Big Data Drives Big Change

The digital age is the age of big data where every piece of technology captures data available for later use. The McKinsey Global Institute (MGI) describes data generated in this way as digital “exhaust data,” data that are created as a by-product of other activities.

The rapid expansion in the use of EMRs and digitally-driven technology—MRI scanners, body sensors, automated lab tests—brings the era of big data to healthcare. MGI estimates that big data presents a $300 billion potential annual value to the U.S. healthcare system. The five broad areas to deliver that value are: 1) clinical operations, 2) payment/pricing, 3) R&D, 4) new business models, and 5) public health. Sub-areas include comparative effectiveness research (CER), clinical decision support, remote patient monitoring, health economics, and personalized medicine.

The four large data sources for healthcare include clinical, pharmaceutical, administrative, and consumer.

New analytic tools such as Semantic Web 3.0—linked data—offer ways for machines to analyze these data sets leveraging approaches impossible using standard relational databases and statistical methodologies. These new tools permit researchers to work around the barriers presented by data sets’ non-conformance to standards for data collection or storage.

Similar to the use of metadata, Semantic Web techniques allow the assignment of descriptors to each data point, providing a context and meaning to the data. This allows machines, applying powerful statistical techniques, to analyze the disparate data sets in ways not available to humans alone due to the data sets’ size and complexity.

Organizations that properly collect, analyze, and utilize big data will achieve a significant competitive advantage over those organizations that fail to recognize the opportunity big data presents.

Excerpts from: Big Data Drives Big Change. PSQH, January/February 2012

Photo Courtesy of  Don Guerwitz Photography – Sahara Dunes. Niger River, Mali

It’s All About Jobs

What would Steve do? Steve Jobs, the 20th century’s greatest and most successful innovator, engrained that mantra into the heads of every Apple employee. Only those staff members who thought through problems the way Jobs did would offer solutions that were acceptable to their boss. Jobs relied upon his own research and intuition, not focus groups, to guide him. When asked about the research that went into the design of the iPad, Jobs replied “None, it’s not the consumer’s job to know what they want.”

Although physicians employ the iPad in many clinical settings, the tablet computer functions as a front end to existing EMR and other clinical applications. The iPad is not an innovation in and of itself but a tool to innovation, and few healthcare information technology (HIT) vendors actively leverage the “innovation” inherent in the iPad in their clinical applications.

What Would Steve Do?

Therefore, we must ask ourselves, what would Steve do in healthcare? First, Jobs would not be constrained by current practice. Like hockey, solutions come from skating to where the puck will be rather than where it is. In addition, he would consider all problems together in an effort to create an “ecosystem” that binds one product with another, the same way Apple now threads together the iPhone, iPad, and iMac with iTunes and iCloud. Jobs cherished style and ease of use, combining them with function and utility. Any Jobs-inspired healthcare application must be intuitive to use, support efficient workflow, and facilitate the delivery of safe, high-quality care to the patient.

Excerpts from: It’s All About Jobs. PSQH, November/December 2011

Photo Courtesy of  Don Guerwitz Photography – Fishing in the Moat, Hue, Vietnam

Web 3.0 Data-Mining for Comparative Effectiveness and CDS

“Turbulent times” accurately describes the state of the American healthcare system. The list of critical challenges is well known—upward spiraling healthcare costs now approaching 17% of GDP, healthcare payment reform, shortage of clinical professionals, aging population, and the economic downturn. While current investments in health information technology (HIT) begin to deliver increased reimbursements to providers, these same at-risk organizations, along with payors, seek better ways to leverage HIT to enhance quality care and reduce costs.

Although much effort focuses on improvement of clinical workflows, an opportunity exists to transform healthcare delivery by implementing evidence-based clinical decision support at the point of care. Such clinical content delivered effectively within new, efficient clinical workflows directs patients toward evidence-based therapeutic plans that produce desired clinical and financial outcomes. While informaticists work on developing these clinical workflows, the lack of clinical knowledge limits the ability of organizations to leverage HIT in order to personalize therapeutic care plans.

Identifying Affordable Therapies

Comparative effectiveness research, supported by data mining, allows organizations to identify affordable therapies that enhance patient care. With the implementation of HIT, data warehouses contain petabytes of searchable clinical, outcomes, genomic, and financial data across multiple patient populations. Bringing together this data using sophisticated knowledge analytic tools and domain-specific interfaces allows researchers to discover relationships among multiple variables gleaned from previously unconnected databases.

