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.

Companies like Cellnovo represent the key role IT is playing in the evolution of medical devices. UK-based Cellnovo began in 2002 as Starbridge Systems Ltd. to develop a novel micropump with only one moving part that made it smaller, more accurate and less expensive. Somewhere along the line, their conventional medical device transformed into a mobile health offering. It now consists of:

1. Pump: A small, waterproof device that can be easily applied, removed, and repositioned on the body. Also includes a built-in accelerometer that registers and stores user activity data.

2. Handset: A hand-held device that communicates wirelessly to control the pump and sends data to a secure website. User can manage dosage, schedule, log supplemental data like food intake, activities, emotions, etc. through this device. The look-and-feel has been compared to today’s appealing smartphones with icon-driven intuitive graphical display and touch screen ability.

3. Online: Websites customized for various participants that are usually involved in managing diabetes- provider, patient, caregivers, etc. Given the variety of people that can be involved in the care team (primary doctor, dietitian, diabetes nurse educator, eye doctor, foot doctor, endocrinologist, exercise trainer…), communication and coordination is an often under-served part of diabetes management. Seems like Cellnovo Online is an attempt to improve just that.

The overall concept is not new. OmniPod by Insulet Corporation (a public company) has a pump and handset. Big players like Medtronic, Sanofi-Aventis, J&J have shown signs of moving in similar direction. With the February 2011 series B financing round of $48.4 million, Cellnovo also seems to have enough runway in this space. As an interesting aside, combining insulin pumps with Continuous Glucose Monitoring System (CGMS) makes a terrific combo- uninterrupted sensing and coordinated, intelligent drug delivery. OmniPod does this.

Solutions like Cellnovo provide not just a way to deliver therapy, but a novel way to collect detailed data about given patient population. Analyzing aggregate data like that can lead to insights at multiple levels- clinical evidence (EBM), provider performance, population health, etc. An interesting decision fork in this evolution would be whether manufacturers leverage commercial computing hardware like smartphones or create their own (like Cellnovo). The former gives wider reach, while latter provides better, medical-grade control (something that FDA probably mandates).

But the key point in all this is about the future of traditional consumer medical devices. The next-generation devices seem to be less conspicuous, continuously connected, more personalized and come with an integrated online component that becomes the window to interaction with multiple parties (caregivers, friends, insurers…like an evolved, niche form of social networking). The new value proposition doesn’t stop at just a hardware device, but becomes a continuous service for managing chronic disease.

One can argue that managing all chronic diseases requires understanding an ever-changing constellation of information continuously generated by a whole ecosystem of participants. This ever-connected disease management approach that removes the burden of keeping journals and pushes information to healthcare professionals can to be applied to many diseases besides diabetes. I’m sure a number of those are already underway.

In an effort to understand what is unique about Zumi Life, I stumbled upon this interview with its CEO. Crunchbase tells me that they started with $700k seed funding in 2007 and got a Series A infusion of $1M in April 2008. With that context, several questions come to mind. Zume Life needs manual input for all the data it needs from the user- and that assumes the user to be reliable enough to put it in. If Zuri had a sensor to automatically capture the critical vitals (like Zeo, Bodymedia, DirectLife, FitBit, LifeShirt and scores of other devices), that would make it infinitely more useful. But I understand that there is no automatic sensor for your mood or for what you just ate, so somethings need to be captured manually. Which is why there are services like RememberItNow, Reqall, Zealog, Polka etc. Still, why not get the medication list for Zuri from PHR platforms like Google Heath? If we assume that the chronically ill and overworked individual remembers to input their care regimen in one place, why wouldn’t they use a simple paper sticky note or a smartphone reminder app? Even a simple Google Calendar or 30Boxes event can be configured to deliver reminder emails that show up as audible, sms alerts on your phone. So is there really a need for a dedicated hardware device in a world that is slowly converging mobile computing platforms? Zuri reminds me of the device that is made to do twitter only.

The price tag was also a bit of surprise. Although there is no official mention of pricing on the Zume Life website, I found a PCmag article from Sept’09 that quotes $35/month or $300/year for the service, and $4.99 for the iPhone app. That sounds way too much money for a basic alerting and journal-keeping service that is 100% manual entry based.

