Life as a Health Data Scientist

Sherine El-Toukhy, PhD, MA, NIH Distinguished Scholar, National Institute on Minority Health & Health Disparities "Can digital health technologies alleviate health disparities?" was the topic of our special interest group panel discussion at the National Academy of Medicine (NAM) Annual Meeting , organized by Lucile Adams-Campbell , Head of Minority Health and Health Disparities at Georgetown University, at the Academies yesterday - a rainy Sunday afternoon..perfect weather for some hot tea and a thoughtful discussion. The AHRQ  publishes the National Healthcare Quality and Disparities Report annually to assess the performance of our healthcare system and disparities based on measures of quality and access.  The report summarized that over 50% of measures that assessed access to healthcare from 2000 to 2017 showed improvement; 33% did not change and 14% showed worsening. Quality of care improved overall but pace of improvement varied with only 1/3rd of care...

A group of Graduate students at the Georgetown HIDS program applying design thinking to Health data  "Make it simple but significant" -- Don Draper, a fictional character on the AMC's TV Show Mad Men.  We could easily attribute Don's success with his advertising campaigns to meticulous application of design thinking. Design thinking is a breakthrough model for human-centered innovation and problem solving where multi-disciplinary teams work iteratively to rapidly prototype products. This process of 1. Need finding 2. Ideation 3. Prototyping 4. Testing 5. Implementing and then back to 1. Need finding has been used across sectors to solve complex problems such as redesigning school curriculum to connect students to the world outside classrooms and designing future aircraft cabins. Last week, our students learned that applying design thinking to healthcare can improve patient and provider experiences as well as reduce medical errors, especially in this day an...

Developing a new drug costs $2.56 billion! (Tufts Study ) We all agree that data-driven drug development can help reduce costs and save time. But how do we collectively make this happen? This was the topic of discussion at a panel organized by the Center for Data Innovation, a non-profit, non-partisan think tank studying the intersection of data, technology and policy. Our panel with Chris Austin , Director of NCATS and Brad Casey , Associate Director of Research Programs at Michael J Fox foundation  was facilitated by Joshua New, Senior Policy Analyst at the Center. We were asked to discuss opportunities and challenges in creating a National Health Data Research Exchange to drive data-driven drug development. I share with you salient points from our panel discussion here.  Why Now? Lot has changed over the last decade to enable this data-driven innovation. Due to digital transformation of the healthcare ecosystem, >95% of hospitals have adopted ...

“What happens if someone yelled FHIR in an exhibit hall filled with 43,000+ Health IT and data science professionals?” This was the trending joke at HIMSS’18 in Vegas this March. An interesting tweet captured all the exercise attendees got while at HIMSS’18 – 382 miles walked (we basically walked from Durham to Atlanta), 737,713 steps traversed (climbed the empire state building 3 times), 255 floors climbed (ran 15 marathons), all just in 5 days at the beautiful Venetian . The excitement was palpable both live and in cyber space. An undercurrent of machine learning (ML) and Artificial Intelligence (AI) was prominent in all forums and education sessions. I jotted down a few key lessons and takeaways: Data engineering is equally important or maybe more important than downstream modeling and algorithms. If taking on large AI projects, be prepared to invest resources in “data janitorial activities” to extract, clean, standardize and prepare data for analysis...

2017 was a busy year at the Georgetown Innovation Center for Biomedical Informatics,  ICBI ! Driven by our mission to apply data insights and informatics in advancing human health, our team led or contributed to numerous innovation, service and education projects. I share a few of our aha moments from 2017 here with you. 1. Innovation Text2Action : Clinicians and patients must know the strength of scientific evidence that associates genes to drugs to advance personalized care. A pubmed search for 50 cancer genes with FDA approved on label or off label treatments and/or investigational drugs in clinical trials yielded 47,558 articles on Nov 13, 2017. This would take a trained biocurator roughly 142,674 hours or 17,834 work days or 8 years to complete. Sounds like a project ripe for automation, right? In collaboration with the Computer scientists at University of Delaware, we developed a NIST TREC Challenge award winning natural language processing method that not only automates...

Modified from Thomas Wilckens, MD Many of us who work at the interface of cancer clinical research and biomedical informatics were thrilled to hear about the cancer moonshot program from President Obama, announced in his final State of the Union Address on Tuesday, Jan 12, 2016. VP Biden, the nominated leader for this effort, has pledged to increase the resources available to combat the disease, and to find ways for the cancer community to work together and share information, the operative word being “share” (after ‘resources’). In this post, I briefly review four thematic areas where informatics is already playing a key role to help realize cancer moonshot goals and identify challenges and opportunities. Immunotherapies: Recent approvals of ipilimumab (Yervoy), sipuleucel-T (Provenge), Nivolmab (Opdivo) and Pembrolizumab (Keytruda) represent important clinical advances for the field of active immunotherapy in oncology and for patients. Immunoinformatics played a critica...

Photo Photo Credit: Health Data Consortium It was a treat to all data enthusiasts alike! What started out five years ago with an enlightened group of 25 gathered in an obscure forum has morphed into Health Datapalooza which brought 2000 technology experts, entrepreneurs and policy makers and healthcare system experts in Washington DC last week. “It is an opportunity to transform our health care system in unprecedented ways,” said HHS Secretary Burwell during one of the keynote sessions to mark the influence that the datapalooza has had on innovation and policy in our healthcare system. Below are my notes from the 3-day event. Fireside chats with national and international leaders in healthcare and data science were a major attraction. U.S. Chief Data Scientist DJ Patil discussed the dramatic democratization of health data access. He emphasized that his team’s mission is to responsibly unleash the power of data for the benefit of the American public a...