Epinephrine auto-injectors, first developed in the 1970s, are the most common emergency treatments for anaphylaxis, often deadly allergic reactions. The limitations of liquid epinephrine and the device’s decades-old technology have kept these life-saving devices out of patients’ hands. Austin-based startup Windgap Medical, Inc. plans to break these barriers with a more convenient, shelf-stable alternative.

In Episode 41 of the MedTech Speed to Data podcast Key Tech’s Andy Rogers and Thomas James sit down with Windgap’s co-founder and Chief Business Officer, Brent Buchine, to discuss the data-driven development of the company’s life-saving technology.

Need to know

· Epinephrine auto-injectors are big business — A $1.3 billion market at Windgap’s founding, sales of epinephrine auto-injectors exceeded $3.1 billion in 2024.

· Few eligible patients get these life-saving devices — Only 52% of American food allergy patients ever receive prescriptions, and epinephrine auto-injectors are only available in 32% of the world’s 195 countries.

· Traditional auto-injectors are relatively large and inconvenient — Only 55% of patients with prescriptions report having immediate access to their auto-injectors.

· Liquid epinephrine is thermally unstable — Doses lose their effectiveness with prolonged heat exposure, forcing patients to refill their prescriptions more frequently.

The nitty-gritty

Buchine and his co-founders saw an opportunity to make epinephrine delivery more convenient and accessible. “We developed a freeze-dried version of epinephrine to make it more stable and double, if not triple, the shelf life,” Buchine explains.

However, lyophilization introduces an extra step in the treatment process. The dried epinephrine must be rehydrated and mixed in a solution before injection.

“If you have a rescue product for emergency use, you have to get it very quickly,” Buchine says. “With modest training, you need to make sure people know how to use the product because their life is at risk if it doesn’t work.”

Windgap’s ANDI® platform is a small, highly portable single-dose auto-injector, Buchine explains. “Simply twisting the cap automatically rehydrates that dose in a couple of seconds — no shaking, no swirling required. It’s ready to inject by pressing the device next to the injection site.”

Windgap and its pharmaceutical clients are still in the commercialization phase, but the company is already looking at the future of complex injectables.

“We see that, fundamentally, formulation pipelines are getting more and more challenging,” Buchine says. “You have multiple injections, you have mixing, you have high viscosity/high volume. The conventional options out there are not as suitable anymore. We’re solving those problems specifically because we think there’s an opportunity to be best in class in that area.”

Data that made the difference:

Developing combination products is a multi-stakeholder problem. “It’s drug, it’s device, it’s patient, it’s prescriber, it’s payer. You’ve got to think about all of those stakeholders along your development.”

Get in front of stakeholders to understand the problem. “We did a lot of surveys and uncovered the opportunity. Patients weren’t getting prescriptions filled or weren’t even going to the doctor to get prescriptions. It was that segment that we spent a lot of time talking to.”

Listen to your customers. “We’ll talk to pharmaceutical companies [and ask] what are some of the biggest challenges you’re facing in your pipeline? And then you just listen. Over time, you look for that recurring theme. That’s what really drove our product strategy.”

Use data to convince investors. “There was a vastly underserved market. Our ability to communicate that to investors and help them understand the opportunity of taking [at the time] a $1.3 billion business to something substantially above that.”

Hundreds of approved devices use artificial intelligence to help physicians diagnose patients faster and more accurately. Brooke & Associates is a legal and regulatory advisory firm that helps medical device makers get AI-powered devices through FDA pre-market approval.

In Episode #40 of the MedTech Speed to Data podcast, Key Tech’s Andy Rogers and Lei Zong speak with the firm’s managing member, Jason Brooke, about the FDA’s latest guidance to medical device developers for integrating AI into their products.

Need to know

• AI’s role in MedTech — AI identifies otherwise undetectable data patterns that humans can apply in clinically meaningful ways.
• FDA’s AI staffing surges — The agency accelerated hiring to develop internal AI applications and support pre-market reviews of new AI-powered devices.
• Radiological imaging leads the pack — More than half of 900+ FDA-approved AI-based products are in radiological imaging.
• Other fields are catching up — Cardiology and neurology applications are more recent entrants in AI-powered devices, but their numbers are growing.

The nitty-gritty

The FDA published “Artificial Intelligence-Enabled Device Software Functions: Lifecycle Management and Marketing Submission Recommendations” in early 2025 to explain how it will address AI’s adaptive nature in medical device regulation.

“This guidance is really focused on a total product lifecycle approach,” Brooke explains.

