data with Weak Labels Conference Forthcoming
Machine Learning for Health Care (MLHC '21), Forthcoming.
@conference{Chen2021,
title = {Detecting Atrial Fibrillation in ICU Telemetry data with Weak Labels},
author = {Brian Chen and Golara Javadi and Amoon Jamzad and Alexander Hamilton and Stephanie Sibley and David Maslove and Philip Laird and and Parvin Mousavi},
year = {2021},
date = {2021-08-06},
booktitle = {Machine Learning for Health Care (MLHC '21)},
keywords = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
2020
Chan, Brandon; Chen, Brian; Sedghi, Alireza; Laird, Philip; Maslove, David; Mousavi, Parvin
Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach Journal Article
In: Scientific Reports, vol. 10, no. 1, pp. 1–10, 2020.
@article{chan2020generalizable,
title = {Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach},
author = {Brandon Chan and Brian Chen and Alireza Sedghi and Philip Laird and David Maslove and Parvin Mousavi},
year = {2020},
date = {2020-07-10},
journal = {Scientific Reports},
volume = {10},
number = {1},
pages = {1--10},
publisher = {Nature Publishing Group},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2019
Liu, Sam; Chen, Brian; Kuo, Alex
Monitoring Physical Activity Levels Using Twitter Data: Infodemiology Study Journal Article
In: J Med Internet Res, vol. 21, no. 6, pp. e12394, 2019, ISSN: 1438-8871.
@article{info:doi/10.2196/12394,
title = {Monitoring Physical Activity Levels Using Twitter Data: Infodemiology Study},
author = {Sam Liu and Brian Chen and Alex Kuo},
url = {http://www.ncbi.nlm.nih.gov/pubmed/31162126},
doi = {10.2196/12394},
issn = {1438-8871},
year = {2019},
date = {2019-06-03},
journal = {J Med Internet Res},
volume = {21},
number = {6},
pages = {e12394},
abstract = {Background: Social media technology such as Twitter allows users to share their thoughts, feelings, and opinions online. The growing body of social media data is becoming a central part of infodemiology research as these data can be combined with other public health datasets (eg, physical activity levels) to provide real-time monitoring of psychological and behavior outcomes that inform health behaviors. Currently, it is unclear whether Twitter data can be used to monitor physical activity levels. Objective: The aim of this study was to establish the feasibility of using Twitter data to monitor physical activity levels by assessing whether the frequency and sentiment of physical activity--related tweets were associated with physical activity levels across the United States. Methods: Tweets were collected from Twitter's application programming interface (API) between January 10, 2017 and January 2, 2018. We used Twitter's garden hose method of collecting tweets, which provided a random sample of approximately 1% of all tweets with location metadata falling within the United States. Geotagged tweets were filtered. A list of physical activity--related hashtags was collected and used to further classify these geolocated tweets. Twitter data were merged with physical activity data collected as part of the Behavioral Risk Factor Surveillance System. Multiple linear regression models were fit to assess the relationship between physical activity--related tweets and physical activity levels by county while controlling for population and socioeconomic status measures. Results: During the study period, 442,959,789 unique tweets were collected, of which 64,005,336 (14.44%) were geotagged with latitude and longitude coordinates. Aggregated data were obtained for a total of 3138 counties in the United States. The mean county-level percentage of physically active individuals was 74.05% (SD 5.2) and 75.30% (SD 4.96) after adjusting for age. The model showed that the percentage of physical activity--related tweets was significantly associated with physical activity levels (beta=.11; SE 0.2; P\<.001) and age-adjusted physical activity (beta=.10; SE 0.20; P\<.001) on a county level while adjusting for both Gini index and education level. However, the overall explained variance of the model was low (R2=.11). The sentiment of the physical activity--related tweets was not a significant predictor of physical activity level and age-adjusted physical activity on a county level after including the Gini index and education level in the model (P\>.05). Conclusions: Social media data may be a valuable tool for public health organizations to monitor physical activity levels, as it can overcome the time lag in the reporting of physical activity epidemiology data faced by traditional research methods (eg, surveys and observational studies). Consequently, this tool may have the potential to help public health organizations better mobilize and target physical activity interventions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background: Social media technology such as Twitter allows users to share their thoughts, feelings, and opinions online. The growing body of social media data is becoming a central part of infodemiology research as these data can be combined with other public health datasets (eg, physical activity levels) to provide real-time monitoring of psychological and behavior outcomes that inform health behaviors. Currently, it is unclear whether Twitter data can be used to monitor physical activity levels. Objective: The aim of this study was to establish the feasibility of using Twitter data to monitor physical activity levels by assessing whether the frequency and sentiment of physical activity--related tweets were associated with physical activity levels across the United States. Methods: Tweets were collected from Twitter's application programming interface (API) between January 10, 2017 and January 2, 2018. We used Twitter's garden hose method of collecting tweets, which provided a random sample of approximately 1% of all tweets with location metadata falling within the United States. Geotagged tweets were filtered. A list of physical activity--related hashtags was collected and used to further classify these geolocated tweets. Twitter data were merged with physical activity data collected as part of the Behavioral Risk Factor Surveillance System. Multiple linear regression models were fit to assess the relationship between physical activity--related tweets and physical activity levels by county while controlling for population and socioeconomic status measures. Results: During the study period, 442,959,789 unique tweets were collected, of which 64,005,336 (14.44%) were geotagged with latitude and longitude coordinates. Aggregated data were obtained for a total of 3138 counties in the United States. The mean county-level percentage of physically active individuals was 74.05% (SD 5.2) and 75.30% (SD 4.96) after adjusting for age. The model showed that the percentage of physical activity--related tweets was significantly associated with physical activity levels (beta=.11; SE 0.2; P<.001) and age-adjusted physical activity (beta=.10; SE 0.20; P<.001) on a county level while adjusting for both Gini index and education level. However, the overall explained variance of the model was low (R2=.11). The sentiment of the physical activity--related tweets was not a significant predictor of physical activity level and age-adjusted physical activity on a county level after including the Gini index and education level in the model (P>.05). Conclusions: Social media data may be a valuable tool for public health organizations to monitor physical activity levels, as it can overcome the time lag in the reporting of physical activity epidemiology data faced by traditional research methods (eg, surveys and observational studies). Consequently, this tool may have the potential to help public health organizations better mobilize and target physical activity interventions.