This blog is a contribution from our customer, Personify Health, the first personalized health platform company. Learn how your team reduced AI model development time by 82% for personalized healthcare.
Personify Health is a global company that empowers diverse businesses and unique people to engage more deeply with their health at lower costs. We’ve created the industry’s first and only personalized health platform by combining health plan management, holistic wellness, and comprehensive navigation solutions.
We are bridging the gap between the enormous potential of AI and the need for smarter healthcare. Our AI-powered platform helps our 19 million members in over 190 countries proactively manage their health with highly personalized recommendations and content covering mental health, nutrition, sleep, exercise, exercise guidance, and more. .
To achieve this level of personalization and increase efficiency across the company, we are accelerating AI adoption with more than 15 predictive and generative AI projects currently underway. DataRobot has been essential in improving the efficiency and effectiveness of our expert team of data scientists, engineers, and data analysts.
Why accuracy and governance are essential for AI in healthcare
Personify Health has the best and brightest data scientists, engineers, and analysts on our team. But to do our best work, we needed a set of tools that would reduce everyday problems like tool overload, clunky workflows, and duplicate work. As a CTO, I want my people to focus on delivering results, not managing broken processes.
I strongly believe in eliminating silos across organizations. Our engineers, data scientists, and analysts need to come together on one platform to scale development cycles and improve productivity. However, we must be careful when making each decision. This is especially true because medicine is a highly regulated field with numerous ethical issues.
We need to combine AI and human expertise for a close personal touch throughout the entire customer journey. Our members trust us to guide their health and wellness through recommendations powered by advanced predictive analytics, while our health coaches leverage generative AI co-pilots to be more effective partners for our community members.
We also use generative AI internally to increase productivity through helper bots for a variety of business functions. Trust in each of these AI applications is absolutely critical to helping us do our jobs and support our member communities to continuously improve their health.
Predictive models are critical to the personalized experiences we deliver on our platform. To inform Personify’s predictions, we consider a dataset containing approximately 275 million people with 700 features. Models need to be trained on constantly changing data at scales of hundreds of models multiplied by millions of members.
DataRobot allows our team to train multiple models simultaneously and compare the output to achieve the highest possible accuracy. An end-to-end platform means you have the tools to deliver results you can trust, quickly.
Personify’s Model Responsibility Standard SupportS
Centralized tools further support our commitment to social responsibility and model accountability by properly instilling ethics, privacy, and governance. At Personify, we are taking a thoughtful approach to AI adoption and use across our company.
steering board
The AI Executive Steering Committee oversees all projects and helps drive decisions at the leadership level.
research and development
The R&D team researches and builds a foundation of generative AI-based frameworks for use cases in operations, commercial marketing, and content creation.
Governance Team
AI policy governance is critical to how we work with data. Our AI policy is disseminated to the platform’s 70+ sponsors so everyone understands how we protect their data. Our governance team guides our AI policy with input from our legal advisors.
Privacy and Bias Mitigation
We work using anonymized data sets that keep member data private. At the same time, it eliminates any potential bias in the model.
integrated platform
To reduce silos and accelerate model times, we chose DataRobot to bring all our teams and predictive models together in one place. We’ve been able to break down these silos across the organization, which is fundamental to our success.
The platform unifies AI analytics across teams, technologies, and data sources and accelerates time to production. Instead of taking 3 weeks to get an acceptable model, multiple models can be created simultaneously in 21 hours.
DataRobot also supports governance frameworks with essential explainability. Having visibility behind your models helps you quickly understand, select, and adopt the right model.
Building momentum for generative AI in personalized medicine
In the future, generative AI will become a bigger part of how we power our organizations. With the foundation we have already built at DataRobot across predictive AI and generative AI models, I am excited about the future of Personify Health.
We’re already integrating all of our generative and predictive AI models within DataRobot to further improve how we manage and monitor them to drive meaningful outcomes for our business and members. This platform is central to many of our goals as we continue to lead the future of AI in healthcare.
For example, we expect to have our own AI conversation hub on the backend that connects to all our products to answer questions for better responsiveness.
We’ve also been experimenting with DataRobot application templates that provide repeatable use case logic that teams can adapt to their specific business problems. This will solve a serious headache for our team and allow us to move at a much faster pace.
Together, Personify Health provides consumers with smarter recommendations that adhere to the highest ethical and legal standards. DataRobot makes it much easier to build and manage AI models, allowing our team to focus on providing better health and wellness recommendations to our customers.
Check out Personify Health’s customer spotlight to learn more about how they reduced AI model development time by 82%.
About the author
Amit Jain, Chief Technology Officer at Personify Health, leverages over 20 years of expertise in SaaS engineering leadership, cloud architecture, data science, and machine learning to create and execute a vision that impacts millions of people around the world.
Meet Amit Jain
