Healthcare Analytics: Landscape & Directions

Analytics in healthcare has been called everything from the only path to reduced costs & improved outcomes to a distraction that will cost substantial money & energy. As always (well, almost always), the actual fact of the matter lies somewhere in between these extreme views. In this post, I’ll look at how analytics are currently being used in healthcare & how they could be used, what the advantages & impediments are & make some predictions – I am supposed to be a futurist after all.

First, a definition – What do I mean by analytics? I mean the systematic analysis of data focused on answering a specific question or set of questions. Analytics is not report generation, nor is it an IT function, a software package or a technical methodology. It is a way of thinking about an organization’s goals that makes use of highly focused analysis of data, not just “big data”, but relevant data. Any analysis that is done must be aligned with an organization’s goals & strategies. Otherwise it may not produce results that lead to actions relevant to the organization.

An analytic adoption model for healthcare organizations, developed by a group of industry experts[1] has been proposed to allow the evaluation of data warehousing & analytics efforts. It consists of the following levels:

     0.  Fragmented Point Solutions 
   1. Integrated Enterprise Data Warehouse
     2. Standardized Vocabularies & Patient Registries
     3. Automated Internal Reporting
     4. Automated External Reporting
     5. Clinical Effectiveness & Accountable Care
    6.  Per Case Payment & the Triple Aim
     7. Per Capita Payment & Predictive Analysis
     8. Per Unit of Health Payment & Prescriptive Analysis

This framework emphasizes the functions associated with successful data warehousing as well as the relationship of payment with various dimensions of providing healthcare: per case, per capita & per unit of health. Is this an interesting way of looking at the evolution of analytics. Looking at part of the current landscape will help answer that.

I say part of because so much work is currently being done that it’s difficult to get the picture as a whole. What we can get is some dimensions or areas of focus & some examples in each area (each area has many, many more examples)[2]:

•           Point-of-Care Recommendations – generally large amount of clinical data analyzed to provide best match to individual patient characterization for delivery of best practice diagnosis & treatment recommendations, not rule-based, but empirical
•       Mayo Clinic – 5M clinical records (approximately 15-25PB) are analyzed to provide best practice treatment for individual patients in real time
•      Beth Israel Deaconess Medical Center – 2M+ clinical records are analyzed to provide best practice treatment for individual patients in real time
•      Kaiser Permanente – 9M clinical records over 10 years (approximately 45PB) are analyzed to provide best practice treatment for individual patients in real time, natural language query system in use
•      Partners Healthcare – combined clinical, operational & financial data, best practice recommendations made at time-of-encounter
•        Outcome & Population Characterization
•         Intermountain Healthcare (partnered with Deloitte) – 90M patient records, two analytic applications developed, Outcome Miner: derives factors that contribute to outcome at the individual level & Population Miner: derives relationship(s) between treatments & outcomes at the population level
•       McKinsey – “next 5% analysis”, analysis of 30M commercial claims to determine “micro-segments of patient population that will allow the identification of the top 6% of patients with regard to cost, assignment of care managers
•        Predictive Modeling
•       ExpressScripts – 1.5B prescriptions/year, use of predictive modeling to determine which patients are most likely to not use prescription as indicated, suggests proactive interventions
•        Research
•       Mt. Sinai Medical Center (partnered with Ayasdi) – used unique analytic method developed by Ayasdi (topological analysis) to evaluate the entire e. coli genome (including 1M DNA variants) to determine bacteria’s response to different antibiotics
•        Operations Optimization
•       Oregon Health & Science University – PAR (periodic automatic replenishment) levels for 4000 infusion pumps established & pump utilization & inventory tracked & optimized

Point-of-Care recommendations are far & away the most numerous applications while research & Operations Optimization appear to be the least. Point-of-Care systems seem to fall at Level 5 (clinical effectiveness & accountable care) on the adoption model. Very few efforts seem, at this time, to fall in the levels above Level 5, which implies that work on price & cost has not yet been emphasized.

