Dr. Nikhil Wagle thought he had an excellent idea to advance research and patient care.
Dr. Wagle, an oncologist at the Dana Farber Cancer Institute in Boston, and his colleagues would build an enormous database that linked cancer patients’ medical records, treatments, and outcomes with their genetic backgrounds and therefore the genetics of their tumors.
The database would also include patients’ own experiences. How ill did they feel with the treatments? What was their quality of life? The database would find patterns that might tell doctors what treatment was best for every patient and what patients might expect.
The holdup, he thought, would be finding patients.
Instead, the important impediment clothed to be gathering their medical records.
In use, there's no single format employed by all providers, and hospitals haven't any incentive to form it easy to transfer records from one place to a different.
The medical records mess is hobbling research and impeding attempts to enhance patient care.
“Data are trapped,” said Dr. Ned Sharpless, director of the National Cancer Institute. “This may be a huge problem. it's phenomenally important.”
The cancer institute has invested many dollars into determining the genetic sequences of patients’ tumors and researchers have found thousands of genes that appear to drive tumor growth.
But until patients’ medical records are linked to the genetic data, life-or-death questions can't be answered.
“What the drug did they get? Did they respond? Did they survive? Were they cured?” Dr. Sharpless asked.
The federal has mandated uniform standards for electronic health records.
“At now, they're to not A level that helps with the detailed clinical data that we'd like for the scientific questions we would like to ask,” Dr. Wagle said.
A few private companies try to tackle the matter.
Flatiron Health, just bought by Roche has obtained about 2.2 million records of cancer patients from medical centers and made them available for research after stripping them of identifiable information.
But Flatiron must employ 900 nurses and authorized tumor registrars, people with master’s degrees in coding data, to place it all into a usable form.
“About 50 percent, if less, of the critical details we'd like for research, are trapped in unstructured documents,” said Dr. Amy Abernethy, the company’s chief medic.
“They are in PDFs. Maybe a doctor put during a note by hand, maybe a doctor typed it.
That the note became a narrative. it's not something which will easily be put into a spreadsheet.”
Dr. Sharpless worries that the info acquired by companies like Flatiron won't be readily available to researchers.
But if the businesses manage to unravel the medical records problem cheaply, he said, “we’d wish to work with them to work out the way to liberate the info .”
Dr. Wagle is making data from medical records and patients’ experiences public as he gets them.
After 2 1/2 years, though, he's disappointed by how little there's to share.
The patient who inspired his project had a lethal sort of thyroid cancer.
She was expected to die for a few months. In desperation, doctors gave her a drug that by all accounts shouldn't have helped.
To everyone’s surprise, her tumors shrank to almost nothing, and she or he survived. She was an “extraordinary responder.”
Why? It clothed that her tumor had an unusual mutation that made it susceptible to the drug.
And that got Dr. Wagle thinking. What if researchers had a database that might allow them to seek out these lucky patients, examine their tumors, and find out genetic mutations that predict which drugs will work?
And what about those that weren't helped by standard treatments? Could they be identified and spared treatments that will not work?
What researchers needed to be an enormous database that collected clinical and genetic data, alongside patients’ descriptions of their experiences.
Those narratives are crucial, Dr. Wagle said, but they're absent from the commercial databases like Flatirons.
Those comprise anonymous patient data, making it impossible to ask the patients themselves how they fared.
Dr. Wagle decided to create a database, starting with metastatic carcinoma, his specialty.
There are about 155,000 metastatic carcinoma patients within us.
He would use social media, online forums, and advocacy groups to succeed in bent patients for his or her records.
The Metastatic carcinoma Project began in October 2015.
Patients are wanting to join, and advocacy groups enthusiastically signed on. So far, the project includes 4,400 women.
Determining the genetic sequences of their tumors and of their healthy cells were straightforward — “the easy part,” Dr. Wagle said.
Gathering their medical records were another story. the info exists altogether kinds of formats, and crucial information could also be missing altogether.
Simply getting the records delivered, in whatever format, has been a nightmare. Records usually arrive as faxes or via mail.
“Even though the patients are saying, ‘I have consented for you to get my medical records,’ there's no great way to urge them,” Dr. Wagle said.
He hired half a dozen people to figure full-time on the project and corralled doctors and other experts to assist part-time. It can take hours to travel through one medical history.
Mary McGillicuddy, who works full-time on the project, explained the system.
When patients enroll, they tell the investigators where they were treated, where that they had biopsies, where that they had scans and were that they had medical procedures.
They give Ms. McGillicuddy and her colleagues permission to request their records.
Ms. McGillicuddy faxes requests for records to every clinic that treated a patient, or diagnosed or sequenced her cancer.
Startlingly, faxing “is the quality,” Ms. McGillicuddy said, for medical records requests.
The process is often frustrating. Fax numbers are often out of date. Some medical centers won't accept electronic patient signatures on the permission forms.
Sometimes, the medical centers just ignore the request — and therefore the second request. In the end, Ms.
McGillicuddy said the project gets fewer than half the records it requests.
Then comes the laborious task of extracting medical information from the records and entering it into the database. A faxed medical history is maybe 100 or 200 pages long.
So far, the carcinoma project has received 450 records for 375 patients.
(Each the patient tends to possess quite one record because the ladies typically are seen at quite one center .)
“Patients are incredibly engaged and excited,” Dr. Wagle said.
except for the records the problem, “right now there isn’t an honest solution.”