CureTogether was started in July 2008 as a way for patients to aggregate their anonymous medical data into an open-source database that can be used by any researcher in the world. They started with three conditions – migraine, endometriosis, and vulvodynia but now count more than 400 on their radar.

There are plenty of precedents to social networking websites for patients, so nothing new from that perspective. But as I read more about this one, it stood apart. The idea of a patient collective focusing on obscure, lifestyle-affecting, painful, chronic and under-researched diseases  and making their raw data available is pretty cool. This WSJ article talks about trend of ‘Personal Informatics’ emerging- where affected individuals obsessively record everything about their life and share it with others. This may usually sound useless and weird, but given the fact that there is no definitive causal understanding of conditions like migraine (even though it affects millions of Americans each year), I find it novel and exciting.

I like this bottom-up, organic approach to furthering research on obscure conditions. Their call for Open-Source Health Research is also an interesting read.  Bit worried by the fact that CureTogether is self-funded. Hopefully they will stay around long enough to claim a large-scale success for one of the diseases.

The US healthcare system has spent decades digitizing clinical documentation and records. Now that most of the data generated during a patient visit is capable of being stored in some electronic manner, the next logical question becomes ‘what do we do with this data?’. There are an increasing number of startups recently that attempt to answer that specific question. 360Fresh uses data-mining technology with the same objective.

Believe it or not, a lot of electronic medical record archives today consists of documents in free text format- no structure or organization, just vanilla narrative text. 360Fresh uses their proprietary data-mining logic to extract meaning from that. Generally speaking, I think there is potential for such offerings; especially when presented in a focused manner. For example, a service that identifies high-risk patients in ED or Labor & Delivery patients could be enormously useful for hospitals. And ‘risk’ can go beyond just clinical perspective, like this vendor that focuses on malpractice risk. And if its near real-time data-mining based on output from existing systems, even better.

Of course, ideally we would want  (and expect) such intelligence to be inherent in the multi-million dollar enterprise Healthcare IT systems that hospitals buy to record the data in the first place. But most of them are either distracted by industry fads (like RHIOs or Comparative Effectiveness) or bogged down by existing product support to innovate in this direction.

David M. Eddy, MD, PhD is a legend when it comes to Evidence-Based Medicine. He coined the term in 1980s, actually. Being exceptionally skilled in mathematics, it was perhaps natural for him to apply it to medicine. The result is Archimedes Model- a mathematical simulation of the human physiology and how it interacts with healthcare interventions.

A more loaded one-line description of Archimedes (taken from his original paper in 2002): “It’s an object-oriented, continuous-time, full simulation model for addressing a wide range of clinical, procedural, administrative, and financial decisions in health care at a high level of biological, clinical, and administrative detail.” Phew. I’ll confess that I don’t know what exactly is under the hood. But I know enough about the informatics field to believe that this approach is viable and very exciting.

This YouTube video explains how the model can be used to run virtual clinical trials. Kasier has already backed the findings of Archimedes to change their diabetes care delivery.  I think there are fantastic, unlimited opportunities for applying such a fundamental model to medicine- personalized health predictions, public health, health policy, cost-effectiveness and what not.  As a startup, they are doing fine. With an impressive list of partners/clients, and a $15.6M RJWF grant (2007), they have a good runway and momentum. They have all the right ingredients to be a change agent for next-generation Healthcare IT.

Google.org’s flutrend is an attempt to model flu activity across US based on the search terms that Google.com users enter around flu symptoms, treatment etc. The underlying premise is that there is a relationship between how many people search for flu-related topics and how many people have flu symptoms. Think of it as a virtual public health surveillance proxy. If you are not convinced that this is a brilliant idea, take a look at how their analysis relates to CDC reporting.

In case you didn’t know, Google.org is the philanthropic arm of Google, and it was formed with the commitment of 1% of Google.com’s profits to address some of world’s most urgent problems (read the famous 2004 IPO letter by Larry and Sergey where they mention it). The site humbly admits that the Flutrends system is experimental. Nevertheless, it’s impressive that in some instances Flutrends was actually predicting flu before CDC.

Of course, not all people who search for flu have flu necessarily, but the power of this analysis comes from the coverage and promptness, not the granular accuracy. The basic idea of harnessing the collective thought (a.k.a. search needs) of the population to predict/monitor health events is fantastic. And this is just the beginning, IMHO. When a population is connected real-time and discussing what they think/want/need, abstracting that information can yield powerful insights- not just for prediction and monitoring, but for most aspects of healthcare (diagnosis, prognosis, news, followup etc).

