Pharma × FDA-regulated software

We know medical device software so you don’t have to.

ACNU, companion diagnostic, imaging endpoint, clinical AI agent. If your asset needs software the FDA has to review, we’ve cleared it before. Petros Pharmaceuticals picked us in May. 45 prior submissions are on the record.

Book a 30-minute partner-fit call
As featured in BioSpace · Petros Pharmaceuticals × Innolitics
BioSpace press release headline: Petros Pharmaceuticals Partners with Innolitics, a Leading Software-as-a-Medical-Device Developer

Featured in BioSpace

Your drug is ready. We make your software ready.

BioSpace announced the partnership on May 20, 2025: Petros Pharmaceuticals (NASDAQ: PTPI) partnered with Innolitics to integrate AI, cybersecurity, patient self-selection, EHR integration, and retail pharmacy components into its first-in-industry SaaS platform, developed as Software as a Medical Device under FDA’s ACNU guidelines for Rx-to-OTC switch.

Pharma teams bring us in once the build-vs-buy call is settled and the next question is partner fit: credentials, regulatory record, execution risk. We’ve shipped 60+ FDA submissions across AI/ML, imaging, and clinical AI.

Read the BioSpace announcement

Your turn

Book the call pharma teams start with.

30 minutes. FDA path, scope, timeline, and whether we’re the right fit for your program.

Book a strategy call →

Proof, not promises

Case studies

FDA clearances, Breakthrough Device Designations, hold letters recovered, multi-indication submission architectures. AI/ML, imaging, clinical AI.

18 months to an FDA-cleared tumor-measurement platform.

Idea → 510(k) → quality system → FDA audit passed. $4M of a $5M / 5-year plan, three years early. The same build pattern fits a pharma trial-imaging endpoint.

  • K202229 AI Metrics
Read the case study →AI Metrics - Dr. Andrew Smith

Modular regulatory architecture for repeat AI clearances.

One architectural change turned every future tumor indication into a lightweight module swap instead of a ground-up 510(k). The same pattern applies to a multi-CDx pharma pipeline.

  • K252922 Neosoma Brain Mets
Read the case study →Neosoma

Blank sheet to FDA-cleared pediatric neuroimaging.

We owned the full lifecycle: design, algorithm rebuild, clinical validation, regulatory strategy, 510(k) submission. GyriCalc cleared (K250686) in July 2025. The full regulated-software pipeline, one partner.

  • K250686 GyriCalc
Read the case study →NeuroSpectrum Insights, Inc

FDA Breakthrough Device Designation in 90 days.

Reframed the regulatory strategy after FDA pushback on an ECG foundation model. Breakthrough Device Designation granted. The pathway pharma BD teams keep asking about.

Read the case study →

FDA hold letter → cleared, without the clinical re-run.

Other consultants wanted another study. We found the path of least resistance. The 510(k) clearance letter arrived in time for Christmas.

  • K231130 SimBioSys
Read the case study →SimBioSys

AI/ML clinical software from scratch, concept to FDA clearance.

Built the app, trained the model, ran the MRMC reader study, cleared FDA. Full AI/ML lifecycle, no external funding. The same package a pharma platform can hand off and get back cleared.

  • K242437 Cube Click
Read the case study →Cube Click, Inc.

12 months: AI cardiomegaly detector, R&D to FDA clearance.

Algorithm R&D → MONAI → clinical performance study → FDA comms → clearance. The cadence pharma BD teams want on a companion diagnostic or imaging-linked asset.

  • K232613 CT Cardiomegaly
Read the case study →Body Check

AI/ML Pre-Sub on time, on budget, FDA-aligned.

Developed an FDA regulatory strategy for an AI platform that converts 2D MRI to 3D joint models. Proactive FDA engagement. Strategy accepted. The Pre-Sub a pharma discovery platform actually needs.

Read the case study →OrthoVentions

Clinical AI Medicare-coding analyzer, SMART on FHIR, 4 weeks.

LLM + EHR + CMS code lookup, working prototype, under a month. The same build pattern for validated clinical AI inside regulated workflows.

Read the case study →Untitled

Voice of the customer

What clients tell their peers.

The lines they repeat on reference calls.

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.

Our first FDA clearance was monolithic — every component submitted as one device. When we needed to clear a second AI indication, we assumed we'd have to re-submit the entire platform. Innolitics saw something we didn't: a modular regulatory architecture that isolated the new CNN as the only component under review. That single insight saved us months of redundant documentation and positioned every future tumor type as a lightweight module swap. We submitted in September 2025 and cleared in December — 3-month review, zero major deficiencies. I've worked with regulatory consultants before. Innolitics is the first one that understood our software well enough to design a regulatory strategy from the architecture itself.

