OM1's AI Platform Enables Landmark 650,000-Patient Real-World Evidence Study Supporting FDA Approval of Hologic's HPV Screening Assay
核心洞察
OM1 (搜索)'s AI-enabled platform supported one of the largest real-world evidence studies ever conducted for an FDA submission, spanning more than 650,000 women across multiple U.S. health systems for Hologic's Aptima HPV Assay (搜索) approval.
The platform automated data processing from electronic health records and laboratory systems, using AI and machine learning to extract key variables from unstructured clinical notes, cytology reports, and pathology records at unprecedented scale.
The study achieved an exceptional site Net Promoter Score of 87.5, demonstrating how automation can significantly reduce manual effort while maintaining data quality for regulatory submissions.
OM1 (搜索), a real-world evidence generation company, has demonstrated the transformative potential of AI-enabled clinical data processing through its support of a landmark regulatory submission that led to FDA approval of Hologic's Aptima HPV Assay (搜索) for primary cervical cancer (搜索) screening. The study, spanning more than 650,000 women across multiple U.S. health systems, represents one of the largest real-world evidence studies ever conducted for an FDA submission.
The approval, announced by Hologic in February 2026, followed a comprehensive real-world evidence study that showcased how advanced automation can meet the FDA's stringent requirements for regulatory decision-making. OM1 (搜索) presented its pivotal role in this achievement at the Medical Device Innovation Consortium Evidence Summit on May 5, 2026.
AI-Powered Data Processing at Unprecedented Scale
Data automation served as the cornerstone of the study, encompassing everything from data acquisition and quality control through final reporting. OM1 (搜索)'s platform ingested data from electronic health records and laboratory information systems from participating centers, then de-identified, tokenized and mapped the information at scale. The system employed AI and machine learning algorithms to extract key variables from unstructured clinical notes, cytology reports, and pathology records.
"Two characteristics really defined this study," said Rich Gliklich, Founder of OM1 (搜索). "One is the scale — 650,000 patients is large by any measure. The second is that a lot of the key variables lived in the unstructured data, the clinical notes and reports."
The study participated in the NESTcc (搜索) (National Evaluation System for health Technology Coordinating Center) program, a structured process specifically designed for assessing real-world evidence for medical devices.
Overcoming Traditional Data Collection Constraints
The massive scale of data processing required capabilities that traditional manual abstraction methods simply cannot support. OM1 (搜索)'s platform addressed this challenge through comprehensive automation that included quality control processes, real-time reporting dashboards for site investigators, and complete traceability and provenance tracking throughout the entire data lifecycle.
Gliklich emphasized that the platform's automation capabilities were essential to making a study of this magnitude feasible. "The site Net Promoter Score averaged 87.5 — which is off the charts, and that probably reflects how much manual effort was reduced with automation."
All AI and machine learning models used for natural language processing of clinical documents underwent rigorous validation and documentation to support regulatory review, ensuring that the automated processes met FDA standards for evidence quality and reliability.
Regulatory Milestone for Real-World Evidence
The approval represents a significant implementation case for real-world evidence in regulatory submissions, demonstrating that AI-powered automation can successfully scale clinical data collection without compromising quality. Studies of this magnitude have historically been constrained by the substantial cost and time requirements associated with manual data collection and abstraction processes.
OM1 (搜索)'s platform approach proves that automation, when combined with rigorous validation protocols, can effectively reduce these traditional constraints while maintaining the data integrity required for regulatory approval. This breakthrough opens new possibilities for leveraging real-world evidence in medical device approvals and other regulatory contexts where large-scale clinical data analysis is essential for decision-making.