The Problem

  • Your investors and board are asking about your regulatory strategy but you are not sure what to say.
  • Uncertain Regulatory Pathways - Without clear guidance, it's difficult to know which route to FDA clearance is fastest and most certain. Without clear guidance, it is impossible to know how much it will all cost and how long it will all take
  • FDA Meeting Preparation - Companies struggle to prepare for, facilitate, and debrief FDA pre-sub meetings effectively without experienced guidance. Often times, companies waste precious minutes during a presub asking questions that a qualified consultant could have answered for them.
  • Breakthrough Device Designation Uncertainty - Determining eligibility and successfully applying for expedited FDA review status is complex and unclear
  • Here's the challenge:
    • You can't afford a failed submission or delays
    • Your team is already overloaded or lacks the skillset to execute with speed and certainty
    • Every month that goes by is another month you could be making revenue and securing market share from competitors

You need one partner who can guarantee speed and success.

You need one partner who can just take it off your hands and do it for you on autopilot.

Our Speed and Certainty Promise

  1. We guarantee a Pre-Submission Package will be submitted in 2 weeks or a partial refund will be issued.
  2. We guarantee FDA clearance If you follow the strategy and partner with Innolitics to lead your FDA application, or a partial refund will be issued.
  3. We guarantee your breakthrough device designation will be granted or a partial refund will be issued.
Let's Meet!

Our Process: Battle-Tested. Speed and Certainty Guaranteed.

Unlike traditional consulting firms that hand you templates and wish you luck, we drive the entire process using our proprietary Medtech OS platform—purpose-built for AI/ML SaMD. We roll up our sleeves and do the work for you so your team does not need to learn it for themselves.

What You Will Gain:

  • Comprehensive regulatory strategy document with:
    • Product code determination
    • Identified predicate devices (for 510(k))
    • Clinical validation strategy
    • Key marketing claims alignment
    • Regulatory risk assessment and mitigation strategies
    • Future submission roadmap
  • Complete FDA pre-submission eSTAR package
  • Statistical power studies for sample size justification
  • Clinical and standalone performance testing plans
  • FDA meeting preparation and representation

Click for more detailed service description

Identifying an optimal regulatory strategy is a multi-variate optimization problem with many variables including budget, timeline, investor milestones, marketing claims, data availability, ease of clinical assessment, presence of a strong predicate.

Our engineers, clinical, and regulatory experts will work with you to find the most optimal solution to get you on the market as soon as possible, following these steps:

  1. Understanding the Business Goals
    • What are you trying to accomplish by bringing the SaMD to market?
    • What markets do you want to sell it in and what is their relative importance?
    • What marketing claims do you need to be able to make about the device’s performance to accomplish these business goals?
    • How will the software be used (e.g., within the clinical workflow or directly by patients)?
    • Draft a rough intended use statement for the device.
  2. Understanding the Software and Clinical Workflow
    • What work has been done on the software?
    • What do you hope to implement in the next year or two?
    • What functionality is the highest risk?
  3. Researching the Regulatory Strategy
    • Determine the product code for the device
    • Identify applicable FDA guidance and Standards
    • Determine available market pathways (e.g., 510(k), De Novo, PMA)
    • If a 510(k), identify possible predicate devices.
    • Will the SaMD need clinical performance testing, and roughly what form this would take?
    • Identify key regulatory risks and ensure they’re inline with the business goals.
    • Determine any architectural design constraints that could reduce how much of the software is considered part of the device (per the 2020 Multiple Function Device Product FDA Guidance).
    • If the device is a series of modules will each module have it’s own IU statement? Will there be an overall software ‘Platform’ which serves as the user interface and which may perform some functions (i.e., image viewer, report generation)?
  4. Develop a Clinical Validation Strategy
    1. The exact scope of this will vary based on the device and may include Performance Testing Study, Multi-Reader Study if needed, Technical Performance Assessments, Standalone Testing, etc.
    • Determine if the product is a CADq (quantification), CADe, CADt, CADx, or CADp (prognostic) device.
    • Explore the data you already have available to ascertain if it can be reused for the study.
    • Work with you to tweak your device’s indications for use and marketing claims to make the clinical validation study significantly easier and faster without sacrificing too much marketing value.
    • Conduct a statistical power study to justify the anticipated sample size.
    • Design the standalone performance study design
    • Design the clinical performance study design if necessary
    • Provide a proposal for the cost necessary to conduct the study(ies)
  5. Write the pre-sub request, including
    • Meeting Purpose
    • Device Description
    • For each algorithm component:
      • Algorithm description and verification strategy
    • Standalone Performance Testing Plan
    • Clinical Performance Testing Plan
    • Training Data Description
      • Demographics, sample size, number of Institutions, qualification of the annotators
    • Validation Data Description
      • Demographics, sample size, number of Institutions, qualification of the annotators
    • Proposed Predicate Device
    • Proposed Indications and Intended Use
    • Predicate Device Comparison (for a 510(k))

For additional details about our process, you may take a look at our published resource “How to Document AI/ML Algorithms in FDA Presubmissions (Q-Sub)”. Note that the approach is continually evolving and may not follow this document exactly.

