I was pleased to be able to spend some time this week with the Statistical and Applied Mathematical Sciences Institute (SAMSI). If you are not familiar with SAMSI, it is a partnership of Duke University, North Carolina State University (NCSU), and the University of North Carolina at Chapel Hill (UNC) focused on statistical and mathematical sciences. They held a great conference this week on Advanced in Precision and Personalized Medicine, and I was fortunate to be able to share some of the progress we’ve made at UNC Health Care in unlocking opportunities in data sciences and analytics. It was impressive to see so many people convened together on this topic. I wasn’t able to stay long, but did get the opportunity to see Glen Colopy’s presentation on monitoring for clinical deterioration, which was excellent.
Take a look at the photographs below and see if you can detect what is unusual about these people. Look carefully!
The answer is that these are not real people — they are photographs generated by analytics.
Using a type of unsupervised machine learning called a generative adversarial network (GAN), Phillip Wang developed the website ThisPersonDoesNotExist.com which dynamically generates a new human face every time the page is refreshed. His model was trained on 70,000 human photographs, and demonstrates how effectively machines can not only process image data, but can be trained to generate new data based on observable patterns.
One attribute of GANs is that it puts two analytical models in competition: one model generates the fake photos, and the other model tries to distinguish real from fake. These exact same techniques are already being used in healthcare to develop analytical approaches to detecting pathologies in clinical imaging!
After taking a break for a few years, I was able to attend this year’s annual HIMSS conference. If you were unable to attend, I can sum up the industry trends in two words: interoperability and analytics. I was there for several days, and I never saw a presentation or exhibit that didn’t discuss analytics. It’s quite a contrast from even a few years ago.
The highlight of the event for me this year was being able to accept UNC Health Care’s award for reaching AMAM Stage 7. As one of the first and only organizations to ever reach the top, I could not be more proud of our teams at UNC Health Care. In addition, I was asked to give a talk on “How Practical Big Data Management Can Drive Value in Healthcare” (session BG5 held Monday Feb 11 at 2:30PM). I’ve posted my slides here if you would like to review the talk.
I had the wonderful opportunity to participate in today’s Health Technology Symposium: Health Ethics at the Intersection of Data and Technology being orchestrated by the Carolina Health Informatics Program (CHIP). If you are not familiar with CHIP, you should be — it is a very unique interdisciplinary research and training program focusing on health informatics research, data sharing, development, and education. The program draws faculty, health care professionals, and students from across the UNC campus to conduct basic and translational research and to offer graduate training in health informatics for scientists across the disciplines and for clinicians in medicine, nursing, public health, dentistry, and pharmacy. I’m fortunate to be able to serve on their Health IT Advisory Board, and always enjoy hearing about the tremendous work they do. See their Twitter feed for examples of their activities.
I’m honored to have been asked by HIMSS to share some of the models for success in developing health analytics capabilities at next week’s HIMSS Big Data & Healthcare Analytics Forum in Boston, MA. As I shared in my last post, UNC Health Care is one of the first and only organizations to achieve Stage 7, the highest level of analytical capability development, as assessed by the HIMSS Analytics International Adoption Model for Analytics Maturity (AMAM). Along with Philip Bradley, regional director of North America for HIMSS Analytics, we will be talking about some of the competencies that are associated with these advanced stages of maturity. I hope you can join us!
If you are interested in what my team and I are up to at UNC Health Care System, WRAL Techwire’s story “Using ‘big data’ analytics to improve healthcare: Growing UNC Health Care data wranglers search for answers” tells the story well.
I was asked by the folks at Corinium Global Intelligence to give a keynote address and participate in a discussion panel at their Chief Data and Analytics Officer Winter Event. It was a great opportunity to provide a little more context behind our strategy of shifting from a project to capability-based approach to analytics application. I tried to weave in a few case studies just so people could see how some of this is actually applied as well.
It was interesting to note the commonalities that are emerging between health care and other industries as it attempts to develop these new business capabilities. Though healthcare’s understanding of how to develop and operate advanced analytics “at scale” is immature compared to, for example, it’s competencies around descriptive statistics in areas like quality measures, the market is evolving rapidly.
Corinium was kind enough to post a copy of the slides to LinkedIn, so I thought I would share the presentation with you as well.
