April 5, 2013
Several recent publications have focused on big data and data sharing in healthcare for secondary use of EMR data. First, the American Society of Clinical Oncology announced CancerLinQ. CancerLinQ is a proof of concept project which demonstrated the ability to integrate data from several cancer centers using existing tools (some open source) for research. While there are critics of this project in terms of it’s scalability and ability to integrate large amounts of data of different cancer types, its approach of attempting to simplify data integration. I commented on CancerLinQ for the iHealthbeat newsletter.
Second is a report from the Institute of Medicine on Sharing Clinical Research Data. This workshop report included pharmaceutical companies, academic researchers, and government agencies whom each have large amounts of research data and are beginning initiatives to make that data available for shared research initiatives. This is a hopeful trend and I hope to see followup on the presentations from this workshop.
Third is a report from McKinsey on The big-data revolution in US health care: Accelerating value and innovation. This report does a good job of focusing on the value of big data in health care, specifically: right living, right care, right provider, right value, and right innovation. Some see McKinsey as a late arrival in the big data realm but the report is a help addition to the discussion that cuts through some of the hype around big data.Share this:
March 1, 2013
Jack Dorsey, co-founder of Twitter and Square, spoke at Cleveland Clinic last night. Certainly a humble guy but also highly focused on using technology to solve problems. Here is the twitter stream from the presentation. Also, check out this cool 360 view.
As you can see, some very quotable lines, such as, related to the blocking of Twitter by Syria, Iran and China, “Information, like water, will always find a way.” And who does he like to read on Twitter – his mom and mom’s dog as well as his favorite authors.
“The biggest thing I learned from Steve Jobs is that you can’t follow in someone else’s footsteps.”
I love this principle of showing not telling. Doors open when I show, not tell.
@jack was asked whether he’s more artist or entrepreneur, he said artist but can never really call yourself one!
“When we drive over the Golden Gate Bridge, we don’t think about it. It’s a utility to reach destination.”
“The most precious thing we have is our health, and it’s the thing we understand least.”
“Design is immediately presenting the function through the form. Determine what is the most meaningful thing and focus on that.”
“Design is more than visual, it’s a practice – process”
“The power of the message to bring value to the receiver. ”
Great quote from
@jack talking about social media making people relatable. “The small details of life are what bind us together”
“I want to build things that will last, that are timeless…”
“Some view programming as a practical, mechanical interface, but I see it as very beautiful.”
“I believe we should build technologies that will disappear.”
But most significant was his business philosophy: Square and Twitter both founded on the premise of being a tool that “gets out of way” so people can focus on important stuff. That made me wonder about health information technology and particularly EMRs. Many (especially providers and patients) that the technology often gets in the way of the encounter instead of disappearing. How can that change? Mostly, I think in the user interface and device level. Can the EMR be mobile rather than having a desktop computer in the exam room? How about the provider being able to dictate and have that information inserted into the record. Are mobile apps for patients and quantified self transparent enough that they get out of the way or are they as clunky as large EMRs?
I think we need @Jack to teach us about the “art” in the UI and to think from the users perspective rather than starting with the technology.Share this:
February 26, 2013
IBM Watson is going to medical school at Cleveland Clinic. What Watson has to bring to medicine is the potential for advanced clinical decision support. Specifically algorithm-based, Bayesian decision analysis, rule based and expert systems. Several hurdles exist to accomplishing this: acquiring and validating of patient data, modeling of medical knowledge, keeping the data up-to-date, validate and integrate with the workflow. This process fits well with the Learning Healthcare System concept from the Institute of Medicine of taking research on evidence-based medicine into clinical decision support.
IBM Watson’s process in medical school will be to improve the inference graphs based on current data through human intervention. Providing clinical decision support is based on EMR data and the medical literature using DeepQA.
“The DeepQA project at IBM shapes a grand challenge in Computer Science that aims to illustrate how the wide and growing accessibility of natural language content and the integration and advancement of Natural Language Processing, Information Retrieval, Machine Learning, Knowledge Representation and Reasoning, and massively parallel computation can drive open-domain automatic Question Answering technology to a point where it clearly and consistently rivals the best human performance.”
Welcome Artificial intelligence to medicine and specifically clinical decision support.
February 21, 2013
My recent Perspective on iHealthbeat focused on the uses of data mining of EMR data which are yet to be fully exploited. My thoughts were provoked by a New York Times article titled, Mining Electronic Records for Revealing Health Data. Although data mining in healthcare has gotten a bad reputation, an approach which respects privacy and a focus on research discovery can yield important results. The potential uses of EMRs in research is another opportunity yet to be realized.
A new article in The Atlantic, The Robot Will See You Now, discusses IBM Watson and other initiatives moving medicine toward what I call Algorithm Medicine and Artificial Intelligence. The potential of mining EMRs to generate real-time clinical decision support has exciting possibilities. However, there are skeptics, especially when the predictions expand to entertain the idea of replacing physicians. Realizing the limitations of technology must be acknowledge. For instance, the concerning problem of copy-and-paste in EMRs would have a negative affect on data mining those records. Also, data mining has presents real challenges both in defining research questions and finding the correct data to answer those questions.
So data mining shows promise but a realistic approach without wild predictions can lead to real discovery and impact on practice.
January 6, 2013
I was happy to have the opportunity to contribute to the iHealthbeat titled “11 Experts on Health IT Progress, Frustrations and Hopes for 2013″ with some very good company. I noted the growth of EMR adoption and mHealth. But I neglected an area which I will be more immersed in this year – Clinical Analytics which is one of the strongest growth areas in Health IT.
Another key set of predictions is by Lucien Engelen. Specifically, the trend toward changes in staffing in healthcare, specifically that more women are becoming physicians and more are looking at part-time work and flexible hours. Also, there are changes in location of care as length of hospital stays decrease and more care is done virtually through remote monitoring and remote communication.
Predictions about technology trends like mHealth need to be placed in the context of other changes in healthcare and there are many including the growth of the ePatient movement.Share this:
December 26, 2012
2012 may go down as a most traveled year for me both in terms of the number of trips and miles traveled but also in terms of new opportunities.
In January, I gave a lecture to the 3rd year medical students at the Cleveland Clinic Lerner College of Medicine on Biomedical Informatics challenging them to think about the future of algorithms in medicine among other topics.
Beginning in February, my chapter on eResearch in the book Health Informatics, was published.
Later in February, it was off to Las Vegas for HIMSS. I was a guest of the Dutch delegation and spoke on Electronic Medical Records: From Clinical Decision Support to Precision Medicine. It was great to see Health IT social media colleagues at the HIMSS social media center. Also during February, I was invited to be on the advisory board for Health Works Collective and contributed to their interest in European trends with a blog post on How Europe is Growing Health Apps.
In March I attended the American Medical Informatics Association Clinical Research Informatics meeting in San Francisco. I presented two posters and one podium presentation all focused on the use of EMR data in research.
Then in April, it was on to the Netherlands for TEDx Maastricht and a visit to Radboud University Medical Center in Nijmeg en to meet at the ReShape & Innovation Center see a preview of the movie The Waiting Room. Also had a tour of the In Vitro programming there with ePatient Dave. Later in April I attend the Epic Research Advisory Council for the first time. Another valuable meeting of other user of the Epic EMR on the secondary use of EMR data in research and how to integrate research into the EMR.
May brought the publication of a blog post in iHealthbeat on A Look at Social Media in Health Care — Two Years Later , a follow up post on my original commentary on Healthcare social media from 2010. Also, I attended the Patient Experience Summit at the Cleveland Clinic which included fellow HealthWorksCollective bloggers Robin Carrey and Barbara Ficarra. Also published was a Technology Brief from the American Association of Medical Colleges on Mobile Apps. These one page summaries are targeted at medical school leadership.
June brought a trip to Barcelona for the Hospital Liquido conference. I presented an updated version of From Clinical Decision Support to Precision Medicine, This was a great opportunity to see one of Europe’s most beautiful cities as well as see the health IT innovation including Doctoralia.
In July I presented virtually at Salud 2.0 in Bilbao, another offering from Spain in medical innovation. My presentation on Social Media in Health Care: A Reasoned Approach was well received. I had the opportunity to answer questions via phone. Hopefully, I will be able to attend this conference in person in a future year.
In August, I was invited to become Adjunct Faculty at Kent State University in Health Informatics. Preparing a course in Clinical Analytics to be taught in May and June, 2013. This is a completely online masters program will be a new experience for me including online videos, readings, assignments and weekly discussion topics. At the end of August I attend the Ohio Health Data Symposium at Case Western Reserve University. Ohio like many states has a rich repository of public health information on everything from chronic diseases to behavioral health.
In early September, I completed a chapter on Computing and Information for a new textbook on Wireless Health: Remaking of Medicine by Pervasive Technologies. The concept of pervasive technology in healthcare is certainly at a tipping point. The book will be out in February 2013. Also in September I attended an internal Cleveland Clinic event, the annual Healthcare Technology Forum which showcased some of the many IT initiatives at all Cleveland Clinic locations including Abu Dhabi.
October 29-31, I attend the Cleveland Clinic Innovation Summit which focused on Orthopedics but included presentations by IBM, 23andMe and Explorys.
November took me to Chicago for the AMIA Annual Symposium. With record attendance (3500), I had the opportunity to organize and present a pre-symposium workshop on Clinical Research Informatics Infrastructure and a poster on the use of a wiki to educate healthcare professionals about secondary use of EMR data. The same week I attend the Informatics Key Functional Committee of the Clinical and Translational Science Awards of the NIH. It was valuable to see what tools are being developed and particularly to attend the Integrated Data Repository workgroup. Also significant for AMIA this year was being featured on the website under Faces of AMIA and participating in the mentorship program, working with an up an coming informaticist, Anja Timmerman. I would encourage all experienced health IT professionals to participate in mentoring to bring along the next generation of informatics.
In December I presented at Cleveland Clinic Medical Informatics Grand Rounds on Use of an EMR-based Registry to Support Clinical Research. Mature EMR systems are quickly become key tools in all aspects of research
Quite a year of opportunities and evolution in my thinking. As you can see, much of my work is shifting from social media in healthcare (although this is still an interest of mine) to research informatics and specifically secondary use of EMR data. More later on what next year might bring.
December 14, 2012
One of the most powerful concepts in changing healthcare is the Learning Healthcare System explained in most detail in this Institute of Medicine report. The concept of using evidence from research to rapidly into practice in a virtuous cycle. But how exactly to operationalize this concept?
Two recent examples are beginning to move along this path in utilizing data to develop customized order sets. One is IBM Watson working with Memorial Sloan Kettering Cancer Center. Using its powerful natural language processing (NLP), Watson is able to match patient data including complex genomics with the wide array of order sets available for different types of cancer. “ The medical center has about 2,000 order sets it can pull from when choosing a cancer treatment.” And data on millions of patients. Finding patterns that match requires the speed and logic of the Watson engine.
A second example uses existing medical knowledge and updates it as published and then converts these into order sets for a procedure-based EMR system. With their combination of the knowledge of current practices in tools like Up-To-Date and an EMR called Provation, they are now combining these products to enable the regular updating of order sets in the EMR including integration with comprehensive EMRs. This demonstrates the last mile of clinical decision support and evidence-based medicine. Bringing the latest discoveries to EMR order sets through an integrated solutions.
Looking forward to more solutions that fulfill the vision of the Learning Healthcare System.Share this:
November 29, 2012
Clinical Integrated Data Repositories are now become common at academic medical centers. With tools like i2b2 and RemedyMD, plus a broad range of analytic tools, access to large volumes of clinical data for research and population management is coming to maturity. The opportunities for use of this data in enabling clinical trials and accelerating research are promising. Quality and patient safety can also be enhanced through use of electronic medical records; a recent New England Journal of Medicine article by Dean Sittig details how to “Use EHRs to Monitor and Improve Patient Safety.” ”Organizations must leverage EHRs to facilitate rapid detection of common errors (including EHR-related errors), to monitor the occurrence of high-priority safety events, and to more reliably track trends over time.”
To maximize these opportunities, physicians and other health professionals must develop skills in understanding and utilizing this data. Medical informatics has been successful in developing tools for data mining, but translating raw data into research questions and disease trends requires training medical professionals in new ways of thinking. Understanding clinical workflow in an EMR does not directly translate into this type of research. One must understand how the data is organized and coded to create disease cohorts for analysis. Informaticists are key in training a new generation of physicians in this skill. Because of the complexity of this clinical data, there are three approaches to this data mining and analysis:
- Self-service data mining enabled by cohort definition tools, both vendor developed and open source
- Analyst provided data – skilled data analysts can pull relevant data sets based on their understanding of the research question and the data. However, there are limitations on the number of experienced data analyst any organization can afford to meet the coming demand
- Predictive analytics – this is the realm of the biostatistician who will be key consumers of large data sets to create predictive models to be used in clinical practice. This is also a limited resource, so prioritizing predictive modeling projects which major impact is key
Data mining and analytics should be taught in medical schools for the next generation of providers. Data visualization will be helpful in exploring this complex, big data. More on this in a future post.Share this:
November 14, 2012
Lucien Engelen of the Radboud ReShape Innovation Center in the Netherlands, had an extensive interview at this innovative conference. In this interview he discusses how his center at Radboud Medical Center will have have a game consultant visit weekly to consult with physicians, patients and others to discuss games for health.
Twitter stream on the conference is at #GFH12EU
November 1, 2012
I am pleased to be officially Adjunct Faculty for the Kent State University Health Informatics Masters and Certificate program. This unique online program is under the school of Information Architecture and Knowledge Management, meaning it has close ties with both library science and nursing. I will be teaching Clinical Analytics in the May-June 2013 time frame and until then designing the course.
The program description states, “This integrated discipline features specialty domains in management science, management engineering principles, health care delivery and public health, patient safety, information science and computer technology.”
The program is completely online which will be a new challenge for me but is certainly becoming common for health and medical informatics programs appealing to those already in the field. The course fits well with my recent experiences of book chapters in Health Informatics and Wireless Health, the latter of which I developed video lectures. Also, my upcoming presentation at AMIA on Clinical Research Informatics Infrastructure.
And since clinical analytics is my daily focus in clinical research informatics, I am looking forward to condensing my knowledge into this course. Convergence within one’s career is not common – I am fortunate to have these opportunities come together.