Of course, it’s easy to criticize others idea. I don’t have the complete facts on the service, its utilization and its founder’s vision. The overall trend of using patient-oriented hardware devices integrated with web and mobile dashboard/analytics to manage chronic conditions is for real. I just think sensors are a key aspect of such devices and that pricing can be Achilles heel for adoption.

Early 2010 Update: ZumeLife has closed operations and is no longer in business.

Zeo system consists of a wearable headband that measure brain’s natural electrical activity. Although their blog has a high-level explanation of how it works, my understanding is that its a single-channel EEG, which seems to be a reasonable way to do sleep analysis in healthy individuals. That data is wirelessly transmitted to a bedside display and stored on an SD card.

Algorithms based on proprietary logic churn out a personal sleep score (called ZQ) to quantify the type of sleep you get. The display unit looks like a bedside alarm clock and shows current and past 2 weeks worth of sleep analysis. Also has some smart alarm clock features like SmartWake alarm that wakes you up at the most suitable time within half-hour of set time. You could upload the data to an online sleep journal through the SD card. The website gives graphs, trends and the ability log other supplementary lifestyle data that can affect your sleep. All that for $249. An additional $100 would get lifetime access to a personal sleep coaching program, which includes regular assessments, goal tracking, email tips etc.

There is no question that Sleep Science is a serious, mature field. Zeo can find its place as a useful adjunct for plenty of sleep-related disorders that affect people who are otherwise healthy. It’s not an FDA approved 11 channel medical grade polysomnogram, and it’d be a mistake to compare it to one. It’s perhaps a closer analog to Actigraphy where a wearable sensor measures overall motor activity during sleep. An actigraph unit is an accelerometer based device like the FitBit, WakeMate, SleepTracker or Axbo.

Accurate or not, Zeo is yet another proof that healthcare is slowly being transformed by sensor-based, portable devices that are capable of analyzing data in a consumer-oriented way to enable individual patient to manage their conditions better.

April ’10 Update: I ordered a Zeo from Amazon in March’10. Been using it for couple of weeks now. The hardware looks and performs well, but I have my complaints. The sensor in headband is bit bulky to sleep with, and I don’t think I’ll get used to the headband anytime soon. The fact that I need to replace the sensor pad every 90 days feels like a hidden cost (they are $24.95  for a pair without S&H) that was not disclosed completely in the marketing.

Software-wise, it’s bit less intuitive than I expected. I’m still wondering what the data tells me. I know Z-score is a overall indicator, but what about the breakdown? Are my 49 minutes of deep sleep enough?  The fact that I woke up 7 times – is that normal? In the end, I’m asking the question- what does this $250 device do for me…  Probably not much because I’m not the target audience for it. People suffering from sleep disorders would perhaps be more receptive.

May’10 Update: Returned it. Sorry Zeo.

June’10 Update: Learned about the Zeo API. Mobile fitness companies RunKeeper and Daily Burn are the first to integrate their services with Zeo. Neat strategy to promote it as a platform.

July’10 Update: Found out about NeuroVigil: another startup in the sleep-monitoring space. Their technology is also based on a single-channel EEG wireless sensor. They claim to be able to send the data (and its analysis) to any mobile device. NeuroVigil’s founder, Philip Low gave an interesting talk at TEDMED in 2009.

Nov’11 Update: Noticed that Zeo now has a cheaper, smartphone-based mobile ($99) solution and original clock has been re-packaged as bedside solution ($149). Smart move, since it makes them more relevant in comparison to other solutions like EASYWAKEme the market.

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.

At the heart of the model are a set of ordinary and differential equations that represent the physiological pathways relevant to diseases and their complications. The ‘variables’ in this model include signs, symptoms, patient behaviors (including adherence), provider behaviors, provider performance, encounters (e.g.  ER visits, office visits, admissions), protocols, guidelines, tests, treatments, etc. Basically, it tries to incorporate all aspects of diseases and healthcare system that are needed to analyze downstream clinical outcomes, utilization and costs.

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.

Jan 2011 Update: The FDA and Archimedes entered into a research agreement to understand the benefits of weight loss compared to the long-term risks of cardiovascular outcomes in patients treated with weight loss drugs.

