I have been on the nursing and vendor side of patient surveillance for more years than I would like to admit in print. In providing clinical surveillance, we nurses have the potential to minimize negative outcomes by preventing adverse events or deterioration in the patient’s status. As a vendor, it is our job to enable health systems to take enormous amounts of data from multiple sources to gain insight that drive decisions and actions. These actions can ultimately improve patient outcomes on a much larger scale. This large scale effect is one of the reasons I can be so passionate about a job that isn’t at the bedside helping patients. I am frequently asked “do you miss direct patient care?” At this point, I honestly can say I do not. I can help exponentially more patients by helping facilities understand their own data and use it to improve outcomes across all of their patient populations. And if I can make the job of collecting and using data less “painful” and more beneficial for my fellow nurses, then even better.

When I refer to Clinical Surveillance, I am specifically referring to the collection and analysis of health data about a clinical syndrome/condition that has a significant impact on the health of the population. This data is then used to drive decisions and actions.

It wasn’t until a recent experience from the patient side did I really take a look at what all of this surveillance data meant to me personally. In the days leading up to my surgery, in typical nurse fashion, I began to run through every worst case scenario in my mind. Suddenly hospital acquired conditions and infections (HACs) were no longer just statistics and numbers. Drug resistant wound infections, blood clots, air embolisms or a catheter associated infection, were all conditions that could now happen to me. I thought of the phrase “ignorance is bliss.” Wouldn’t it be better if I didn’t know all of the things that could happen to me?

I was determined that I would dictate a great deal of my care to help ensure I escaped the inpatient experience unscathed by any HAC or other negative outcome. While my intentions were strong willed, once I was post op and medicated, preventing a negative event never again crossed my mind during my stay. Most of my cognitive exercise was spent trying to locate the button for the wonderful machine that delivered the elixir of pain relief or making the long eight foot trek across the floor to the rest room.

It wasn’t until after I was home that I realized that despite my good intentions, we must rely heavily upon the care teams and facilities to keep us as safe from these conditions. It was clear that they were using past surveillance data and studies to keep me safe. Because my surgery (per historic data) did contribute a risk factor for Deep Vein Thrombosis (blood clots), they put the SCD (Sequential Compression Device) on my lower legs from post op to discharge. I was given the proper pre-op and post-op antibiotics to ensure my risk of surgical site infection was minimal. They also kept all devices that came in contact with me – such as blood pressure cuffs and stethoscopes – in my room, thus cutting down on my chance of getting a drug resistant infection from other patients.

I have no doubt that my inpatient experience was influenced by clinical surveillance data collected and studied. While it is always very important to be an informed patient engaged in our own care, I do now realize that clinicians and vendors who collect and study this data are the ones who are able to get insight and drive actions for our positive outcomes.

The world of healthcare has witnessed a major paradigm shift this past decade instigated by the now widespread use of electronic medical records and medical informatics. This new world of electronically entered, stored, and exchanged medical information has all but eliminated the numerous shortfalls of the departed world of folder and paper medical records.

This shift is ongoing with new focus on accountable, affordable, high quality and patient-centric healthcare. Technological advancements in analytics and big data also hold great promise for healthcare organizations as they embark upon this new era of medical services.

Although relatively new to healthcare IT, analytics and big data are well established technologies. While working in the Bing group at Microsoft, I was in charge of the monitoring team where we built fairly complex subsystems for capturing, collecting and aggregating multiple petabytes of data on a daily basis from upward of a million servers hosted in Microsoft data centers worldwide. The solutions we built provided near real-time insight from this data, which enabled us to support operational and strategic business decisions and actions.

Realizing the benefits and promise of these analytics and big data in other industries, the media is beginning to create a lot of hype about how these technologies can help transform healthcare. Established companies, such as IBM, and new startups, have entered the race to turn this hype into reality; however, the intricacies of healthcare make it quite challenging to use these technologies to their full potential.

Caradigm’s analytics vision, described in this short whitepaper, is focused on enabling clinical analysts to derive insight from data and drive actions through decision support.

I firmly believe that by leveraging both analytics and big data in our intelligence platform, and delivering a growing portfolio of population health management and analytics solutions, Caradigm will enable healthcare providers to flourish in the new era of accountable quality healthcare and services. The race is definitely heating up!

This blog post is informative in nature and is not related to Caradigm products.

As I wrote about previously, the volume of medical data vastly exceeds the ability of humans to process it without the aid of computers. But through the use of real-time and predictive analytics, that data can become a powerful resource. Real-time and predictive analytics enable organizations to turn their data stores into knowledge and insight with speed and accuracy that no human could ever achieve. And that insight could enable a different action to be taken – potentially improving an outcome, saving money or even saving lives.

I believe we need to think about how a new generation of decision support in the form of real-time analytics can be surfaced for immediate application. And importantly, these analytics should allow users to look at individual situations using a population-based context. Think about a patient who presents with a fever and shortness of breath. Early efforts at clinical decision support may have flashed an alert on the screen that says “consider pneumonia” or “consider ordering a CXR.” In response the clinician enthusiastically (sic) responds, “Duh.”

