Israeli smart software flags patients at risk for colon cancer
search

Israeli smart software flags patients at risk for colon cancer

Medial EarlySign adapts financial algorithm modeling for medical purposes, analyzing blood tests and letting health care services know who needs to be tested

Illustrative: A team of surgeons operating in the hospital (iStock)
Illustrative: A team of surgeons operating in the hospital (iStock)

Medial EarlySign, an Israeli startup, has developed machine learning-based software that analyzes standard blood test results to identify patients at high risk of colon cancer.

The product, called ColonFlag, does not directly diagnose colon cancer, but it is currently being used by doctors at Israel’s healthcare provider Maccabi to flag patients at high risk of the cancer, enabling the system to be proactive about getting these patients tested.

The firm was set up by Ori Geva, Ofer Arieli and Nir Kalkstein in 2009. Kalkstein is an expert in big data and machine learning algorithms, who also co-founded Final Israel Ltd., an algorithm-based trading company.

“In Final, Kalkstein’s technology used AI to crunch financial data to predict where assets are going,” said Geva in a phone interview with The Times of Israel. “Now, we are using medical algorithms with that same modeling method to look at medical records data and predict where people are going.”

“We can tell health providers which patients to focus on and which would benefit from an early intervention, and how best to do this,” he said.

The artificial intelligence market for healthcare applications is expected to expand rapidly globally, with revenues growing at 40 percent annually through 2021 and reaching $6.7 billion by that year, a report by the Frost & Sullivan research and consulting firm says.

AI has the potential to “improve outcomes by 30 to 40 percent” while reducing the costs of treatment by as much as 50%, the report says.

“Already playing a critical role in other industries, AI systems are poised to transform how we think about disease diagnosis and treatment,” said Frost & Sullivan transformational health industry analyst Harpreet Singh Buttar in a statement. “Augmenting the expertise of trained clinicians, AI systems will provide an added layer of decision support capable of helping mitigate oversights or errors in care administration.”

Medial EarlySign taps into the databases of healthcare organizations to scan blood tests for signs of people who are at high risk of developing colon cancer by comparing them to the blood patterns of patients afflicted with the illness. The startup has studied the medical records of some 20 million individuals in Israel, the UK, the US and Asia Pacific through databases holding the information and trained the algorithms to learn the patterns and identify them in high-risk patients.

“There are a lot of untold stories within our records data” that often get overlooked by overworked professionals, said Geva. But “computers do not tire,” he said. The algorithms scour millions of data points and flag for risk factors, getting the medical system to take a closer look at certain individuals.

The colorectal cancer solution is the first application of the technology the company has started marketing. “We have dozens of models at different stages of development” for other illnesses, he said, including flu, diabetes and hypertension.

Geva said he hopes these applications will be “on the market in the next few months.”

The company is currently working to get commercial deals in the US and working closely with “US entities” to see what other challenges their algorithms could address, he said.

In Israel, Maccabi has installed Medial EarlySign’s server as part of its IT system. “They provide us data on the patients” and determine when they want to be flagged — at what kind of resolution and risk level — Geva explained. According to the set parameters, Medial EarlySign’s  software scans the database and flags individuals who meet the criteria. For the service, healthcare providers could pay either a monthly subscription or an annual license fee, depending on how much use they make of the software, Geva explained.

The company has raised some $50 million to date in two funding rounds, including from the Hong Kong-based Li Ka Shing Fondation and Israel’s aMoon Fund, said Geva.

The firm’s main push will be in the US, he said, and for that purpose has set up an office in Boston. The firm is based in Kfar Malal and employs 30 workers.

Israel is considered a global leader in AI, high-performance computing and computer vision, as well as in healthcare. According to data compiled by the nonprofit Startup Nation Central, Israeli venture capital funding in digital health startups jumped by 30 percent in 2017 compared with 2016 to almost $340 million, with a total of 470 digital health startups operating in seven subsectors, including AI.

(This story was updated to correct the names of the health providers that are using the ColonFlag product)

read more:
comments