The primary deliverable of this phase is the pre-sub documents that are sent to FDA. We’ll also include a regulatory strategy document that includes most of the same information, as well as a few additional information that is not always shared with FDA:

  • Key marketing claims
  • Key regulatory risks (i.e., issues that may prevent getting the SaMD to market, how likely they are to occur, and how to respond to FDA comments if they arise)
  • Strategy related to future submissions (although the focus of the strategy will be on the first submission)

The regulatory strategy will be completed within 2 weeks of project commencement.

Why Innolitics?

  • All we do is software as a medical device (SaMD) and AI as a medical device since 2012
  • 50+ SaMD and SiMD products cleared through FDA
  • We have experience with all the flavors of AI enabled medical devices including CADq (quantification), CADe, CADx, CADt, and CADp (prognostic)
  • We have full time MDs, PhDs, software engineers, and regulatory experts on staff
  • We are the only ones offering a speed and certainty guarantee

We've Done This Before

Case Studies

Radiology Software Fast 510(k)

Fast 510(k) for a medical image viewer starting with no documentation

Read the case study →

Rob Lewis - Radiology

Fast 510(k)Guaranteed AI/ML 510(k) Submission in 3 MonthsGuaranteed Strategy, Q-Sub, and BDD in 2 Weeks510k
Logo, Software Services Firm with First Product

Fast 510(k) for Breakthrough IVD

Guide an engineering team without FDA experience through a 510(k) for a breakthrough in vitro diagnostic (IVD) platform

Read the case study →

VP of Systems R&D - Microbiology

Fast 510(k)Guaranteed AI/ML 510(k) Submission in 3 MonthsGuaranteed Strategy, Q-Sub, and BDD in 2 Weeks510kIVD

Body Check (FDA Cleared End to End AI/ML SaMD)

AI/ML engineering and FDA clearance of a radiology AI/ML quantitative imaging SaMD.

Read the case study →

Dr. Steven Rothenberg MD - Radiology

Medical Imaging AI DevelopmentSoftware DevelopmentRegulatory StrategyFDA Hold Letter ResponseFast 510(k)FDA CybersecurityGuaranteed AI/ML 510(k) Submission in 3 MonthsGuaranteed Strategy, Q-Sub, and BDD in 2 WeeksAI/ML510kImage Processing
Logo, Body Check

RadUnity (FDA Cleared DICOM Workflow Engine)

We implemented a data-intensive DICOM image processing system to aid clinical workflows. We built this as a modern web application for ease of use. We prepared a complete 510(k) submission for the device and obtained FDA clearance. Both engineering and FDA clearance were completed within 14 months, starting from the ground up.

Read the case study →

Tim Szczykutowicz, PhD - Radiology

Software DevelopmentFast 510(k)Regulatory StrategyFDA Hold Letter ResponseGuaranteed AI/ML 510(k) Submission in 3 MonthsGuaranteed Strategy, Q-Sub, and BDD in 2 WeeksWeb-AppImage ProcessingDICOM510k
Logo, RadUnity

Smile Dx (Dental CADe AI/ML SaMD)

Innolitics partnered with Cube Click to develop Smile Dx, an AI-powered dental diagnostic tool that enhances dentists’ ability to detect caries (cavities), periodontal disease (gum disease), and periapical radiolucencies (PARL). The project showcases our engineering expertise through the development of a comprehensive web application with deep learning capabilities, while also demonstrating our regulatory competence by successfully guiding the product through FDA pre-submission and 510(k) submission processes.

Read the case study →

Dr. Richard Ricci, DDS, MS, FAGD, Dr. Andrea R. Cambria, DDS, FAGD - Dental

Guided 510(k)Software DevelopmentWeb-AppAI/MLImage Processing510k
Logo, Cube Click, Inc.

NSI (Automated Neuroanatomy in Infant brains)

Innolitics partnered with NeuroSpectrum Insights to develop Gyricalc, a diagnostic tool for neurodevelopmental conditions in children as young as two years old. This project showcases our engineering expertise in transforming a research idea into a fully developed web application and highlights our regulatory proficiency in successfully navigating the FDA pre-submission and 510(k) submission processes.