In turn, this new clinical knowledge enables clinicians to personalize treatment for patients based upon their genetic background by linking it to descriptive patient data and outcomes. Personalized medicine transcends analysis of a population-based cohort by placing the patient within a sub-population that better reflects the expected outcome from a prescribed treatment. Embedding this personalized medicine knowledge within an EMR’s clinical decision support module facilitates the delivery of these evidence-based best practices at the point of care.

Semantic Web

Sophisticated software indexes the databases on metadata that “describe” each data point. Although the indexing allows for rapid retrieval of the data, it more importantly builds links among each data point based upon the descriptive information contained in the metadata. Discovery of these relationships is impossible without semantic web technology and the ability of computers to utilize it to read and understand metadata. Experts can utilize semantic web technology to query multiple large data sets to explore comparative effectiveness hypotheses.

Excerpts from: Web 3.0 Data-Mining for Comparative Effectiveness and CDS. PSQH, September/October 2011

Photo Courtesy of  Don Guerwitz Photography – School Outing. Hanoi, Vietnam

Say No to Paper

Paper came one pill away from killing my 91-year-old mom. Only through luck did we dodge a medical error that could have extinguished a life that survived the Great Depression, World War II, polio epidemics, the birth of two children, the Cold War, the loss of her husband, and more than 60 years of employment. Up until her admission on May 7th, she never experienced being an ill patient in a hospital.

Mom was admitted to a hospital affiliated with her cardiologist located in Westchester, New York, a location close to the home of my sister, a trained endocrinologist with more than 20 years of clinical experience. After treatment for an upper respiratory infection, urinary tract infection, and symptoms of viral pericarditis, Mom was discharged to my sister’s home.

After a week of rest, she returned to Westchester for continued recuperation with my sister. Unfortunately, her condition worsened after a few days, leading her physician to re-admit her to the hospital. At the conclusion of a few days of further tests and treatment, she was transferred to the hospital’s co-located rehabilitation facility for several days to continue her treatments in a less acute care setting. Due to the lack of availability of required therapy over the upcoming Memorial Day weekend, we collectively decided to have Mom discharged to my sister’s home where she could receive better care.

Holiday Weekend Dangers

As Mom suffered from new onset of intermittent atrial fibrillation, the physicians prescribed Pradaxa, an anticoagulation therapy drug that greatly reduces the probability of stroke in patients suffering from atrial fibrillation. The decision to discharge my mom on the Friday before a holiday weekend immediately proved problematic. Pradaxa at the 75 mg dose was unavailable in several pharmacies in the area around the hospital.

Over a 2-hour period, working with a very helpful social worker in the hospital, we convinced the outpatient hospital pharmacy to fill a prescription for the drug. While my sister prepared Mom for discharge, I rushed down to the pharmacy with the paper prescription for 75 mg of Pradaxa. With the prescription bag in hand, I rushed up to meet my mom and sister to help them prepare for discharge.

I handed the prescription to my sister who promptly opened the packaging and looked at the bottle of meds. “This is wrong”, she shouted. “Mom should be on 75 mg not 150 mg.”

Although the prescription was written correctly, the pharmacy dispensed the wrong dose. Knowing my mom had just dodged a potentially fatal medication error, I promptly returned to the pharmacy with the incorrect mediation in hand and explained to the pharmacist what happened. All color left his face as he began to apologize profusely. He just experienced a sentinel event that required immediate and complete reporting.

Anatomy of an Error

Reviewing the sequence of events surrounding the medical error, it becomes clear how it occurred. Although the handwritten prescription was legible and correctly written for 75 mg of Pradaxa, the pharmacist mistakenly selected an unopened, 60 capsule bottle of Pradaxa 150 mg to fill Mom’s prescription. He then placed the medication in a sealed paper bag, attaching the prescription receipt to it. Had the hospital been equipped with ePrescribing and an electronic medication administration system, the system would have immediately alerted the pharmacist of the dosing error. The scanned barcode of the bottle of 150 mg of Pradaxa would not have matched the expected barcode of a bottle of 75 mg capsules.

Going forward I will never allow anyone I know to be treated in a facility that bases its medical care on dangerous paper-based processes. Nor should any American ever be subjected to such inferior care. If we continue our efforts to promote and properly deploy healthcare information technology, this soon will be true.