So, if point-of-care, analysis of outcomes & predictive modeling of various kinds are the current areas of analytic focus, what areas might be interesting & productive that are not being emphasized today? I have been surveying a variety of healthcare organizations (informally) by talking to people at conferences, meetings etc., & this is what I’ve been hearing.

•           Can various forms of trend analysis be combined with geo-locational data to provide insight into very local conditions, for instance: Are specific diagnoses concentrated locally & if so are they associated with specific clinical characterizations?      
•      Can trend analysis of changes in population served be combined with larger scale demographic data, for instance: Are large-scale demographic trends driving trends in numbers of patients, ethnic grouping of patients etc.? Are larger-scale demographic trends going to influence whether healthcare organizations & specific locations should be invested in, for instance: In an area where the overall population is decreasing rapidly, should clinics, health centers of hospitals remain open? What factors, other than demographic trends, should influence these decisions?
•            Is there a relationship between cost of care & cost of outcome on a per patient, per provider &/or per location basis?
•       Can data on service utilization & demographics be used to model service utilization trends for planning purposes?
•       Are there bottlenecks in clinical & operational workflows that affect quality of care & outcome (it’s not clear that the data for this analysis is generally available, although several business process modeling methodologies could be used to address the issue)?

These are just a few of the many areas of inquiry & specific inquiries people have talked to me about. Only the largest healthcare organizations I’ve spoken with (Partners Healthcare, Vanderbilt Medical Center etc.) have focused on point-of-care recommendations as an analytic goal. This is, in part, because only these organizations have access to the ultra-large clinical data sets that are optimal for this type of analysis. Even where data aggregates, such as data warehouses, have been developed by medium & small sized organizations, the organizations have tended to focus on specific operational & financial questions as sustainability is their biggest issue. This generalization, like all such generalizations, must be taken for what it is worth – a generalization from not very much data.

What, then, are the impediments to the use of analytics as I have been describing it. There are the obvious ones of lack of resources, lack of expertise, lack of experienced personnel etc., but for small-to-medium size healthcare organizations, the largest impediment I have seen is the lack of an approach to providing appropriate data for analysis. Many organizations are using conventional data warehouse & extract techniques that at a minimum require semantic & syntactic normalization as well as transformation & standardization of the data in order to have meaningful results. I have seen, reviewed & participated in a number of projects over the last year in which results were not usable because data were aggregated without this work being done (in many cases by an outside contractor hired by the healthcare organization). I have also participated in a project where the definition of core elements like “encounter”, “outcome” & “provider” could not be determined from the data & could not be agreed upon by the project participants[3].  As we say, “Garbage in, Garbage out.[4]”

Even those organizations that are using more contemporary analytic methods, such as Hadoop-based analytic stacks, often have trouble with use of data for lack of experience & expertise. This will improve as more organizations move to these methods & more people are trained in their use.

The second major impediment that I have seen while working with healthcare organizations is a lack of understanding of what analytics is & can do – this is especially true in reference to the difference between analytics & reporting. All healthcare organizations do reporting from their clinical & practice management data: what quality measures scored highest in the practice? Lowest? What departments had the highest numbers of patients etc.  Analytics is different in that we are trying to explore less obvious, & in some cases non-obvious & unintuitive relationships in the data, often in very large data sets. I have had many people that I work with on this ask me if “analytics” can improve their reporting of quality measures. The answer is yes, if you are looking for underlying factors affecting performance, but not if you a simply trying to get better results on quality performance from your data. This is mainly an experience & education issue.

Of course, these issues are a result of many of the obvious impediments: lack of resources, expertise & so on…

So where are we on healthcare analytics? It seems clear (to me at least) that the use of analytic techniques to explore clinical & operational data will become more & more important in the next several to the extent that if a healthcare organization is not developing this expertise & using it to try to optimize clinical & operational efforts, that organization will fall behind in the effort to meet the Triple Aim of improving the experience of care, improving the health of populations & lowering the cost of care per capita. Organizations can use pattern matching in ultra-large data sets to provide improved diagnosis & treatment planning at point-of-care which is of core importance to the patient, but they will also have to begin to explore the relationships between cost & provision of care for both individuals & populations in order to begin to lower such costs, & begin to do predictive modeling & trend analysis in order to be able to optimize utilization of scarce resources & to sustain their operations. The inclusion of methodologies from other disciplines such as business process modeling for workflow optimization, other modeling & simulation techniques for optimization of efforts such as: CPOE (inventory & ordering models), pharmacy utilization, other operations optimization & even analysis of social media data (to extract information of use in clinical & operational workflows) will be essential. We are just at the beginning of the analytics effort & “letting a thousand flowers bloom[5]” is the best way to move toward a consolidation & consensus of what works. Five years from now, healthcare organizations will routinely be analyzing data for the continuous improvement of clinical & operational efforts & actual meaningful use will include such analysis as a core part of what healthcare organizations do. If it doesn’t, we’ll still be stuck in our current morass of huge amounts of data, but little insight or wisdom about how to provide care & control costs.

Next up: More on social media in healthcare (I may be getting too obsessed with this…)

---

[1] http://www.healthcatalyst.com/healthcare-analytics-adoption-model/

[2] The list was created from personal communication & web search (2-10 June 2014)

[3] It is interesting (?) that the only outcome they could unanimously agree on was the death of the patient.

[4] Apparently first used in a syndicated newspaper story about early computerization efforts at the Internal Revenue Service in April, 1963; although my favorite (earlier) example comes from Charles Babbage who in 1864 wrote,” On two occasions I have been asked, "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?" ... I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question.” Babbage, C. 1864. Passages from the Life of a Philosopher. Longman & Co. London. P.67.

[5] Although most people think that when Mao ZeDong initiated the Hundred Flowers Campaign in 1956, it was to allow dissidents to express themselves so they could be identified & dealt with.

Healthcare as a Market...

[1]In my last post, I wrote about what re-engineering efforts might be like in healthcare & why they might be relevant & productive. I also mentioned (as I have several times in these posts) that re-engineering worked well in segments like automobile manufacturing & aerospace because these industries operated primarily as an actual market, but that it might not work as well in healthcare because healthcare does not operate as an actual market. What does this statement mean? & Why is it important in understanding the possibilities for healthcare reform & the potential evolution of healthcare? In order to understand we need a little Economics 101 on what markets are & how they operate.

What is a market, & what characteristics do economies that depend on markets exhibit[2]? A simple definition of a market economy would be: “an economy in which decisions regarding investment, production and distribution are based on supply and demand, and prices of goods and services are determined in a free price system[3]” Such an economy would several essential characteristics:

•         Limited government control & intervention
•    Extensive cost & price transparency
•        Competition in costs & prices based on this transparency as well as the quality of goods & services

Let’s look at each of these characteristics with respect to healthcare.

The Gross Domestic Product, that is the value of the total output of all goods & services in the country, for 2013 was $15.8 Trillion (with a T). We’ll use this as a baseline for other values. Total healthcare spending in the U.S. in 2013 was $2.94 Trillion[4] or 18.6% of the GDP. Total government spending[5] on healthcare in 2013 was $1.22 Trillion or 7.8% of GDP & 42% of overall healthcare spending. This is important for several reasons.

First, we can hardly assert that this market has limited government control & intervention if federal spending on healthcare is 8% of the GDP & 42% of total healthcare spending (for 2013, earlier years have similar percentages). $1.22 Trillion is a lot of money, even by Everett Dirksen’s standard[6], but of course, he was allegedly only talking about billions. Even so, the influence of the federal government, just on the spend side on healthcare, is immense. This influence is separate from the legislative & policy impact of the federal government on healthcare. Both the HITECH Act[7] & the Patient Protection & Affordable Care Act[8] have substantially influenced healthcare in this country. All told, healthcare is far from independent of government influence.

