This website is supported by the Food and Drug Administration (FDA) of the U.S. Department of Health and Human Services (HHS) as part of a financial assistance award [FAIN] totaling $15,000 with 100 percent funded by FDA/HHS. The contents are those of the author(s) and do not necessarily represent the official views of, nor an endorsement, by FDA/HHS, or the U.S. Government.
AR-BIC 9th Annual Meeting
Bioinformatics, Big Data, AI, and Public Health:
An Integrated World
Monday, March 13 – Tuesday, March 14, 2023
Wyndham Riverfront Hotel in North Little Rock, AR
Increasingly, 21st century healthcare relies upon big data streams (e.g., image, graphic and omics data) from emerging technologies. These types of data tend to be complex and multi-dimensional, and from efforts to automate digitization of legacy reference studies, necessitating integrative strategies. Meanwhile, Artificial Intelligence (AI) approaches to synthesize, interpret, and leverage data have demonstrated significant impact across a broad range of scientific disciplines. Data connectivity, computational resources, and new/advanced bioinformatic strategies fuel the rise of AI, providing new insight into underlying mechanisms of human health and disease and their susceptibility to exogenous perturbations. Thus, this meeting will provide a platform to present and discuss the current state-of-the-art practice and on-going efforts in applying AI in healthcare and enabling efficient data mining to promote public health.
Important note: abstracts must be submitted by February 24, 2023. Instructions to submit can be found via the Eventbrite order form.
Monday, 3/13, from 10 am-1 pm: Registration and Poster Setup
Monday, 3/13, from 1-2:30 pm: Pre-Conference Workshop 1: AI for Natural Language Processing
Instructor: Xiaowei Xu
Workshop Description: AI for NLPs is a fast-growing area and has been widely used in a broad range of scientific disciplines. This workshop is to introduce the basic concept and application of AI for NLPs including causal inference. You will learn
1. Causal inference from free texts.
2. Language models.
3. Learning representations.
4. Integration of language models with machine learning.
5. AI and NLP applications to drug safety and pharmacovigilance.
Monday, 3/13, from 1-2:30 pm: Pre-Conference Workshop 2: Deep Learning Based Analysis of Histopathological Images of Breast Cancer
Instructor: Joe Zhang
Workshop Description: Breast cancer is now the most commonly diagnosed cancer in the world and the disease is the leading cause of cancer mortality in women worldwide. The automatic diagnosis of breast cancer by analyzing histopathological images plays a significant role for patients and their prognosis. However, traditional feature extraction methods can only extract some low-level features of images, and prior knowledge is necessary to select useful features, which can be greatly affected by humans. Deep learning based methods can extract high-level abstract features from images automatically. In this talk, I will introduce deep learning methods for analysis of histopathological images of breast cancer and address the following questions:
· What are the impacts of image data property and preprocessing?
· How to select or develop deep learning models and perform fine-tuning?
· What metrics are used to evaluate the performance?
· How to combine machine learning techniques for performance improvement?
· What are the generalizability, challenges and promise of deep learning based methods for diagnosis of other types of cancer?
Monday, 3/13, from 3-4 pm: Opening Ceremony
Opening Remarks: Namandjé Bumpus
Keynote Lecture: Joseph Sanford & Kevin Sexton
Keynote Description: Machine learning and artificial intelligence have the opportunity to change healthcare. Eric Topol, MD believes, “The greatest opportunity offered by AI is not reducing errors or workloads, or even curing cancer: it is the opportunity to restore the precious and time-honored connection and trust—the human touch—between patients and doctors.” Joseph Sanford, MD and Kevin Sexton, MD will talk about the implementation of these technologies into an enterprise medical record system focusing on the challenges, opportunities, and common missteps they’ve encountered as Chief and Associate Chief Clinical Informatics Officers at UAMS. They’ll also introduce clinical informatics, the youngest medical specialty, and what role this specialty will play in the future of these technologies.
Monday, 3/13, from 4-5:30 pm: Industry Views and Tools: How Health Care Data Analytics Improve Quality of Care
Chair: Bryan Barnhouse
Speakers: Kenley Money, Aaron M. Novotny, Elizabeth Parker, Amanda Novack, & Nichole Stanley
Session Description: Organizations across Arkansas use data analytics and computing to increase revenue, reduce costs, create operational efficiencies, and improve overall performance. Data analytics used by hospitals, clinics, and other health care-affiliated organizations do all of that and save lives.
