After losing his sister to cancer, a former Apple exec wants to make it easier for patients to get their health records
Many cancer patients still carry piles of paper records and imaging CDs between visits. While companies are working on a solution to this problem, several challenges remain.
Anil Sethi learned this firsthand after his younger sister, Tanya, was diagnosed with stage IV breast cancer.
He created a previous startup, Gliimpse, with the goal of helping her after she was first diagnosed. The company was later acquired by Apple, where Sethi worked for two years as director of health records, until he received a call from Johns Hopkins that Tanya would have only two weeks to live.
He left and drove her across the country as they sought specialists who could help.
“We bought Tanya another five months of life as we roamed the country in search of a Hail Mary,” he said.
When she died, Sethi promised that he would work for the rest of his career to make sure people would no longer view breast cancer as a death sentence. With this goal in mind, he founded his current startup Ciitizen in 2017.
If his previous work at Apple was to make it easier for many people to get medical records from different facilities, Ciitizen’s current approach is profound. While the company isn’t exclusively for cancer patients, Sethi is focused on making the platform work for them first, given the sheer amount of information they have to manage.
Many health records efforts focus on retrieving information using Fast Healthcare Interoperability Resources (FHIR), an interoperability standard that allows them to extract certain health information from health record systems with patient consent. But that standard doesn’t currently cover everything, including pathology reports, information about tumor size and grade, and discharge summaries, that Tanya needed.
“An API can’t get out of a database … what it doesn’t have in the database in the first place,” he said.
Since many of the built-in EMR databases still focus on billing, this information just wasn’t there.
Instead, his solution is to use the patient’s right of access to retrieve all their records, documents and genomics reports. The users can tell the company where they received care so that Ciitizen can track the ‘breadcrumbs’.
“When Tanya was at Hopkins, they were using Epic, so I used her login and I got 30 or 40, maybe 50 records, one outage, no problem,” he said. “But when I used her HIPAA access right to fill out a form, sign it and send it to medical records, we got a dump of 2,200 pages. So we’re looking at two orders of magnitude different.”
Of course, this comes with a tradeoff. While information coming in through an API is calculable, those 2,200 pages he received were all sent in a big, cluttered PDF.
That’s why Ciitizen trains machine learning tools to turn this into standardized, actionable information. It aims to retrieve and codify the 20 key elements needed by oncologists.
The service is free for patients. It has a feature that allows them to identify clinical trials for which they may be eligible, and to share their data with researchers, if they wish. Users can download their records or request to delete them.
“I think we’ve all had a Tanya in our lives,” Sethi said. “You need to know why you’re doing this job. This is really hard work.”