John R. Zaleski is CTO & VP of Clinical Applications at Nuvon, Inc. Dr. Zaleski works in fields related to healthcare information technology, clinical informatic... Read More
Blog
2.20.2012 | 0 Comments
Kent Bottles’ piece “break out of the prison of the American health care delivery system” nails it: just as the 19th century focused on the new idea of identifying pathology of disease, the 21st century needs to be the one that evolves beyond screening for ailments that are already there, to the point of (in Dr. Susan Love’s words) finding of root cause.
2.20.2012 | 1 Comment
According to Lucy Mckeon in her article “The coming medical revolution“, that’s how much medical data are produced yearly. In this article she interviewed Dr. Eric Topol, Chief Academic Officer for Scripps Health.
In this interview, Dr. Topol lists three areas in which data–big data–and the human genome are contributing to the shift toward personalized medicine. I briefly summarize these below and leave to the interested reader the link to the page above:
1) Pharmacogenomics and the ability to assess whether certain patients will respond to certain drugs based upon genotype. The statistics stand at $350B for the amount the US spends annually on prescription drugs. Many drugs do not work on certain individuals (e.g.: Plavix – 1/3 of those taking have no response; Metformin – 1/4 of diabetics unresponsive). The effects of underlying genetics could be better understood with a genotype of individuals, thereby resulting in better targeting of drugs based on individual. Genotyping is a major big data producer.
2) Cancer therapy and tumor genomics in comparison to the germline DNA of the individual. Comparative analysis can lead to better, more directed therapies. Certain cancer treatments, when directed based on the underlying genotype, can lead to better outcomes. Cancer therapy is a major big data consumer.
3) Reduction in what Topol terms the idiopathic relative to “guessing” at therapies that would / could / should be revealed by the underlying genome that would establish biological basis for disease.
2.19.2012 | 0 Comments
Powered by Twitter Tools
2.18.2012 | 1 Comment
Is social media the new way of life? Are we to avoid it as a fad or simply agree to “become one with the Borg?” Is social media a means for improving the communication between we as the patient and we as the physician? There are many reasons to use social media, and many reasons to avoid it…especially if you are a professional. Once something appears on the Web it is effectively there forever (I know…)
I have been maintaining this blog for about 4 years now and have over 120 posts on various topics related to clinical decision making, medical devices, and data as well as links to my books, etc. I maintain this primarily for myself… as a professional diary and as a social tool for professional interaction. By and large this goal has been and is being achieved. Yet, I read something interesting on the use of Google+, with special emphasis on a use case for physicians, primarily, that provides a vehicle for interaction among themselves, possibly with their patients, and as a safe haven that is not quite as revealing as Facebook and not as “minimalist” but yet as open as Twitter.
In the world of medicine, especially in the relationship between physician and patient, it is extremely important to maintain privacy and control of the conversation. One of the key challenges in the health information technology age is ensuring that patient information and the communication between physician and patient remain private with control in the hands of the participants. I emphasize that security and control are key. The next generation of social media may involve more of the security and less of the social. This aspect of communication, once trustworthiness is assured, may represent or reflect the maturing of the technologies that heretofore have been seen as the wild west.
2.14.2012 | 0 Comments
When I began conducting my own research ~20 years ago, I envisioned interaction among large numbers of databases from which I could automatically draw needed information to assemble the models I required to verify performance of one patient in comparison with a population of patients having the same specific characteristics. The comparison of a test patient with a population was not only the basis for my predictive methodology but a basic tenet of Bayes’ Theorem and conditional probability. I envisioned back then a day would come when all the data I was attempting to cobble together by hand and by computer would be readily available… perhaps 10 years down the road.
Fast forward to today.
In the AHRQ’s opening FAQ about what comparative effectiveness research (CER) is, they state that, they state that “Comparative effectiveness research is designed to inform healthcare decisions by providing evidence on the effectiveness, benefits, and harms of different treatment options.”
