We guarantee your AI/ML SaMD will be submitted to FDA within 3 months. That's 3 months of intensive, full-service engagement — then FDA's review clock takes over. This service builds on our Regulatory Strategy engagement, which lays the groundwork for a guaranteed outcome.
"7 weeks to submission and 6 months to FDA clearance. Innolitics delivered exactly what we needed. Fast, thorough, no surprises, and full service." — Dr. Peter Killcommons, MD, CEO Medweb
We are the only firm in the industry offering this guarantee. However, not all algorithms qualify. Here are the criteria for our speed and certainty guarantees.
Client’s first medical device. No documentation. 510(k) cleared in 12 months while engineers stayed focused on dev.
Prototype → 510(k) → QMS → FDA audit passed. Multi-year partnership with ongoing development.
Other consultants couldn’t make progress. We finished their software docs in 4 months — 3x faster than expected.
Built and cleared an AI cardiomegaly detector end-to-end: algorithm R&D to 510(k) clearance in under 12 months.
Built and cleared a DICOM image processing SaMD in 14 months. Full-cycle: engineering to 510(k) clearance.
We built the app, trained the AI, ran the MRMC study, and cleared FDA.
Full-cycle development of GyriCalc, a first-of-its-kind pediatric neuroimaging diagnostic. FDA cleared (K250686) July 2025. Filed for IPO in June 2025.
FDA regulatory strategy and Pre-Submission for an AI platform converting 2D MRI to 3D joint models. Delivered on time and budget
We don’t just hand you templates and wish you luck, we drive the entire process using our proprietary Medtech OS platform—purpose-built for SaMD. We roll up our sleeves and do most of the work for you so your team does not need to learn it for themselves.
We publish what we know. Here are some of our articles and resources:
ArticleAI/ML
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 clearance...
Yujan Shrestha
ArticleAI/ML
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.
Yujan Shrestha
ArticleAI/ML
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 thro...
Yujan Shrestha
ArticleAI/ML
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 runt...
Yujan Shrestha
ArticleAI/ML
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,...
Yujan Shrestha
ArticleAI/ML
This article outlines Innolitics’ process for developing machine learning algorithms for FDA-cleared medical devices. It covers documentation requirements, common pitfalls (over...
Yujan Shrestha &
ArticleAI/ML
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 avoi...
Yujan Shrestha
ArticleAI/ML
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 ...
J. David Giese
ArticleCybersecurity
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 ...
J. David Giese &
ArticleRegulatory
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’...
J. David Giese
ArticleCybersecurity
Practical suggestions and tips for authoring SBOMs for medical devices and for using them to monitor for cybersecurity vulnerabilities.
J. David Giese
ArticleRegulatory
A comprehensive FAQ for people who are interested in creating a new medical device software to learn the basics about the US regulations.
J. David Giese
ArticleRegulatory
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.
J. David Giese
Pricing depends on your device, timeline, and scope. Contact us for a custom quote.
If FDA rejects due to deficiencies in our work (bad documentation, missed requirements, poor submission quality), a partial refund will be given. The refund is not applicable If rejection is due to your device's clinical performance or a clinical study that was less powerful than the one we planned for in week 1.
Yes. Just add data and we can handle the rest. This is done via a separate service.
That's actually common. Week 1 identifies exactly what needs to be finalized. Your engineers typically need to containerize the algorithm and run verification tests during Sprint 3. We provide the protocols and guide the process. If significant algorithm work remains, ask us about bundling our AI/ML Development service.
Plan for 1-2 full time engineers for the entire 3 month engagement. We drive the regulatory and documentation work, but your engineers are essential for algorithm-specific tasks like containerization, running verification tests, and answering technical questions.
No. If you containerize your algorithm and can run inference on command, we don't need your code or weights. We work with the inputs, outputs, and documentation. If you want us to help optimize or debug the algorithm, then yes—but that's optional.
Yes, we handle De Novo classifications. The process and documentation requirements are more extensive than a 510(k), so expect a longer timeline. We'll scope the full engagement during a discovery call.
We handle that too. Let's chat.
No problem. We also offer slower paced engagements. Let’s chat.
No problem! We’ll show your team how to move with speed and certainty as long as your team has an open mind to use our templates, embrace our process, and follow our lead.
We serve as your regulatory correspondent and handle all FDA communications. If the FDA requests additional information, we coordinate the response. Our clearance guarantee means if rejection is due to deficiencies in our work, you get a partial refund.
At the end of the engagement, all deliverables will be provided as Word documents that can be stored in any QMS. We must use our templates and software (i.e. Medtech OS) during the project for maximum speed. Medtech OS is built on Notion and provides AI/ML-specific templates, automated traceability, and real-time collaboration. Many clients continue with Medtech OS because it makes subsequent 510(k)s significantly faster.
This service works best for:
If your device doesn't fit, we'll tell you upfront in the discovery call and recommend alternatives.
In a 30-minute call, we'll assess if your device is a good fit for this service or alternative services and provide a clear path forward.
Every great partnership starts with a conversation. Fill out the form below for a discovery call, and an Innolitics team member will contact you soon.
I learned more from an hour-long Innolitics sales call than an entire paid engagement from other consultants.
Richard Clark
Executive in Residence at Washington University