But imagine a more robust system, where the clinician is provided with the following information: “Of the last 100 patients seen in your hospital with this age group, complaint, and vital signs, 61% had a URI, 32% had pneumonia, 4% had pulmonary embolism, and 4% had other diagnoses. The 1-month mortality was 3.2%. Admission rate was 24%. And by the way, there has been a recent outbreak of atypical pneumonia among patients from Community Long Term Care, so public health requests this patient have a urinary antigen test for Legionella.” Now the physician is able to ask the computerized system, “show me the last 100 patients seen by me with these complaints,” and can then explore the data across her own personal cohort of patients and determine her own admission rate, bounce-back rate, or other parameters. Now decisions can be made for an individual patient using a population-based context.

Emerging real-time analytics have the potential to provide this kind of significant value. The idea is to enable depth of insight across a broad distributed set of data — at a minimum, across a hospital and its many departments and affiliated clinics, but even better across multiple hospitals and multiple outpatient medical practices, where traditionally an observable pattern can be obscured by the sheer number of patients being treated and the episodic nature of medical care today.

Predictive analytics work in a similar way, but with a focus on analyzing data and providing probabilities of various outcomes in the future. In the scenario above, imagine the decision support system provides additional information: “Of the patients with this symptom complex discharged from the emergency department, the predicted 72-hour return rate is 15%. Factors positively correlated with 72-hour return rate include: patient age, pulse oximetry on initial visit < 95%, absence of primary care follow-up visit within 48 hours, and absence of case management and/or visiting nurse within 72 hours.” Based on this type of knowledge, clinicians can further analyze the patient’s situation and make an effort to modify the key risk factors to increase the probability of successful outpatient care. Staff can proactively develop care transition plans and strategies to engage patients, families, case managers and visiting nurses as appropriate for follow-up care.

An organization can also use predictive analytics across populations for multiple purposes. For example, to determine how soon a larger or new facility will be needed to serve a growing patient population. Predictive analytics can be used to inform provider payment structures, reduce fraud, and identify specific future challenges for programs such as Medicare and Medicaid.

So both real-time and predictive analytics take the power of data beyond mere storage, categorization and traditional periodic reporting. Key medical insights can seem like the proverbial needle in a haystack; just increasing the amount of data that can be stored is the equivalent of adding more hay, but real-time and predictive analytics serve as a powerful magnet to expedite the search for the needle.

For these analytics to reach their potential, systems need to bring together all data across the organization and in many cases across multiple organizations, liberating data stores that have been historically siloed in legacy systems. In my next post, I will discuss a surround-and-supplement strategy for upgrading health IT systems so that organizations can take advantage of their legacy data, moving to a new generation of systems that serve future needs at a manageable cost, and without throwing away past investments.

What are your data challenges? What are the questions that you would like your data to more readily answer for you? If you have analytics in place, what problems have you solved through their use — and especially, has your organization improved outcomes? I’d like to hear about it.

Ask physicians about decision support systems, and you’ll probably get some groans and rolling eyes. Traditionally, decision support systems have amounted to little more than a set of annoying alerts, flagging issues that clinicians are already aware of and wasting precious time.

Early efforts to provide decision support have rarely surfaced the real insights that are needed for improving patient care, whether for an individual patient, or for a population of patients served by a practice or hospital. In fact, the National Research Council has concluded that the institution of healthcare is not adequately structured to help clinicians systematically improve their decision-making and practice, due in part to difficulties with data integration and sharing. Physicians develop a high comfort level with their decision-making processes, but they simply do not know what they do not know.

This no longer has to be the case because modern information technology has the potential to not just digitize record-keeping and paper-based processes, but to enable medical professionals and patients to leverage the wealth of available electronic medical information in a way that supports a new standard of analysis and decision-making.

The era of big data is no longer approaching; it is here now. An EMC-sponsored study found the world’s information is doubling every two years, with a colossal 1.8 zettabytes to be created and replicated in 2011. This is the equivalent of every person in the world having over 215 million high-resolution MRI scans per day. In medicine, the PubMed database sponsored by the National Institutes of Health now covers 4,600 journals that have pertinence for medical research publishing, and includes more than 22 million citations.

The volume of available medical data clearly exceeds the ability of individual humans to effectively process the information and consistently make superior decisions.

To be worth the time and effort of implementation, however, intelligent decision support technology must be able to use the analytical and predictive capabilities of high-power computing to help medical decision-makers go beyond record management to real insight and discovery. Enabling intelligent insight and discovery requires a robust integrated system capable of overcoming the challenges that exist in health IT today. We can understand the key components of such a system by outlining its five pillars:

• Using real-time data feeds and predictive analytics to facilitate advanced decision support across the healthcare spectrum, including both clinical and non-clinical settings.
• Facilitating the transition from legacy systems to modern integrated health data systems by creating a framework that provides a sensible, cost-effective, surround-and-supplement migration strategy and enhancing rather than interfering with workflows.
• Using metadata-based approaches to manage the massive data volumes available and to enable flexible data-management strategies that easily adapt to change.
• Encouraging innovation by leveraging a modern services-oriented architecture and through the use of a robust platform supporting multiple modular and portable applications.
• Ensuring high-level performance and results through comprehensive evaluation and control mechanisms.

In my next posts here I will explore these five pillars in turn, starting with the first pillar, real-time data and predictive analytics.

I’d also like to hear from readers who have been working with decision support systems, to know what has been successful for you and what has simply increased your workload without extending clinical insights. What has your experience been?