How Cornerstone AI makes data “right” for healthcare

To further reinforce our commitment to providing cutting-edge data technology coverage, VentureBeat is delighted to welcome Andrew Brust and Tony Baer as regular contributors. Monitor their posts in the data pipeline.

AI has the potential to transform healthcare. From predicting the risk of terminal illnesses to developing new medicines, companies are harnessing data-driven algorithms to improve the quality of patient care in every way possible. The use cases should only grow from here, but there are also some hurdles along the way. Example: the lack of high quality datasets.

Healthcare organizations cumulatively generate around 300 petabytes of data every day. This information is stored in all systems but not used effectively due to poor preparation. Basically, data teams, who tend to create manual rules for data cleansing, are struggling to keep pace with growing volumes of information. They spend most of their time, almost 80%, preparing data – making it accurate, connected and standardized – rather than exploring and analyzing it for potential and life-saving AI applications.

The Complete Cornerstone AI Solution

To solve this problem, San Francisco-based company Cornerstone AI has launched a solution that automatically characterizes, harmonizes and cleanses health data in a fraction of the time taken by traditional methods. The company also announced that it had raised $5 million in seed funding.

According to Cornerstone, its platform’s algorithm uses a combination of custom Python and R code to analyze each table and data point – inferring their structure and validity – then organizes the tables for analysis while deleting and correcting all of them. notable errors.

“A data team doesn’t have to configure anything in the system other than telling them what the patient ID field is. The system automatically learns the structure of the data and then automatically learns the patterns in the data. Data teams can be up and running in the system from day one, reviewing AI results in the UI,” said company co-founder and CEO Michael Elashoff.

After correction, the results are shared as part of a data quality report.

Deployment

Although the company is still in its infancy, it has deployed its solution to several healthcare companies. In one case, a medical device company, which spent six months on data cleansing, was able to speed up the process by 20 times or just nine days. The system already covers the full range of structured and semi-structured health data, from medical records, clinical trials, registry data, claims, digital health and sensor data.

“In a recent validation study we performed, the system identified 98% of data issues, with a specificity of around 99.9%,” the CEO added, saying the platform can run 750 million recordings in about two hours.

He also clarified that unstructured information, such as faxes or pathology reports, remains outside the scope of the platform, at least for now.

Plan ahead

With this round of funding, which was led by Healthy Ventures, Cornerstone plans to continue to develop its product and its rope to more customers, potentially long-term contracts.

“Customers have told us that the machine learning (ML) models our system builds for data cleansing have applications beyond getting a high-quality data set,” Elashoff said. “For example, the patterns and relationships identified by the system can be used to identify patients whose response to treatment or surgical recovery differs from what it should be. In these cases, the software identifies potential clinical information that may have been hidden in the complexity of the data. So we are using the funding to develop this functionality to enable businesses to get the most out of their data. »

Datadog and New Relic are other notable players in the field of data cleansing and preparation, but they are not specific to the healthcare sector, like Cornerstone AI.

“We developed the algorithm specifically to work with medical data, with its high complexity and high error rate. we are trying to detect,” the CEO pointed out.

Beyond that, unlike other systems, the company’s platform generates an explanation for every issue detected and provides a built-in regulatory-grade audit trail that tracks all changes.

VentureBeat’s mission is to be a digital public square for technical decision makers to learn about transformative enterprise technology and conduct transactions. Learn more about membership.

About Hector Hedgepeth

Check Also

Folbigg’s life and advances in genetic research

New South Wales will conduct a second inquiry into Kathleen Folbigg’s convictions. At the center …