EvolutionIQ unveils its AI-powered technology to reduce the cost of insurance claims

Processing bodily injury claims is not just a matter of analyzing numbers and evaluating transcripts of events. Because a given claim can be open for 10 years and contain hundreds of data points and medical notes, adjusters must be de facto medical experts to make informed decisions.

“It’s not like transaction data in a spreadsheet,” said Thomas Vicrota, CEO of claims routing platform EvolutionIQ. “The bodily injury claims can be a medical book to read through.”

Insurance is a huge industry – worth an estimated $1.3 trillion in the US alone. Insurers pay approximately $230 billion annually in claims payments across disability, workers compensation and complex business injury lines.

But for the benefit of insurers, regulators and the general public alike, that amount can – and should – be significantly reduced, according to Vykruta. To this end, EvolutionIQ has developed what it calls the insurance industry’s first artificial intelligence (AI) claims routing technology.

EvolutionIQ leads with ML

The three-year-old company, which today announced a $21 million Series A funding round, has built its own system based on deep learning, an advanced branch of machine learning (ML). This augments AI Recurrent Neural Networks (RNNs), which are based on time-series data or data that includes sequences.

This allows the system to monitor each open group short and long-term, individual disability, workers compensation, property and casualty claims within the examiner’s purview to guide them to those that require more attention, new procedures or complex decision making. It will generate a list of the few that are most doable, along with a “deep explanation” of the cause and effect you should aim to achieve.

For bodily injury, the system can read a complete chain of events describing a claim and rely on the RNN data to simulate injury sequences, comorbidities (the presence of multiple diseases or medical conditions), demographics, conditions, and other factors. These can then provide predictions about when the claimant may recover, how far they may recover and what working conditions and responsibilities they can return to.

For example, with a short-term disability claim, a worker may have gone on vacation for a week and will be in line with several similar workers. The system will pick up on that and decide that they can return to work within 45 days, for example, as long as they receive certain vocational training.

“You’ll put the information right in front of the examiner,” Vicrota said. “It’s a glass ball where they can see,” This is where you should be spending your time. “

As he pointed out, the two seizures can be overshadowed by dozens of complex claims that can last for years and often amount to hundreds of thousands of dollars. They can be documented in hundreds of disparate pages and in many structured and unstructured formats.

Furthermore, “these are impossibly complex problems because there are physical injuries,” he said. “You have to be a physician in many cases to understand comorbidities. There are too many complex problems and too few people who cannot solve them.”

However, he said, the deep learning system and human artificial intelligence in the loop must have people connected to it. Examiners are not excluded; Instead, they contribute to the system as it constantly learns, evolves, and recalibrates based on new data and events. “Dealing with physical injuries is a really complex task and a big data problem,” Vicrota said. “The system must partner with human experts.”

Insurance claims management update

Working with clients including Reliance Standard, Principal and Sun Life, EvolutionIQ has processed millions of claims. Carriers and third-party officials who have been using its software for more than a year have seen their claims flow reduced by up to 45%, according to Vykruta, and the incidence of workers transitioning from short-term to long-term disability has been reduced by nearly 50%.

“The Claims Department is ready for an update,” said Vikruta, a former AI technical lead at Google. “It is the biggest operational problem that carriers have because it is a huge human effort that can be greatly improved with data. Tens of thousands of claims are open at any time and there is a huge opportunity to influence them now with the right information.”

Vykruta explained that the funding will be invested in research and development and the development of new units of artificial intelligence. He will also help build the company’s team of engineers, data scientists, and product and customer service experts. The company currently has 45 employees — many of whom come from Google, Facebook, Amazon and Bloomberg — and plans to increase that base to 85 by the end of the year. Vicrota noted that more than 25% of EvolutionIQ’s technical staff come from Google, which is a rarity for companies in the insurance industry.

As he pointed out, insurance is a huge and essential industry for the modern world, but he also emphasized the fact that EvolutionIQ’s long-term goal is to reduce the industry’s operating costs and premiums – which benefit everyone, from companies, to adjusters, to claimants and policyholders alike.

“We are very focused on making this claims process more efficient and affordable for everyone,” he said. We consider this future inevitable. In the next five years, every company will have to move a system like this, or else they won’t be able to keep up.”

The first round of EvolutionIQ was led by Brewer Lane Ventures. Also participating were seed investors FirstRound Capital, FirstMark Capital and Foundation Capital, along with Altai Ventures, Asymmetric Ventures, Reliance Standard Life, New York Life Ventures, Guardian Life and Sedgwick.

VentureBeat mission It is to be the digital city arena for technical decision makers to gain knowledge about transformational enterprise technology and transactions. Learn more about membership.

Leave a Comment