AR-BIC attendees interested in learning how some of Arkansas’ leading companies leverage the power of health care data analytics should attend this session. The speakers will review the challenges, opportunities, tools, and applications to convert large, accurate data into actionable and innovative solutions in their quest to improve the quality and efficiency of care and services for better patient and client outcomes.
Monday, 3/13, from 4-5:30 pm: Bioinformatics and AI in Pathogen Surveillance and Microbial Genomics
Chairs: Douglas Rhoads & Steven Foley
Speakers: Arvind Ramanathan, Jing Han, & Se-Ran Jun
Session Description: This session will explore different aspects of bioinformatics and the possible application of AI for surveillance, prevention, and treatment for microbial pathogens.
Monday, 3/13, from 6-8 pm: Poster Session
Tuesday, 3/14, from 8:30-10:30 am: AI and Healthcare
Chairs: David Ussery & Jonathan Bona
Speakers: Subhi J. Al’Aref, Catherine Shoults, Brian Delavan, Fred Prior, Jennifer Fowler, & Grover Miller
Session Description: This session includes six lectures from Arkansas scientists that are involved in using machine-learning methods for understanding medical and healthcare data. Three of them are professors from UAMS, using AI to help in research in cardiovascular medicine, cancer imaging, and drug design. The other three are Ph.D. graduate students from three different graduate programs, using machine learning methods for mining social media for adverse drug reactions, public health, and for ‘crowdsourcing AI solutions’ to challenges in Healthcare.
Tuesday, 3/14, from 8:30-10:30 am: Integrated Genomics for Precision Oncology
Chair: Joshua Xu
Speakers: Leming Shi, Ahmet F. Coskun, Dan Li, Donald Johann, & Fenghuang (Frank) Zhan
Session Description: Tumor initiating and development are driven by molecular events. Over the decades, multiple types of high-throughput omics profiling technologies have been developed and adopted in clinical research. Integrated genomics analysis can help us better understand the mechanisms and phenotypic traits of cancer, tailor treatments and improve clinical outcomes. This session includes five presentations to advance integrated genomics for precision oncology, covering multi-omics reference samples, single-cell sequencing, best practice in bioinformatics, and real-world data from clinical studies.
Tuesday, 3/14, from 11 am-12 pm: Keynote Lecture
Speaker: Ruth Roberts
Tuesday, 3/14, from 12-1 pm: Lunch
Tuesday, 3/14, from 1-2:30 pm: Drivers of Public Health in the U.S. Population: Why Valid Self-Report Measures Matter
Chair: Samantha Robinson
Speakers: Todd Shields, Ethan Dennis, Mary Margaret Hui Cunningham, & Torre (Jake) Darby
Session Description: This session will serve as a forum for psychometric and public health researchers from two institutions in our state both to share insights from a recent nationally representative survey and to realize the future potential of utilizing validated self-report measures to inform public health initiatives, including those related to mental health.
Research related to the conference theme or otherwise relevant will be presented in both 10-minute standard and 15-minute presentation formats, depending upon time allocation for the session. By providing an opportunity for the dissemination of this multi-institutional, multi-disciplinary work of this research group, this session will truly showcase the collaborative power of our Arkansas researchers.
The session may also include a panel discussion. During this portion of the session, speakers will have the chance to share with their fellow researchers their experiences working with national large-scale survey data.
Tuesday, 3/14, from 1-2:30 pm: Machine Learning and Deep Learning for Big Data Analysis and Drug Development
Chairs: Huixiao Hong & Shraddha Thakkar
Speakers: Joe Zhang, Jie Liu, Vibha Jawa, & Nuria Mencia Trinchant
Session Description: Currently, artificial intelligence, mainly machine learning and deep learning, is in a Cambrian era with new advanced algorithms being developed and applied across almost all fields. While machine learning and deep learning were developed and applied in the context of other fields, they have all been successfully applied to big data analysis and drug development. To give well-deserved attention to the many facets of applications of machine learning and deep learning to big data analysis and drug development, this session will provide the audience a great lineup of presentations that report most recently progresses in applications of machine learning and deep learning to big data analysis and drug development from well established scientists in this field from various institutions.
Tuesday, 3/14, from 2:30-3 pm: Poster Awards and Concluding Remarks