PeriCALM Patterns 3.0

PeriCALM Patterns 3.0 is a software-based clinical decision support system designed to assist in obstetrical monitoring by providing secondary information from fetal heart rate and uterine pressure recordings. The device operates through a neural network-based algorithm to detect and measure features in electronic fetal monitoring records, validated through non-clinical assessments and a retrospective clinical study.

PeriGen, Inc. has received a positive determination for its PeriCALM Patterns 3.0, a sophisticated software system engineered to augment clinical decision-making during obstetrical monitoring. This device provides secondary information by annotating and summarizing fetal heart rate and uterine pressure recordings, specifically identifying baseline, accelerations, decelerations, and contractions. Intended for use in both antepartum and intrapartum monitoring from 32 weeks gestation, the system serves as a supplementary tool, with explicit warnings that patient management decisions should not solely rely on its outputs. The regulatory review concluded that PeriCALM Patterns 3.0 is substantially equivalent to a legally marketed system. At its core, the device is a software algorithm that leverages neural networks to detect and measure critical features within electronic fetal monitoring records. Non-clinical evaluations, encompassing software and cybersecurity assessments, were successfully completed. Furthermore, a retrospective clinical study demonstrated the device's performance to be comparable to that of qualified clinicians, affirming its safety and effectiveness for use across the specified gestational age range without introducing new concerns.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific parameters or features do the neural networks analyze in FHR and uterine pressure recordings, and how do these contribute to the annotations?; How does the device's performance compare to various levels of clinician experience (e.g., junior vs. senior clinicians) in the retrospective study?; What are the documented limitations or edge cases where the device's annotations might be less reliable, requiring particular clinician vigilance?; Beyond providing secondary information, what are the potential long-term impacts of integrating such AI-powered systems on clinician training and the overall standard of care in obstetrics?; Are there plans for prospective, multi-center trials to further validate the device's impact on clinical outcomes, such as rates of intervention or adverse events?