Personalized Medicine – Processing Millions of Health Data Points

“When you go to the doctor’s office and they do a blood test, they typically measure no more than 20 things. With the technology out there now, we feel you should be able to measure thousands if not tens of thousands if not ultimately millions of things. That would be a much clearer picture of what’s going on.”

This quote comes from a fascinating article by Jon Cohen called, “Examining his own Body, Stanford Geneticist Stops Diabetes in Its Tracks.” The idea is simple, but extremely powerful. I think it also paints a clear future for healthcare.

Michael Snyder is right that we need to have tens of thousands and ultimate millions of data points to be able to really effectively treat the human body. When I start to think about this, it actually makes me proud that the medical profession can treat a patient as well as it does with such limited information. Yet, it also gives me great optimism that the best advances in healthcare are still ahead of us.

As I’ve mentioned multiple times before, I believe that the body of medical knowledge will become too complex for the human mind to process on its own. In fact, we might already be there today. When you add in thousands and eventually millions of additional data points, then no one could even start to question this idea.

How then will we be able to process all these data points? Despite the human minds amazing characteristics, it will have to be assisted by technology. The human mind won’t likely be taken out of the equation, but computing power will assist the human mind to make much better decisions.

One problem with this idea is that the EHR software of today aren’t designed to handle this type of processing. EHR software is the database of healthcare and some might say that’s even a stretch. Does that mean that we’re going to have to deploy a new wave of software and technology to support this type of smart healthcare data processing?

About the author

John Lynn

John Lynn

John Lynn is the Founder of, a network of leading Healthcare IT resources. The flagship blog, Healthcare IT Today, contains over 13,000 articles with over half of the articles written by John. These EMR and Healthcare IT related articles have been viewed over 20 million times.

John manages Healthcare IT Central, the leading career Health IT job board. He also organizes the first of its kind conference and community focused on healthcare marketing, Healthcare and IT Marketing Conference, and a healthcare IT conference,, focused on practical healthcare IT innovation. John is an advisor to multiple healthcare IT companies. John is highly involved in social media, and in addition to his blogs can be found on Twitter: @techguy.


  • John,
    I don’t think the processing has to be done within the EHR software. However, we need better means of connecting the EHR data and genomic/personalized data repositories.

    The “big data” analytics that are already being used in retail and financial services serve as a good model–although let’s hope that the healthcare consumer has greater access to the data that are collected, as well as the ability to contribute data.

    That said, I agree that EHR software in general has to evolve from its current limited functionality to a more integrated tool within the research and clinical systems.


  • Janice,
    I agree that the processing doesn’t necessarily have to be done with the EHR software. In fact, the idea of EHR as the database of healthcare means that it likely won’t be done there.

    What the EHR does need to do is provide the information so it can be processed. Plus, it needs the capabilities to provide the processed data results to the doctor.

  • Someone I know gets a quick blood test once or twice per month. One drop of blood pricked from a finger. It gets sucked up into a tiny machine, and a minute later, there is a print out of a group of critical blood related numbers. A copy of that sheet gets added to the patient’s very thick medical file folder. No online storage, no long term analysis, no matchup of readings to related treatments, no way to determine if certain alternative treatments that had been tried really had an effect, all because none of the data gets sucked into a viable EHR. IMHO, moronic. Especially considering that the illness in question is one about which nowhere near enough is known or understood. A connected EHR that had data like this could make a huge difference just for the patient, and if this data were collected on many patients could have an even bigger effect.

Click here to post a comment