Physicians rely on evidence, in the form of corroborating (and some contradictory) studies to validate and verify hypotheses related to treatment. Accepted treatments and approaches for care are those most usually associated with corroborating evidence–a great deal of corroborating evidence. Not all data arrive in the form of simple measurements. Data take on the form of studies, published research papers, laboratory results, films, guidelines, textbooks, and from bedside medical devices.
To a degree, the electronic health record (EHR) was seen as a key element in achieving the type of data richness that was necessary to support comparative effectiveness research. The EHR and its adoption are necessary but (yet) insufficient in terms of the CER enterprise. In “Optimizing Health Information Technology’s Role in Enabling Comparative Effectiveness Research“, Navathe and Conway note that “…[f]or CER to be conducted, …EHRs must be connected to data networks enabling access to at least portions of their captured data. It will be challenging to implement EHRs on a large scale and to develop electronic networks substantial enough to produce observational data that alter clinician, patient, and other decisions.”
As Navathe and Conway state, healthcare data is not just personal, it is a strategic asset upon which basic research depends. Despite visions of a unified, singular database “Borg” where all data would go to be mined endlessly by large mainframes, the facts most probably near term and into the future are that data will be federated. They will reside in many different pockets “owned” by many separate and disparate institutions large and small. The key, then, to my mind, is not figuring out how to assemble them into some common structure, but enabling their inter operative interaction, much the way the Internet operates today. When we type in a Google query, we are not interacting with some great big “WOPR” computer (references to the 1983 movie WarGames), we are interacting with millions of computers around the world.
What I did not realize 20 years ago that I have finally come to realize is that I thought then the “hard” problem was solving the predictive model for the patients I was monitoring, when the really hard problem was assembling all of the data together from the many disparate sources. Through all of the standards committees and claims of interoperability, we are really a long way off in terms of enabling the one thing that would allow us to do what I had started out almost 20 years ago doing: automating the data collection, from any source, that would allow us to focus on the real business of health care research, and would enable the vision of comparative effectiveness research.
2.12.2012 | 0 Comments
Powered by Twitter Tools
2.06.2012 | 0 Comments
Some months ago I meant to put this on the blog and it has been sitting in draft form wallowing.
In reference to the medical device alarms topic, there is a very good source for high frequency and fidelity monitoring data. The MIMIC-II database is an excellent source for waveform level modeling data taken from critical care patients and deidentified for use in research. A key reference for the scope of the data found in the database (which is generally available for access at no cost) can be found in the following paper:
Saeed et al:, Multi-parameter Intelligent Monitoring in Intensive Care II (MIMIC-II): A public-access intensive care unit database
2.06.2012 | 0 Comments
So, I was reading Information Week Healthcare and there is a great piece titled “Healthcare IT Needs More Crazy CIOs“. In this article Paul Cerrato talks about MD Anderson Cancer Center’s CIO Lynn Vogel. It turns out that they developed their own EMR, and for many of the reasons I have been discussing with my physician colleagues. One reason stood out bang on the dot:
Most commercial vendors are focused on either routine hospital or physician care, Vogel says, and don’t incorporate the latest clinical research data into patients’ records.
CIO Vogel continues:
In cancer care, that routine just doesn’t work, Vogel says. “It used to be a university would do the research. Five, six, seven or eight years later, it would show up in some clinical practice,” he says. “We want to shorten that. When people have cancer, they don’t want to wait four or five years.” They want to learn about new research right away, so they can enroll in clinical trials. “That’s what drove us,” Vogel says about the center’s work to incorporate research into clinical processes faster.
MD Anderson plans on sequencing all of its patients within the coming years and the vast amount of data requires innovative ways to extract and manipulate it. While this is not outside the realm of existing technology, it may be beyond the capabilities of most EMR systems to provide along with the required flexibility for research.
Glad to see the innovative spark alive and well at a major healthcare provider, and in the person of their CIO!