Excerpts from: Say No to Paper. PSQH, July/ August, 2011

Photo Courtesy of  Don Guerwitz Photography – Gamelan Orchestra. Bali, Indonesia

Watson, Come Here I Need You

Although a call for Watson brings to mind Alexander Graham Bell’s first words on the telephone or Sherlock Holmes greeting to his physician companion, The New York Times heralded another Watson on its February 17, 2011, front page. The artificial intelligence computer system won on the game show Jeopardy! In the television program’s only computer versus machine match-up, Watson defeated Brad Rutter, the biggest all-time money winner, and Ken Jennings, the record holder for the longest championship streak. Watson had access to 200 million pages of structured and unstructured content, which consumed more than four terabytes of disk space.

This experience with Watson illuminates how artificial intelligence computer systems offer healthcare providers robust, evidence-based clinical decision support. In addition, it identifies the special role humans play in diagnosing and treating patients. If combined together, these capabilities can synergistically offer higher levels of valuable and effective care.

For information technology to play a valuable role in reducing healthcare costs while enhancing quality of care, it must be deployed in a way that completely reinvents how care is delivered, professionals provide the care, and technology is leveraged. Watson’s success on Jeopardy! demonstrates the capabilities of computers to store and retrieve medical knowledge at the point of care, thereby freeing clinician minds from the unnecessary burden of recalling facts. Clinicians are freed to focus on their patients while more effectively utilizing their ability to identify unusual patterns previously obscured by the “noise” inherent in a busy practice.

In 2011, progressive organizations will further the deployment of computer-based clinical decision support, rework the roles of all caregivers, and transform their processes to achieve ever-increasing levels of quality, safety, and efficiency of care delivery.

Excerpts from: Watson, come here. I need you. PSQH, May/June, 2011.

Photo Courtesy of  Don Guerwitz Photography – Loading the Boats after Market. Sanka, Myanmar (Burma).

Seeing Is Not Believing

Consider this scenario. An adventure traveler begins his trek to a remote village in the Andes. Upon arriving at the airport, he rents a car and begins his journey on winding roads to the village. After 90 minutes of driving, he encounters an intersection with a traffic light. Upon seeing the bottom of the light glowing brightly, he continues through the intersection.

Suddenly, his car is knocked sideways by an automobile that crashes into his front passenger side door. No one is injured but both cars are severely damaged. Figuring his “attacker” ran a red light as his light was surely green, he jumps out to accuse the other driver of reckless driving. Upon further investigation, our traveler learns that in this part of the country, traffic lights are constructed differently than in the United States. Although a red light means stop and a green light means go, green lights are placed at the top of a traffic light while red lights are at the bottom, completely opposite what is followed in the U.S. and most of the world.

Who is at fault here? I am pretty sure our traveler saw the bottom light as red but his brain processed it as green, meaning go. In every other situation encountered by this traveler, a glowing light at the bottom of a traffic light was green, and it meant “go.” For human beings to navigate the world efficiently, we generalize our surroundings.

Inference Rather Than Analysis

The effort required to analyze each situation requires too much brain processing and would cripple our ability to do things. Therefore, when we encounter situations that are familiar to us, we infer much of the situation, using only a limited amount of the reality as a template for what we are seeing and experiencing. Only when we encounter completely novel situations, do we dial back our inference and concentrate on the activities in front of us. Yet, even then, we do a significant amount of inference to make efficient our interpretation of the situation.

Workflow and process redesign must consider not only the existing patterns of care delivery and the ways to make them better, but also the inherent way human beings process their environment. As noted above, inferring the environment is critical to our maneuvering through our daily lives. A workflow that does not consider the impact of inference on the actions of human experts can easily lead to medical errors.

As organizations work at deploying health information technology and deliver clinical transformation through redesigned workflows, they need to recognize the basis for many of the errors we, as human beings, make in our everyday lives. By recognizing our limitations and designing around them, we can fully reap the safety benefits of health information technology in our delivery of patient care.

Excerpts from: Seeing Is Not Believing. PSQH, March/April, 2011

Photo Courtesy of  Don Guerwitz Photography – The Burning Ghats. Kathmandu, Nepal

Show Me the Money

The most important lesson in medical care comes from a bank robber who stole more than $2 million and spent more than half his life in jail. Named after Willie Sutton, the one of the most prolific bank robbers in history, Sutton’s law states that when diagnosing, one must consider the obvious. Diagnosticians should first conduct those tests that will confirm the most likely diagnosis, and order them in a sequence that has the highest probability of delivering an accurate diagnosis. This approach also minimizes unnecessary tests and reduces costs.

