Update time: 2018-07-13 10:41:08

Pitfalls of health Big Data

Leo Anthony Celi / Atipong Pathanasethpong 

The adoption of electronic health records (EHR) has created new opportunities for clinical research using large, rich patient-level databases. With these data, researchers are in a position to approach questions with statistical power previously unheard of in medical research. In this workshop, we present and discuss challenges in the use of EHR data for research, as well as explore the unique opportunities provided by these data.

Applied Statistical Learning in Python

Calvin Chiew

This workshop aims to introduce clinicians to popular statistical methods used in machine learning, without delving into the underlying mathematical theory. We will focus on the random forest and support vector machine for classification, as well as general concepts of model fit and cross-validation. In the hands-on exercise, you will be asked to implement and evaluate these models on a clinical prediction problem. No prior programming experience is assumed. Basics of the Python language and Jupyter notebook environment will be covered.


Image Recognition in Healthcare

Guido Davidzon


Interpretation of imaging data is paramount in the practice of modern medicine. The number and complexity of medical images continues to grow together with the awareness of human errors in healthcare. These could challenge the scalability of human-only interpretation of medical images. Recent advances in deep learning show that computers can aid humans in the task of analyzing medical images with the promise of increasing accuracy and maybe improving clinical outcomes. This workshop will introduce participants to the use of machine learning for image classification. Participants will initially learn about recent work in AI and medical imaging and then apply newfound knowledge.


Design Thinking and Human-Centered Design

Tony Gallanis


Frailty is an unmet challenge around the world. With an aging population that will live longer than ever before, the needs of the elderly are of great importance. The science and research behind aging and the frailty phenotype are increasing rapidly to address our aging society. This presentation will cover the influx of new research on frailty among the elderly and teach design thinking solutions through human-centered design to rapidly overcome the challenges of an aging population. The presentation will specifically showcase avenues for machine learning in relation to human-centered design and propose applications in society.


Data for Improvement Workshop

Mataroria Lyndon


Data is a critical element of improvement. This workshop will provide an introduction to improvement science in healthcare. By using case studies and team-based activities, participants will learn practical skills and techniques for quality improvement - systems thinking, measurement, analysis, and implementing change into practice. While this session is focused on healthcare, participants will gain the ability to formulate and create changes that can have a lasting impact in other fields and disciplines. No programming skills are required.


Introduction to Digital Phenotyping

Maia Majumder


This workshop aims to familiarize participants with the public health utility of Google Trends. Through experiential learning, attendees will use spatiotemporal data extracted from the Google Trends platform to explore hot topics in public health surveillance. Limitations and use cases will be discussed.

Laying Down the Pipeline for Health Analytics in the University Teaching Hospital

Alvin B. Marcelo

Teaching hospitals are sources of tremendous amounts of data which can be used for analytics, but in many low to medium income countries, emerging privacy regulations and unfamiliarity of university officials on the governance and ethical aspects of data sharing have prevented the availability of such data for these purpose. The Asia eHealth Information Network promotes the Mind the GAPS framework which reminds officials to ensure that there should be strong governance behind the Universitys analytics program, a clear architecture shared by the stakeholders, good and capable program management, and adoption of standards for interoperability. 

Entrepreneurship & Innovation

Chris Moses

In this workshop, we will learn about tried and tested ways to build the rightproduct. The biggest risk you have in new product development is building the wrong thing. How do we figure out if were solving a real problem? How do we learn this quickly and cheaply? What tools do I use, and how many people do I need to talk to before I can confidently move forward? Now that we know how to validate our product ideas, lets practice one of these methods. We will work in groups to first diverge, then converge on 1 idea per team, then rapidly develop a low-fidelity prototype we could take to users for testing. This hands-on workshop will give participants a fun way to make rapid progress and minimize groupthink during product development

Machine Learning Tools in Healthcare Analytic

Wanida Kanarkard

Machine Learning (ML) is the fastest rising topic in health analytics is of extreme challenge. The aim of Machine Learning is to develop algorithms which can learn and progress over time and can be used for predictions. It offers a variety of alerting and risk management decision support tools, targeted at improving patients' safety and healthcare quality. This workshop will introduce machine learning tools e.g. H2O, Google Colaboratory, Microsoft ML are built to solve different challenging problems in healthcare.

Clinical data mining: real practice and pearls
Kittisak Sawanyavisuth

This workshop aims to facilitate clinicians to conduct a research in their clinical practice. The participants will learn how to develop research questions, collect clinical data, and use appropriate statistics. Clinical data sources and national data sources will be demonstrated. All other issues regarding clinical research will be discussed including tips for manuscript writing, submission to the right journal, or how to response to reviewers’ comments.

Contact us:

copyright © 2018 KKU Datathon, Khon Kaen University. All right reserved.