Good management practices govern traditional medical device development, so documenting the development process in pre-market submissions is not as critical. AI model development is different because the model can evolve once in service.

“There’s a level of information that’s necessary in submissions for AI-based technologies that we haven’t had to provide to the FDA before,” Brooke says. “They want a lot of information,” Brooke says. “That’s an area I think may be problematic because a lot of that is somewhat trade secret.”

AI-specific guidance touches almost every aspect of a company’s submission, from risk assessment to labeling to cybersecurity. Brooke highlighted how the FDA’s approach to AI data management could change development practices to ensure the independence of training and validation data sets. For example, companies must separate their clinical sites geographically and temporally.

“This guidance gets into the weeds,” Brooke says. “It’s important for companies to understand this if they’re developing an AI-based product.”

Data that made the difference:

In addition to discussing the FDA’s proposed AI regulations, Brooke discusses the challenges companies face in bringing AI-powered medical devices to market.

“If you take away anything from this podcast,” Brooke says, “it’s that there’s a lot of burden associated with developing an AI-based medical device. If you don’t need to, then I wouldn’t recommend doing it.”

Slow and steady wins the race. Do your homework, plan for the FDA review, and then engage the agency at the right time to get them on board.

Thoroughly characterize your data sources. Devices like ECGs can vary by vendor, model, site location, patient, and many other factors. The FDA wants to know how this variability could affect the downstream AI model.

Develop a strong clinical validation plan. The FDA will limit claims and require disclosures when a device that performs well overall underperforms among certain patient groups.

Successful organ transplants depend on quickly getting donor organs to their recipients. MediGO, now part of CareDx, pioneered logistics technologies that help make these life-saving procedures more successful than ever.

In Episode #39 of the MedTech Speed to Data podcast, Key Tech’s Andy Rogers and Lauren Eskew speak with MediGO co-founder Dr. Joseph Scalea about how data led the startup to solve challenges in the organ donation supply chain.

Need to know

America’s nationwide organ donor network — From Hawaii and Alaska to Puerto Rico, patients are on a nationwide waitlist for compatible donor organs.

Organ donation used to be local — As recently as the 1990s, most organ transplants came from local Organ Procurement Organizations (OPOs), so long-distance transport was rare.

Today’s organ logistics are complex — Every organ donation requires a singular supply chain combining private or commercial aircraft and ground vehicles to link fifty-six OPOs with hospitals.

The nitty-gritty

A practicing transplant surgeon and currently the Vice Chair of Innovation in the Department of Surgery at the Medical University of South Carolina, Dr. Scalea has seen a dramatic improvement in the efficiency and survivability of organ transplants.

Operations that once took hours are now routinely completed within an hour. At the same time, complication rates are at all-time lows. Many technological advances made these improvements possible, but Dr. Scalea saw opportunities in the organ transplant system’s operations.

“We have about twenty-four hours to move a human kidney from the donor hospital,” he explains. This tight turnaround led Dr. Scalea to explore the potential for drone delivery. “We were watching the [transportation] time go up,” he recalls. “We hypothesized that using drones to seamlessly go from the donor to the recipient hospital might allow the recipient side more flexibility to get better outcomes.”

Data that made the difference:

Data drove MediGO’s decision-making and ultimately led to a pivot from drone to supply chain technology. “We fundamentally believe that this problem is worth solving for the community,” Dr. Scalea says, “so what data are required to make this a business? It was through a combination of customer discovery, key informant interviews, and a ton of research into the space.”

Identifying the actual customer was key. “We initially focused on the transplant centers,” Dr. Scalea says, “and then fundamentally recognized the organ banks responsible for moving the organs were the right customers. Organ banks didn’t see as much immediate value in the biotelemetry. What they needed was logistics.”

From there, the MediGO team could understand their customers’ financial concerns. “We needed to understand funds flow — how those customers get reimbursed for the work they do.”

As a practicing surgeon, Dr. Scalea inherently understood the customer’s customers. “I was very fortunate to be an active transplant surgeon while standing up MediGO. Every day, I’d go to the hospital and ask myself, ‘Where’s the organ?’ This problem was real.”

“As our colleagues around the country read the research we were publishing, it became clear there was a groundswell of interest in this problem being solved.”

Ohio-based Avation Medical has developed a bioelectric wearable device for at-home treatment of overactive bladder, promising improved quality of life for patients suffering from the most common cause of incontinence and urinary urgency.

In Episode #38 of the MedTech Speed to Data Podcast, Andy Rogers discusses the Vivally System, entrepreneurship, and more with Avation Medical co-founder Jill Schiaparelli.

