Health Day at KDD 2019
The SIGKDD Health Day was first held during the KDD 2018 conference in London. Due to its overwhelming success, we are happy to invite you to attend Health Day at SIGKDD 2019 to be held in Anchorage, Alaska. We plan to expand the event this year by including additional plenary sessions and a panel discussion along with various workshops, tutorials and a poster session.
Due to the rapidly increasing healthcare costs and the direct impact that health has on the quality of human life, there is an urgent need to gain insights on various health-related conditions and causal factors for human diseases using recent advances in data analytics and machine learning. Given that the health data is diverse and can be collected in various forms, there is a tremendous need to bring researchers from different disciplines and perspectives to share their insights. This health day will establish a platform for researchers to express their thoughts and recent progress in health analytics techniques and solutions.
Efficiently and effectively building machine learning and analytical models using the data collected within the healthcare domain pose various challenges. The healthcare data is typically sparse, noisy, temporal, heterogeneous, multi-source, and uncertain. More importantly, preserving patient privacy and hence lack of data availability presents an additional layer of complication in accessing the required data for conducting research. This Health Day will also bring together researchers from a wide spectrum of healthcare-related disciplines such as clinical medicine, biomedical informatics, computational epidemiology, public health, social sensing, bioinformatics, and genomics. In addition to prominent academic researchers, there will be several practitioners working in healthcare industry who will be discussing the challenges and opportunities that arise in the current healthcare practice.
In summary, the Health Day at SIGKDD 2019 will include a broad range of activities - a plenary session consisting of invited talks and panel discussions, workshops, and tutorials.
On behalf of the Health Day organizing committee, we welcome you all to attend this event!
Aug 4: A Prelude to Health Day 2019
In silico modeling of medicine refers to the direct use of computational methods in support of drug discovery and development.Machine learning and data mining methods have become an integral part of in silico modeling and demonstrated promising performance at various phases of the drug discovery and development process.In this tutorial we will introduce data analytic methods in drug discovery and development. For the first half, we will provide an overview about related data and analytic tasks, and then present the enabling data analytic methods for these tasks. For the second half, we will describe concrete applications of each of those tasks. The tutorial will be concluded with open problems and a Q&A session.
- Cao (Danica) Xiao (IQVIA)
- Jimeng Sun (Georgia Tech)
Medical research and patient caretaking are increasingly benefiting from advances in machine learning. The penetration of smart technologies and the Internet of Things give a further boost to initiatives for patient self-management and empowerment: new forms of health-relevant data become available and require new data acquisition and analytics’ workflows. As data complexity and model sophistication increase, model interpretability becomes mission-critical. But what constitutes model interpretation in the context of medical machine learning: what are the questions for which KDD should provide interpretable answers? In this tutorial, we discuss basic forms of health-related data – Electronic Health Records, cohort data from population-based studies and clinical studies, mHealth recordings and data from internet-based studies. We elaborate on the questions that medical researchers and clinicians pose on those data, and on the instruments they use – giving some emphasis to the instruments “population-based study” and “Randomized Clinical Trial”. We elaborate on what questions are asked with those instruments, on what questions can be answered from those data, on ML advances and achievements on such data, and on ways of responding to the medical experts’ questions about the derived models.
- Myra Spiliopoulou (Univ Magdeburg)
- Panos Papapetrou (Univ Stockholm)
August 5: Health Day 2019
Panel: Healthcare Beyond the 4 walls: An AI opportunity
The future of healthcare will exist beyond the walls of hospitals and doctors’ offices. Telemedicine, precision medicine, consumer health, and digital health are all advances in healthcare designed to extend beyond the traditional clinical setting. Innovative approaches are needed to deliver care in unorthodox settings and in novel arrangements. What are the opportunities for AI in these situations? How can AI serve to “meet patients where they are” and help people find and use resources to make healthcare work for their advantage? We will be joined by a stellar panel of doctors and data scientists with experiences in these fields. These are practitioners who are experienced in the challenges, the successes, and the pitfalls of
applying AI in the community or home setting.
