Tag Archives: GIS

Using Data to Improve Long-Term Care

In the last 20 years, the insurance industry has rapidly become one of the most data-driven and complex industries in our global economy. With the advent of wearable technologies, improved data-collecting capabilities and the increasing dominance of behavioral economic theories, insurance companies are inundated with data. Used well, these large sums of data can greatly benefit insurance companies and consumers. Returns on policies will increase, along with efficiency, while risk and overall costs will decrease.

However, using all this data well is extremely difficult and requires years of work and expertise. Through my more than 25 years of actuarial and statistical modeling experience, I have seen insurance companies use data well, increasing their profitability in the process. Big data can be a significant asset for insurance companies over the next 100 years, or it could bog down the industry, exacerbating issues that are currently affecting companies across the globe. All this really depends on how the insurance market adapts to and uses big data today, in the early stages of this big data era.

See also: Understanding New Generations of Data  

My current focus is the application of behavioral psychologies to build predictive models to maximize the effectiveness of insurance technologies in the design of new products. Insurance is becoming mediated more and more by mobile, wearable and artificial intelligence (AI) technologies. As generations become more connected through media technologies, leveraging media psychology, actuarial science and data science will be vital to the predictive future of insurance. This is particularly true with regards to attracting new, younger customers to life insurance and other insurance products. Young people are demanding a customer experience centered on quick and easy app-driven solutions over traditional, slower, life insurance models.

There is great potential for the long-term care industry to benefit from innovative technologies that leverage big data, machine learning and artificial intelligence. For example, home care can be improved through the use of robotics and interactive telehealth technologies to mediate the interaction between patients and medical professionals in real time, improving patient outcomes. Wearable technology to monitor biometrics, other than steps, in real time can instantaneously inform of a pending health event requiring medical attention. Big data and computing power are exploding at factorial rates, enabling algorithms to search for significant correlations in seconds rather than months, and the difference has proven to be life-saving. However, it is critical to understand how these algorithms work to prevent abuses of consumer protections.

The GIS advanced regulator training will equip regulators with a conceptual understanding of the machine learning algorithms leveraging big data being used to develop consumer insurance rates. They will learn how to test the appropriateness, power and validity of these statistical modeling tools against the data companies that are using it to build pricing algorithms and fuel AI algorithms. Regulators will also receive training in how to interrogate data for completeness and how to identify hidden biases that may unfairly discriminate against consumers. This training will also engage regulators in discussions of the ethical use of big data, machine learning and AI in preparation for a future where insurance is nearly 100% mediated by technology.

See also: Healthcare Data: The Art and the Science

Companies will have to become good digital citizens and work with regulators to ensure an industry that fosters innovations beneficial to consumers without compromising legal standards and the ethical treatment of all consumers. A future of insurance mediated by big data, predictive algorithms and AI will have great benefits for the human experience. The industry and regulators through cooperative efforts can ensure this promising future for consumers.

I will be moderating the “Can Big Data Save Long-Term Care” breakout panel on Wednesday, April 24, and am organizing and leading the big data and advanced modeling training on April 22-23 and April 25-26 at the 2019 Global Insurance Symposium in Des Moines. To register to attend GIS please go to: https://globalinsurancesymposium.com/register/

The Most Important (and Overlooked) Tech

Geographic information systems (GIS) may conjure up images among insurers of an old technology that tends to be used by a few passionate specialists at their company. It is true that the technologies for mapping and visualization have been around for decades. (I first saw a demo of GIS for insurance in 1989, and the potential blew me away). It is also true that usage in insurance is often limited to a few high-value areas of the business. Although GIS can hardly be called an emerging technology – much like AI, which has also been around for many years – it could be considered a resurging technology.

This is a new era for GIS. The core GIS technology platforms have been extended to enable solutions for what many now call location intelligence. There are some good reasons why insurers should be considering an enterprise location strategy as an important element of their overall business strategy.

