Yale Unveils New AI Tool to Ensure Pathological Accuracy

The system is currently under pilot testing and is being integrated into the workflow so that pathologists can click on an icon to generate the AI report check

Researchers at Yale School of Medicine’s Department of Pathology have developed an AI tool designed to check pathology reports against patients’ full medical records. The tool detects any discrepancies and eliminates any errors before the final report is released.

“What we envisioned is a program that checks every report and compares it against the medical record, then sends a notification to the pathologist if there’s an error is detected,” said Joana Gibson, director of Quality and Patient Safety at Yale Pathology.

By finding errors before the report is finalized, the release of incorrect reports can be prevented.

The department, recognizing the risk caused due to pathological reports, collaborated with software developer Joe Celano to develop an AI-based tool that automatically reviews draft pathology reports against key patient records, including requisition forms, operative notes, and imaging data.

The system flags any discrepancies, such as a “left breast” report when the chart indicates “right breast”, allowing pathologists to verify and correct issues before finalizing reports.

“We built feedback into the system,” said Celano.

“When they run the application, it checks the case to see if everything matches , does the requisition form match the operating notes, do the operating notes match the final diagnosis? It catches things like laterality, someone wrote left side, but was it supposed to be right? The tool will do an analysis, and there is a section for the user to provide feedback. Users enter comments and evaluate how well the tool is working, and the Informatics Team then fine-tunes the application to address user concerns,” he added.

Reportedly, the system is currently under pilot testing and is being integrated into the workflow so that pathologists can click on an icon to generate the AI report check.

The team has further noted that the AI tools just add a level of scrutiny and do not replace human review, by catching inconsistencies that might otherwise be missed.

Stay tuned for more such updates on Digital Health News