Trustworthy AI helps provide equitable preventative care for diabetics
There are over 30 million people in America who have diabetes, and people with diabetes need to remain vigilant about their health. They need the extra attention and resources provided by their healthcare systems because, unfortunately, around 38% to 40% of people with diabetes end up visiting the ER due to complications. Healthcare organizations – both providers and payers – across the nation are seeking transformative new ways to render quick aid to vulnerable members. For many, part of the solution is trustworthy AI.
A large North American healthcare organization uses AI-infused data fabric architecture to help them identify vulnerable members who can benefit from timely intervention. The issue became clear to the provider when they established a community health advocacy program, with units ready to reach out to member communities to promote better health and improve health outcomes but needed a system to identify the people who most needed the help. If they could deliver preventative care, they could also reduce member trips to the ER and help members enjoy a better quality of life, while reducing costs for the company and optimizing hospital staff and equipment.
What’s a data fabric and how is it different from a data mesh?
Healthcare providers use technology to identify members for proactive care
The goal was to predict these risk periods within 30–60 days before hospitalization would be necessary, to give community health advocates time to intervene. In addition, they needed demographic data to ensure appropriate care for the community in need. For example, if a non-Spanish-speaking advocate reaches out to a primarily Spanish-speaking community, the odds of success will be much lower. The healthcare company understood that it’s not enough to build an accurate machine learning model; they needed to connect it to the human experience.
To accomplish this, the organization collected a vast amount of patient data, learned how to best process it, and built predictive machine learning models to identify their most at-risk members. Unfortunately, at this step in the journey to AI most businesses run into trouble with their data and AI initiatives. And with good reason: it’s a lot of data to process effectively, and not all AI systems are created with the proper ethical guardrails in place. Organizations need to be able to trust their data science outcomes. An AI system, especially one with such an impact on healthcare, must be fair, explainable, secure and transparent. The AI must be trustworthy.
A lot can go wrong when an organization decides to operationalize AI, and avoiding undue risk is a significant part the process. To mitigate that potential risk, many business leaders are finding success using data fabric patterns created by other organizations and adapting those patterns to their specific organizational processes.
What healthcare is doing with data fabric and AI to mitigate risks
A data fabric architecture provides visibility and insights into data, enhanced access, control over your data and advanced protection and security. Here’s how that North American healthcare company achieved its goals using data fabric.
The first step was ensuring they were using the correct data sets. They started with claims data generated by the insurance company. This claims data contains demographic and diagnostic information about the patient’s medical visit. While this is essential information and a necessary step toward recognizing at-risk members with diabetes, it only tells half of the story. To complete that story, the provider brought in external socioeconomic data to further fine-tune the machine learning models.
Learn more about how a data fabric architecture delivers trustworthy AI.
How trustworthy AI provides better help
Using a data fabric architecture and AI, the North American health plan provider can ensure quality healthcare at affordable prices across diverse member races and social classes. The data fabric architecture patterns identify 80% of at-risk members who need intervention, the automation saves time, increases efficiency and provides a pathway to get plan members help when they most need it. Additionally, advocates have access to better information about the communities they serve, and data transparency makes it easy for advocates to explain why members are receiving a visit, which builds trust in the process and maintains a good relationship between the plan provider and members.
Just as being accurate in your predictions is important, it is equally important that the predictions be equitable. The plan provider must have confidence that the predictions will cover a diverse member population, to ensure quality care reaches everyone.
After connecting all the different data sources within the data fabric of IBM Cloud Pak for Data—the claims data, the socioeconomic data, and the demographics data—the machine learning model was taught which correlations and patterns are essential. Then guardrails (a mechanism for honing the outcomes of the machine learning model) were put in place to catch any bias and generate explanations for the model predictions.
Once the provider deployed these models, they had an automated pipeline for delivering equitable care and tailored experiences via explainable AI.
IBM Expert Labs offers a variety of architecture patterns mapped to successful use cases and common entry points like data governance, trustworthy AI, and AIOps. The health plan provider used it to improve their members’ health and well-being. What could your business use it for?
The post Trustworthy AI helps provide equitable preventative care for diabetics appeared first on Journey to AI Blog.