Couldn’t attend Transform 2022? Check out all the top sessions in our on-demand library now! Look here.
Sixty percent of American adults live with at least one chronic condition, and 12% with five or more. They spend exponentially more on health care than people without chronic conditions. For example, 32% of adults with five or more chronic conditions make an emergency room visit at least once a year. In addition, 24% have at least one inpatient admission, in addition to an average of 20 outpatient visits — up to 10 times more than those without chronic conditions. In fact, 90% of US $4 trillion health care spending is for people with chronic and mental health conditions, according to to the Centers for Disease Control and Prevention (CDC).
The fundamental way in which healthcare organizations reduce these costs, improve the patient experience and ensure better health for the population is through healthcare management.
In short, care management refers to the collection of services and activities that help patients with chronic conditions manage their health. Healthcare managers proactively contact patients in their care and provide preventive interventions to reduce ED hospitalizations. Despite their efforts, many of these initiatives are delivering sub-optimal results.
Why current care management initiatives are not effective
Much of healthcare management today is based on past data
For example, health care managers identify patients with the highest costs in the previous year and begin their outreach programs with them. The biggest challenge with this approach, according to our internal research, is that nearly 50-60% of expensive patients were cheap in the past year. Without proper care, a large number of at-risk patients are left unattended with the reactive care management approach.
MetaBeat will bring together thought leaders to offer advice on how metaverse technology will change the way all industries communicate and do business October 4 in San Francisco, CA.
The risk stratification used by the healthcare management team today is a national model
These models are not localized, so understanding the social determinants of individual locations is not considered.
The primary focus of the care management team is mainly on the transition of care and the prevention of readmissions
Our experience working with several clients also indicates that readmissions only account for 10-15% of the total withdrawal. The focus on proactive care management and avoiding future avoidable emergency care and hospitalization is missing. This is the key to success in value-based care models.
In a given year, expensive patients can become cheap patients
Without such a detailed understanding, outreach efforts can be ineffective in reducing healthcare costs.
How AI can increase the success of healthcare management
Advanced analytics and artificial intelligence (AI) offer significant opportunities for healthcare management. Health risks are complex and driven by a wide variety of factors that go far beyond a person’s physical or mental health. For example, a person with diabetes is at higher risk if they also: low income and limited access to medical services. Therefore, when identifying the needs of patients at risk, additional factors for those most in need of care should be taken into account.
Machine learning (ML) algorithms can evaluate a complex set of variables such as patient history, previous hospital/ER admissions, medications, social health determinants, and external data to accurately identify patients at risk. It can stratify and prioritize patients based on their risk scores, allowing healthcare managers to design their reach to be effective for those who need it most.
At the individual level, an AI-enabled care management platform can provide a holistic view of each patient, including their past care, current medications, risks, and accurate recommendations for their future course of action. For the patient in the example above, AI can equip healthcare managers with HbA1C measurements, drug ownership ratio, and predictive risk scores to deliver the right care at the right time. It can also help the care manager determine the number of times they need to reach each patient for maximum impact.
Unlike traditional risk stratification mechanisms, modern AI-based healthcare management systems are self-learning. When healthcare managers enter new information about the patient — such as last hospital visit, change in medication, new habits, etc. — AI adjusts its risk stratification and recommendations engine for more effective outcomes. This means that ongoing care for each patient improves over time.
Why payers and healthcare providers are reluctant to embrace AI in healthcare management
In theory, the impact of AI in healthcare management is significant – both governments and the private sector optimistic about the possibilities. Yet in practice, especially among those who use the technology on a daily basis, i.e. care managers, there appears to be reluctance. With good reason.
Lack of localized models
For starters, many of today’s AI-based healthcare management solutions are not patient-centric. Nationalized models are ineffective for most local populations, rejecting predictions by a significant margin. Without accurate predictions, healthcare managers lack reliable tools, fueling even more skepticism. Carefully designed localized models are fundamental to the success of any AI-based healthcare management solution.
Not driven by the needs of the care manager
On the other hand, AI is not now ‘care manager-driven’ either. A ‘risk score’ or the number that indicates a patient’s risk means little to the care manager. AI solutions must speak the user’s language so that they become familiar with the suggestions.
Healthcare delivery is too complex and critical to be left to the black box of an ML algorithm. It should be transparent about why each decision was made – there should be explainability that is accessible to the end user.
Inability to demonstrate ROI
At the healthcare organization level, AI solutions must also demonstrate ROI. They need to influence the business by moving the needle to key performance indicators (KPIs). This can include reducing healthcare costs, easing the burden on the healthcare manager, minimizing emergency room visits, and other benefits. These solutions should provide healthcare leaders with the insight they need into hospital operations and delivery metrics.
What is the future of AI in healthcare management?
Despite the current challenges and failures in some early AI projects, the industry is just teething. As a rapidly evolving technology, AI is adapting to healthcare needs at an unprecedented pace. With continued innovation and responsiveness to feedback, AI can become the superpower in the armor of healthcare organizations.
AI can play a major role, especially in proactive care management. It can help identify patients at risk and provide care that prevents complications or emergencies. It can enable healthcare managers to track progress and provide ongoing support without patients ever having to visit a hospital to receive it. This, in turn, will significantly reduce healthcare costs for caregivers. It will enable patients to live healthy lives in the long term and promote the overall health of the population.
Pradeep Kumar Jain is the chief product officer at HealthEM AI.
Welcome to the VentureBeat Community!
DataDecisionMakers is where experts, including the technical people who do data work, can share data-related insights and innovation.
If you want to read about the latest ideas and up-to-date information, best practices and the future of data and data technology, join us at DataDecisionMakers.
You might even consider contributing an article yourself!
Read more from DataDecisionMakers