Isabel Healthcare

In July 1999, Jason and Charlotte Maude started Isabel Healthcare after their then 3 year old daughter Isabel was nearly fatally misdiagnosed during a hospital stay. They involved clinical experts to lead the research and development of a pediatric diagnostic decision support system, and in June 2002 Isabel diagnostic tool was launched. The tool that helped clinicians generate differential diagnoses and then narrow down to the most likely, based on provided clinical information like signs, symptoms, labs and history. It started with pediatric-only diseases, but expanded to adult version in January 2005.

Isabel’s solution is based on sophisticated pattern-recognition technology from Autonomy, a huge pure software company based in UK. The powerful Autonomy engine is unleashed on a database built from medical textbooks and journal content, and claimed to have >100,000 documents covering >10,000 diseases. Think of it as a web crawler, that indexes authoritative medical text instead. The software’s strength lies in identification of the patterns that naturally occur in text, based on the usage and frequency of words or terms that correspond to specific medical concepts. Each diagnosis is assigned clinical weighting scores derived from expert opinions reflecting prevalence effects based on factors like age, gender, geography etc. The user interface incorporates Natural Language Processing to make the interaction more intuitive and easy for the clinician.

I’ve known about Isabel since 2007, and used it for a few months with very positive results. Was specially impressed with the software’s ability to handle free text, and the company’s openness to a peer-reviewed validation process in an effort to convince the medical community. It seems they have done a serious corporate make-over in 2010: renewed website, cleared pricing and changed management (Interesting fact- ex-CEO Joseph Britto now works for Autonomy).

Autonomy announced a clear healthcare-focused initiative this month, called Meaning-Based Healthcare platform (perhaps trying to capitalize the current buzz around Healthcare IT Meaningful Use regulation). Strangely, there is no clear cut mention of Isabel on the AutonomyHealth website. Regardless, with the vast amount of unstructured data being generated in healthcare, technologies like Autonomy have a bright future.


Neurologic examinations are unique in medicine. Unlike other fields of medicine in which one can touch (surgery, orthopedics) or see the disease (eg, dermatology, ophthalmology), neurologic conditions often manifest in cryptic ways. Which is why simple clinical examination done with basic tools (reflex hammer, tuning fork, pin…) are always relevant for initial evaluation.

Touch Diagnostics is a small startup that has created four iPhone applications that provide a new way to administer some of the neurologic exams:

  1. Nystagmus is a  disorder with periodic rhythmic, involuntary movement of the eyes. One of the ways to test for it is by using a ‘Optokinetic Drum‘, which relies on the response of the eye to continuously moving pattern that has contrasting elements. Now the drum can be expensive and comes with real-world problems (storage, disinfection etc.). OKN+â„¢ is a simple app that replaces the drum for $2.99.
  2. In Finger Oscillation Test, individuals are instructed to tap their index finger as quickly as possible for few seconds, keeping the hand and arm stationary. It measures motor speed and helps determine particular areas of the brain that may be damaged. $2.99 DigiTapâ„¢ is replacement of older devices for this test.
  3. Reaction time is a simple measurement (in milliseconds) between the presentation of a stimulus and the elicited response. The results can be used to assess fatigue, concussion, sobriety, etc. ReActâ„¢ does that for $2.99.
  4. Tremors are unintentional movements, and sometime these micro-vibrations are too small to notice with naked eye. For $3.99, TremorTracerâ„¢ provides a way to perform some subjective tremor tests (like Archimedes Spirals in which patient tries to trace a line inside a spiral space)

Okay, so these apps are not exactly cut for the top 25 list on iTunes. And they may never gain traction amongst the myriad of health-related apps out there. The clinical value of doing these tests, although foundational, is also no match for a CT scan. A neurologist I spoke with was quick to point out that doing these test the old-fashioned way doesn’t take much time, and the results are not that crucial anyway (for clinical course of action).

Regardless, I like the way these apps cleverly digitize a small subset of real clinical tests even when the hardware (i.e. the iPhone) was never intended for clinical applications. There will be a time in future when these smart computing devices open up to third-party hardware add-ons like scopes or sensors- temperature, pulse oximeter, etc. Then this would be a valid and viable genre of applications. Till then, we need to ‘fit the test to the device’ rather than the other way around.


VisualDx is healthcare’s answer to the visual search trend led by companies like, etc. VisualDx helps identify dental and medical diseases by letting providers search for diagnosis based on how a disease looks and presents itself.

Rochester, NY based Logical Images is the company behind VisualDx. Understandably enough, it was founded by two dermatologists from University of Rochester in 1999. At its core lies a pretty big repository of clinical images (they claim > 60K) that are tagged with clinical metadata like symptoms, location, history etc. A user can browse through diagnosis domains or input findings to reach a relevant set of images.

There is a 15-day trial for non-enterprise users, and individual subscription pricing ranges from $49.99 (Pediatric) to $99.99 (Adult) for a year. Student discounts brings it down to a very reasonable level ($29.99 and $49.99 respectively) in my view. The company has leveraged their content to create an online consumer health resource called Skinsight. Besides the clever name, I really liked their slick ‘Skin Condition Finder‘ tool. Overall, it’s a smart approach for gaining market recognition and expanding services.

The concept of Diagnostic Decision Support (DDS) often comes with the implicit notion of text-based query, so I really like the ‘visual’ DDS approach. Dermatology, Pathology are obvious choices to implement such an approach and situations like ER, bioterrorism, infectious diseases are prime contexts since there is not enough time to engage a pure text-based knowledge base. Also, some conditions are rare enough that most practicing physicians and non-specialists haven’t actually seen one in real life. Other factors like dark skin, atypical presentation can be confounding. It’s handy to have a this as a medical education tool and as a care delivery aid in facilities where specialists are not available all the time.