We likely wouldn't have received our Breakthrough Device Designation without Innolitics. When FDA initially pushed back, they quickly understood the concerns and responded with clear, well-supported data. Their expertise in software, medicine, and FDA's AI/ML expectations made a decisive difference in the outcome.

After spending $500K over five years on consultants who knew how to sell but couldn't execute, Innolitics took us from concept to FDA clearance in under 18 months for a first-of-its-kind MRI neuroimaging device. When FDA questioned our original approach, they adapted without losing momentum. We submitted on schedule and cleared in 4.5 months. I've seen many engineers at J&J and Ethicon — Innolitics is many standard deviations ahead of the curve.

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.

We recently got FDA cleared and Innolitics' responses were absolutely clutch to craft the strategy that finally worked. Unlike other consultants, who wanted us to do more work and spend more money on clinical testing, Innolitics found a path of least resistance using a combination of our existing validation and thoughtful responses to FDA. We received the best Christmas present ever – our 510(k) clearance letter.

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
Company logo

How we engage

Two ways to work with us. Your call.

Same team, same quality system, same FDA reviewers, whether we carry the whole build or wrap the work your team already did. Recent examples of what we build: Rx-to-OTC gating software (ACNU), AI-enabled companion diagnostics (CDx), imaging AI for trial enrichment, FDA-qualified drug and device development tools (DDT and MDDT), and validated clinical AI agents.

Option A

End-to-end build

We design, build, validate, and submit. Engineering, regulatory, AI/ML, and cybersecurity under one roof. No vendor handoffs, no translation layer between the people writing the code and the people writing the submission.

Best for: Pharma teams without internal SaMD engineering, or programs where speed to submission matters more than who owns the code day-to-day.

Option B

Bring your own software or AI

Your team has the software or the model. We wrap it in the FDA-grade lifecycle (design controls, V&V, cybersecurity documentation, human factors, PCCP) so it can be referenced in an NDA supplement, a De Novo, a 510(k), or a DDT qualification package.

Best for: Teams whose discovery, clinical science, or in-house software is already working and FDA-ready is the missing layer.

Partner fit, fast

Tell us what you need built. We'll tell you if we're the right fit.

Straight talk in 30 minutes: scope, timeline, team, references. No deck theater.

Book a partner-fit call →

Before you book the call

The questions pharma buyers ask on the first call.

We want to bring our own algorithm. How do you handle model IP?

Your model stays yours. We wrap it in the FDA-grade lifecycle (IEC 62304, V&V, cybersecurity, PCCP). You own the weights, the code, the training data provenance. We author the regulated-software shell around it.

Can we start with something smaller than a full build, like a pre-sub or gap analysis?

Yes. A four-week fixed-fee Regulatory Gap Analysis returns a scored readiness report, pathway recommendation, and remediation roadmap. Most pharma programs start there before committing to a build.

Can the software live on our infrastructure, or does it have to run on yours?

Either. We deliver containerized artifacts and infrastructure-as-code. Most pharma clients host production themselves once we hand off. Staging and V&V can run on either side.

How do you price, fixed-fee or T&M?

Both. Discovery and gap analyses are fixed fee. Builds are typically milestone-based fixed-fee for scoped workstreams, T&M for evolving scope. We surface the tradeoff before you sign.

What do we actually get at the end of the engagement?

Everything. Source code, design history file, V&V protocols and reports, traceability matrices, submission artifacts, cybersecurity package, post-market plan. Your regulatory team owns the asset from day one.

How do you coordinate with our existing CRO, biostatistician, and clinical lead?

CROs run drug trials; we run regulated software. Different FDA centers, different artifacts. We map to their deliverables, attend their meetings when software touches endpoints, and stay out of their lane otherwise.

Can you meet with FDA on our behalf, or do we have to lead?

We do both. Some pharma teams want us in the pre-sub room as the software voice. Others want us prepping their regulatory lead and staying in the background. Decided per meeting.

Depth if you want it

Further reading.

Recent Innolitics editorial on the FDA’s new ACNU pathway, the cautionary balance sheet behind the last wave of digital therapeutics, and the validation benchmarks FDA actually approves for AI/ML.

AI Validation

Definitive Guide to AI/ML SaMD Acceptance Criteria

Yujan Shrestha
Oct 26, 2025

Ready to move

30 minutes to a partner-fit decision.

You’ll talk to someone who has cleared this class of software before, in this FDA center, on deadlines that mattered.

Book a 30-minute call →

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.