Overview

Fast-growing biomedical and healthcare data have encompassed multiple scales ranging from molecules, individuals, to populations and have connected various entities in healthcare systems (providers, pharma, payers) with increasing bandwidth, depth, and resolution. Those data are becoming an enabling resource for accelerating basic science discoveries and facilitating evidence-based clinical solutions. Meanwhile, the sheer volume and complexity of the data present major barriers toward their translation into effective clinical actions. There is thus a compelling demand for novel algorithms, including machine learning, data mining and optimization, that specifically tackle the unique challenges associated with biomedical and healthcare data and allow decision-makers and stakeholders to better interpret and exploit the data.

Recent years have witnessed major breakthroughs in machine learning that is equipped with powerful optimization technologies. For example, the concept of “deep learning” often leads to automated feature discovery from data and it has achieved impressive performances than traditional learning methods when processing large unstructured corpora. For biomedical informatics needs, deep learning methods have recently made notable advances in processing brain-imaging data and making neuroscience discovery, although their utilities to more biomedical informatics use-cases still awaits further assessment. On a general note, biomedical data often feature large volumes, high dimensions, imbalance between classes, heterogeneous sources, noises, incompleteness, and rich contexts. Such demanding features are also driving the development of numerical optimization algorithms in tandem with that of machine learning algorithms.
​
The BOOM workshop aims at catalyzing synergies among biomedical informatics, machine learning, and optimization. This workshop is targeting an audience of applied mathematicians, computer scientists, industrial engineers, bioinformaticians, computational biologists, clinicians and healthcare researchers who are interested in exploring the emerging and fascinating interdisciplinary topics. It is designed to foster exchange of ideas between often-disparate groups that are unaware of each other's research, and to stimulate fruitful collaborations among different disciplines.​



Topics of Interests

We encourage submissions from, but not limited to, the following inter-linked areas:

Category I: Machine Learning and Optimization Algorithms
● Applying cutting-edge machine learning (e.g., deep learning) and optimization techniques to tackle real-world medical and healthcare problems.

● Addressing challenges and roadblocks in biomedical informatics with reference to the data-driven machine learning, such as imbalanced dataset, weakly-structured or unstructured data, noisy and ambiguous labeling, and more.

● Designing novel, applicable numerical optimization algorithms for biomedical data, that is usually large-scale, high-dimensional, heterogeneous, and noisy.

● Re-visiting traditional machine learning topics such as clustering, classification, regression and dimension reduction, that find application values in newly-emerging biomedical informatic problems.

● Other closely-related disciplines, such as image processing, data mining, new computing technologies and paradigms (e.g., cloud computing), control theory, and system engineering.


Category II: Biomedical Informatics Applications
● Computational Biology, including the advanced interpretation of critical biological findings, using databases and cutting-edge computational infrastructure.

● Clinical Informatics, including the scenarios of using computation and data for health care, spanning medicine, dentistry, nursing, pharmacy, and allied health.

● Public Health Informatics, including the studies of patients and populations to improve the public health system and to elucidate epidemiology.

● mHealth Applications, including the use of mobile apps and wearable sensors for health management and wellness promotion.

● Cyber-Informatics Applications, including the use of social media data mining and natural language processing for clinical insight discovery and medical decision making.
​
We encourage papers with important new insights and experiences at the intersection of machine learning, optimization and bioinformatics. Those contributions should shed light on at least one topic mentioned above, while the above topics have obvious overlaps. For topics in Category I, we invite both theoretically novel and application-driven papers. For those in Category II, the idea is to keep the interested application domain focused yet broad, echoing multiple scales, ranging from molecules, individuals, to populations.


Submission

The IJCAI BOOM’17 workshop solicits:
(1) Full Papers (6-8 pages + reference) that describe original research work that have not been published before, which will be published in a special issue of EURASIP Journal on Advances in Signal Processing (JASP).
(2) short abstracts (1 page) that either highlight significant works that have been published or accepted recently or report unpublished research findings, which will be included in workshop online proceedings (unarchived).


Important Dates

Submission deadline: April 18, 2017 (tentative)
Acceptance notification: May 13, 2017 (tentative)
Camera Ready: June 15, 2017
Workshop: late August, 2017