We expect a lively panel with a diversity of perspectives to address these issue and others such as:
(young children, pregnant women, mentally and physically disabled)?
- How can digital health and precision medicine be used in underserved populations?
- What are the frontiers for behavioral and mental health care?
- Are there opportunities for AI/ML to augment healthcare in austere environments?
- What are the realities of the digital divide and how does it affect your work?
- What are the unexpected barriers of engagement with patients (and their families)?
- What additional considerations are needed when protected populations are involved
- Carly Eckert
Dr. Eric Eskioglu, MD
Executive Vice President & Chief Medical Officer
2019 KDD workshop on Applied data science in Healthcare: bridging the gap between data and knowledge
Healthcare is, traditionally, a knowledge-driven enterprise with an enormous amount of data - both structured and unstructured and these data can impact positively on the development of data-driven healthcare including precision medicine. However, in the era of big data, the mining of this data in a manner that leads to clinically actionable outcomes remains a challenge. In the deep learning era, is knowledge extraction and modeling (e.g., feature engineering, label acquisition, and knowledge graphs) still critical? Can state of the art methods identify disease subtypes Can knowledge-backed AI lead to more interpretable informatic models? How do data scientists and physicians apply this knowledge in collaboration to further the field and improve healthcare? After witnessing so many great achievements from deep learning lately, we propose to invite world-leading experts from both data science and healthcare to discuss and debate the relevance and importance of knowledge, in order to address real challenges and make an impact in healthcare. More specifically, we plan to attract high-quality original research from emerging areas with significant implications in healthcare and invite open discussions on controversial yet crucial topics regarding healthcare transformation.
Fei Wang, Pei-Yun Sabrina Hsueh, Prithwish Chakraborty, Mansoor Saqi, Dr. Carly Eckert, Lixia Yao, Fred Rahmanian, Muhammad Aurangzeb Ahmad and Ankur Teredesai
With escalating globalization, urbanization, and ecological pressures, the threat of devastating global pandemics becomes more pronounced. The impact of Zika, MERS, and Ebola outbreaks over the past decade has strongly illustrated our enormous vulnerability to emerging infectious diseases. There is an urgent need to develop sound theoretical principles and transformative computational approaches that will allow us to address the escalating threat of a future pandemic. Data mining and Knowledge discovery have an important role to play in this regard. Different aspects of infectious disease modeling, analysis and control have traditionally been studied within the confines of individual disciplines, such as mathematical epidemiology and public health, and data mining and machine learning. Coupled with increasing data generation across multiple domains (like electronic medical records and social media), there is a clear need for analyzing them to inform public health policies and outcomes. Recent advances in disease surveillance and forecasting, and initiatives such as the CDC Flu Challenge, have brought these disciplines closer––public health practitioners seek to use novel datasets and techniques whereas researchers from data mining and machine learning develop novel tools for solving many fundamental problems in the public health policy planning process. We believe the next stage of advances will result from closer collaborations between these two communities, which is the main objective of epiDAMIK.
B. Aditya Prakash, Anil Vullikanti, Shweta Bansal and Adam Sadilek
The goal of the 18th International Workshop on Data Mining in Bioinformatics (BIOKDD’19) is to encourage KDD researchers to tackle the numerous challenges of mining and learning in Bioinformatics, Biomedical and Health Informatics. To embrace SIGKDD 2019’s Health Day, the workshop will feature the theme of Data Science Meets Bioinformatics. This field focuses on the use popular Big Data frameworks, data visualization, and effective data mining and machine learning approaches for the analysis of large amounts of heterogeneous complex biological and medical data, together with innovative applications in Bioinformatics and Health Informatics. The key goal is to accelerate the convergence between Data Mining and Biomedical Informatics communities to expedite discoveries in basic biology, medicine and healthcare.
Da Yan, Sharma Thankachan, Jake Chen and J. Zaki Mohammed
How can we assist you?
We'll be updating the website as information becomes available. If you have a question that requires immediate attention, please feel free to contact us. Thank you!
Please enter the word you see in the image below: