Posts Tagged ‘Innovation’
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.
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
October 31, 2012
At the Cleveland Clinic Medical Innovation Summit, there was a discussion about big data in health care which moved to the issue of patient engagement and the need for not only transparency of data but also providing tools to manage and interpret data. Two panelists had important inputs – 23&Me and Dr. Harris, CIO of the Cleveland Clinic. What is needed includes PHRs, like MyChart, but also interpretation of results, such as offered by 23&Me. The tools must provide actionable results.
IBM Watson was also featured with a new initiative with Cleveland Clinic to “send Watson to Medical School” using medical students and others to improve paths for medical decisions. This exciting prospect is an experiment in human-computer interaction and machine learning. See this video for more details:
Finally, the top ten innovations announced at the conference including everything from handheld imaging to bariatric surgery.Share this:
October 26, 2012
This is a new textbook editted by Mehran Mehregany for the Wireless Health course at Case Western Reserve University in Cleveland (the course is actually conducted in San Diego). I wrote Chapter 12, Computing and Information, which outlines changes in information technology in the past 10 years and how these are enabling pervasive computing in health care. The release date is February 2013 so stay tuned. Check out the table of contents which includes a broad range of topics from gaming and social networks to medical device design and electronic instrumentation.Share this:
August 22, 2012
The Rainforest was recommended to me by my friend Enoch Choi who lives in Silicon Valley. The book has a fresh perspective on Silicon Valley pointing out the affect of the western pioneer spirit on California in general and the Valley in specific. A spirit of independence and willingness to take risks is proposed as a basis for the unique entrepreneurial direction of the Valley. The book uses several summaries of principles, such as, extra-rational motivations and “err, fail, persist”, what stood out to me were two themes which may sound contradictory: Rule breaking and Trust. This quote about rule breaking sums it up:
“For the Rainforest to thrive, people must accept that rule breaking and believing in grand aspirations are acceptable forms of social behavior. They enable someone to believe that what was previously been considered impossible is in fact possible.” And regarding trust: “the willingness to take the initiative to trust others” and “demonstrate the transparency of its motivations as part of its routine transactions.”
Although the rainforest analogy seems to go to far at times, the concept of enabling international collaboration is right on. The book makes a strong case for the unique environment which spawns innovation in the Valley and questions the ability of many cities and regions which would like to foster innovation and new companies to do so without that unique environment. One exception Cleveland Clinic which has not only generated multiple patents and spin offs but also is now showing other health care organizations how to commercialize their intellectual property.Share this:
July 20, 2012
Several new publications about Big Data in healthcare are showing up with good analysis of this emerging field.
First, an article from PharmExec called “Super-Size Me: Optimizing the Information Explosion” which came out in May. They note new sources of information including:
- Electronic Medical Records
- Social Media
- Real world evidence
- Personalized medicine
- Track and trace systems
They see significant potential value in big data:
» Uncover unmet needs
» Assess the feasibility of clinical trial designs and recruit trial subjects
» Demonstrate product value
» Conduct pharmacovigilance
» React more quickly to market changes via real-time market measurement and sophisticated KPIs
» Enhance commercial activities and enable more personalized messaging
» Deploy predictive capabilities rather than retrospective analytics
And next they note the layers of technology required:
- Collection, Aggregation, and Storage
- “Nowcasting,” real-time data analysis, and pattern recognition will surely get better.
- The good of Big Data will outweigh the bad. User innovation could lead the way, with “do-it-yourself analytics.”
- Open access to tools and data “transparency” are necessary for people to provide information checks and balances. A re they enough?
- The Internet of Things will diffuse intelligence, but lots of technical hurdles must be overcome.
- Humans, rather than machines, will still be the most capable of extracting insight and making judgments using Big Data. Statistics can still lie.
- Respondents are concerned about the motives of governments and corporations, the entities that have the most data and the incentive to analyze it. Manipulation and surveillance are at the heart of their Big Data agendas.
June 14, 2012
Electronic Medical Records: From Clinical Decision Support to Precision Medicine
With an emphasis on lethal lag time and how EMRs can be used to bring new discoveries to medical practice more quickly.Share this:
June 7, 2012
The themes of this conference, lead by Jorge Juan Fernández García, are:
- H ealthcare / Medicine
- I nnovation
- T echnology
- E ntrepreneurship