I was delighted to be invited to PharmaSUG China’s annual conference to deliver a keynote address on the state of health analytics. It was an amazing trip!
During my visit, I had an opportunity to meet with some executives of one of Shanghai’s largest health delivery systems. Speaking through interpreters, we discussed how the use of advanced analytics can help transform the quality and cost of care. One of the most significant contrasts I noticed between this discussion and others I’ve participated in was the marked lack of focus on financial analytics. Because China’s health care system is government funded, hospital systems are less driven to focus their time and energy on issues like reimbursement — a major driver of costs here in the US for both hospital systems (who are forced to employ armies of reimbursement experts to get paid for the patient services they deliver) and the patients (who can face anything from rising co-pays to bankruptcies due to escalating health care costs). The entire focus of our conversation was how to help patients get better health outcomes.
Beckers Hospital Review gave a nice shout out to 5 health delivery organizations that are investing in data-driven population health programs. Our team at the UNC Health Care System was one of the five recognized for the work we are doing.
CIO Review recently published an article I wrote regarding how the health care industry can increase the value from their information technology assets. The article, called The Coming Era of High Performance Medicine, focusing on the intersection of enterprise architecture and data sciences.
For those that may be unaware, I’ve taken on a new role with the UNC Health Care System, and I am building a new team. We are creating an innovative, industry-leading example of a system-wide health analytics organization – one that is truly focused on bringing advanced analytics, data sciences, agile engineering, and user enablement together to empower health care. If you love data and want an opportunity to really see how it can improve patients’ lives in one of the nation’s leading academic medical systems, we just might have the perfect opportunity for you.
Go to UNC Health Care’s Career page and search on keywords “Enterprise Analytics” to see the current openings. The site is constantly be updated with new roles, so check back often.
Information Management did a nice article on the work our team has been doing in using data and analytics to reduce hospital readmissions. It also covers some of the principles we have used in building our enterprise analytics strategy and organizational functions.
UNC, Duke, and other universities in our state have a joint Health Informatics Research Seminar series, and they were kind enough to ask me to come share some thoughts on the state of the health analytics industry. You can see a recording of the talk titled Making Medicine Smarter Through Analytics and Data Sciences by clicking the seminar broadcast link.
Medical Informatics World asked me to deliver a keynote address on how analytics are evolving within the health and life sciences markets. They were nice enough to record the talk and post it to YouTube, so I’ve provided the link here. If you’d like to see the slides and hear the accompanying talk track in more detail, I’ve posted a slide recording to YouTube as well. The basic question I’m intending to address is whether medicine truly become a performance-driven industry.? The complexity residing at the intersection between the science of medicine, the delivery of health care services, and natural patient variation has made it difficult to scale organizational performance beyond the effectiveness of individual contributors. Yet other fields such as space exploration, battlefield operations, meteorology, financial services, and automotive racing have demonstrated that comparably complex systems can be characterized and even managed to very high levels of performance. By adopting similar capabilities in the context of population health, accountable care, and personalized medicine, my premise is that health and life sciences organizations can unlock a new era of clinical, financial, and operational high performance.
I also delivered a separate talk on enterprise architecture, which I will post separately later. And I got the opportunity to share the stage with some of my favorite industry speakers during two panel discussions.
I recently had an interesting Twitter exchange with my friend Dan Munro over at Forbes regarding a KevinMD posting, Quality is a Word that Lacks Universal Meaning. The article touched on one of my book topics: the industry’s reporting-centric, manufacturing-oriented conceptualization of quality is ambiguous and unreflective of the problem space. We need to look at quality differently…
Well, today is the day — Health Analytics: Gaining the Insights to Transform Health Care is finally out! I promised to cover the book in more detail, so today I thought I would take the opportunity to answer some of the more common questions that I get asked about the book.
This past summer, I was fortunate enough to be asked to deliver one of the keynote addresses at the first Health Analytics Symposium conference. Afterwards, a number of people asked for copies of my materials, which I’m fine to provide except no one ever knows what I said around each slide, and the slides themselves are far from self-explanatory. So I managed to get a partial recording of my presentation, and have posted it here for those that might be interested. Note that some of this content will be in my upcoming book on health analytics. More on that later.