Using behavioral science and AI to meet the needs of patients and providers
Leveraging insights from AI and behavioral science can improve financial outcomes as well as clinical outcomes.
Why do people make decisions that are not in their best interest? Why do people forgo opportunities that will improve their physical or economic well-being? Thanks to the groundbreaking work of researchers like the Nobel Prize Richard Thalier, we know why people often don’t act rationally. They can be affected by biases such as “availability heuristic”, “bounded rationality” or “loss aversion”. These technical terms simply explain why people make “bad” or suboptimal decisions. behavioral science takes psychology and real-world data into account when analyzing and predicting human behavior.
We believe that in healthcare, leveraging insights from behavioral science along with data and AI can improve financial and clinical outcomes.
Patient Access and Revenue Cycles: Defining the Problem
Problems of patient access to health care are a major problem for health systems. Take, for example, a patient eligible for Medicaid. We know that patients presenting as self-payers can be a significant source of financial pressure on healthcare systems. These patients may experience significant acute services; but if they are uninsured, the likelihood that the health system will be reimbursed for the services provided is very low. Therefore, helping these patients enroll in Medicaid, disability, and other types of federal, state, and local programs is important, for the patient themselves and for the provider.
Denials of medical claims are also on the rise. According to Changing healthcare data, refusals have increased by 23% since 2016, representing more than 11% of all complaints. About half of these denials are due to front-end revenue cycle issues such as authorization/eligibility.
COVID has disrupted the authorization, eligibility and registration process. Between attrition due to burnout and the unintended consequences of vaccination mandates, hospitals are chronically understaffed. Sometimes hospitals cannot ask a specialist to meet with a potential candidate in the emergency department to help determine if they are eligible for Medicaid. Fast forward and you end up with a patient in debt and a hospital not being reimbursed for the care they provided.
The lack of adequate clinical triage also creates problems for the patient and the provider. Providers can sometimes struggle to identify, triage and segment patients to the most efficient care setting. When providers are unable to triage patients appropriately, patients often turn to the emergency room or do not seek care at all.
Another source of friction and inefficiency is “care transitions” – which refers to the movement of patients between healthcare professionals, facilities and home as their condition and care needs change. Ineffective care transition processes lead to adverse events and higher hospital readmission rates and costs.
Enable better decisions
So how can behavioral science help address these and other pernicious issues plaguing our healthcare system? Take, for example, a patient’s ability to weigh all available information and options. Faced with a medical problem, the patient can be shaken by many stresses, including fear, anxiety, financial insecurity. Behavioral science teaches us that this can lead to “cognitive exhaustion.” Simply put, the mind is overwhelmed with too much information and overwhelmed with too much stress to properly process all the signals.
Therefore, communication with the patient can and should be simplified and associated with feelings of empathetic support. Behavioral science tells us that just because a given action will benefit the patient does not necessarily mean that they will act. But by breaking tasks down into simplified “calls to action” and making common cause with the patient (“Let’s finish together”), we can nudge the patient towards the desired outcome.
Behavioral economics can also be used in efforts to enroll patients in medical coverage. The fear of loss – “loss aversion” – is psychologically twice as powerful as the possibility of gain. So, as we engage patients, we can make them more likely to start an enrollment process if it promises to allow them to “not miss a thing”, rather than “make an improvement”.
Small slices: coupling behavioral science to data science
Using behavioral science in patient engagement is inherently a personalized process. One size does not fit all. Data science and AI can help us match the message to the patient and the appropriate platform. This allows us to recognize much more specific slices of the population and moves us away from broad segmentation.
We can identify people most likely to qualify for disability programs or Medicaid. It can also help us understand the right method of communication, and to whom, at each stage of the patient journey.
For example, one might assume that a grandmother in her 60s would prefer phone calls and written communications from her suppliers. However, we know from our data that many seniors are much more digital savvy than you might expect. They have taught themselves how to text and interact on social media so maybe they can keep in touch with their grandchildren. Communicating with them digitally for certain transactions and events may be most appropriate, which traditional broad segmentation would not allow us to recognize.
Data and AI can also predict which patients are most likely not to show up. We know that no-shows hurt efficiency and resource management. So if we know who is most likely to miss an appointment, we can remind them of their appointments more frequently, remove the sticking points that are causing them to miss the appointment, and deploy resources hoping that a certain percentage of people do not show up despite our best efforts.
Transforming the patient and provider experience
Behavioral science coupled with data and AI can inform a nuanced approach, which helps us understand patient motivations and needs and helps inform how best to target patient access strategies. This helps us better understand how to interact more effectively and how to more effectively use an omnichannel communication approach to interact with the entire patient population.
Above all, combining behavioral science, data, and AI leads to better fiscal and clinical outcomes for patients and providers.
Jason Lee, Vice President of Product Management
BA, economics, Harvard University; MBA, Health and Corporate Social Responsibility, Walter A. Haas School of Business at UC Berkeley
Jason Lee oversees offerings throughout the revenue cycle to ensure Change Healthcare’s portfolio of RCM service offerings meet key customer needs. Jason is passionate about developing solutions that help patients navigate effortlessly through their healthcare journey.
Tabitha Hillman-Burcham, behavioral science researcher and senior AI manager
BA, International Journalism, Ohio State University; PhD in Behavioral Psychology, Ohio State University
Tabitha Hillman-Burcham is a behavioral specialist at Change Healthcare. She leads a team of behavioral science experts within the AI organization who aim to understand and advocate for the motivations, intentions, feelings, and needs of select populations. She is currently an adjunct professor at Indiana University.