The concept is applicable to domains outside of healthcare too. Take twitter for example. Twitter is another platform with mass adoption where people are having real-time conversations about what they are thinking/doing. Just look at what intelligent twitter mashups did for getting real-time snow report of the Feb’09 storm in UK or the Dec’08 Ice Storm in New Hampshire. There are health related examples too- the feb’09 salmonella-in-peanut-butter recall could be tracked promptly on a Twitter feed (btw, this slideshare presentation by PF Anderson at the University of Michigan explains ‘Twitter for Health’ in detail. Thanks to Christine Gorman for the link).

Healthmap is a perfect example of what technology can do to adavnce healthcare information. It aggregates online media reports to enable infectious disease intelligence on a global level. Its a near real-time internet-based infectious disease surveillance that is free from political and geographical restraints.

Healthmap extracts real-time information from more than 10,000 sites every hour and text mines them for disease and location patterns using bayesian filtering. The interface is clean and intuitive mashup with google maps. Links to the source of alert and a ‘heat index’ (composite score for each incidence based on things like recency of alerts, number of sources etc) are provided.

There are limitations too-  dependance on other sources, unstructured text, lack of integration between sources, not comprehensive, etc. But if you think of it as a free resource that supplements existing public health systems, its a great asset for general public and clinical professionals.

Physician Connect is a new community area on Medscape that allows physicians to securely engage online with other physicians in discussions on clinical as well as non-clinical topics that are relevant to the practice of medicine. The site was launched early this year, and is claimed to have gathered 20,000 registrants since (according to their Q1 FY08 Earnings Call Transcript). I guess that is enough for them to call themselves “…the largest online community of physicians and healthcare professionals today”. Why bother with modesty or proof.

The business idea is to mine the community generated data and monetize it by letting sponsors directly participate and gain real-time insights into physician attitudes and perceptions. They provide online CME (free), journal articles and news/meetings/conference coverage. The standard WebMD fare of Medscape Drug Reference, expert columns and interviews are included too.

PatientsLikeMe is a social networking site that enables patients to share information around disease conditions. It was started in 2004 by concerned family members of an individual with ALS (Lou Gehrig’s disease). Users can register for free and interact around eleven conditions: ALS/Motor Neuron Disease, Anxiety, Bipolar, Depression, HIV/AIDS, Multiple Sclerosis, OCD, Parkinson’s disease, PLS, PMA and PTSD. For a site focused on limited number of disease conditions, they get some serious traction:

PatientsLikeMe enables affected individuals to find others with similar condition, share experiences, and learn what works and what doesn’t. Users can also track their progress and keep up with relevant research. The knowledge of first hand information about a disease experience, treatment effectiveness or side effect is very powerful for managing these complex multi-system diseases.

Needless to say, the rich data generated by such a focused and engaged community is invaluable for research. So no surprise that one of the revenue models behind PatientsLikeMe is the sale of anonymized data from and permission-based access to their user community.

Sermo is a free online community restricted to verified US physicians. It was founded in 2006 by Daniel Palestrant. Although its not the only one in this niche, Sermo has managed to get plenty of press and continuous funding ($3m in 2006, followed by $9.5m and $26.7 in 2007).

So what is special about Sermo? For one, it has been forming all the right partnerships. Take its alliance with the country’s largest physician organization (AMA), collaboration with pharmaceutical giant Pfizer and the agreement with main regulatory authority FDA. Second, it’s been successful in getting traction from a very fickle and tech-resistant group of prefessionals- physicians. Their compete.com report is pretty impressive:

The site claims 65,000 users and generates revenue by charging outsiders for access to the community. The data generated by physician interactions around medical events, treatments, observations, opinions provide valuable insights to commercial organizations. The ‘information arbitrage’ model, as Sermo calls it, is shown below:

Sermo is not alone in trying to aggregate and monetize the lucrative US physician community. Docsboard, SocialMD, DoctorNetworking are others in the game. There is competition in adjacent spaces too: NurseGroups, NurseLinkup are focusing on the registered nursing professionals, StudentDoctor.net focuses on medical students. Even finer niches like women in medicine are online (MomMD).