How predictive analytics ensures a smooth ride for patients
It’s terrible to make a patient wait. There’s no other way to say it. Whether it’s at the doctor’s office or at home for a ride to an important medical appointment, no one likes to be delayed. Underserved populations, unfortunately, do a lot of waiting because of a dearth of secure, dependable transportation, which impedes good health, well-being and the overall patient experience. “Transportation barriers are often cited as barriers to healthcare access,” according to the Journal of Community Health. “Transportation barriers lead to rescheduled or missed appointments, delayed care, and missed or delayed medication use. These consequences may lead to poorer management of chronic illness and thus poorer health outcomes.”
Part of breaking down barriers to healthcare and improving health equity is ensuring transportation to and from healthcare providers is safe, reliable and accessible no matter who the rider may be. Because if we can break down transportation barriers, we have a good chance of improving health among underserved populations. “Take, for instance, patients with transportation barriers that prevent them from making their appointments or going to the pharmacy to refill prescriptions,” an article in Health Affairs posits. “Through our analysis, we’ve found that within a specific population of high-risk patients, those with a transportation barrier had a 63 percent higher risk of readmission.”
If we can make a substantive impact on transportation, we have the possibility of improving patient satisfaction, lowering healthcare costs for patients and providers and improving health outcomes.
Predictive analytics and NEMT software
One way to get there is by using advanced non-emergency medical transportation (NEMT) software. We can use ideas from Advanced Traffic Management Systems (ATMS), typically seen in the trucking industry, to help build NEMT. ATMS is designed to relieve the issues and obstacles caused by significant and continuous traffic on roads and highways. Since we strive to do the same in healthcare transportation, we can use some ATMS concepts along with our own predictive analytics to make real-time decisions to positively impact patient trips. Predictive analytics can help us reroute trips on the fly, make and change trips and, importantly, decrease the amount of time a patient waits for a ride. We want to mitigate traffic congestion, accidents, rush-hour traffic and more. “The rising need for mobility, especially in large urban centers, consequently results in congestion, which leads to increased travel times and pollution,” according to an article in the journal Sustainability. “The first step dealing with congestion in urban areas is the detection of congested areas and the estimation of the congestion level.”
Many NEMT providers work in urban areas, as well as smaller cities and towns, all of which come with unique traffic challenges. No matter where the transportation needs exist, however, an NEMT’s purpose is to bring riders quickly and efficiently to healthcare services by, as the Sustainability authors say, increasing “positive effects” through the better use of data analytics. To close the ride/arrival time gap and thwart high levels of congestion, we can use patient location and driver location data, possibly using GPS found in smartphones or vehicles, to reroute vehicles immediately to the right place at the right time. In addition to decreasing wait times, we can improve patient satisfaction and the overall ride experience with a more responsive ride management system.
Driving change with analytics
By evaluating the elasticity of other quality metrics, and determining overall program optimization goals, predictive analytics can be used for pre-dispatch/routing decisions to achieve other key program goals and facilitate high-level strategic investments in member health. These improvements are capable of largely transforming lower-level routine service tasks into automated decisions with human oversight for improved scalability and program control.
We can use predictive analytics to better understand and act on several transportation-related challenges.
- Using predictive analytics to achieve on-time arrivals for appointments can also be combined with proprietary predictive models to drive further improvements in quality and cost management. Routing decisions identified via predictive analytics, for example, can be used to optimize performance according to programmatic objectives by applying meaningful routing decisions before dispatching a driver.
- Historical transportation data can be used to predict rider no-shows to provide interventions for improved network efficiency, cost management and/or programmatic interventions to improve rider adherence to appointments. This can lead to improved patient health outcomes, which may help generate a favorable cost reduction for a health system.
- Forecasting complaints is critical to improving the patient transportation experience. To do so, we can select specific values as they relate to a rider’s experience. This allows a view into expected ride-related criticisms that will need an automated or human intervention.
- Data from NEMT, meal delivery, medication management and remote monitoring can be fed into predictive models to identify transportation routing decisions. To the extent transportation becomes the backbone for these services, we can simultaneously model projected outcomes using data from each. This allows us to develop an overall expected value of care as it relates to the entire package of services delivered.
Predicting the future
As more NEMT routes are digitized and the data is collected and analyzed, it will be easier to transform the NEMT industry and provide patients with an around-the-clock, on-demand and generally improved ride registration and trip experience.
The goal, whether you’re a healthcare transportation provider, a driver or a patient, is to meaningfully alter the entire NEMT model by utilizing predictive analytics to create an improved experience for everyone involved because no one wants to wait for a ride any longer than they must.