K-numberK251779
Device nameOmnipod 5 algorithm
ApplicantInsulet Corporation
Product codeQJI
Device classClass II
Decision dateDec 3, 2025
DecisionSubstantially Equivalent
Regulation862.1356
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

The Omnipod 5 algorithm is a software-only automated insulin delivery system that works with compatible continuous glucose monitors and insulin pumps to automatically adjust insulin delivery based on glucose readings and predictions. It is intended for managing type 1 diabetes in patients 2 years and older and type 2 diabetes in patients 18 years and older, and requires a prescription.

Technological characteristics

The Omnipod 5 algorithm uses Bluetooth Low Energy wireless communication and operates on the Omnipod 5 ACE Pump in either automated (closed-loop) or manual (open-loop) modes. Key differences from the predicate include a lowered target glucose range of 100-150 mg/dL (versus 110-150 mg/dL) and a modified ADR alert that allows users to remain in Automated Mode after acknowledgment. Both devices are algorithmic software intended to automatically adjust insulin delivery based on iCGM readings and predicted glucose values.

Test standards cited

Software verification and validation testing was performed in accordance with IEC 62304:2015 and FDA's General Principles of Software Validation guidance (January 11, 2002). Interoperability documentation was provided per FDA's Design Considerations and Pre-market Submission Recommendations for Interoperable Medical Devices guidance (September 6, 2017). Performance validation was conducted via in silico clinical trial per FDA's Assessing the Credibility of Computational Modeling and Simulation guidance (November 17, 2023).

Substantial equivalence argument

The Omnipod 5 algorithm has identical intended use, indications for use, device type, principles of operation, and technological characteristics as the predicate SmartAdjust technology (K241777). The software modifications—adding 100 mg/dL target glucose capability and improving the ADR alert—do not raise different safety or effectiveness questions. In silico clinical validation demonstrated that simulated performance with the 100 mg/dL target is non-inferior to real-world predicate performance with 110 mg/dL target, supporting substantial equivalence.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →