Friday, May 31, 2013

Forward Movement

I recently received an email, the contents of which are shared below:

CONGRATULATIONS!

You have been nominated by Andrew Rens to receive a Shuttleworth Foundation Flash Grant to work on your CrowdSourced Dermatologic Picture Database. We have a funding model that rewards brilliance and new ideas by awarding full-time Fellowships. However, bubbling around
the periphery of our model it has become clear that there are voices that are not heard, ideas not seen and Fellows that are not ready to be Fellows - just yet... This is where you and the new Shuttleworth Flash Grant come in.

We tasked our Fellows to seek out and nominate an impressive change agent, who may not be able to concentrate on their brilliant idea yet. This grant is for the sum of $5,000 and will be awarded to you personally to bring that idea forward. The only string attached is that we ask you to live openly, tell us and the world what you have done with the money.

_______________________________________________________________________

I am very thankful for the opportunity. This pilot financing will be used for website development and beta-launch. The bottleneck up to this point has been mobile and web development. The goal is to use as many open-source platforms as possible in order to limit cost and because the project speaks to open-source values.

Concept for Open Source Dermatology Database
The pilot grant will be used for the development of a platform (website-mobile if finances allow). The platform will be used to facilitate the proof of the following idea: An global online community of non-professionals can effectively create a database of dermatology skin pictures of sufficient accuracy and volume such that it will produce a database that is more valuable compared to current proprietary databases. One unique value of this project is that the product – the database with tagged skin images will be made available under a creative commons data license to all. The data represents a collection of global biological information. The project is trying to use the website as a platform for sharing this knowledge in the form of skin pictures.

This has never been tried before, in quite this way. Patientslikeme.com enables the sharing of patient contributed information, the angle is more from a patient support group perspective. Another uniqueness for this project is the idea of the medical community inviting wisdom and participation from patients. The openness and invitation to contribute is a different posture compared to the current status of medical knowledge creation. Medical research is currently conducted in such a way that information about how you reacted to a medication is recorded from you as a one in a large study. The information is stored in a data-set and is the property of the university medical center or pharmaceutical company conducting the research. The research subjects rarely have complete/open/free access that they were a part of creating. The current posture infuses the culture surrounding personal medical records in the United States. In many instances, there is formality and red tape to cut through in order to obtain your personal health information - in an age where access to information is becoming more ubiquitous. 

This concept brings up large questions. At this point, these are open questions for the which the implementation of the project will seek to address. That is a part of the joy of the project for me. From the viewpoint of the physician, one question is how accurate do you need the diagnosis on the submitted picture. We know that not every visit with a doctor generates the correct answer with regards to a skin rash. There are not the resources to follow up and send  a dermatologist and examine and biopsy every piece of skin from a submitted image. The first layer is to ask the user to submit an image of a skin lesion or rash only after it has been evaluated by a medical professional.

Several other open questions:
How do you ensure unhelpful image submissions are limited (ie. non skin)?
What is the photographic/pixel quality needed in order for the image to be seen clearly/re-usable and ultimately useful?
What data needs to be submitted along with the image? To much information and you lose participants, too few pieces of info (age, diagnosis) and you limit the power of the database.
How do you guard against fraud such as fake/false submissions?
Should you be required to submit an image in order to use the database?

At this point I am seeking to engage with web developers and move the idea forward.



Monday, May 27, 2013

Data Exhaust

In 2010 more than a billion visits were made to clinicians in the United States by patients in the ambulatory setting. Ambulatory means an office based, outpatient clinic. This is compared to, and specifically not an emergency room, or surgery, or a clinic inside of a hospital, but a free standing building. Most of those patients were seen by general practitioners.

Of those 1 billion encounters approx. 50 million left their visit having been diagnosed with a disease of the skin or subcutaneous tissue (a word meaning just underneath the skin). These numbers of skin disease diagnosis come from visits to pediatricians, family medicine physicians, as well as dermatology specialists.This data is from the publicly available National Ambulatory Medical Care Survey, conducted yearly by the United States Centers for Disease control.

The table below displays results for skin diagnosis for the years 2008, 2009, and 2010.

Primary diagnosis at office visits, classified by major disease category. United states. 2008-2010

Diagnosed as: Diseases of the skin and subcutaneous tissue

Year
Number
2010
           50,224,000
2009
           43,109,000
2008
           46,097,000
        139,430,000

Considering the previous post indicating the size of currently active skin image databases, these numbers suggest they are performing at a margin below their capacity. The implicit suggestion here is that at every office visit that a healthcare provider diagnosed a skin disease, if a  picture image was also captured (by doctor or patient) and contributed to a common database, the volume of images would far outpace the current offerings  This gap represents the data exhaust of the clinical encounter. There is valuable information captured in the eye of the professional, used to make decisions and move forward with treatment. The utility of the information carries forward in the mind’s eye of the individual doctor which made the decision about the diagnosis. However, when it is not shared, the utility of that encounter has diminishing returns, as the doctor retires from practice for example.

