Title: Opportunities for Machine Learning and Noninvasive Sensing to Impact Emergency Cardiovascular Care
Organizers: Omer T. Inan (Georgia Institute of Technology); Jin-Oh Hahn (University of Maryland); Jacob Kimball (Georgia Institute of Technology)
Overview: While wearable sensing for cardiopulmonary health is typically covered in standard sessions at BHI, there is a compelling need to bring the emergency care community together for a special session aimed at (1) elucidating some of recent scientific discoveries in the field; (2) familiarizing the community with new sensing technologies, materials, and analytics methodologies; and (3) understanding some of the emerging sensing modalities and signal processing/system analysis algorithms. We anticipate that bringing these speakers together to discuss the latest trends in their respective areas will lead to synergistic opportunities for collaboration, and will also result in productive and exciting conversations at BHI for future research opportunities.
Title: Contactless Vital Signs Monitoring for AI Healthcare
Organizers: Wenjin Wang (Philips Research, Eindhoven University of Technology); Xuyu Wang (California State University)
Overview: Contactless health monitoring based on camera and wireless sensors is an emerging research topic with numerous biomedical and healthcare applications, especially in the background of COVID-19. Various contactless sensors, such as optical camera (RGB, Infrared, Terahertz), radio frequency (radar, WiFi, RFID), acoustic, capacitive and magnetic sensors, can be exploited to measure physiological signals (e.g. heart rate, respiration rate, blood oxygen saturation, blood pressure, skin temperature) and activity signals (e.g. movement, emotion, context) from a human face and body to assess the health condition. AI-based signal and image processing techniques are essential steps driving these measurements. In turn, the fusion of different sensor streams provides the AI model an additional source to get new insights of health informatics (e.g. public health informatics, big data analysis, smart clinical alarms).
Title: Personalized Dietary Informatics for Precision Nutrition
Organizers: Edward Sazonov (The University of Alabama); Oliver Amft, Benny Lo (Imperial College London)
Overview: The special session will include talks from the experts in this fast-growing field. Various sides of the problem will be presented by the inter-disciplinary team of researchers, including nutritionists, behavioral scientists, engineers and data scientists. The topics will include a review of core open issues, description of the sensor-based approaches to detection and monitoring of food intake, image and video processing methods, including use of AI for food recognition, issues of wearability and compliance, and other topics of interest.
Title: Leveraging big data, machine learning and computable knowledge technologies to build learning health systems
Organizers: Guilan Kong (Peking University); Allen Flynn (University of Michigan)
Overview: Learning Health Systems (LHSs) have been proposed as healthcare systems with best practices seamlessly embedded and new knowledge captured as an integral by‐product of providing care. LHSs undertake cyclical activities that collect big data from clinical practice, generate new knowledge from big data and apply that new knowledge in practice. However, traditional means of analysis are not capable enough to transform big data into valuable knowledge. Modern analytic methods including machine learning and optimizations are needed to discover meaningful knowledge. Once meaningful knowledge is generated, how to utilize the it to fuel LHSs is a challenging problem. Computable knowledge technologies have been proposed as a type of approach to embed newly generated knowledge seamlessly into a LHS cycle. Motivated by the above, we propose this special session which fits well with the conference theme.
Title: In silico clinical trials: AI and biomechanical modeling of heart disease
Organizers: Nenad Filipovic (University of Kragujevac)
Overview: In-silico clinical trials take advantage of human-based modeling and simulation technologies. This methodology has been used for modeling and simulation in both the pre-clinical trials and clinical evaluation of a future medical drug and device since its inception, taking this broad spectrum of applicability into account. Biomechanical modeling gives opportunity for a patient-specific model in order to improve the quality of prediction for the disease progression into life-threatening events that need to be treated accordingly. In this special session lectures will present combination of AI and biomechanical modeling with advanced research support tools for disease characterization, and the discovery of new knowledge; that can improve the predictive power of the patient-model.
