Presenters: Maggie Cheng (Illinois Institute of Technology)

Overview: The workshop will focus on the study of brain networks. The topics of the workshop include both biomedical signal processing and big data analytics/machine learning, with a necessary addition in connectomics. The modelling, analysis and inference on brain activities from a complex network approach is complementary to the study of neuro-informatics. The workshop will solicit research presentations that address computational models and analytical tools, as well as the use of large-volume, high-dimensional experimental data. Both mathematical modelling and machine learning/artificial intelligence will be covered. The theme of the workshop is consistent with the theme of BHI-2019. It is relevant to two conference tracks, and yet not fully covered by any of the tracks. Therefore, it is necessary to propose a workshop specializing in brain network analysis. 

For details click here 


Presenters: Maria Teresa Arredondo (Universidad Politécnica de Madrid); Holly Jimison (Northeastern University)

Overview: The goal of this workshop is to stimulate, through the view of different professionals in the Biomedical Engineering research arena, advancing women in the workplace. Women in biomedical and health informatics (BHI) face significant challenges in developing their careers, especially in leadership roles. A workshop focused on women’s career development provides important information and resources and helps build a community of women leaders and mentors to support professional growth of our future leaders. The intended audience includes women at all stages in their careers, from students to seasoned veterans, as well as anyone who wishes to mentor women in BHI.

For details click here


Presenters: Nenad Filipovic (University of Kragujevac)

Overview: Today the treatment in the medicine still relies exclusively on diagnostic imaging data to define the present state of the patient, biomarkers and experience of the medical doctors to evaluate the efficacy of prior treatments for similar patients. Computational methods, big data analytics, machine learning, artificial intelligence, bioinformatics, give 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 Workshop authors will present with advanced research support tools for disease characterization, and the integrative informatics; associations among heterogeneous data, that can improve the predictive power of the patient specific model. 

For details click here


Presenters: Pangiotis D. Bamidis (Aristotle University of Thessaloniki); Christos A. Frantzidis (Aristotle University of Thessaloniki)

Overview: The workshop aims to present recent advances in the organization of clinical or pragmatic trials involving data acquisition of neurophysiological, biological, sensorial and behavioural data for enabling robust and early identification of sleep and sleep-related breathing disorders at early stages. It welcomes submissions that deal with the issue of multi-modal information fusion in order to result in integrative models capable of providing data regarding the daily activity levels of their users as well as sleep patterns, such as sleep duration, quality and efficiency. Development of sleep analytics derived by the combination of multi-modal fusion with deep learning methods has the potential to provide insight into yet unobserved facets of sleep enabling precision medicine. The workshop aims to provide insight into the following research questions:

• Organizational issues related with unobtrusive, continuous data acquisition outside laboratory/clinical settings. • Integration of features derived from heterogeneous recording modalities (questionnaires, time-series, image and video analysis). • Recent advances in precision sleep modelling and challenges towards precision medicine.

For details click here


Presenters: Yufei Huang (The university of Texas at San Antonio); Yidong Chen (The university of Texas at San Antonio)

Overview: The advances and decreasing costs of genome sequencing and other high throughput technologies have led to the creation of large volumes of diverse datasets for biomedical research and drug discovery. This explosion of extensive genomic data provides exciting opportunities for developing machine learning and especially deep learning solutions for the discovery of new knowledge that can be used for better understanding of human pathological conditions and for the development of a more personalized, less toxic and more potent treatment regimen. In this tutorial, we propose to provide comprehensive survey for deep learning models developed for “omics” data and drug response prediction. The goal of the tutorial is to educate audiance about the basics of deep learning models, how deep learning can be applied to genomics data to address important biomedical resarch questions, and how deep learning advances the prediction of drug responses. 

For details click here