David Bailey

Creating a Medical Record Exchange for Research

Google's Sergey Brin and Larry Page recently dismissed healthcare research in America:

Generally, health is just so heavily regulated. It's just a painful business to be in. It's just not necessarily how I want to spend my time. Even though we do have some health projects, and we'll be doing that to a certain extent. But I think the regulatory burden in the U.S. is so high that think it would dissuade a lot of entrepreneurs. -- Sergey Brin

I am really excited about the possibility of data also, to improve health. But that's-- I think what Sergey's saying, it's so heavily regulated. It's a difficult area. I can give you an example. Imagine you had the ability to search people's medical records in the U.S.. Any medical researcher can do it. Maybe they have the names removed. Maybe when the medical researcher searches your data, you get to see which researcher searched it and why. I imagine that would save 10,000 lives in the first year. Just that. That's almost impossible to do because of HIPAA. I do worry that we regulate ourselves out of some really great possibilities that are certainly on the data-mining end. -- Larry Page

However, creating an exchange like the one described by Larry is possible. Let's start by evaluating the interests of the different parties involved:
  • What do researchers want?
    • Researchers want access to medical records. Ideally, they want easy access to a large quantity of diverse medical records. And they want patients to trust them.
  • What do patients want?
    • Patients want their medical records to be private and protected. And they want researchers to be able to better help them.
  • What does the government want? (Because the government always seems to be involved in others' business.)
    • The government wants everyone to follow the rules (HIPAA).

Both patients and researchers understand they fundamentally need each other to succeed.

Next, as with any project, let's look a how research currently works. Large university medical centers treat lots (millions) of patients per year. These patients' medical records are just now being stored electronically. Researchers at the university can create studies and request medical records. These studies have to first be approved by the university's Institutional Review Board (IRB) before the researcher is allowed access to the medical records. The researcher then performs his or her study and can publish the results.

So, what are the problems with the current system? Like Sergey and Larry said, there is a lot of red tape. Any changes to a study have to be approved by the IRB again. Most universities are limited to just one hospital or a few hospitals. This means they have a limited number of patients, a limited geographic sampling of patients, a limited set of standard treatments, etc. These limits hinder research studies. Also, typically only researchers at universities have access to the university's medical records. A brilliant private practice doctor would have to partner with a university. Multi-university studies require a sponsor at each university and a review by each university's IRB. As you can see, large scale research projects don't happen easily.

So... How do we fix the problem?

We need to create an exchange (data warehouse) for patient records. But where will those records come from? They can't come from the doctors, hospitals, or universities. Those are all regulated by HIPAA. The records must come from the patients themselves. Here's how:

  1. As mentioned above, everyone's medical record is becoming an electronic record. Patients have a right (under HIPAA!) to request a copy of their medical record from their doctor or hospital.
  2. Patients can then take their medical records and upload them into the exchange. The exchange shows them everything they are uploading. It requires the patient to remove some identifiers (name, social security number, etc.) and allows substitutions for other identifiers (home address will be converted into just a zip code). However, the patient has the ultimate approval for what information is uploaded. They can also enter information not in their medical record. For example: How often do you exercise? What do you eat? What do you do for work?
  3. The warehouse stores this information in a consistent, secure manner.
  4. Researchers create accounts with the exchange. They have to provide their medical license information and go through a training program.
  5. Researchers can then create studies, provide a description of the study, and request data. Patients can auto-accept requests for their data, or they can require their approval for each study. The exchange might impose a limit on the amount of data a researcher could request in a time period. Each request is logged in the researcher's account and the patient's account.

Patients can delete their accounts at any time. However, once a researcher has accessed their data, it cannot be revoked. The exchange could charge researchers for each study and pay patients for their records. The exchange could be created as a for-profit company,but patients would be more willing to upload their records to a non-profit. The exchange could also be used by researchers to recruit patients for their clinical studies.

This framework still needs a few tweaks, but it has huge potential. There are issues, technical and legal, to overcome, but they are not impossible.


Reply to this article.


Email Me Photography Delicious Facebook Flickr 43 Things Github Instagram LinkedIn SummitPost Twitter Yelp