Healthcare Analytics: Concepts & Assumptions

“Data is a precious thing and will last longer than the systems themselves.” – Tim Berners-Lee, inventor of the World Wide Web.

In the past several years, we’ve heard an immense amount about data, big data, data analytics & every possible topic related to data. We know that 90% of all currently available data has been generated in the past two (2) years![1] We also know that every business publication has had articles on data (Business Week, May 2013; Harvard Business Review, December 2013; Forbes February 2014 to name just a few), & that every business consultant such as Accenture, Deloitte, Gartner etc. has a practice or advisory in this area.

Closer to home, many large healthcare organizations are developing analytic systems utilizing very large amounts of data to provide diagnostic, treatment planning & operational guidance. Examples would be the point-of-care recommendation systems currently used by Kaiser Permanente & the Mayo clinic, among others, that provide near-real-time diagnosis & treatment planning guidance to providers at a patient’s bedside. Dr. Watson (IBM) is another well-known example.[2] These systems use millions of patient records, often recorded over long periods of time, as well as thousands (or more) journal articles & physician’s notes to provide their analysis & recommendations. Not many healthcare organizations have this amount of patient data available, so what are the implications of analytics for most hospitals, clinics & practices, & how can they take advantage of analytics to make better clinical & operational decisions.

First, let’s define what we mean by data & analytics. Data, in this sense, is a set of qualitative or quantitative values. Simply restated, pieces of data are individual pieces of information[3]. They may be numeric (quantitative), or words or sets of words (qualitative) or even hybrids such as addresses (77 Massachusetts Avenue, E40-248). Analytics, in general, is the discovery & communication of meaningful patterns in data[4]. Contemporary analytics has taken on a more specific meaning, especially in contrast to statistical analysis of data (the application of statistical hypothesis testing methods to data). Analytics today are a set of methods for data organization & analysis that are applied when data have (some of the) the following characteristics:

• Volume: management of multiple petabytes of data
• Velocity: management of data values that are changing rapidly (e.g. NASA’s launch sensor net of >1M sensors of various types sampled 3x/second)
• Variety: many different types of data in different formats & from different sources

In healthcare, data variety is most often the issue. This type of data is very difficult to organize & analyze in a conventional sense.

What are the differences between analytics & conventional analysis? They can be summarized as follows:

• Contemporary analytics is the empirical characterization of data & information. An example would be: A physician at Kaiser is using their point-of- care recommendation in order to confirm a diagnosis & develop an optimal treatment plan. The physician is entering patient parameters while doing a bedside examination. The point-of-care recommendation system evaluates 4 PB of patient data against a set of patient parameters entered at the point-of-care for a specific patient, & it finds 9,372 cases similar enough to use for comparison with the patient. That is not a statistical prediction of similarity, but an exact empirical characterization. In the same sense, if that system classifies treatment plans of those 9,372 cases according to outcome, that is not a statistical prediction of outcome, but an exact characterization of the outcomes present in the data. This changes how we think about results in that we are looking at exact characterizations not predictions with associated probabilities. This is true of even smaller sets of data.
• Contemporary analytics does not require extensive data transformation & normalization. Analytic systems such as Hadoop-based analytic stacks aggregate data in many different forms (alphanumeric, text, image, other media) & from many different sources (EHR, financial systems, practice management, public health systems, other private & public data sources), & perform analysis across all of these types (e.g. cost/service/location/provider or number of patient interactions vs. macro-demographic & population trends). It does require an understanding of the normalized definitions of common terms (encounters, providers etc.), especially if cross-organizational comparisons are to be made.
• In general hypotheses & informational relationships are informed by the analysis, not by a priori assumptions. This means that empirical characterization is carried out by performing inquiry developed by consensus of the healthcare organization’s staff (or designees, all parts of the organization should be represented) aligned with strategy. Then hypotheses are formed (& relationships defined) based on empirical results & analysis may continue.

OK – so we know something about data & analytics, but what does this actually mean for healthcare organizations. As a technologist, I have to say that as interesting as the technology of analytics is, it’s not the point. The point is a way of thinking about data & analysis. I use the phrase “data as an asset” as shorthand for this way of thinking. Thinking of data as an asset means that you (& your team) look at data in a larger context than just the clinical &/or operational data that you have. You think about data in relation to the strategy of your organization & in relation to the kinds of strategic decisions that are required to keep your organization healthy. Thinking of data just as facts is no longer enough to create the largest amount of value from that data, you must think of data strategically. This means having an awareness of data, your own as well as external data… data from city, county, state & federal programs… data from other organizations… as much relevant data as you can discover & access.

Once you start thinking about data as an asset, there are some things you can do to utilize data strategically.

1. First is to review (or develop) your organization’s strategy & identify what decisions are embedded in it. 
2.  Next is to identify what data you have access to that is relevant to those decisions. This may, in fact, not be entirely straightforward. You may include data that is not immediately apparent as relevant. Remember, one of the characteristics of analytics is that the relationships in the data are defined empirically by inquiry, not a priori.
3. Third is to convene groups of heterogeneous groups of stakeholders to develop areas of inquiry to be address by analysis. These can be quite general (e.g. the relationship of the provision of specific enabling services to outcome or cost), but they must be related to the organization’s strategy & to the decisions that need to be made to carry out that strategy.
4. Fourth, detailed analytic queries are developed to address the areas of inquiry & carried out. 
5. Finally, results are interpreted & presented in support of data-driven decision-making. Queries can also be redesigned, modified or enhanced at this point & rerun.

Recent conversations with CIOs & other healthcare executives at conferences & other meetings have focused on several areas of inquiry that are strategic to the continued growth & success of these organizations. These areas have included:

• Classifying patients according to risk & cost: This requires defining a set of classes (such as healthy patients, patients with chronic conditions, patients with multiple chronic conditions, patients with chronic conditions & behavioral health issues, etc.) & then analyzing the patient population with respect to these classes. Additionally it often does additional analysis to determine the cost of care for each patient & each class. This allows the top 1%, 5% & bottom 5% etc. of patients to be identified with respect to cost & may lead to interventions once causes & similarities in these classes are also analyzed.
• Determining the cost of providing specific clinical & non-clinical services (where data is available): This can be done along various axes such as per location, per time period, per provider; all of which may provide insight into costs & with additional analysis into the relationship of services to outcomes.
• Analyzing population trends utilizing both internal clinical & demographic data as well as publicly available data (such as State provided population trend data per location, time period etc.): This can provide insight into encounter trends as well as revenue trends.

Many other areas of inquiry are possible, but need to be aligned with the organization’s strategy in order to be productive & to enable data-driven decision-making.

As I mentioned above, the technology of contemporary analytics is also interesting, & it will be covered in my next post.

[Please Note: A version of this post appears as my column for Technology in Focus on the RCHN Community Health Foundation website (www.rchnfoundation.org)]

---

[1] http://www.sciencedaily.com/releases/2013/05/130522085217.htm

[2] http://www-03.ibm.com/innovation/ca/en/watson/watson_in_healthcare.shtml

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

[4] http://en.wikipedia.org/wiki/Analytics

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.

Once More Into the...

OK - No matter how many times I start this, I never seem to be able to continue consistently. So maybe consistency isn't necessary, maybe doing something interesting that I think is important is necessary, we'll see...

As many of you know, I have been working in healthcare information technology (HIT) for the last 3 years - ever since I left EMC. I got connected with Sam Karp at the California Healthcare Foundation (CHCF, www.chcf.org) started working on the software technology used in the RHIO in Santa Barbara County (CA), SBCCDE, now defunct, & have been working on HIT ever since. Currently, I'm working in two areas. The first is studying how technology is adopted in healthcare organizations. This is an extension of the work I've been doing at MIT in manufacturing organizations (in auto & aerospace, esd.mit.edu/people/scholars.html). I have also been working (as part-time CTO) with a company that provides practice management & Electronic Health Records (EHR) software for Community Health Centers (CHCs). CHCs are federally qualified organizations that provide healthcare to uninsured & underserved populations. This work is now associated with the RCHN Community Health Foundation in NYC, where I am Director of Technology Research (www.rchnfoundation.org). In my copious spare time, I continue to survey & write about emerging technologies & trends as well as consult to early stage companies. I'm having fun.

My next several posts will describe the technology adoption work, so stay tuned...

[FYI - My Stepson, Christopher Culliton is responsible for the photo. If it looks professional, he works doing set lighting for major movie productions & is currently Best Boy on the new James Cameron sc-fi movie, Avatar, being filmed in New Zealand]