- Patient engagement is a key element of quality healthcare delivery. In order for patients to maintain their well-being, they must take an active role in their care and understand what they must do to stay healthy.
As wearable devices, patient portals, and social media, become more commonplace, both patients and providers now have access to more big data than ever before. However, all this information may do more harm than good if clinicians and patients do not have meaningful tools for interpreting, sharing, and interacting with this data.
Healthcare leaders can leverage big data analytics tools, including artificial intelligence, machine learning, and natural language processing, to draw useful conclusions and ensure patients actively participate in their own care.
What are the top ways providers can utilize big data analytics technologies to boost patient engagement in the clinical, research, and home environments?
Using patient data to tailor chronic disease management
Patients with chronic diseases must engage in management strategies and adhere to treatment plans in order to maintain their health and keep care costs low. Self-management interventions can allow patients to independently keep track of their health and actively engage in their own care.
But despite the potential value of these treatment plans, patients often lose motivation to continue chronic self-management programs if the content, goals, and benefits are not tailored to their individual needs.
To ensure patients are actively participating in chronic disease management plans, organizations can use patient data to develop predictive risk scores and design individualized treatment strategies.
In a recent interview with HealthITAnalytics.com, Lillian Dittrick, Fellow of the Society of Actuaries, explained that providers can utilize alternate sources of data to build predictive models and refine care management plans.
“Both payers and providers have a wealth of information that they can use to build models. Healthcare providers can also acquire some other sources, like the social determinants of health, for example, that will really help the strength and accuracy of their models,” she said.
“We tend to identify quite a few people who have different chronic conditions or other issues that call for enhanced management. When we use predictive models to look at all the variables, it helps us prioritize those patients who are really going to be receptive to changing something in their lifestyle, such as nutrition or exercise.”
Patients with mental illnesses can also benefit from tailored treatment plans, and organizations can use existing data to design individualized care strategies.
At Beacon Health Options, a behavioral health management service provider, clinicians are using machine learning tools to extract actionable insights from structured and unstructured patient data.
With this information, the organization is working to enhance care coordination for patients with mental illness, as well as ensure patients stay engaged and adhere to their care plans.
“Our goal is to move from being a reactive model that solely looks at what has happened historically to being a much more predictive, proactive, and targeted service provider,” said Dr. Emma Stanton, Associate Chief Medical Officer for Beacon Health Options.
“It’s an opportunity to bridge the siloes that exist in the healthcare delivery system, and it’s an example of where machine learning can help to bulldoze through those traditional barriers to make progress for an incredibly vulnerable segment of the patient population.”
Applying natural language processing tools to enhance patient health literacy
In order for patients to take an active role in their own care, they must have a solid understanding of their medical data, as well as how to use that information to make more informed health decisions.
While the surge in patient portal adoption has made it easier for patients to access their clinical data, many still struggle to make sense of their medical information. Low health literacy rates, complicated by medical jargon, can lead to poor medication adherence, misinterpretation of lab results, and deficient disease management.
Natural language processing (NLP) tools have emerged as a viable solution to this issue, allowing individuals to translate complex medical information and improve patient health literacy.
In 2017, researchers from Yale, UMass, and the VA applied NLP algorithms to electronic health record (EHR) data and matched clinical terms with lay-language definitions. The team found that the NLP tool outperformed baseline systems in precision when presented with unlabeled evaluation data, showing the potential for NLP to enhance patients’ engagement with their medical information.
A separate 2018 study published in JAMIA also demonstrated the potential for NLP to improve patient EHR comprehension.
Researchers developed an NLP system that defines EHR terms for patients at or below the average health literacy level.
After collecting physician feedback, the group made changes to the system’s usability, clarity, and specificity, which improved the tool’s ability to recall medical definitions.
Although neither study was designed to develop a fully-functioning system that could be used in a real clinical setting, the early results of both show that NLP could soon play an integral role in patient engagement and health literacy.
Leveraging artificial intelligence to increase clinical trial engagement
Clinical trials can facilitate the development of novel treatments, more accurate diagnoses, and innovative cures for debilitating diseases.
However, research has indicated that clinical trials may not accurately represent real-world demographics, with many trials failing to include women and minorities. This can lead to insufficient testing of drugs for patient safety and effectiveness.
Many patients have to travel long distances to clinical research sites, which presents a significant barrier to participation.
A 2016 survey found that 65 percent of patients are unlikely to enroll in clinical trials, with nearly half of respondents citing concerns about traveling to research locations to receive treatment.
Artificial intelligence tools have the potential to increase engagement in clinical trials, offering researchers a simpler way to recruit and connect with diverse patient populations.
A recent report from Deloitte found that virtual trials that utilize AI-driven tools such as smartphone apps and wearable devices support both passive and active data collection, and can significantly enhance patient enrollment and engagement in clinical research.
“Digital technologies can transform how companies approach clinical development by incorporating valuable insights from multiple sources of data, radically improving the patient experience, and increasing the amount and quality of data collected in trials,” the report stated.
Researchers can use these tools to reduce patient travel burdens and allow patients to participate in clinical trials from the comfort of their own homes.
Additionally, AI can help accelerate the time-consuming process of matching patients to appropriate clinical trials, a challenge that is also associated with low patient participation rates.
Mayo Clinic and IBM Watson Health recently partnered to develop an AI-driven tool that accurately matched breast cancer patients with relevant clinical trials. After using the tool for 11 months, Mayo Clinic saw an 80 percent increase in trial enrollment.
“This has enabled all patients to be screened for all available clinical trial opportunities,” said Tufia Haddad, MD, a Mayo Clinic oncologist and physician leader for the Watson for Clinical Trial Matching project.
“The speed and accuracy of the tool and the team of screening coordinators allow our physicians to efficiently develop treatment plans for patients that reflect the full range of options available to support their care.”
Mayo Clinic and Watson Health plan to continue developing the tool to include trials for other types of cancer, as well as for other elements of cancer treatment, such as surgery, radiation, and supportive care.
Big data analytics tools can help stakeholders across the care continuum to enhance patient engagement in clinical research and care.
By leveraging AI, machine learning, and NLP, organizations can allow patients to actively participate in their own care, leading to improved care delivery and health outcomes.