  • Ease of Use: This might seem counterintuitive because the use of GIS systems traditionally required individuals with deep skills in data, geography, demography and other sciences. But today, the user interfaces have been modernized, templates and apps abound and business users are able to leverage the technology without difficulty.
  • Open Platforms: The sharing of maps, apps and data related to GIS solutions is extensive. Collaboration among government agencies, businesses and individuals is in high gear, especially because location intelligence-based solutions are often leveraged to address important societal issues. A prime example of this is the collaboration that occurs during natural disasters.
  • New Data and Maps: The spread of connected sensors and devices across the planet has produced many new data sources, enabled the creation of new mapping layers and dramatically increased precision. A connected device might be indoors or outdoors, stationary or moving, urban or rural and able to collect highly accurate data about objects and what is happening to and around them.
  • New Spatial Technologies: The technologies for indoor mapping, 3D, temporal analysis and many other aspects of spatial technology continue to advance rapidly. In addition, the scale and speed of real-time processing open up opportunities to capitalize on the technologies.

From an insurance standpoint, GIS creates possibilities for gaining insights about managing risks, understanding customer needs and behaviors and improving operations. More precision is possible in analyzing the exposures in a book of business, selecting and pricing risks and handling claims (especially CAT claims). New risks and customer needs can be identified, leading to new products/coverages or more insight into geographic locations for agents. New services can be provided to policyholders, including real-time alerts and information to help them better manage their risks.

See also: Strategist’s Guide to Artificial Intelligence  

The potential business use cases and high business value warrant the attention of senior executives. Insurers should seek to create an enterprise location strategy, harness the new era of technology and build on the expertise of existing GIS users in the organization, ultimately enabling a broader range of employees to solve problems in their respective domains.

Model for Collaboration and Convergence

The Global Insurance Accelerator, based in Des Moines, Iowa, has just participated in the fourth Global Insurance Symposium. Two of the big takeaways are that the insurtech movement is maturing, and there is indeed convergence happening between the traditional industry and the entrepreneurial startups that have new ideas and business models. For the insurance industry to advance, there must be a great deal of collaboration between all types of participants in the marketplace. The GIA represents a great example of how this collaboration can be facilitated.

Since its inception, the GIA has promoted collaboration instead of disruption. There is a clear focus on insurtechs and their potential to bring transformative ideas to the industry, but not with the objective of displacing the existing industry players. The model is designed to look for mutual benefit for insurers and insurtech startups. Insurance companies, regulators, investors, academia and other industry experts like SMA are actively involved with insurtechs to guide and support them as they mature.

See also: Insurance Coverage Porn  

The idea is that there is a win-win situation when the strengths of the traditional industry (capital, regulatory experience, scale, risk knowledge, etc.) can be blended with the strengths of insurtechs. The startups bring an entrepreneurial spirit, speed, innovation and new business models to the game. The best ways to partner and take advantage of these combinations require hard work and are enhanced by facilitating organizations like the GIA.

As the transformation of the insurance industry continues, more and more insurers are seeking to actively partner with insurtechs, leverage emerging technologies and institutionalize innovation. At the same time, the insurtech community in general is maturing and has a greater understanding of the insurance industry and the need to collaborate than it had a couple of years ago. This evolving formula creates the potential to provide new ways to deliver the customer experience, improve operational efficiencies and assist customers in risk management and wealth accumulation, resulting in success for insurers, insurtechs, and other market participants.

population health

A New Dimension in Population Health

With the healthcare landscape changing from fee-for-service to fee-for-value models, healthcare provider systems (hospitals, clinics, independent physician associations, etc.) are now, more than ever, under pressure to effectively manage the health and cost outcomes of their given populations. Under such models, providers are not only providing healthcare service to the patients, but they are also sharing in the financial risk and reward of patient costs. To effectively become a value-based organization, providers today are adopting a process broadly termed “population health.”

