AI system may help clinical labs spot problems before they affect patients
Weill Cornell Medicine researchers have designed an AI system that could help clinical laboratories identify problems before they disrupt testing and delay patient care. These laboratories analyze samples such as blood, urine, tissue or other bodily fluids to help doctors diagnose and treat diseases. However, growing test volumes, workforce shortages and increasingly complex diagnostics are…
An AI system is being developed by researchers at Weill Cornell Medicine to assist clinical laboratories in detecting issues before they affect patient care. Laboratories test various bodily fluids to assist in disease diagnosis and treatment. However, the increasing volume of tests, staffing shortages, and complex diagnostics are straining laboratory operations.
The researchers have devised Laboratory Agentic Reasoning and Integrative Analytics (LabARIA), a novel framework utilizing multiple specialized AI agents to bolster laboratory quality and operations efficiency. Writing in npj Health Systems, the researchers explain that LabARIA integrates several AI tools to monitor laboratory quality and operations more effectively.
Existing AI algorithms in laboratory medicine are fragmented and siloed, whereas LabARIA aims to unify these capabilities, identifying patterns across diverse laboratory operations that individual tools may overlook. The framework would interface with existing laboratory information systems and databases, rather than replacing them.
Central to LabARIA is a data coordinator that channels information to specialized AI agents, tasked with monitoring specimen quality, testing turnaround times, analytical quality control, instrument performance, and regulatory compliance. Additional agents would anticipate inventory and staffing needs. LabARIA can detect anomalies and consolidate data to aid lab personnel in early investigation and resolution of problems.
Improving laboratory quality and efficiency through AI can enhance healthcare delivery. Currently, lab staff routinely perform checks and retrospectively troubleshoot potential analytical issues when results violate quality-control rules. LabARIA could potentially identify concerning trends prior to triggering a formal quality-control violation, such as fluctuations in performance related to reagents or other testing materials.
Issues may also arise prior to testing when specimens are compromised during collection, handling, or transportation. LabARIA could identify patterns in specimen-quality indicators necessitating investigation. Early intervention could prevent disruptions and delays in reporting results. The researchers stress that human oversight is essential, as LabARIA incorporates built-in accountability, including traceable data records and reasoning behind recommendations, enabling laboratory professionals to override the system if required.
The framework is still a conceptual design, and the research team plans to conduct experiments using retrospective laboratory data to refine the system. Once sufficient evidence is acquired, the team will explore implementing the system within a clinical lab. Even after deployment, the team will persistently monitor the system to ensure secure and effective operation.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