Sutton’s law grew out of a famous response to a reporter’s question attributed (perhaps falsely) to Sutton. When asked by a reporter why he robbed banks, Sutton allegedly replied, “because that’s where the money is.” In reality, he probably said, “Go where the money is… and go there often.”

More than 20 years ago, payors and providers experimented with capitated arrangements where IPAs—Independent Practice Associations often constructed from a broad swatch of primary care and/or specialty physicians—contracted with payors to provide services to a population of insured individuals. Although numerous variations of capitation were tried during that time, capitation arrangements did not succeed in reducing costs, increasing provider compensation, or improving quality of care. Many physicians continued to over-utilize services.

Like so many ideas in healthcare, the old, after a time of dormancy, becomes the new. The excitement around accountable care organizations (ACOs) and patient-centered medical home projects is based upon much of the same thinking that excited healthcare policy makers 20 years ago. With ACOs and patient-centered medical homes, primary care physicians would be responsible for both the care and cost of care for patients assigned to them. Those physicians able to keep their patient population healthy while reducing the cost burden associated with treating their population would share in the savings to the payor.

What our healthcare system will look like at the end of 2014, when the final provisions of the Affordable Care Act of 2010 become active, may be fuzzy today, but a rough picture of it can be drawn by following the flow of financial incentives. By 2014 the effects of removing lifetime caps on medical costs, eliminating the process of denying coverage due to pre-existing conditions, emphasizing the use of proven disease treatments, and reducing reimbursement for preventable medical errors and readmissions shifts the care incentive from providing more care to providing only care that is needed.

Healthcare information technology will play a critical role in delivering these new models of care delivery and financing. Only through robust information technology can we track and report on performance, offer clinical decision support to enhance safety and quality, and monitor the health of populations of patients. Healthcare information technology offers the critical tools to move clinicians from their focus on episodic care, where financial incentives were based upon piecework, to much broader population-based care, where financial incentives promote the delivery of favored clinical outcomes that efficiently utilize resources. Therefore, to understand the current and future changes to our healthcare system, you need only to know where the money is and where it is flowing.

Excerpts from: Show Me the Money? PSQH, November/December, 2010

Photo Courtesy of  Don Guerwitz Photography – Breaktime. Jokhang Temple, Lhasa, Tibet

A True Tipping Point?

From the signing of healthcare reform legislation to the release of final rules for “meaningful use,” events in 2010 are driving toward a true transformation in the delivery of healthcare in the United States. Optimism is high that we will finally see tangible benefits from healthcare information technology as measured by enhanced quality, improved access, and lower costs. I recently reviewed some testimony given to a subcommittee of the U.S. Senate Finance Committee that highlighted the role of healthcare information technology in transforming healthcare delivery.

Here are excerpts from that testimony.

“It is with great anticipation I approach this committee today to give testimony on health care issues and the effect new information technologies will have on the delivery of care. Clearly the swirling debate on how to restructure our health care system has raised the awareness of all Americans to this important issue. It is through the management of information, in particular its dissemination, that we can address some of our health care challenges. We need to use new information technologies to provide physicians, patients, providers and payors with the appropriate, relevant information to produce good, acceptable outcomes from appropriate cost-effective care.

“The information technology revolution is changing the way medical care is delivered. These new tools provide physicians with the opportunity to access relevant clinical information on a real time basis to most likely impact on their patient care. Using standards, guidelines, protocols, and information available from profiling using normative data bases, physicians can obtain useful information on their patterns of care. Patients can obtain understandable information on their disease process, thereby becoming an informed consumer of health care. Organizations exist to educate physicians and other health care professionals in the use of these systems. For-profit firms are developing the tools and making the investment needed to convert data into information.

“My final advice to this committee is hold on tight, the medical information superhighway has no speed limit.”

Excerpts from: A True Tipping Point? PSQH, September/October, 2010.

Photo Courtesy of  Don Guerwitz Photography – A Farmhouse, Central Turkey

Is “Meaningful Use” Meaningful?