Given the fact that Adverse Drug Effects (ADE) are one of the leading cause of death in the US, there is significant market opportunity in consumer education and support around it. Couple of nifty features that I like:

• Direct meds import from Healthvault
• Community Knowledge Base – an aggregation of information and experiences from people who are on multiple drugs. This feature is currently in private beta, but I think that it can be a great revenue opportunity once it gets some traction in terms of number of users. There are plenty of pharma companies who would pay good money for getting early (even though informal) insight into side-effects, efficacy, interactions, and usage patterns of their drugs.

Seems like they are planning to integrate with DestinationRx and Polka, which is a good idea since the traffic from those sites will already be primed for the services that PharmaSurveyor provides. The advisory board has some significant names, including Barney Pell, Matthew Holt and Mark Musen.

They do have some interesting marketing techniques like analyzing celebrity cocktails, not requiring registrations, etc. Business model seems to be only google ads for now, which is no surprise given their research-oriented background. The site is more a proof-of-concept for the underlying technology (although I’m not sure what it is exactly). It’ll make a lot of sense to integrate this service with commercial CIS offerings, and take it one step beyond just using RxNorm.

Aug’10 Update: PharmaSurveyor service changed its name to SurveyorHealth. Now they also offer mobile apps for iPhone and iPad.

What a great startup idea. Service demand can be tapped easily since users are searching the web for highly specific keywords (almost all include the keyword “trials”, so bit of SEO and keyword advertising would direct the traffic effectively). Other sources are the rapidly growing PHR platforms like Google Health and Microsoft Healthvault- both encourage developers to write apps that provide such value-added services based on user’s health information. Supply is readily available on ClinicalTrials.gov, a government-sponsored online public registry of clinical trials in US.

TrialX.org is completely free for users (patients). They let investigators create free accounts to post their trial information directly, but charge a fee for providing access to the interested potential trial enrollee. It’s hard for trial investigators to find eligible patients who are motivated to stick around for the complete trial. TrialX solves both the problems for them.

Imagine the possibilities if this service gets integrated into CIS vendor products. A patient coming in for advanced  breast cancer treatment can be flagged right at admission and be given the option to enroll in an experimental drug trial right then, if they so choose. If nothing else, it’ll give the medical research community a much more real-time opportunity to advance the science.

September 2010 Update: Just read about another startup in the same space- MyTrus. They have little information on their website, so not much to discuss at this time.

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 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.

They have various analytical graphs and trends, messaging, mobile edition and even twitter integration. I think the concept would have been much more powerful if there was a way to eliminate manual data entry by patients. So integration with blood glucose monitors that can sync data to the website would be great- perhaps using platforms like Healthvault?

Side note: Diabetes is perhaps one of the most well-represented diseases online. There are a ton of resources out there- David Mendosa has a good list here.

The ides has potential. GPS-based real-time meal recommendations based on your daily intake requirements and goals can be a simple way to stick to healthy eating habits. Webdiet also has a feature where you can order your meal in advance through your mobile device. Not sure about their coverage though- feature like these need to have granular, wide geographical coverage before they can be found useful by users. Maybe we will see some social networking features in future (who is eating what in your network? Geez..).

They are currently in invite-only beta, but have plans to launch on a freemium model early 2009 (so you can join and get basic service for free, but it’ll cost you to upgrade to a preimum service with more features).

September 2010 Update: WebDiet seems to be a part of the publicly-traded Nutrisystem, Inc. now. Can’t find any past news about an acquisition though.

ClearSense aims to help you make sense of your health information by providing the data analysis technology called REDBOX (developed at Bioinformatics Research Center at the Medical College of Wisconsin). I couldn’t find any information around what exactly makes REDBOX unique- it seems like it consists of data analysis models and algorithms that are optimized for health related data (although the devil is in the details for a technology like this). The company behind both of them is Point One Systems, which seems to have spun off from the Research Center.

The sample reports look Web 2.0-ish, with simple interface and layout. The actionable items and alerts are clearly outlined along with tips and educational material. I dont have enough health information in my Google Health account (fortunately I’m in the pink of health) so there was not point in taking ClearSense for a spin on my info.

Although there is minimal info about ClearSense’s unique selling point, the overall concept may actually prove to be useful if/when PHRs take off in future. Hopefully, ClearSense will survive to see that day.

August 2010 Update: Clearsense doesnt exist anymore. Neither does Point One Systems. Oh well.