Second, price in healthcare is not transparent. Several recent studies have shown differences in healthcare charges that are both regional & within regions. In fact, it is quite possible that hospitals across the street from each other may charge substantially different amounts for the same procedures. One of many, many possible examples is that an uncomplicated birth at Bellevue Hospital (Manhattan, NY) costs the patient $6,330 (median), while next door at NYU Langone Medical Center the cost is $12,222[9]. A recent Institute of Medicine report[10] found that difference in Medicare costs had to do with the large variation in the cost of post-acute services such as home health care, while differences in commercial insurance costs were mainly caused by the wide difference in reimbursement that doctors & hospitals negotiate with individual insurance payers. These differences in cost to patient are not evident, unless one makes it their business to find them out. Even then it’s difficult, as many healthcare organizations are not inclined to make this kind of information readily available.

There are two other issues with transparency: the actual cost to provide a service is not available or sometimes not even known, & both Medicare & Medicaid costs are fixed but Medicaid costs are set by each individual state based on differing sets of criteria & standards of care. This pretty much ensures that a “consumer” of healthcare services will not have real transparency for either the price they pay for a service or what that service costs their provider. We won’t even discuss the fact that a provider may charge the patient one thing, Medicare may pay 10%-25% of that to the provider & the patient may be billed a fraction of the difference. We’ve all gotten the (in)famous Explanation of Benefits (EoB) form that states at the top: “THIS IS NOT A BILL”. Transparency in both price & cost is just not available in healthcare.

Finally, does competition on cost & price exist in healthcare? In a real market, competitive forces would act to minimize both production cost & price.  In other industries, competition is a fact of life – automobile manufacturing was mentioned at the beginning of this post. Price & cost competition are key drivers in structuring this industry as well as determining what the price of goods to consumers is. This does not appear to be the case in healthcare as situations such as the one cited above for Bellevue Hospital (1^st Avenue & 26^th Street, NYC) & Langone Medical Center (1^st Avenue & 29^th Street, NYC) show that very different price (& cost) structures exist & are tolerated virtually next door to each other. This is not an atypical case.

So, it really doesn’t appear as if healthcare is structured like or acts like a market. It is very heavily controlled & influenced by the federal government, both financially & legislatively. It does not have price or cost transparency, & it also does not appear to exhibit price or cost competition in a conventional sense[11]. What might this mean for healthcare reform & evolution?Re-engineering, that is the systematic modification of business process & practice to align with corporate goals & customer needs, can be done regardless of the economic environment that an organization exists in. It is, however most effective, when that organization exists in a market economy. Competition on cost of goods, consumer price & quality of goods produced drives a number of organizational strategies including:     

• The need for “continuous improvement” in lowering cost, aligning price with customer expectations & improving the quality of good produced; this, in turn, drives:

o   Efficiency in the use of capital, such as research & development investment

o   Innovation in both process & product

o   Strategies focused on customer needs.

Without competition, an organization has no need to focus on these types of efficiencies. Without price & cost transparency, there is no real competition & in an economy heavily influenced by government, organizations have fixed strategies aligned with government requirements, not customer needs. As we have seen, healthcare is a very mixed economy with substantial government influence, little transparency & limited competition. We talk a lot about the need for more effective & efficient use of R&D investment (new medical devices, more spending on clinical & public health infrastructure, etc.) & innovation (modified clinical & administrative practice, new health information practices, etc.), but the primary vehicles for much of this are legislative. The use of electronic health records is a step that is inevitable, but meaningful use (HITECH Act) is a legislative requirement, not an organic development arising from perceived patient needs.

