The AI Revolution Series – Addressing Health Related Social Needs With AI
AI can boost quality of care in the home health and home care industries
THE VBP Blog
May 23, 2024 – As healthcare continues to evolve, the integration of AI offers not just medical advancements but also innovative solutions to broader social challenges that impact health outcomes. These challenges, including social determinants of health (SDOH) and health related social needs (HRSN), include factors like housing, nutrition, education, and access to care, which can significantly influence individual and community well-being.
In our last blog in our AI series, we have looked at how AI can be used to predict and treat behavioral health conditions. In this blog, we will explore the potential of AI in revolutionizing how we find and tackle the underlying social factors that significantly impact health outcomes. From predicting areas at risk of health disparities to automating the connection between patients and social services, the capabilities of AI are vast.
As advocates, we are excited to see the ways that AI can health address HRSN and provide whole-person care that providers may not have been able to before. However, we need to ensure that proper care coordination and follow up continues with human interaction, so things do not slip through the cracks. To learn more about our advocate’s perspective, check out our full write up at the end of the blog to hear more of our thoughts!
Social Determinants of Health vs. Health-Related Social Needs – What’s the Difference?
Health related social needs and social determinants of health are often used interchangeably, but there is a difference between the two. Both significantly influence individual and community well-being, but they encompass slightly different aspects of health.
Social determinants of health are the macro-level economic and social conditions that influence health outcomes. These include factors like socioeconomic status, education, neighborhood and physical environment, employment, and social support networks, as well as access to healthcare. Essentially, SDOH are the societal causes that affect the health of populations.
On the other hand, health-related social needs are individual-level and refer to the personal social or economic factors that can hinder an individual’s ability to manage their health. These needs can include food insecurity, unstable housing, lack of reliable transportation, or inadequate access to job opportunities.
While SDOH refer to systemic issues affecting groups of people, HRSN focus on the immediate social needs that directly impact an individual’s health. Addressing both is crucial for improving health outcomes and achieving health equity, but interventions may differ in scale and approach.
Using AI to Screen for Health-Related Social Needs
Screening for and addressing HRSN and SDOH is essential for improving health outcomes. It’s something that the U.S. Department of Health and Human Services (HHS) and CMS has made a priority, and AI offers an avenue for healthcare providers to do just that. One of the issues the healthcare industry faces in addressing these is that HRSN and SDOH are often under documented in health records. And even if screening does occur, the essential information is often spread through rambling clinician notes. That is where AI comes into the picture.
By leveraging AI’s data analysis and language processing capabilities, this information can be extracted from clinical texts. In fact, a study by the team at Mass General Brigham led by Danielle Bitterman, M.D., have shown that large language models trained by researchers could identify almost 94% of patients with adverse social determinants of health, while official diagnostic codes include that data in only 2% of cases.
Bitterman hopes to now quantify how this data extraction can improve patient outcomes. However, she is aware of the difficulty of operationalizing this type of AI-application. “We’re at just the inflection point of these models entering clinic… AI models, because they can process so much data… can find hidden correlations that may reveal sensitive information about patients,” Bitterman said.
However, she knows that things like bias and patient consent must be considered, adding, “The public right now does not have enough of a voice in how AI is being developed and implemented. If practitioners begin using AI to inform care and not telling patients about it, that could cause harm…and we’re going to lose a lot of trust early on and lose a lot of the amazing opportunity of AI to support healthcare.”
This goes back to our earlier blog, where we addressed patient privacy and data security concerns. We know that SDOH and HRSN can be sensitive in nature, and consumers may not want them brought up. That is why healthcare professionals need to consider how each individual might want or not want AI to be used on their data.
Despite these risks, the benefits and potential of AI cannot be overlooked. Through AI models, providers can identify and predict SDOH and HRSN that may impact patient outcomes and allow them to be addressed to improve overall consumer well-being.
AI Can Help Providers Address HRSN
In addition to screening for HRSN, AI can also help providers and consumers address these needs head on. The first way AI can do this is by enabling targeted interventions, such as connecting individuals with housing support, food assistance programs, or transportation services, tailored to their specific circumstances. AI can facilitate the integration of the information into care plans and connect consumers with local resources and support services. This not only ensures a more comprehensive approach to care but also fosters a healthcare environment where whole person care is the emphasis.
AI also facilitates the integration of healthcare and social services by streamlining referral processes and tracking outcomes. For instance, AI platforms can automate the referral process to social services, reducing administrative burdens and ensuring that patients receive the support they need promptly. This is essential, especially when the healthcare industry is facing a drastic labor shortage. Additionally, by monitoring the effectiveness of these interventions, AI can provide valuable feedback that allows for continuous improvement of programs designed to address HRSN.
In a broader context, AI can also optimize resource allocation by predicting which social interventions will have the most significant impact on health outcomes for a general population. This helps by ensuring that limited resources are used efficiently. For example, predictive models can identify areas where food insecurity is contributing to poor health outcomes, allowing for focused deployment of nutritional support programs. Another example, is using AI to locate where access to healthcare is limited, like in rural areas, so telehealth and other avenues to expand access to care can be implemented.
Simply put, AI offers a powerful tool for healthcare providers to understand and address the complex social factors affecting health. By enabling more precise identification of needs, facilitating efficient interventions, and fostering integration between healthcare and social services, AI can significantly contribute to whole person care and better health outcomes.
Advocates Perspective
AI holds considerable promise for addressing health-related social needs, offering innovative solutions that can potentially transform patient care and public health outcomes. By leveraging AI to analyze and interpret the vast amounts of data surrounding HRSN, healthcare providers can identify at-risk populations and intervene more quickly and effectively. This proactive approach not only helps in mitigating health disparities but also ensures that healthcare resources are allocated more efficiently and equitably. However, while the benefits are substantial, the deployment of AI also raises concerns about privacy, data security, and the potential for systemic biases that could exacerbate existing inequalities. For consumers to truly benefit and health equity to advance, the integration of AI into healthcare needs to be thoughtful and ensure that AI systems are transparent, fair, and inclusive.
Onward!
Share This Blog!
Get even more insights on Linkedin & Twitter
About the Author
Fady Sahhar brings over 30 years of senior management experience working with major multinational companies including Sara Lee, Mobil Oil, Tenneco Packaging, Pactiv, Progressive Insurance, Transitions Optical, PPG Industries and Essilor (France).
His corporate responsibilities included new product development, strategic planning, marketing management, and global sales. He has developed a number of global communications networks, launched products in over 45 countries, and managed a number of branded patented products.
About the Co-Author
Mandy Sahhar provides experience in digital marketing, event management, and business development. Her background has allowed her to get in on the ground floor of marketing efforts including website design, content marketing, and trade show planning. Through her modern approach, she focuses on bringing businesses into the new digital age of marketing through unique approaches and focused content creation. With a passion for communications, she can bring a fresh perspective to an ever-changing industry. Mandy has an MBA with a marketing concentration from Canisius College.