In an article titled, “How big data can revolutionize pharmaceutical R&D”, the McKinsey Global Institute estimates that applying big-data strategies for better informed decision making could generate up to $100 billion in value annually across the U.S. health-care system, by optimizing innovation, improving the efficiency of research and clinical trials, and building new tools for physicians, consumers, insurers and regulators to meet the promise of more individualized approaches.

A lot has been inked about the pharma and healthcare industry lagging behind the retail and financial services industries in the use of big data.  Our premise is that deep data, and not big data, is critical for healthcare.  Deep data is about combining the relevant data streams with domain knowledge and analysis, not merely pursuing data acquisition while hoping that “insights” emerge from correlation.  With the availability of new data streams like clinical trial performance, climate, adverse events reporting, personal medical devices, and more, the trick is to identify value in these data streams and merge the appropriate streams to gain new insights.  Determining value in the data streams and knowing which ones to merge requires domain expertise to visualize the use-cases.

When improving clinical trial efficiency, the key focus areas would be site selection, investigator selection, and patient recruiting.  Clinicaltrials.gov is an important data stream that provides a rich view of various trial sites, study parameters, investigators and site performance.  Mapping the competitive activity for trials can be built to identify white spaces for site selection.  Fig 1 below shows the trial locations for various solid tumor studies being conducted in California for a Sponsor and its competitors.  While the Sponsor seems to be active in Southern California, the competition seems to have a higher density of locations in Northern California.  If we were to drill down further and examine the number of studies per location being conducted for solid tumor (Fig 2), it presents a totally different picture for the Sponsor.  Competition is conducting more studies at the same or similar locations as the Sponsor, which could lead to challenges in patient retention.

Source: Clinicaltrials.gov, HCUP California 2011

Taking the next data stream – Hospital Discharge, can help identify patients with tumors at various hospitals (Fig 3).  When this information is overlaid on the trial sites, we can evaluate potential sites with lower competitive density.

Investigator performance can now be evaluated based on study parameters and trials across competitors.  When data streams across Clinicaltrial.gov and social media are combined we can get a fair measure of investigator experience (Fig 4) and any compliance or regulatory issues (Fig 5)

Fig 4: Investigator Experience

Fig 5: Compliance/Regulatory Issues

Domain knowledge is critical in creating the problem statement and evaluating data streams for incremental gain.  Deep data allows for an optimal way to structure problems, analyze data and evaluate results, as opposed to the big data approach of hoarding data and performing analytics to get insights.  As seen in the above example, while Clinicaltrial.gov is a thin data stream, its content allows for rich evaluation of competitive and investigator landscapes for trials.  Layering additional data streams like Hospital Discharge, the FDA site and other social sites allows us to build a nuanced view of potential sites/investigators for trials.  Similarly, deep data techniques could be utilized for better targeting of physicians, hospital key account management and patient therapy adherence.

How do you manage Ms. Healthy Spender & Mr. Chronic Thrifty?

Member 0ADCF33F9A0F1642 (Ms. Healthy Spender) is a 40 year old healthy female whose annual health insurance payments total $67,742.  According to Kaiser Family Foundation the US per capita healthcare spend was $6,815 in 2009.  Upon further examination, Ms. Healthy Spender has no chronic conditions but complains of abdominal pain.  She has had one laparoscopic procedure performed on her and has medication spend of $63,561.  How do health insurance companies identify members like Ms. Healthy Spender and drive appropriate programs that will help her manage her health while reducing costs?

Member 0ADCF33F9A0F1642 Healthcare spend

Segmenting customers based on their behavior, understanding the needs of the various segments and then delivering programs to meet these needs has been the foundation of successful marketing strategy.  For health insurance customers, primary behavior is driven by the member’s health condition – whether they are healthy or have chronic conditions, the utilization of health services – the number of office visits, lab tests and hospitalization, and amount paid to consume these services – premiums, co-pays, out of pocket payments and claim payments.

Natural segments are members with multiple chronic conditions who are incurring high medical spend, healthy customers with low medical spend and members with life events (like pregnancy) who incur periodic medical spend.  From our analysis we have seen other segments like healthy members with high medical spend – like Ms. Healthy Spender above.  On the other hand are segments with members who have chronic conditions and low medical spend or utilization.  Member 0AC037393027DB82 (Mr. Chronic Thrifty) is a 58 year old male suffering from hypertension and cholesterol with annual spend of $303.

Member 0AC037393027DB82 Healthcare spend

Understanding behavior of unhealthy members with low spend is critical as they could develop complications over time resulting in higher spend.  Some common reasons for low spends have been lack of medication adherence, inadequate knowledge about their health conditions or financial condition.  Addressing these behaviors through care co-ordination, member education, care alerts/reminders or shifting to an appropriate plan might result in improved health outcomes.  Similarly healthy members with high medical spend could be due to undiagnosed or misdiagnosed health condition, member desire for periodic health check or possible waste and abuse.

Over time there has been a shift in responsibility to individual consumers for making decisions about their health and related spending.  Payers can help consumers in making these decisions by providing appropriate information.  More importantly decisions about health are prone to irrational behavior similar to what has been witnessed when consumers make decisions about their 401k or buying a car. Douglas Hough, a John Hopkins researcher, has conducted extensive research on anomalies around health behavior – why do patients insist on a prescription or having a procedure performed when visiting a doctor?  Patients do so because of an “action bias,” wherein people are predisposed to the idea that doing something is better than doing nothing, even though watchful waiting might be the most rational course. This is how patients with virus-based common colds end up with prescriptions for antibiotics that do nothing against viruses.

Behavioral segmentation is a powerful tool to understand customer behavior.  Understanding the possible psychology behind various behaviors and being able to develop programs that address customer needs is critical for delivering superior member experience.