2.05.2012 | 0 Comments
Powered by Twitter Tools
2.02.2012 | 1 Comment
Months ago I wrote about the AAMI Summit on Clinical Alarms. This prompts some ideas for research to mitigate nuisance and general patient medical device alarm problems:
Historic information provides some notion of what is risky for patient: events and information from multiple sources can establish an a prior assessment of whether a patient is experiencing distress. These conditions are not unique and have been seen previously by multiple clinicians over time. Hence, the historical information can be a great filter for establishing what is real and what is not real in terms of alarms and medical device alarm management. Just as automatic feedback control systems provide a feedback to the plant model as to deviations from expected performance, such is analogous with medical device alarms.
Part of the challenge is how to combine the information from multiple sources. This combination of information is not simply co-displaying them in a common format or user interface. It is presenting the data intelligently to the end user, possibly in a processed manner that determines, based on their combination, whether the result is a bona fide alarm condition. This rather cerebral aspect of the processing is the dilemma. Leaving out even the regulatory aspects of the situation, understanding what the processing is actually doing–the “plant” part of the automatic feedback control system–must be represented accurately.
A medical device alarm from a single device provides an indicator with respect to the sensors that are being measured for that one device. For instance, a physiologic monitor that is only measuring pulse and ECG cannot report an alarm on End Tidal CO2 or respiratory rate. On the other hand, a mechanical ventilator cannot report an alarm on heart rate or on ST segment elevation. The two devices report medical device alarms according to their particular sensors and objectives. However, the combination of the two devices can provide corroborating evidence. For instance, an ASYS alarm could be caused bya lead disconnecting from the physiologic monitor or from the patient. But, an ASYS alarm occurring at the same time as an APNEA alarm would provide corroborating evidence. This is rather a tragic example, but one that demonstrates the correlation of two events.
The fusion of multi-source devices can also provide a mechanism for reducing data overload while at the same time increasing useful information is one that I find to be very interesting. There are many research efforts surrounding modeling. Yet, integrated system modeling (multi system integrated assessments) has really yet to be shown (publicly) as viable in medicine–and generally accepted in operational use, not to mention for medical device alarms.
I would like to leave this here for now and follow-up in more detail on these areas. The medical device alarm field is fertile ground for integrated systems engineering application.
2.02.2012 | 0 Comments
My recent participation in an NSF Grant review at PENN on Tuesday and, in particular, Dr. C. William Hanson’s overview briefing during that event, brought to mind some things that he and I had worked on back in the early to mid 1990s. During the course of the presentations, which I found to be very fine and informative, it had occurred to me that basic research is still being conducted in areas that remain relatively untouched or unresolved today, some 16 years later. At the tail end of my dissertation it had been requested by my committee (Dr. Hanson in particular) to lay out key areas of future research that could stand upon what we had done and, in particular, focus on the problem of automation.
Extracts from that long-ago written conclusion read as follows:
“Develop… a larger database of spontaneous minute volume data to verify that it is possible to achieve a more accurate interpolation methodology…”
“Develop…a database of respiratory state data that can be easily recalled for real-time diagnosis and analysis by the critical care staff…by providing an easy way to download this information for…processing would permit the storage of each patient’s data, along with information on patient condition, to be used to classify each patient according to surgery.”
“[A]utomate the weaning process…motivated in part by the need to safely reduce costs and instill more uniformity in the respiratory weaning process across a larger patient population. Moreover, one desirable quality of such an automated methodology is that is would not require the input of such information as patient mass, gender, …anesthetic dosages…to operate effectively. The control system responsible for regulating patient respiratory support should use only that information available through the ventilator…Evidence and trends in patient care exist to suggest that automating post-operative weaning in patients who are not problematic is not only possible, but inevitable as hospitals strive to streamline and reduce the costs associated with critical care medicine.”