Title: Sensor-based behavioral informatics in support of Health Management and Care
Organizers: Manolis Tsiknakis (Foundation for Research and Technology – Hellas); Nikolaos Tachos (University of Ioannina)
Overview: Health-related behaviors are among the most significant determinants of health and quality of life. Improving health behavior is an effective way to enhance health outcomes and mitigate the escalating challenges arising from an increasingly aging population and the proliferation of chronic diseases. Modern mobile technologies, such as smartphones and wearable sensors, offer unprecedented opportunities to sense and intervene on patient health behaviors in real-time, in real-world contexts, and at enormous scale. It is also of high importance to link health/medical science with behavioral informatics building on the advancement of data science/engineering and Artificial Intelligence (AI) for more active, tailored, personalized, real-time, and automated health management and care.
The field of behavioral informatics has the potential to optimize interventions through monitoring, assessing, and modeling behavior in support of providing tailored and timely interventions. This special session will highlight recent and ongoing patient-centered research using wearable sensing ecosystem and machine learning/AI to optimize interventions through monitoring, assessing, and modeling behavior in support of providing tailored and timely interventions.
Title: Advanced Sensing and Computing Techniques for Sleep Monitoring
Organizers: Wei Chen (Fudan University); Amara Amara (Geneva University)
Overview: Sleep, as an indispensable part of daily life, contributes to self-repairing and self-recovering. However, nowadays more and more people are suffering from sleep disorders. It not only deteriorates the quality of life and raises health risks, but also becomes a significant cause of morbidity and mortality and imposes a significant economic and social burden. Seeking innovative solutions and new technologies for sleep monitoring and management is very important. The emerging technology on sensing techniques and artificial intelligence has inspired innovation in sleep research. The novel sensing materials, remote and wearable sensors, as well as unobtrusive monitoring technique enable continuous and comfortable monitoring of sleep multi-parameters, like electroencephalography, electrocardiography, respiration, blood oxygen saturation, etc.; artificial intelligence including traditional machine learning methods, deep learning methods, and expert systems paves the way for accurate processing of vast amounts of sleep data, like sleep staging, efficient detection of sleep alterations and sleep disorders, etc. With the multi-disciplinary research on sleep, smart sensing systems, biomedical signal processing, and deep learning help bring new development for improving the quality of sleep for people ranging from babies to the aging population during their everyday life and have a long term social impact.
Title: AI-driven Informatics and Technologies for Cardiovascular Care using multi-modal data from EMRs and/or Wearables
Organizers: Bobak Mortazavi (Texas A&M University); Wenyao Xu (University at Buffalo)
Overview: The integration of clinical cardiovascular outcomes research with biomedical and health informatics remains an important interaction that requires more formal merging of communities. Cardiovascular disease (CVD) represents a major and rapidly growing burden to the healthcare ecosystem. However, there are challenges principally around: 1) Acquiring information; 2) Developing modeling techniques that address information streams; and 3) Interpreting the inherently high uncertainty of data. In this special session, topics examined include existing wearable/EMR IT infrastructure, Interpretation of longitudinal data and variability, integrating wearable and clinical data, explore & stratify patient risk using clinical data (e.g., clinical decision making), and perform digital biomarker discovery in clinical and remote settings and transitions to telehealth settings.
Title: Real World Data analytics supporting High Value Care
Organizers: Fernando Seoane (Karolinska Institutet); Vicente Traver (Universitat Politècnica de Valencia)
Overview: The possibility to provide High-Value Care is one of the promised outcomes brought to healthcare organizations that successfully undergo through a fully digital health transformation. High-Value Care is seen by most as a way to be able to provide healthcare within the quadruple aim of healthcare, in other words providing care optimizing between benefit for the patient, burden for the healthcare professional, health outcome for the population and financial sustainability.
To provide High-Value care requires data and useful algorithms exploiting the latest capacity provided by AI. Real-word data is continuously generated across healthcare organizations but accessing it and develop the customized data processing algorithms required to feed in real-time useful information to clinician pose a multidimensional challenge combining regulation, ethics, data interoperability, data analytics and clinical acceptance. To present these challenges together with plausible solutions is of high importance for anyone working within clinical informatics, allowing care processes reengineering from that perspective.
