Transforming Clinical Data Management with AI: Insights from Carta Healthcare’s Greg Miller

In today’s healthcare landscape, data is both an invaluable asset and a significant challenge—especially when it comes to clinical registries. Health systems are under increasing pressure to collect, manage, and analyze growing volumes of clinical data, much of which remains trapped in unstructured formats like free-text notes and scanned documents. As these demands escalate, so do the costs, inefficiencies, and risks associated with manual data processes.

To explore how artificial intelligence (AI) and automation are reshaping this critical aspect of healthcare operations, we spoke with Greg Miller, VP of Business Development at Carta Healthcare. In the following Q&A, Miller shares his insights on the challenges health systems face in managing clinical registry data, how AI can help address those issues, and what healthcare leaders should consider when integrating automation into their data management strategies.

What are the biggest challenges health systems face in managing data for clinical registries, and how have these impacted cost, efficiency, and data quality?

An estimated 70–80% of clinical data in EHRs, labs, imaging systems, and other sources exists in unstructured formats like free-text notes and scanned documents. Extracting insights from this data—for purposes like populating clinical registries, identifying clinical trial candidates, or powering analytics—still relies heavily on manual processes. These workflows are time-consuming, costly, and represent an inefficient use of highly skilled clinical resources.

How do health systems evaluate the trade-offs between investing in AI-driven automation for clinical data management versus relying on traditional manual methods?

Health systems weigh AI-driven automation against manual methods by considering cost, efficiency, accuracy, and scalability. While AI reduces labor and speeds processes, it requires investment and fine-tuning for complex clinical data. Manual methods offer expertise, but can be slow and inconsistent. Many adopt a hybrid approach to balance AI’s efficiency with human oversight for quality assurance.

What strategies have you found effective in addressing the concerns of clinicians and administrators who are hesitant to embrace AI in clinical data management?

Clinicians and administrators often approach AI adoption in clinical data management with caution, but overcoming their concerns is achievable with the right strategies. Transparency is key to explaining how AI works and addressing data security helps build trust. Showing real-world success stories and launching small-scale pilot programs allows stakeholders to see tangible benefits firsthand. Engaging these professionals early in the process ensures solutions align with their workflows, while continuous feedback fosters improvement and trust. By emphasizing that AI supports rather than replaces human expertise, health systems can reassure teams and pave the way for seamless integration.

What are some key factors healthcare leaders should consider when deciding whether to adopt AI for clinical data management?

Healthcare leaders weigh several critical factors when deciding whether to adopt AI for clinical data management. They consider how AI aligns with strategic goals, its potential return on investment, and whether it enhances scalability and efficiency. Ensuring data security and regulatory compliance is paramount, as is evaluating the accuracy and reliability of AI insights. Staff buy-in and training play a key role in adoption success, while pilot testing helps validate effectiveness and minimize risks. By addressing these considerations thoughtfully, leaders can make informed decisions that balance innovation with organizational needs.

How can AI and automation improve both the accuracy and completeness of clinical registry data while also reducing operational burden?

AI and automation transform clinical registry data management by speeding up the process, ensuring accuracy and data quality and streamlining workflows. These tools reduce human error, extract data from unstructured sources, and process large volumes efficiently and quickly. By automating repetitive tasks, they lower operational burdens and costs, enabling real-time insights and scalability. This not only improves data quality but also frees healthcare professionals to focus on patient care, creating a more efficient and effective healthcare system.

Looking ahead, how do you see AI transforming clinical data management in healthcare?

AI is transforming clinical data management by enhancing speed, accuracy, and scalability. It automates data abstraction, extracts insights from unstructured sources, and identifies trends in real time for better decision-making. By streamlining workflows and ensuring compliance, AI reduces administrative burdens while improving patient outcomes, driving a more efficient and patient-centered healthcare system.