Read the case study →

Andrew Stewart - Neurology

Software DevelopmentGuided 510(k)Regulatory StrategyWeb-App510kImage Processing
Logo, NeuroSpectrum Insights, Inc

Orthopedic AI/ML SaMD Strategy and Presub

OrthoVentions, a medical device startup accelerator partnering with Hospital for Special Surgery, needed FDA regulatory strategy for Gemini—an AI-powered SaMD platform creating 3D joint models from 2D MRI. After finding two other consultants suboptimal, they chose Innolitics for proactive FDA expertise, pragmatic approach that preserved strong existing work, and strategic project management. Innolitics delivered a robust FDA Pre-Submission on time and within budget. The outcome: “They did what they said they were going to do, and they did it within the budget that they said they were going to do. So there were no surprises.”

Read the case study →

Dr. Jagi Gill, MD - Radiology

Regulatory StrategyAI/ML
Logo, OrthoVentions

Testimonials

7 weeks to submission and 6 months to FDA clearance. Innolitics delivered exactly what we needed. They took ownership of the entire DHF and 510(k) package—documentation, cybersecurity, risk management, the works. When we hit internal roadblocks, they found ways to keep us moving. When scope decisions needed to be made fast, they made the right calls. Fast, thorough, no surprises, and full service. That’s how regulatory consulting should work!
Dr. Peter Killcommons, MD

Dr. Peter Killcommons, MD

CEO MedWeb

I needed a software development partner to write the software, train the AI, and get FDA clearance. An investor once told me that it would take me $5 million and 5 years to get to where we are now. Innolitics got me here 3 years ahead of schedule and $4 million dollars under budget.
Dr. Andrew Smith, MD PhD

Dr. Andrew Smith, MD PhD

Co-Founder at AI Metrics & Chair of Diagnostic Imaging at St. Jude Children’s Research Hospital

They were proactive, informative, and very well-versed in the regulatory challenges of AI in medical imaging… Unlike competitors, who sometimes take a blanket approach, Innolitics didn’t throw the baby out with the bathwater. They recognized the good work already done and built upon it… We reviewed other capable firms, but none showed the same depth of understanding of the rapidly evolving landscape of AI and regulatory requirements. Their proactive stance with the FDA gave us confidence that we were in the right hands, compared to competitors who seemed more reactive.
Dr. Jagi Gill, MD

Dr. Jagi Gill, MD

Founder and Managing Director

Working with Innolitics has been a fantastic experience. Their technical and regulatory expertise is exceptional—it’s not just programming; it’s science combined with a deep understanding of FDA regulations. Interacting with their team feels like collaborating with fellow scientists who navigate the complexities of regulatory compliance effortlessly. Their mastery in detailing the ends of the slice ranges (they’ll know what I mean) and guiding us through the FDA process has been impressive. I’ve recommended them multiple times and will continue to do so.
Tim Szczykutowicz, PhD

Tim Szczykutowicz, PhD

CEO

During a presubmission meeting, the FDA acknowledged that Innolitics were “extremely advanced” in their understanding of the regulations. The FDA essentially concurred with all of Innolitics’ advice, demonstrating a deep understanding of the regulations, even in the face of ambiguous topics such as CADe vs non-CADe. They expertly, and politely, navigated the FDA call with our best interests in mind while fostering a collaborative exchange with the agency.
Dr. Ilya Pyatnitskiy, MD

Dr. Ilya Pyatnitskiy, MD

Cofounder of AUMI AI

We came to Innolitics with a complex AI/ML CADx algorithm and an aggressive timeline. Honestly, we weren’t sure it was possible. Yujan and the Innolitics team turned that assumption upside down. Through their leadership, the combined Innolitics, Lunit, and Volpara Health team delivered a complete submission package—DHF, software documentation, clinical performance assessment, the full eSTAR—in 13 weeks! What impressed me most wasn’t just the speed. It was how they handled the complexity—both technical and organizational. Our device uses AI algorithms for diagnosis, which presented unique regulatory challenges. We also had a multi-national, cross-functional team that needed coordination across time zones and disciplines. The Innolitics team managed all of it. They knew exactly how to position the device, which predicates to target, and how to draw the medical device versus MDDS boundaries in a way that held up under scrutiny. Most importantly, they structured the technical documentation so FDA reviewers could actually understand what we built without getting lost in the ML weeds. That combination—deep regulatory knowledge, technical fluency, and the ability to keep a complex team moving in the same direction—is rare. Most consultants have one or two of those. Innolitics have all three. They didn’t cut corners. Every deliverable was thorough, well-written, and backed by their deep knowledge of medicine, software engineering, and FDA expectations. If you’ve got a sophisticated AI/ML device and need full service regulatory expertise that moves at the speed and certainty, Innolitics is the only call worth making.
Terri Kim

