The Power of Real-World Data: Unlocking Insights with Aetion’s Smart Subgroups Interpreter
Introduction
Real-world data collected from patient journeys offers a wealth of insights into patient characteristics and outcomes, as well as the effectiveness and safety of medical innovations. Researchers ask questions about patient populations in the form of structured queries, but without the right choice of structured query and deep familiarity with complex real-world patient datasets, many trends and patterns can remain undiscovered.
Aetion’s Solution
Aetion is a leading provider of decision-grade real-world evidence software to biopharma, payors, and regulatory agencies. The company provides comprehensive solutions to healthcare and life science customers to transform real-world data into real-world evidence. Aetion’s technology uses the science of causal inference to generate real-world evidence on the safety, effectiveness, and value of medications and clinical interventions.
Smart Subgroups Interpreter
The Smart Subgroups Interpreter is a feature of Aetion’s Discover application, which uses unsupervised learning methods to uncover hidden insights. This feature identifies clusters of patients with similar characteristics, such as similar prevalence profiles of diagnoses, procedures, and therapies. These subgroups are further classified and labeled by generative AI models based on each subgroup’s prevalent characteristics.
How it Works
The Smart Subgroups Interpreter combines elements of unsupervised machine learning with generative AI to uncover hidden patterns in real-world data. The workflow includes:
- Create the patient population: Users define a patient population using the Aetion Measure Library (AML) features, which standardize variable definitions using scientifically validated algorithms.
- Generate features for the patient population: The AEP computes over 1,000 AML features for each patient across various categories, such as diagnoses, therapies, and procedures.
- Build clusters and summarize cluster features: The Smart Subgroups component trains a topic model using the patient features to determine the optimal number of clusters and assign patients to clusters. The prevalences of the most distinctive features within each cluster, as determined by a trained classification model, are used to describe the cluster characteristics.
- Generate cluster names and answer user queries: A prompt engineering technique for Anthropic’s Claude 3 Haiku on Amazon Bedrock generates descriptive cluster names and answers user queries.
Solution Overview
The solution uses Amazon Simple Storage Service (Amazon S3) and Amazon Aurora for data persistence and data exchange, and Amazon Bedrock with Anthropic’s Claude 3 Haiku models for cluster names generation. Discover and its transactional and batch applications are deployed and scaled on a Kubernetes on AWS cluster to optimize performance, user experience, and portability.
Outcomes
The Smart Subgroups Interpreter enables users to discover patterns among patient populations using natural language queries, even without prior expertise in real-world data. Users can now turn findings from such discoveries into hypotheses for further analysis across Aetion’s software, generating decision-grade evidence in a matter of minutes, rather than days, and without the need for support staff.
Conclusion
In this post, we demonstrated how Aetion uses Amazon Bedrock and other AWS services to help users uncover meaningful patterns within patient populations, even without prior expertise in real-world data. These discoveries lay the groundwork for deeper analysis within Aetion’s Evidence Platform, generating decision-grade evidence that drives smarter, data-informed outcomes.
Frequently Asked Questions
Q: What is the Smart Subgroups Interpreter?
A: The Smart Subgroups Interpreter is a feature of Aetion’s Discover application that uses unsupervised learning methods to uncover hidden insights and identify clusters of patients with similar characteristics.
Q: How does the Smart Subgroups Interpreter work?
A: The Smart Subgroups Interpreter combines elements of unsupervised machine learning with generative AI to uncover hidden patterns in real-world data.
Q: What is Aetion’s technology?
A: Aetion’s technology uses the science of causal inference to generate real-world evidence on the safety, effectiveness, and value of medications and clinical interventions.
Q: What is Amazon Bedrock?
A: Amazon Bedrock is a fully managed service that provides access to high-performing foundation models from leading AI startups and Amazon through a unified API.