So, you say, what can be done? It seems clear (at least to me) that government must play some role in the evolution of healthcare from where it is as a mostly planned market to a more efficient open market. The kinds of large changes that are required may eventually happen as healthcare evolves, but we do not have 15-20 years (in my humble opinion) for this to happen organically. The government has already acted to try to institutionalize innovation in the form meaningful use of electronic health records. This program needs to evolve (possibly in Stage 3) to start moving at least this portion of the healthcare segment toward a better market profile. What does this mean?

There are several directions that I think can be productive here:

•         Make healthcare substantially more patient-centered – There are a lot of initiatives around this, but patient-centered needs to really mean people taking responsibility for shared decision making[12] with their providers. This, in turn, means that people need to be able to access the information they need including information on at least: treatment options & effectiveness, provider performance, as well as price & cost transparency. This type of information is not currently readily available or when it is, understandable, but that needs to change. This type of decision-making will drive competition as transparency & quality of product (patient experience & outcome) make people better consumers of healthcare services.

o   Programs such as Meaningful Use, PCMH, etc. need to emphasize making this information available to patients & facilitating this type of decision making.

•         Provide guidelines & best practices for workflow modification to focus on patient-centered care. This does not necessarily have to be done by the government, although some initial projects & seed funding could be helpful. Many organizations are in the process of making changes to workflow in order to better align with the use of EHRs, but the emphasis really should be on patient-centered care, not meaningful use. This would emphasize such processes as:

o   Simplified administrative workflow for intake & patient information gathering

o   Clinical workflows emphasizing:

§   Co-ordination of care between & among care teams

§  Care transition from team-to-team & location-to-location

§  Realistic medication reconciliation that allows for not just prescription & claims data, but actual usage data gathered from the patient & other sources

An organization such as the Institute of Medicine, the Kaiser Family Foundation, the Robert Wood Johnson Foundation or any of a large number of credible clinical organizations could begin by making their current processes &/or proposed guidelines available.

These suggestions are just a beginning. Healthcare needs to evolve to be a market driven by: customer (patient) needs, competition & innovation & patient participation in order to begin to address cost control (both cost of services to providers & to patients) & improvement of outcomes. Government programs are inevitable at this stage of market development, but they will be successful only to the extent that they facilitate the evolution of healthcare to a more open market.

Coming up:

• Who actually is the “customer” in healthcare. This question is key to market development.
• Lessons learned from the Path to Analytics Project (in progress)
• Revisiting the GM C4 Project & what it tells us about healthcare evolution

---

[1] Image, HPHSmedia, http://www.hphsmedia.com/?p=1851

[2] Please Note: There is a good deal of political content & controversy associated with the idea of markets & how they do & should work. I am not advocating any political position, but simply trying to use generally accepted ideas of markets in relation to healthcare & healthcare reform.

[3] http://en.wikipedia.org/wiki/Market_economy

[4] GDP figures & all healthcare spending figures from: CMS National Healthcare Spending Projections 2011-2021, http://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/NationalHealthExpendData/Downloads/Proj2011PDF.pdf

[5] includes: SCHIP, DoD, VA, workers compensation, Indian Health Service & other federal programs

[6] “A billion here, a billion there, pretty soon you’re talking about real money”, apocryphal but attributed to Everett Dirksen (R. IL) speaking about taxes

[7] Title XIII, PL 111-5 (42 CFR §412-413, §422, §495)

[8] PL 111-148 (45 CFR §144-§156)

[9] http://www.kaiserhealthnews.org/stories/2013/december/12/ny-state-hospital-charges-vary-wildly.aspx

[10] Institute of Medicine. Variation in Health Care Spending: Target Decision Making, Not Geography. Washington, DC. The National Academies Press. 2013

[11] It should be noted that it does exhibit competition on services, but not on the price or cost of services.

[12] See my post on Clinical Workflows & Other Arcane Rituals (12/16/13), http://posttechnical.blogspot.com/2013/12/clinical-workflow-other-arcane-rituals.html