Apixio is one of the few startups tackling this issue. Their analytics engine indexes the underlying data, processes queries and provides context-relevant results. The core technology is supposedly based on Apache’s Pig (a data-flow language and execution framework for parallel computation), Hadoop (a framework that allows for the distributed processing of large data sets across clusters of computers) and Cassandra (a scalable multi-master database).

There are a number of terminologies (read ontologies) in healthcare, trying to specify the concepts and relationships from a particular perspective. LOINC, ICD, SNOMED, CPT are common examples, but see a pretty comprehensive list of all human-related ontologies at BioPortal (filter by category ‘Health’).

So a medical-grade search service offering would need to traverse such terminologies and surface all relevant, normalized data related to the query. For example, a search for keyword “breathlessness” in a patient with long, complicated medical history would bring up documents and encounters that mention items like wheezing, PEFR, smoking, asthma management. It’s no short order to do all that analytical crunching.

Sophisticated data transformation and abstraction offerings are certainly needed for making sense of complex healthcare data. Niche efforts like Apixio, 360Fresh, are signs of growing market realization that the era of just trying to digitize healthcare data is getting over. Now we start figuring out what the heck to do with all the incoming bytes.

PS: Advanced analytics offerings in healthcare are an interesting topic. See this wiki page for a living list of relevant companies in this space.

The website is not currently recommended for clinical use- mainly because the images have not yet been verified by pill manufacturers. Still, it’s a smart tool that can benefit multiple care settings. Many seniors coming through the emergency room and clinics don’t remember the name of their pills, but can recall its visual characteristics. A tool like this can be a great addition to EMRs and even PHRs.

September 2010 Update: Found out that the Epocrates free mobile drug reference app has a “Pill ID” feature which shows pictures of what the pill looks like. Wonder if those are the same images as the NIH pillbox.

Practice Fusion’s is free. Free software, free hosting, free service. It is  supported by ‘non-intrusive’ ads. They have figured out a way to utilize Google Adsense APIs in a way that is compliant with HIPAA, i.e. doesn’t adversely affect patient privacy. Their CEO said in a 2007 interview that Practice Fusion will provide advertisers with basic demographic information about the physicians who view the ads – such as their city and specialty – but will not reveal names. If the users don’t want ads, they have an option to pay $100/month/provider to make them go away. As for the lineage, the company is backed by SalesForce both in terms of investment and advisory board. I guess that is where they inherit the ‘online, real-time, risk-free, on-demand’ marketing message.

I’m an absolute fan of free software, and believe in the utopian dream of free, ubiquitous EMRs. But I scratching my head on how exactly does an EMR work with an ad-supported model. Fact 1 – Doctors (esp. private practice) doing electronic documentation want to minimize distractions and click on as little items as possible. Fact 2 – Google Adsense sends you a check only if the users click on an ad. Those two facts are contradictory. How many doctors in their right mind will take time out in the middle of care delivery to click on an ad? I’ll bet none. Not many will pay $100 either.

There is some evidence that they charge some unpublicized fees ($50/month/provider “support” fee according to this commenter at another blog Note: Updated: See Emily’s comment to this post).  Practice Fusion claims their user base is now up to 18,000 and they are the “fastest growing EMR” but those sound like marketing tactics rather than hard facts. For example- This press release says that they are “fastest growing ” with 1300% growth rate. Well that is perhaps because they are comparing two convenient times – in early 2008 they had about 1000 users, and in early 2009 they had reached 13,000.

I’ll try not to judge them based on unverified complaints and odd press-releases, but I seriously doubt that good, competitive Healthcare IT software and it’s support can be sustained solely on the basis of only an ad-supported model.