Theme 10

Theme 10: Biomedical & Health Informatics


Engineering and Medicine in Extreme Environments: Space

Carolyn McGregor AM, Ontario Tech University, Canada
Anna Chernikova, Russian Institute for Biomedical Problems, Russian Academy of Sciences (RAS). Moscow, Russia
Anastasiia Prysyazhnyuk, Canadian Space Agency
Robert Brumley, CommStar Communications

Natural extreme environments, together with forced/man-made extreme environments such as extreme sports, public safety and armed forces are conditions where specific physiological adaptations maintain physiological functionality to ensure survival.

This mini symposium will focus on the extreme environment of Space. Current research fields of engineering, computer science and space medicine will be presented that support the provision of health and wellness support in Space.

This mini symposium include:

Introductory remarks on Space as an Extreme Environment – Space exploration has led to revolutionary discoveries about how the human body functions in Space. This presentation will provide an overview of Space as an extreme environment.

Dry Immersion as an Analogue for Space – Dry immersion has been used for over 50 years as a terrestrial analogue for researching the implications of weightlessness. In this presentation Dry Immersion will be introduced together with the research directions in prior studies on all male participants and a new study on all female participants.

Medical technologies for deep-space exploration – There are many parallels in provisioning healthcare for astronauts in space and people in remote communities. This presentation will explore current directions within medical technologies for deep-space exploration and their implications for provisioning care in remote communities in Canada.

New approaches to Space Communications using Space Data Relays – The provision of healthcare in Space from Earth has been limited traditionally by network bandwidth limitations. In this presentation, deep space data management through space data relays will be introduced along with the implications for provisioning healthcare in Space from Earth using this network.


Health Monitoring: How Emerging Technologies Can Help?

Guangzhi Wang, Tsinghua University, China
Hairong Zheng, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China
Alan Murray, University of Newcastle, UK
Kangping Lin, Chung Yuan University, China
Henggui Zhang, University of Manchester, UK
Leandro Pecchia, University of Warwick, UK
Chengyu Liu, Southeast University, China
Li Li, Chinese Society of Biomedical Engineering, China

This half-day workshop is organized by the Chinese Society of Biomedical Engineering and is geared toward graduate students, young researchers and enthusiasts entering the field of human Health Monitoring, especially during the era of worldwide COVID-19. Recent advances in artificial intelligence (AI), wearables and Internet of Things (IoT) devices has led to an explosion of routinely collected individual health data. The use of big-data and AI methods (such as the items of deep learning, machine learning, computational intelligence, etc) to turn these ever-growing health monitoring data into clinical benefits seems as if it should be an obvious path to take. However, this field is still in its infancy, and lots of essential concepts and method solutions should be clarified in depth. Among them, how to enhance the clinical efficiency and individual benefit from the massive data and AI methods, and how to improve the rationality and interpret ability of AI algorithms in practical applications, are two major challenges. The purpose of this workshop is to provide a platform for discussing the latest progresses, such as AI approaches, wearable device development, feature engineering and computational intelligence techniques for human health monitoring, and exploring the new solutions, with an emphasis on how these methods can be efficiently used on the emerging need and challenge—dynamic, continuous & long-term individual health monitoring and real-time feedback, aiming to provide a “snapshot” of the state of current research at the interface between device development and clinical application & individual benefit, between signal analysis and standard database development. It could help clarify some dilemmas and encourage further investigations in this field, to explore rational applications of AI in clinical practices for health monitoring.


Detection of Stress and Mental Health Status Using Wearable Sensors

Huiyuan Yang, Rice University, USA
Han Yu, Rice University, USA
Alicia Chotto, Rice University, USA
Maryam Khalid, Rice University, USA
Kusha Sridhar, Rice University, USA
Thomas Vaessen, University of Twente (Netherlands) and Katholieke Universiteit, Leuven (Belgium)
Akane Sano, Rice University, USA

Moderate stress can help a person in many beneficial ways to confront a challenge, but excessive stress, on the other hand, can cause negative impact, for example, increasing susceptibility to infection and illness, and affecting a diverse range of physical, psychological and behavioral conditions, such as anxiety, depression, and sleep disorders. In addition, excessive stress, a common phenomenon in our society, can decrease job productivity and negatively impact overall health and well-being. The ability to detect or predict stress levels could enable better self-management of one’s behavioral choices in ways that might prevent excessive stress. While various methods have been proposed for automatic stress detection or prediction in the wild from wearable or mobile phone data, it is an understudied research question of reproducibility, due to the lack of a proper publicly accessible dataset and baselines. This workshop introduces to the research

community the first publicly accessible datasets with both anonymized hand-crafted features and deep features for in the wild stress detection or prediction challenges. The datasets we are planning to make public are 1) IMEC (momentary stress labels with electrocardiogram, skin conductance, and acceleration data) 2) AMED (daily stress labels with steps, heart rate, and sleep data) 3) EUREKA (stress and mental health symptom labels with mobile phone sensors) Furthermore, we present baselines for future studies as well as several multimodal fusion approaches that jointly models different physiological and behavioral signals.

The goal of this workshop is to raise awareness of reproducibility problems in modeling wearable data in the wild, inspire ideas and collaborations, and drive the research frontier. This workshop gathers researchers with multidisciplinary expertise (computer science, engineering, psychology and medicine) both in academia and industry, fostering their collaboration towards the new state-of-the-art methods for monitoring and improving the mental health and wellbeing.

More Information