New technology speeds diagnosis of 7 autoimmune diseases
Shlomit Steinberg-Koch was going through a personal tragedy when the idea for her new startup, Predicta Med, hit her like a landslide.
Nadav Shoham, a colleague of Steinberg-Koch and a good friend of his former employer, Mazor Robotics, was attempting to cross a high altitude pass in the Annapurna region of the Nepalese Himalayas in 2015 when he was caught in an intense snowstorm and died.
Shoham also suffered from celiac disease. Although not related to the tragedy, it was something he and Steinberg-Koch talked about frequently.
In 2019, Steinberg-Koch participated in a medical technology hackathon. Israel’s HMO Maccabi provided participants with anonymized patient data.
“One of the challenges was detecting celiac disease,” Steinberg-Koch recalls. “I thought, wow, I have to do this. It started as a memorial project in Nadav. But then I won the contest and said, ‘OK, now I really have to do something with this.’ »
That “something” morphed into Predicta Med with an expanded mandate: to help primary care physicians diagnose not just celiac disease, but six other hard-to-identify autoimmune diseases.
Autoimmune diseases are those in which the immune system, instead of attacking diseases and infections, attacks the body itself. Autoimmune diseases tend to be incurable although not fatal.
Steinberg-Koch launched the company in 2020, after Medtronic acquired Mazor for $1.6 billion in 2018. Mazor Robotics founder Professor Moshe Shoham, Nadav’s father, was the first investor . The eight-person Ramat Gan-based company has so far raised $2 million and is close to closing a full funding round.
Although Steinberg-Koch has a bachelor’s degree in biomedical engineering, at Mazor she was geared more towards a product management role. So she brought in a second partner, Benny Getz, formerly CTO of cybersecurity startup Kayhut, to add the necessary technical capabilities to the team.
An unmet need
Predicta Med, as the name suggests, uses artificial intelligence and machine learning to help doctors determine if they are considering Crohn’s disease, ulcerative colitis or celiac disease.
It also diagnoses rheumatoid arthritis, psoriatic arthritis, multiple sclerosis and lupus with an average accuracy of 84%.
“It takes an average of four years and four different doctors to correctly diagnose an autoimmune disease,” Steinberg-Koch told ISRAEL21c. “It’s an unmet need.
And a dear.
A 2019 report revealed that more than $100 billion is spent each year to diagnose and treat inflammatory conditions such as Crohn’s disease or fibromyalgia. (For comparison, COPD costs the US healthcare system some $50 billion; cancer costs $125 billion a year.)
Predicta Med begins by aggregating data from two main sources: electronic medical records (EMRs) and insurance claims. The company has already aggregated 2.7 million EMR data points and 1.7 million claim records in Israel and will expand this to the US as it gets closer to launch – target date is end of 2022 and, for the current version of the product, FDA approval is not required.
This is because Predicta Med does not make the actual diagnosis; it is a decision support system that presents results to primary care physicians who then place the call – typically to refer a patient to a gastrointestinal specialist.
Going forward, “we plan to do more diagnostic work, and we may need to get FDA approval in the future,” Steinberg-Koch says.
Helps family physicians detect autoimmune diseases
Predicta Med targets clinics and hospitals with a strong practice of family medicine because these physicians are the primary gatekeepers of healthcare but are not specialists trained in difficult diagnoses.
Although about 50 million Americans suffer from autoimmune diseases, says Steinberg-Koch, “symptoms of different autoimmune diseases overlap, making them particularly difficult to diagnose.”
Celiac disease alone can present in 300 different ways, says Steinberg-Koch. It can be a child with diarrhea and a high fever or a teenager with growth problems.
Doctors are also under pressure: how to make a complete differential diagnosis when you only have a few minutes with a patient?
“We were able to prove that we could detect autoimmune disease up to four years before the family doctor,” Steinberg-Koch notes.
The product will be integrated with physicians’ existing EMR systems, so there will be no major changes to their usual workflows.
Companies like Epic and Athena, two of the leading manufacturers of EMRs, have markets where a product like Predicta Med’s can be purchased.
This isn’t Steinberg-Koch’s first dance to detect disease. In 2012, she wrote an algorithm to detect melanoma, “but we were a bit ahead of the market. Artificial intelligence and telehealth were just getting started at the time.
300 different events
Predicta Med is working with several design partners to help evaluate its proof-of-concept product and define its interface.
The company started by working with Maccabi in Israel and has since added Stanford Medical Center and Hoag Hospital in Orange County, California. Predicta Med also participates in the Intel Ignite accelerator in Israel.
There is a personal perspective for me: as someone who was diagnosed with Crohn’s disease at the age of 13 after suffering from stomach pain as a preteen, I wonder if the Predicta Med solution could have saved me years of unnecessary pain.
Indeed, says Steinberg-Koch, “The idea is to prevent all this misery.”
“We are not replacing biopsy or endoscopy, but we can alert primary care physicians so they can refer a patient to a gastroenterologist early enough to prevent deterioration or surgery,” he explains. she.
Steinberg-Koch’s initial motivation to launch Predicta Med has never left her. “Every day I think about Nadav and his responsibility. It’s a huge weight on my shoulders.”
For more information on Predicta Med, click here