Title: Mobile Digital Solutions in Patient Care
Organizers: Galina Ivanova (University of Leipzig, Medical Faculty, ICCAS); Georgios Raptis OTH Regensburg, University of Applied Sciences)
Overview: The transition from classical digital health applications to mobile medical applications is vastly increasing in speed. The development of mobile IT- technologies and – infrastructures can hereby be identified as the major driving force. This includes the development of portable sensors as well as changes in legislation, which drive the permission of Apps as medicinal products and their financial coverage by health insurance companies. Furthermore, the in the meantime substantially changed acceptance of such digital solutions as well as supply restrictions, e.g. brought by the Corona crisis itself, play a substantial role in the development of such supply solution. The creation of patient centered, individualized IT solutions requires interdisciplinary teams that represent the interests of the various user groups – patients, relatives, clinicians, physicians, other treatment providers, nursing staff. The teams also ensure interoperability, transfer and availability of information and data. Such solutions, especially intersectoral solutions, are rare because regulatory hurdles must be overcome in addition to the complexity of the systems and processes themselves. Therefore, a discussion on the topic of mobile digital solutions in patient care is highly topical and urgently needed.
Title: Healthcare Analytics. Improving Healthcare outcomes using Multimedia Big Data Analytics
Organizers: Imran Razzak (Deakin University); Guandong Xu, (University of Technology, Sydney); Peter Eklund (Deakin University)
Overview: The field of health informatics has revolutionized the face of health care in the past decade. The increasingly aging population, prevalence of chronic diseases and rising costs have brought about some unique healthcare challenges to our global society. Informatics based solutions have not only changed how information is collected and stored but also played a crucial role in the management and delivery of healthcare. Intelligent and automated data processing has never been more critical than it is today. In recent years, intelligent systems have emerged as a promising tool for solving various healthcare-related domains. With the advent of various swift data acquisition systems and recent developments in healthcare information technology, vast amounts of data have been amassed in different forms. One of the key challenges in this domain is to build intelligent systems for effectively modelling, organizing and interpreting the available healthcare data. Healthcare service providers are increasingly acknowledging the strategic importance of data analytics. However, the challenge becomes how to take Big Data and translate it into information that can be used by healthcare professionals for decision making to improve healthcare outcomes and improve the quality of care. This special issue will respond to the research challenges by encouraging researchers in the computing world to bring to bear novel techniques, combinations of tools, and so forth to build effective ways to handle, retrieve, and make use of healthcare data.
Title: Computational Approaches in Neural Engineering
Organizers: James Weiland, Professor BME and Ophthalmology & Visual Sciences, University of Michigan
Overview: Computational approaches are essential for refinement and optimization of implantable neuromodulation systems. Implantable stimulators activate the nervous system to create sensory perception or modulate neural activity. These stimulators are becoming increasingly complex. A wide range of stimulus parameter settings are possible and a greater number of electrodes are being deployed. Thus, manually fitting or optimizing the stimulus output is intractable in a reasonable amount of time. To address this challenge, computational approaches that predict optimal stimulus or guide fitting based on biomarkers are becoming increasingly important to support the programming of sophisticated implants. Neural recording is an important biomarker for closed loop systems and modeling can inform the design of neural recording interfaces and aid in the interpretation of neural data. In this special session, we will present emerging methods for modeling neural stimulation and recording and computational approaches to optimizing the neural interface.
Guidelines for the submission of Special Session papers
Authors must submit a 1–page Special Session paper to participate in Special Sessions. Optionally, authors can submit a 4-page paper (for the same 1-page paper) to be reviewed and included in the conference proceedings (this is covered as 1 registration).
The benefits for each category are the following:
–4-pages SS papers: These papers will undergo the normal review process of regular-full length papers. The authors of accepted 4-pages SS papers will have the privilege to publish their work in IEEE Xplore and in the Conference Proceedings. In case of a potential rejection of a 4-page SS paper, it can be submitted as a 1-page extended abstract.
–1-page SS papers: These papers will undergo a sanity check. The authors of 1-page SS papers will have the privilege to present their work orally. However, they will not have the right to publish their work in IEEE Xplore and in the Conference Proceedings.