I’m bit surprised why it’s not a widely subscribed resource in hospitals, public health entities, medical education and general EMR vendor products. Anyway, it’d be interesting to see this visual content embedded in other consumer tools (like iTriage, FreeMD) and enterprise offerings (Isabel Healthcare, SimulConsult, Curbside.MD etc.). Wonder which firms are competitors for VisualDx today…


Palpitations, dizziness, and fainting can often be symptoms of underlying heart disease. The key to the correctly diagnosing them is reliable documentation of the underlying cardiac rhythm when symptoms occur. Holter and Event recorders are the two noninvasive methods have been usually used to do such long-term ambulatory monitoring, but they often end up being insufficient or ineffective for various reasons (low yield, not long enough, etc.). In the recent few years, Mobile Cardiac Outpatient Telemetry (MCOT) term has gained ground, in part due to Cardionet’s products. MCOT is a viable alternative to conventional cardiac monitoring:  it’s real-time, portable and can be done over extended periods.

With that background, Corventis becomes an interesting entrant to the MCOT space. Their technology platform consists of a bandaid-size wireless sensor patch called (“PiiX”) that detects, records and transmits physiological data to a portable hub (called “zLink”). zLink is a cellphone-size device that sends the data over wireless network to ‘Corventis Monitoring Center’, which is a staffed to do preliminary interpretation and urgent physician notification. They offer these capabilities in two forms: NUVANT (ECG based continuous arrhythmia monitoring) and AVIVO (non-ECG physiological paramters monitoring). Corventis has some big venture names behind it: KPCB, Mohr Davidow, DAG ventures. They recently got FDA clearance for NUVANT in January 2010.

Cardiac diseases are certainly the prime target for any wireless remote monitoring startup. Corventis is not alone. iRhythm’s Zio Patch is designed to diagnose cardiac arrhythmia by providing  up to 14 days of continuous recording. Once done, the Zio Patch can be mailed back to the company for analysis. Unfortunately, the Achilles heel for all of these companies is reimbursement. So far, private insurance companies and CMS are not convinced that such services are worth paying for. MobiHealthNews has an interesting post about this trend here.

I’ve written about a number of consumer-oriented ‘wellness’ services by startups that are using wireless sensors to detect simple metrics like activity and help you achieve a healthy lifestyle. Corventis, iRhythm are good examples of medical-grade services utilizing the same basic technical framework and abilities for managing life-threatening conditions. Once we get over the barrier for reimbursement, you can bet on the remote monitoring market for serious medical conditions exploding. We can wait for that to happen, but I’m personally convinced that as consumers take more charge in managing their conditions (and health insurance continues to spiral the drain from a cost and outcome perspective), there is a growing scope for remote monitoring services that consumers will pay for themselves.

PS: I had a discussion with Corventis founder, Darryl Drinan a few weeks ago. He had three insightful comments for anyone thinking about getting into the remote monitoring space:

  • If you have a choice, focus on therapeutic service, not diagnostic
  • Product alone is not enough, always tie it to a service
  • Patient education is a big problem (if you need to do it for them to use your device, you are hosed)


iTriage is a mobile app that helps users understand, prioritize their acute health-related symptoms and seek appropriate and close-by care. Its service is also available on the web at iTriageHealth.

At the core is a symptom-checker that lets users do a high-level categorization of what could be wrong with them, and how serious/not can it be. That functionality is nothing special, since there are multiple services that do that both online and mobile. Also included is a nationwide directory of care facilities (including urgent care, retail clinics, pharmacies and physician offices) and nurse advice phonelines (sorted by insurance provider). Your smartphone knows where you are, so the neat service is to be able to find directions to the nearest facility with few clicks. It may not sound like much; but when you are away from home, it’s pretty useful to be able to quickly figure out the nearest urgent care or retail clinic. iTriage is also trying to take this service to another level with the addition of ‘ER wait times‘ functionality in select cities. That way a user can further filter out the facilities based on wait times. Even if this is not really present/reliable in your area today, I think it’s a brilliant extension of a service like iTriage. Because its not a question of if this will be useful, but when. Once there is a critical mass of hospitals in an area submitting their ER-time feed to iTriage, the rest will find it hard not to do the same. There is a need for public to have a near real-time pulse on ER utilization, and services like iTriage provide a good platform for it.

The other interesting aspect is their partner service integration. Healthgrades provides the physician/hospital quality reports within iTriage, although users need to pay to get info beyond minimal basic report. Teladoc provides the 24×7 physician advise service (its phone consultations are for under 40$ mostly). They also partner with a claims adjudication organization (name?) that helps consumers negotiate thier medical bills. One can argue that a lot of the above functionality can be accomplished with a mobile browser or search app. But the value-add of a dedicated app is to provide fast, context-relevant info and be a steady companion as the user traverses the acute healthcare system.

I heard Paul Hudson, MD (co-founder) speak at the Mobile Health 2010 conference last month. He used an intriguing term to describe their technology: “symptom-to-provider technology”. Guess that is one way to think about a IT service that holds your hand from beginning to end of an acute care episode. He placed iTriage in the “multi-billion $ self-referral market”, and gave couple of interesting factoids about it’s current utilization:

  • Around 89% iTraige members are commercially insured
  • It’s use has gone beyond Emergency care in some cases- people have used the Healthgrades info to switch providers

Both of those underscore the fact that consumers need a trusted guide in handling how they interact with the acute care system. ERs, Urgent Care centers are the way most people experience care delivery most of the time, and having insurance doesn’t really help in making a good choice. With mobile phones getting smarter, the ‘self-referral’ market is ripe for innovative services.