Setting acceptance criteria incorrectly (too high or too low) can delay your FDA submission by weeks or trigger rejection. This guide analyzed 784 AI/ML medical device clearances to provide concrete, data-driven thresholds. You’ll find specific starting points: AUC of 0.9, Sensitivity/Specificity of 0.8, Dice of 0.8, Kappa of 0.85, and Bland-Altman LOA within ±10% of mean physiological values. Learn which statistical methods FDA accepts most often, how to justify your criteria using special controls and predicates, and what to do when your device fails testing.

Here we analyze over 200 FDA 510(k) and De Novo summaries to tease out best practices for AI/ML study designs and adjudication strategies specifically.

This article shows how to achieve an AI/ML SaMD 510(k) submission in ~3 months by running a compact, well-powered MRMC study while continuously accruing standalone evidence through washout. It clarifies roles, sizing, units, and endpoints, with device examples, flowcharts, and a checklist to prevent rework and delays.

The article outlines a method for documenting AI/ML algorithms for FDA pre-submissions. It emphasizes clear algorithm descriptions to avoid delays. Key steps include visual runtime descriptions, dataset analysis, non-ML testing, annotation details, AI/ML test plans, and performance metrics. It stresses reducing annotation costs and leveraging existing data while advising comprehensive documentation for effective FDA evaluation.

This article outlines the process of developing an AI/ML algorithm from scratch and getting it FDA cleared. It covers the four phases of the process (Explore, Develop, Validate, and Document) and discusses the costs, time, and data requirements involved. It also provides advice on regulatory strategy, data annotation, and algorithm prototyping. If you’re interested in developing a medical device involving AI/ML.

This article outlines Innolitics’ process for developing machine learning algorithms for FDA-cleared medical devices. It covers documentation requirements, common pitfalls (overfitting, data leakage, augmentation errors), and a systematic workflow using four key reports: Input Verification, Data Augmentation QA, Model Performance, and Model Comparison—ensuring safe, effective, and compliant AI development.

A practical guide for engineers new to medical imaging AI, highlighting common pitfalls—like coordinate-system errors and orientation mix-ups—and providing simple checks to avoid them.Ask ChatGPT

With predetermined change control plans (PCCPs), FDA has given manufacturers a great new regulatory tool. In this article, we discuss PCCP best practices and questions based on our experiences with FDA and our thorough research of the FDA databases.

This article provides an in-depth exploration of medical device cybersecurity requirements, including best practices and FAQs. It also includes examples and resources for those looking to implement or improve their own threat modeling processes.

The FDA says developing your design inputs is “the single most important design control activity,” yet writing good design inputs is difficult. This article presents Innolitics’ answers questions our clients frequently ask us about design inputs and analyzes a number of poorly written example requirements.

Practical suggestions and tips for authoring SBOMs for medical devices and for using them to monitor for cybersecurity vulnerabilities.

A comprehensive FAQ for people who are interested in creating a new medical device software to learn the basics about the US regulations.

The “Unresolved Anomalies” document is required for the FDA’s pre-market submissions. This article includes best practices, FAQs, and examples for writing this document.