The conclusion then goes into the specific algorithm for reducing the support automatically. Undoubtedly, another research focus altogether. Nonetheless, this was written in 1996. Evidence-based medicine is a key objective in the application of treatment today. Furthermore, the databases that were referred to in the research do not (yet) exist today. There are clinical information systems, electronic medical records, and varying levels of discrete data that comprise them. But, the level of data richness described in that conclusion still does not exist today.
The one key reason I focused so heavily in my career on medical device connectivity has been because of the inability to uniformly collect the information at the bedside so necessary to support these types of research (and, ultimately, to support the care models related to automated management). While there certainly exist safety concerns surrounding the automated aspect of any process in healthcare, the objective at that time was to provide more uniformity around the process of weaning. Furthermore, respiratory weaning was merely an exemplar to serve as an expression of the larger application of predictive methodologies based upon data normally collected at the bedside.
In order to improve situational awareness it is necessary to have access to the latest information. Part of that situational awareness relates to the observations collected from the patient. Observations in the high acuity spaces comprise the visual, audible and sensory based set that every clinician is familiar with. These are further augmented by historical information, patient demographic, and the training that each clinician receives. Integrate, fuse, or otherwise combine these data together and the situational awareness increases greatly. It is this situational awareness that was sought to be demonstrated through the research at that time and remains an important focus of research into the future.
2.01.2012 | 0 Comments
Yesterday I attended an NSF grant status review at the University of Pennsylvania. I had a chance to visit with some old friends of mine and to reacquaint with some new friends. It is striking to me the energy in the area of systems engineering in the medical field that has taken place since I was a student there some 16-20 years ago. When I was a student at PENN, the notion of applying systems engineering to medicine was not even a field: it was the study of one lone student in the department. I am happy to see such growth.
While I cannot get into the specifics of the discussions of the various projects, I will lend my overall impressions vis a vis the types of concepts that are being focused on, and that are a major focus in healthcare and medicine today.
Useful use (as opposed to Meaningful Use) of data within the enterprise is a huge objective in the treatment of patients:
1) using past information and history to assist in reducing the likelihood of readmissions;
2) better management of those patients, particularly in critical care who are likely to suffer from sepsis, ventilator acquired pneumonia, etc.;
3) reduction in the number of medical device alarms that bombard the clinicians;
4) better use of integrated information through application of interoperability standards.
All of these areas are of high value. As I noted in my “outbrief” at the end of the meeting, my views, while highly motivated by pure research, are more governed by the pragmatic from the perspective that I live with customers and their problems, and this motivates me to write on areas that are both pragmatic but motivated by research interests of my own.
The term “Big Data” has often been used, and by itself is nothing more than marketing tripe. To my mind, systems engineering and the various concepts related to it, from situational awareness to systems of systems engineering, has been around a long, long time, primarily as related to the aerospace/defense industry (a former industry of my own). What is becoming more and more clear is that the effective use of data–not just mining it for whatever trend falls out of the net–is the real value. Combining specific information associated with diagnoses and then determining from that which patients are likely to be readmitted; which patients are likely to respond favorably from a certain course of treatment, etc. are outcomes assessments that carry with them great value but also great responsibility.
Pragmatically, most hospital systems that I have been involved with professionally are still at the stage of connecting the dots: getting information from point A to point B. As is typically the case, large academic research institutions are out in front looking at the why and wherefore of what to do with the information–the futuristic. Once something becomes generally accepted in clinical practice, that is when the futuristic becomes commonplace.
Yet, something else is happening now: I see even smaller community hospitals beginning to look at the futuristic from the perspective of how it can assist in the commonplace practice of medicine. It is not just the matter of connecting the dots of how data gets from one point to another; or how certain functions (e.g.: CPOE, eMAR) need to be rolled out into the institution, but what happens with the information after that. Interestingly, a motivation for this is the care and management of patients with chronic ailments and/or co-morbidities. Managing the patient once he or she leaves the hospital is of much more interest, regardless of the size of the institution.
Assisting in this management is the effective study of past history and increasing situational awareness surrounding patients in their home environments as well as in the hospital and how they compare with respect to peers. This is the focus and benefit of big data–where it is going. And we are at the beginning.
1.30.2012 | 0 Comments
There are two very good posts that I stumbled upon this morning, both at KevinMD. The first, “Society expends huge sums on futile healthcare,” by Jim Demaine, MD, and the second, ”Diagnosing an illness is an art,” by Stewart Segal, MD, touch on aspects of what I call the “Personalizing of Medicine.”
As opposed to the oft-used term “personalized medicine,” I truly mean the “personalizing of medicine” from the perspective of our individual experiences. The process of being treated for an illness, whatever it is, is a highly personal process. Each of us has a story. Each individual is unique. This is important to remember as we in the field use terms such as “Meaningful Use” and “electronic medical records,” and others that tend to take the focus off the personal and refocus on technologies or population statistics.
Don’t get me wrong. All have their place. Yet, it is necessary to understand that while we are well it is much easier to speak in emotionless, colorless tones about medical care and what is right for “society” and reducing “costs.” It is a different matter when it changes from the objective to the subjective; from the general to the personal. Each of us has a story, and many cry out to have that story told. I have my own, but the reason I went into the medical and health field is entirely personal, as well. Someday I will relay that story.
So, the point of this post was reflection: medicine is personal. The physicians who practice it visit with each patient individually. While the statistics and analysis are useful for assessing the patient’s treatment, each patient must be treated individually since each patient has an individual and unique story. Sometimes I fear that in the process of discussing Meaningful Use this fact is forgotten. So, while we strive for better medicine, let us also remember that the objective must also be to ensure that the “personalizing of medicine” is not removed from treatment and patient care.
1.29.2012 | 0 Comments
Powered by Twitter Tools
1.29.2012 | 0 Comments
Powered by Twitter Tools
1.27.2012 | 1 Comment
A recent post entitled “Innovative technologies can markedly enhance safety,” by Stephen Schimpff, MD, prompts the writing of this post. The famous book “To Err Is Human” that many (most?) are aware of, published back in the late ’90s by the Institute of Medicine identified or estimated that upwards of 98,000 individuals died each year due to preventable medical errors, and that the bulk of these errors were estimated to be due to medication or surgically-related causes. Technologies have evolved as well as procedures since that time. The Electronic Medical Record (EMR) has evolved since then as well as specific functions in clinical decision support, including electronic medication administration checking (sometimes referred to as eMAC or eMAR) and computerized practitioner order entry (CPOE) among others. Several elements of situational awareness in these functions including affording the practitioner of patient-specific information (vitals, demographics, laboratory information, etc.) that might inform the practitioner of certain facts to assist in better decision making, as well as verifying that a specific patient is indeed the recipient of a specific drug at a specific dose and at a specific time.
“Situational awareness,” as defined in an NIH Medical Surge Capacity Workshop, “is a term that simply means understanding the current situation. It is the ability to look at a huge variety of data, determine what is relevant, synthesize the data, and act on it.”
Many years ago, in a previous life of mine (I think it is in excess of 20 years now) I had cause to apply this concept in another field–aerospace. I link the concept described above with another extra-medical term: that of multi-source data fusion (I used this term a few times at a recent medical device alarm summit, which I chronicled in a past post). The terms are not unrelated and apply to the larger picture of making sure all information surrounding a decision that can be had is provided for the decision maker’s purposes, as well as the nature of the surrounding environment.
Situational awareness, multi-source data fusion, interoperability are all terms that I have used and “interacted” with in past lives stretching back more than 20 years now in “that other field” of mine before I entered into healthcare and healthcare information technology. The essence of systems engineering is taking multiple sources of information or multiple systems (or a combination of the two) and developing an understanding of how they operate and interoperate to solve a larger problem involving the fusion and/or coupling of them. Examples abound around us.