Need to Know

• Bioelectric medicine is an alternative to pharmaceuticals and surgery — Selectively stimulating the nervous system can enhance, control, or fix a function without the tradeoffs of other treatments.
• Overactive bladder is a prime candidate for bioelectric solutions — Forty-five million Americans have overactive bladder, with nine million preferring adult diapers to traditional treatments.

Nitty Gritty
Although not fully understood, overstimulation of nerves in the bladder wall produces spasms, creating an urge to urinate as often as thirty times a day in extreme cases.

Few sufferers choose sacral nerve stimulation, the gold standard treatment, which requires a device implanted near the spine to stimulate nerves regulating bladder behavior.

“The moment you say surgery, it complicates things.” Schiaparelli explains. “You need a physician who knows how to do it, you need a patient who’s willing to have what could be a very extensive surgery, and you need a payer who’s willing to pay for the surgery.”

Drugs for overactive bladder have unwelcome side effects that cause most patients to drop out of the care pathway.

“When you look at those dynamics,” Schiaparelli says, “it screams a need. Patients want something that takes surgery out of the equation, doesn’t have the side effects of drugs, and is convenient.”

Avation Medical’s Vivally System is an ankle-worn device that indirectly stimulates the sacral nerve through the tibial nerve without surgery. The device measures responses to adjust its stimulation automatically in real-time.

“This physiologic closed loop allows the patient to have personalized, effective therapy in just thirty minutes once a week,” Schiaparelli says.

Data that made a difference
As a serial entrepreneur, Schiaparelli has learned that success requires understanding and meeting the needs of three key stakeholders: the patient, the physician, and the payer:

• Overactive bladder patients dissatisfied with traditional treatments are an enormous market.
• Most physicians can only offer prescriptions for imperfect drug therapies that do not generate revenue for their practices.
• Payers don’t like either option since surgery costs reach $40,000 while drugs require lifetime prescriptions.

“Every area we checked into, it made sense. This technology in this market checked all those boxes to say there’s a need. We thought this was a real opportunity to disrupt the market.”

But success requires addressing the needs of other stakeholders, including regulators and investors.

Regulators’ expectations, for example, drove Avation Medical’s decision to implement quality control processes while starting its first clinical trial. “We knew that was going to be very important because we planned to use the clinical trial with our FDA submission.”

Aligning Avation Medical’s investors’ expectations was just as important, with each investment round supporting the next stage in development and commercialization.

Schiaparelli takes a holistic perspective on a Med Tech startup’s data strategy.

“It’s speed, absolutely,” Schiaparelli says, “but it’s also intelligent data that speaks to the needs of all the people that you’ll need to demonstrate to down the line.”

Transforming Chronic Pain Treatment with a Lean, Data-focused Development Strategy

Based in Washington, DC, AlgometRx has developed a technology platform that will let clinicians perform objective pain assessments to improve treatments for chronic pain.

In Episode 37 of the MedTech Speed to Data Podcast, Key Tech’s Andy Rogers and AlgometRx Chief Operating Officer Kevin Jackson discuss how collecting the right data sped the Nociometer platform’s development.

Need to know

Pain diagnosis is challenging — Patients self-report their experience, which is inherently subjective and variable.

Pain treatment involves trial and error — Finding the right treatment plan often requires a months-long iterative process.

Risks of inappropriate drug treatments increase — Poor understanding of pain’s causes leads to the over-prescription of the wrong drugs, a contributing factor to the opiate crisis.

The nitty-gritty

AlgometRx’s technology platform emerged from research by the company’s founder, Dr. Julia Finkel at Children’s National Hospital. A pediatric anesthesiologist, Dr. Finkel must assess pain in children who lack the words to describe their experiences.

“She wanted something that she could use in clinic to help better understand patients’ pain,” Jackson explains. “Something that’s simple enough that anyone could use in a variety of settings.”

The Nociometer platform selectively activates nerve fibers and evaluates the patient’s physical response — without causing additional pain.

“We’re able to identify the physiologic underpinnings of that pain experience, and that allows clinicians to better understand what’s happening.”

An objective assessment of the patient’s pain lets the clinician make faster, better-informed decisions, but the real value will come from monitoring treatments. Rather than waiting three months to see if a treatment works, patients can return to the clinic a week later for a follow-up measurement. “That gives the clinician different information they wouldn’t have had, Jackson says. “We can get right to the root of it, and you avoid six, seven, eight visits.”

Data that made the difference:

AlgometRx discussed this first-of-its-kind technology with the FDA before developing its proof-of-concept prototype. “We had this novel concept of a pain biomarker and device, so we wanted to know how we would even bring a device like this [to market].” FDA feedback informed a development strategy focused on gathering data from specific populations.

AlgometRx leveraged partnerships to support this focused strategy. Working with Johns Hopkins researchers under an NIH Sprint for Women’s Health grant, AlgometRx is developing pain response data sets for patients with systemic lupus and carpal tunnel syndrome. The startup is also a member of JLABS, Johnson & Johnson Innovation’s life sciences incubator, where they get valuable insight into the Nociometer platform’s potential role in pharmaceutical research.

Running a lean operation lets AlgometRx prioritize data. Jackson is the startup’s only full-time paid employee. Dr. Finkel, AlgometRx’s board, and a network of consultants and contractors bring their expertise as needed. “We don’t have a robust employee base, but we have a robust team,” Jackson says. “We’ve run this lean approach where we only bring in people as needed. Obviously, our investors love that idea because it’s spending money on device development and data generation.”

Data drives MedTech growth, from the leanest startup to the world’s most valuable pharmaceutical company. In Episode #36 of the MedTech Speed to Data Podcast, Key Tech’s Andy Rogers discusses data-driven trends in medical technology with Anand Subramony, Eli Lilly’s Vice President of Drug Delivery, Device, Connected Solutions & Innovation.

Need to know

· Quarter-century perspective — After getting his PhD in chemistry and materials science from Purdue University, Subramony spent the next twenty-five years developing novel medical technologies for firms like Johnson & Johnson, Novartis, and AstraZeneca.

· Cutting-edge combination product development — Now at Eli Lilly, Subramony’s team is responsible for combination product development, from early development through commercial development, for new delivery dosage forms.

The nitty-gritty

Subramony drew upon his career-spanning perspective to discuss significant data-driven trends that impact the entire industry, not just Eli Lilly.

One topic he raised in his conversation with Andy was using data to monitor disease state progression. Already an important element of fields like neurology and oncology, extensive data collection will become essential to a wider range of treatments. For many conditions, Subramony explains, disease state is a binary evaluation.

“You can really understand disease state progression using digital biomarkers and collecting data throughout [the treatment],” Subramony said. “I think these are areas where there is a lot of potential.”

Another data-driven trend Subramony discusses is the adoption of direct delivery therapies. When treating tumors and other conditions, off-target toxicity can cause unfortunate side effects. Genetic medicines, such as mRNA therapies, can target the cell surface, protect the cargo, and prevent endosomal escape.

“It’s going to disrupt the way we look at drug delivery from macroscopic pen auto-injector deliveries to microscopic, targeted deliveries where you need to take the therapeutic moiety into the site of action,” Subramony said.

Data that made the difference:

This episode’s wide-ranging conversation covered many additional topics of interest to the MedTech community, including:

GLP-1 treatments are “really transformative” for individual patients who can afford them. However, bringing costs down will depend on data demonstrating how lower obesity and healthier lifestyles reduce the overall burden on the healthcare system.

For sensors and connected devices to go beyond “bells and whistles,” the industry must drive value from how we use that data. Relating compliance to efficacy, for example, makes moving patients from less effective to more effective therapies easier and faster.

Continuous monitoring can improve healthcare outcomes but requires new data management practices to govern how much data is collected, who is collecting and viewing the data, and what are the privacy rules protecting patients.

Cell therapy research and manufacturing are driving demand for automated high-throughput equipment to improve quality, reduce costs, and shorten the development cycles of innovative treatments that save lives. But what factors shape a startup’s journey from the lab to commercialization?

In Episode #35 of the Speed to Data podcast, Key Tech Business Development Manager Kelly Parker leads a panel of industry experts who discuss high-throughput automation in cell therapy screening and manufacturing.

Daniela Hristova-Neeley, Ph.D., is a partner at the advisory firm Health Advances, where she is a leader in the diagnostics and life sciences tools practice.

Blair Morad is Senior Director of Engineering at Cellino, a startup developing autonomous biomanufacturing technology for personalized cell therapies.

Nova Syed is a founder and angel investor in the deep tech and healthcare sector. Most recently, Syed was the founding VP of Product at Mekonos, a developer of silicon nano-needles for cell therapies.

Need to know

Three factors drive requirements in cell therapy screening:

· Customers are studying a huge variety of biological systems and drug targets.

· Business requirements drive the need for faster and cheaper therapy development.

· Meeting regulatory standards demands high-quality, reproducible data.

In manufacturing, meeting GMP makes design requirements even more complex as the product must:

· Improve flexibility and scalability.

· Improve quality control and traceability.

· Lower manufacturing costs.

· Reduce human interaction to improve efficiency and quality.

The nitty-gritty

Given the many competing business, market, and regulatory requirements, the instrument design process inevitably forces developers to make tradeoffs.

The panelists agreed that quality is table stakes, which means technologists and business leaders must balance time, cost, and scope.

“You have to be ruthless when it comes to prioritizing your differentiator,” Hristova-Neeley said.

In Morad’s experience, understanding the organization’s core competency is essential to focusing on the right problems.

Data that made the difference

The three panelists shared their lessons learned from hard experience in the healthcare technology business.

Get early feedback from the market. “Product-market fit doesn’t just happen,” Syed explains. “Unless you get feedback directly from the users and the customers, you don’t have the data to iterate to the next cycle.”

Hristova-Neeley agreed. “It’s always important to hear what the customers have to say. Automation is certainly important, but it’s not the only thing that is going to solve how we do cell therapy manufacturing or cell therapy development.”

Look for outside expertise. “When you’re working with the right experts,” Morad said, “they know how to ask the right questions that are helpful to move forward.” A good startup employs many intelligent people, but they won’t know everything about everything. Find outside partners who have already built the assays, workflows, automation modules, and other elements outside your core competency so you can focus on your innovations.

Pictorlabs is a California-based startup developing a cloud-based platform that uses artificial intelligence to improve tissue sample analysis through virtual histological staining.

In Episode #34 of the Speed to Data Podcast, Key Tech’s Andy Rogers speaks with Pictorlabs Chief Product Officer Raymond Kozikowski about his company’s all-digital approach to tissue sample testing.

Need to know

· Histopathology — The visual analysis of stained tissue samples to diagnose cancer and other conditions.

· Tests have long turnaround times — Selection, preparation, and imaging can take as long as a day to return one test’s results to the physician.

· Tests are requested sequentially — The results of one test determine the next test in the decision tree, so physicians can’t order all the tests simultaneously.

· Cancer patients must wait — On average, there is a forty-day gap between biopsy and first treatment.

The nitty-gritty

As Dr. Kozikowski explains, “Histopathology has traditionally been a chemistry-based testing paradigm. Every cancer case starts with a biopsy, and those tissues are transformed into data that inform the diagnosis and therapeutic options.”

Pictorlabs’ solution uses one tissue sample to create a virtual stain that simultaneously generates results for dozens of tests within minutes.

“What we’re doing is teaching AI algorithms the relationship between validated test results and the underlying signature from that unstained piece of tissue,” Dr. Kozikowski said. “From a single patient sample, you’re no longer limited to running one chemical-based test. You can run ten, twenty, thirty AI-based tests.”

Although the company thought it faced a long march toward the clinical market, Pictorlabs found an opportunity in a different market.

“There’s a really robust cancer research market, both the academic medical centers and the pharma companies. Where we really got traction wasn’t necessarily as a replacement [technology] but a complement to other kinds of tests.”

Dr. Kozikowski cites spatial biology as an example. Cells express their genes and RNA differently depending on their location in tissue. Understanding this spatial relationship could yield new, more targeted therapies.

“A challenge with interrogating RNA targets,” Dr. Kozikowski explains, “is that you often can’t also run traditional staining-based tests. With virtual staining, we’re actually able to complement those RNA-based tests with a pseudo-staining result. This is perfectly fit for purpose in those workflows.”

Data that made the difference:

The importance of data to AI development isn’t surprising, but Pictorlabs needs more than quantity.

“There’s also a lot of nuance in the design of that dataset and making sure it’s fit for purpose,” Dr. Kozikowski says. “Has it seen the diversity of human disease in that training dataset to really make sure that it generalizes accurately and robustly?”

Partnerships with the research community have helped refine Pictorlab’s technology. One of these relationships is with Dr. Michael Kallen, a pathologist at the University of Maryland’s School of Medicine.

“Diagnosing lymphoma or leukemia can be very, very complex. You have the challenge of managing a complex workflow in the lab and the complexity of making sense of all those test results spread over weeks or maybe even a month.”

“[Dr. Kallen] saw the opportunity. We’ve been partnered with that department for a while now, exchanging data to help train algorithms and get feedback from pathologists. We’ve just received an innovation grant to deploy our technology side-by-side with their existing workflows to look at the value.”

Watch the full video below to learn more about Pictorlabs’ virtual staining solution and to hear Dr. Kozikowski’s advice to product managers and entrepreneurs.