Now that the “meaningful use” rule has been finalized by the Office of the National Coordinator (ONC), many organizations turn their focus to a rapid deployment of electronic medical record (EMR) systems in an effort to achieve transformation of the United States healthcare system. Unfortunately, EMR adoption is just one tool used to transform health care, and not the single transformative activity so many believe it to be. Transformation of healthcare encompasses enhancing quality of care, improving patient safety, expanding access to care, and reducing the cost of care. EMRs deployed to satisfy the criteria for “meaningful use” can impact these factors, but only within a comprehensive framework that recognizes the role of incentives, clinical decision support, and healthcare information technology (HIT) in facilitating transformation.

Introduction of new technology often distracts us from our primary task. Our fascination with the technology leads us to focus on what the technology can do, rather than what we need the technology to do. This misguided use of technology also occurs when it is used for healthcare delivery. Many EMR implementations focused on the impressive features of the EMR software rather than the workflow requirements of the clinician users.

Healthcare transformation requires a comprehensive vision of care delivery that recognizes the interrelationships of the many stakeholders. Technology by itself only helps improve those interrelationships, while the underlying structure that the interrelationships are built on remains.

Therefore, the “meaningful use” criteria are meaningful in that they help ensure the use of EMRs in ways that can enhance healthcare delivery, they do not transform healthcare. The recently passed Patient Protection and Healthcare Reform Act (2010) does much to move us toward a better healthcare system, but it too does not transform healthcare. Transformation requires many factors working together in an iterative process to deliver the expected results. Some of those factors are outlined below.

Until economic incentives of all the stakeholders align, care delivery will remain inefficient and suboptimal in quality and safety. Providers are incented to provide more care, payors are incented to withhold care, and patients, detached from the direct costs of care, have been molded to always expect care. The culture of healthcare in America is based on the false belief that more care is better care.

Transformation of healthcare requires a complete disruption of our current system of healthcare delivery. Clinical roles require redefining. Workflows will change to meet the needs of these new clinical roles, allowing the HIT tools, such as EMRs, to be leveraged to improve care. “Meaningful use” criteria is a nice first step to help ensure the effective deployment of HIT tools such as EMRs. Nevertheless, it is just a very small step towards truly transforming healthcare.

Excerpts from: Is “Meaningful Use” Meaningful? PSQH, July/August, 2010

Photo Courtesy of  Don Guerwitz Photography – First Light. Bhaktapur, Nepal

Regulate HIT Tools as Medical Devices? Yes and No

The Food and Drug Administration recently announced it is reconsidering its previous decision to exclude health information technology (HIT) tools from regulation as medical devices. When last evaluated in the late 1990s, this decision made common sense. At that time HIT consisted of rudimentary clinical documentation systems, electronic reference materials, and administrative applications. As even these tools were not well integrated with each other and into clinical workflow, they represented more of a digitization of paper-based activities rather than something truly transformational.

Today, HIT functionality far outstrips what was even dreamed about 10+ years ago. In addition, applications function in an integrated manner truly providing the clinician with a clinical experience much different than that offered using paper-based clinical documentation or simple clinical decision support tools.

The role of physicians, nurses, and other healthcare professionals is changing. These providers are becoming more dependent upon the clinical content within the HIT tools, often deferring to “decisions” made by these tools. Such examples include differential diagnosis, prescribed diagnostic and therapeutic treatments, choice of drug, and drug dose calculations. Although the previous rationale for not considering such HIT tools medical devices was based upon the intermediation of the provider between the recommended clinical activity and actual actions taken on behalf of the patient, the strong reliance on these very sophisticated HIT tools today puts this premise into question.

The FDA must study in detail the quality and safety issues inherent in integrated HIT applications before rushing to regulate HIT tools as medical devices. An uninformed effort to regulate HIT tools as medical devices may cause more harm than good. Applying the same standards used for medical devices to HIT tools makes little sense as HIT is neither a standalone application nor strictly a medical device. They are integrated applications that can impact quality and safety in ways far dissimilar to standard medical devices.

Regulation of HIT tools as medical devices is currently premature. Although HIT tools do directly impact patient care and therefore surely require some level of regulation, such regulation cannot be done without the requisite understanding of how HIT works within clinical workflow. The regulations must be constructed to advance HIT use while simultaneously protecting patients.

Excerpts from: Regulate HIT Tools as Medical Devices? Yes and No. PSQH, May/June, 2010

Photo Courtesy of  Don Guerwitz Photography – Running the Rapids, Mae Hong Son, Thailand