Terri Kim

Head of Strategy and Corporate Development at Lunit

Innolitics are more than a group of top SaMD engineers and reg consultants—they are trusted advisors and are like family. They are a one stop shop for AI/ML algorithm R&D, full stack web development, and FDA regulatory clearance. We built SmileDx, a dental CADe from scratch all without needing to raise external funding and within a reasonable timeframe.
Dr. Richard Ricci, DDS, MS, FAGD

Dr. Richard Ricci, DDS, MS, FAGD

CEO

Innolitics’ team epitomized proficiency, professionalism, and precision. Their expertise extends beyond FDA regulations, encompassing intricate facets of DICOM, radiology workflows, and adept software engineering. Venturing into this without their support would have potentially stretched our timeline to 9 months or more. Earning the FDA clearance (K231385), for us, is more than just an accomplishment; it’s a monumental milestone.
Amr Abodraiaa

Amr Abodraiaa

CEO of Rology

Thanks to Innolitics, we were able to complete the software documentation for our 510(k) in just 4 months. They flew onsite to absorb how our software worked and provided detailed guidance. Without Medtech OS, training, and support, I can easily imagine the process taking 12 months. Our engineering team was able to focus on feature development instead of being bogged down with documentation. We tried three different consultants before finding Innolitics. None of them could deliver. Innolitics took the reins and made it happen. I don’t see how we would have completed our 510(k) without them.
VP of Systems R&D

VP of Systems R&D

IVD Startup

Our Publications

We are thought leaders in the AI/ML enabled medical device software space. Here are some of our many articles and resources:

Definitive Guide to AI/ML SaMD Acceptance Criteria

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.

Read more →

Yujan Shrestha

ArticleAI/MLRegulatory

Definitive Guide to AI/ML SaMD Ground Truthing

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.

Read more →

Yujan Shrestha

ArticleAI/MLRegulatory

How to Plan MRMC and Standalone Studies for a 3-Month 510(k)

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.

Read more →

Yujan Shrestha

ArticleAI/MLRegulatory

How to Document AI/ML Algorithms in FDA Presubmissions (Q-Sub)

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.

Read more →

Yujan Shrestha

ArticleAI/MLRegulatory

AI/ML from Idea to FDA

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.

Read more →

Yujan Shrestha

ArticleAI/MLRegulatory

Medical Imaging AI/ML Engineering Guide: Best Practices and Examples

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

Read more →

Yujan Shrestha

ArticleAI/MLSoftware

PCCPs: Best Practices, FAQs, and Examples

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.

Read more →

J. David Giese

ArticleAI/MLRegulatory

Medical Device Cybersecurity: Best Practices, FAQs, and Examples

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.

Read more →

J. David Giese and Bimba Shrestha

ArticleCybersecurity

Design Inputs: Best Practices, FAQs, and Examples

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.

Read more →

J. David Giese

ArticleRegulatorySoftware

Medical Device SBOMs: Best Practices, FAQs, and Examples

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

Read more →

J. David Giese

ArticleCybersecurity

Medical-Device Software Regulations: Best Practices, FAQs, and Examples

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

Read more →

J. David Giese

ArticleRegulatory

Unresolved Anomalies: Best Practices, FAQs, and Examples

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.

Read more →

J. David Giese

ArticleRegulatory

FAQs

Do all AI/ML-enabled devices require clinical validation?

If your AI model is used for triage, to detect disease, to diagnose disease, or is involved in guiding therapeutic decisions, then you will likely need to validate its performance using clinical data. That is, a reference standard that has been defined by clinical experts.

This is true even if your device as a clear predicate.

Can I publish a breakthrough device designation?

Yes! We have seen many companies receive funding and/or get acquired after getting a BDD. It is a positive market signal.

What is a Pre-Sub?

A Pre-Sub is a formal method for getting feedback from the FDA. See FDA Pre-Subs: Best Practices, FAQs, and Examples for more details.

Is one Pre-Sub always sufficient?

In many cases, we can find a path to market and an acceptable clinical validation strategy with a single Pre-Sub. Sometimes after the first Pre-Sub, there is remaining regulatory risk that requires further FDA interaction.

We’re very early stage. Is this service still appropriate?

Our AI Regulatory Strategy service is meant for companies who have a somewhat well-defined intended use and have made some progress developing their model. If you’re very early stage, feel free to read our resources to seek guidance on your pathway.

Can you work with our existing regulatory consultants?

Absolutely! We frequently consult with in house teams on topics related to AI/ML, software, and cybersecurity.

Can you help with other jurisdictions outside the US?

Unfortunately, no. Although most of our team members have experience with CE marking, Health Canada, UKCA, and other regulatory submissions—we’ve decided to focus just on the US market so that we can be experts in this jurisdiction.

We have partners we can coordinate with for international regulatory consulting.

Let’s Go!

In a 30-minute call, we'll assess if your device is a good fit for our program or alternative services and provide a clear path forward.

Let's Meet!

Let's Talk

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.