The “population health” process usually starts with identifying key segments of a population that face certain risks of adverse health outcomes and thereby high cost — a step known as “risk stratification.” Once risk is stratified, appropriate patient intervention programs are employed to improve: access to health, targeted encounters with providers and continuous monitoring of patient risk. This leads to lower emergency room visits, better clinical outcomes (such as properly managed blood glucose levels for diabetics) and lower financial cost.

There are many proven methods of risk-stratification to assign patients to low-, medium- or high-risk groups. For example, the adjusted clinical groups method examines patient diagnoses, and the elder risk assessment method assigns risk based on patient demographics. In today’s market, we observe many proprietary methods of risk stratification developed by various provider systems. The variables used in risk stratification can be classified into the following categories:

  1. Clinical: Data from electronic medical records (EMRs), patient vitals, laboratory data, etc.
  2. Administrative: Usually patient claims that track diagnosis and procedures already conducted
  3. Socio-Economic: Patients’ social situations, family and friend support systems, language preference, community involvement, the degree of influence that out-of-pocket expenses could have on the patient’s well-being, etc.
  4. Lifestyle: Health and activity tracking devices such as Fitbit, Apple Watch, etc., which carry critical daily lifestyle data about a patient

While the above categories play a large role in risk stratification, a new dimension known as “spatial access” can significantly lend leverage to the provider systems in affecting patient outcomes. For some patients, the overall risk may increase significantly because of their spatial, geographical and transportation access to medical and wellness resources. Spatial access refers to patients’ geographic proximity and ease of mobility to resources such as hospitals, primary care physician offices, primary and specialty care clinics and nurses. The geographic arrangement of patient and provider resources can play a significant role in healthcare utilization. For example, patients living in areas with fewer healthcare resources — regions often termed “doctor deserts” — have been linked with higher rates of preventable ER visits that are notorious for raising healthcare costs without necessarily improving healthcare outcomes. Using geographical and spatial analysis to supplement existing risk stratification techniques can help providers with an untapped method of assessing risk and generating better ROI in the long run.

To incorporate spatial access analysis into risk stratification, providers must:

  1. Gather patients’ social network geographic information
    Most EMR systems already contain patient address information, but they often lack information about the patients’ social network. The following types of data should be collected and refreshed on an annual basis:

    • Distance to closest primary care clinic, both straight-line and network-distance;
    • Distance to closest primary care provider, both straight-line and network-distance;
    • Spatial density of medical resources in a given area, especially primary care services;
    • Access to vehicle transportation, either on the patient’s own or through a family member; and
    • Proximity to public transportation.
  2. Conduct “spatial access” risk stratification
    Using a geographic information system (GIS), assign relative risk to each patient based on each of the components listed above, then create a composite risk based on all of the attributes.
  3. Represent population risk stratification visually via mapping
    Examine which areas of a provider’s service areas are prone to having individuals with high risk; look for clusters of high- or low-risk patients in doctor deserts. Viewing individual or aggregate risk through mapping would offer analysts and decision makers a comprehensive view of what types of risk are occurring in their service area.
  4. Strategize how to implement interventions based on locations of high-risk patients
    If clusters of high-risk patients exist in a certain area, begin to strategize about what kinds of interventions may alleviate the problem. Interventions may include the placement of new primary or specialty care clinics. Because creating clinics can be challenging, increased use of mobile provider teams can be an alternate solution. Lastly, a combination of telemedicine and mobile medicine should be assessed for the right mix of care for doctor deserts and lack of physical clinics.

Understanding the spatial context of patient demand vs. provider supply of healthcare service is an important component for accountable care organizations to conduct accurate risk stratification. Moreover, incorporating GIS into healthcare service analyses improves decision-making capabilities for evaluating, planning and implementing strategic initiatives. By taking advantage of the analytic capabilities of GIS and spatial access risk stratification, healthcare service providers are better equipped to more comprehensively understand their patient population and to thrive in this new value-based world.