One example known by most of us that combines the concepts of situational awareness and systems engineering is the automobile. The automobile combines many systems: engine, brakes, passenger compartment, electrical, … These are separate systems with interfaces among one another to support their integrated whole in the entity of what we call the “car” or “truck.” The separate systems on their own contain elements that are completely independent of one another; do not even depend on one another for their localized functions. Yet, to accomplish the end-user’s purpose of “driving down the road” and supporting a variety of use cases for the end-user (e.g.: driving to the grocery store; driving to work; driving to grandma’; pulling a boat, etc., etc., etc.), all must operate in conjunction with one another through defined interfaces that pass prescribed information.
The situational awareness of the end-user (i.e., the driver) is essential to safe and effective operation of this integrated systems architecture. The scenario of “turning left” involves the integration of the systems described in the paragraph above. However, “turning left” into traffic could be a fatal operation. Situational awareness dictates when it is safe, appropriate, legal to “turn left.”
Returning to the world of medicine, the end-user in this instance (say, the physician) is presented with a system of systems (some integrated, some not), possibly presented in the form of vital signs, laboratory information, orders, etc.. The physician can order a specific drug, but the situational awareness of that physician will define whether at the current moment it is safe and effective to do so based upon the patient’s condition, past history, etc.
As information continues to become a key enabler and facilitator for medicine, it is important to understand that it is not simply that data are provided, but that the integration of the whole of the information available along with past history and knowledge within the “wet wear” of the physician dictate (and constrain) what must be done at a given moment. Providing the tools leading to that knowledge vital to decision making is where healthcare information technology’s true value may lie–just as providing rear-view mirrors on a car are key to the situational awareness of the driver.
1.22.2012 | 0 Comments
Powered by Twitter Tools
1.22.2012 | 0 Comments
Powered by Twitter Tools
1.22.2012 | 0 Comments
“We are increasingly skeptical of terms like “crowd sourcing”, “social”, “big data”, or “mobile” as cover for a product that has only a website placeholder and a hypomanic founder. A mature dialogue means admitting that fixing health care isn’t easy, and that the current system while broken is not made up of fools who despise novelty.”
- Rebecca Coelius
This is from an article on KevinMD titled “A guide for entrepreneurs to get a doctor’s attention”. I have been thinking about this article for about a week now and it is right where my brain is at based upon the interactions I have been having with various physicians from institutions across the country. Don’t get me wrong, the concept and vision of “Big Data” – data that are too big for conventional processing in localized databases and analytics engines, and which, if mined appropriately, can result in enormous value for the end user — is really not a new concept.
No, it is not.
For example, I can describe from personal experience one project in the late ’90s on data warehousing related to healthcare that was rather similar. I am sure other “veterans” can describe similar experiences. I think the technologies were a tad more crude then; we did not have the iPhone, iPad, Android and numerous other novel “information appliances” (with apologies to Donald Norman), but the concept of gleaning intelligence from large quantities of data has been around for a long, long time.
But the main point of the article is for entrepreneurs to focus in on the right areas. Many years ago I once had a mentor tell me that it is a wrong conclusion to state that when provided with more information the uncertainty in the target declines. I treated that as an axiom for a long time. Yet, my beliefs have changed on this front. When presented with too much of the WRONG information, or CONFLICTING information, uncertainty does indeed increase, as well as confusion. This extends to my beliefs about “big data“. Having more information is only useful when it is properly vetted with the right stakeholders. This does not mean that all stakeholders are correct, merely that ideas can be reduced to gimmickry if not properly focused. The KevinMD article illustrates this rather directly. Working with clinical end users to align on what is most important to improving the relationship and understanding of the problems they face is the best way to achieve acceptance and closure on a specific technology. To exclude the clinical end user or minimize the challenges they face, whatever they may be, is to risk existence and acceptance of a technology.
The above statement is certainly not “rocket science.” Yet, it is oftentimes overlooked that if you are targeting a technology towards a specific individual or to solve a specific problem, it may be better to participate in the circles of those who are treating patients rather than the larger IT forums that are more flashy.
1.15.2012 | 0 Comments
Powered by Twitter Tools