This is occuring in the context of 50% of the U.S. cellular phone market with smartphones as of early 2012. That means a portion of each of these doctor’s visits (i the United States) happens with a either a patient or physician, or both, with an internet connected camera sitting in their pocket throughout the entire experience. My personal experience with patients and my own family suggests we are utilizing this technology to take pictures of things that happen to our skin. Unfortunately, there is not yet a platform for citizens to participate in the science. 

Thinking forward, this idea is inherently a global project. As robust mobile telephony spreads there is global potential. A chart aggregated on Wikipedia suggests 5 billion people live in countries with >70% mobile phone penetrance.

Allowing the non-professional individual to contribute to the commons is the conceptual next step. The crowd-sourced dermatology database is one platform for one disease category that will attempt to capture that potential.


Much in the same spirit that built open source soft-ware, this data is inherently part of the global commons. Human biology is unique to the individual, but also shared and common to us all. The data from personal pictures of a patient's skin is inherently private-in the sense that it is connected to one individual and part of their personal health record, protected and disclosed at their discretion. However, in another very real sense the image skin forms part of a common knowledge. The coders who produced much of the Linux operating system, which forms infrastructure that supports much of the internet, contributed their knowledge to a common project. It allowed those that came after them to use prior leaps in knowledge to step even further. This pursuit of open knowledge, rich in other fields, has found limited voice in the house of medicine up to this point. This project represents a new kind of trial, a proof of concept. 

Email with questions.

Friday, May 10, 2013

Strengths, Weaknesses, Opportunities, Threats


Concept of Crowd-Sourced Dermatologic Picture Database

Project: An online and mobile platform through which participants voluntarily submit user-obtained images of a skin rash or lesion that has been evaluated and diagnosed by a health professional. 

The purpose is to create the largest database database of dermatologic images
The unique value added will be that the raw data will be curated as an open source project. 
The intention is not to make medical diagnosis. Nor is the goal to have individuals contribute without professional interaction. There is a level of accuracy that is needed between image and diagnosis. That exact level remains point is an open question. Non-professionals up to this point are typically not involved in this way with the collection of biologic data. This project is unique because opens up the potential volume of contributors to the civic space, while actively engaging in answering the question on accuracy. 
The hypothesis behind the project is that a larger volume of images even at a lower accuracy rate is of equal or greater value compared to the proprietary curated databases.
Participation will open to contribution to by all; and the resultant community product (the database) will be made openly accessible to all, layman and professional alike.

Strengths
Weaknesses
  • Monetary cost of starting (website) is relatively cheap in early stages.

  • Small team in initial phase. Low manpower costs up-front.

  • Participation with website/database  could enable users immediate gratification. Access to image database is free/open to world for research etc. i.e. - other skin conditions with similar “tags” could show up on screen after submission.

  • The concept readily taps into the ethos for a more genuine/communal approach to solving the worlds problems
    • Limited accountability over submitted images. As a truly open site limited ways to prevent upfront the inappropriate image submissions (ie genitals or cartoon images)

    • Similar to prior: at beta stage (unless there is some type of research funding) has limited ability to “double check” validity of user-submitted diagnosis. Relying on trust-worthiness of the crowd of participants (this could also be a strength). Cost of double checking images via phone, or person-person review would be large.

    • Limited initial monetary and human capital (person-hours) to devote to early development of project.

    • Initial small team has limited execution experience in the entrepreneurial space.

    • Not-for-profit driven at conception; not extensive thought has been given to potential for monetization which may limit broader interest/investment.

    • Has never been truly tested in this specific way, first-mover advantage, which brings with it all of the potential pitfalls such as potential for legal disadvantages.

      Opportunities
      Threats
      • Potential for database of vast size, larger than current private databases (see previous post)

      • Medicine is specialized, and the culture is often slow to adapt and adopt change. This intransigence allows space for innovation with a relatively  lower risk of early competition compared to other industries.

      • Ability to tap into the power of the crowd - similar to paradigm shifts already further along in  encyclopedias (think Wikipedia) and news (think Twitter). Enabling the community to more fully participate in the health conversation has potential for better outcomes/lower costs.

      • Riding with the wave of the “crowd sourcing” concept, not in a hollow way that  some companies are trying to do for marketing purposes.

      • This project would solve 1 problem-crowd source 1 specific health niche. If  there is proof of concept --> idea becomes  a building block of a larger project to crowd-source health data then → build on the data to aid in diagnosis, treatment, research.

        • Smart phone technology and the rapid pace of product development and iteration means the next generation of IT minded doctors (US/India or any other global player) can be expected to move quickly into the crowd-sourcing concept 

        • Medical Culture at large makes a baseline assumption that the doctor, the professional, contains sacred knowledge.This project tries to break in and take some of the power away from the dominant culture, which can be threatening. If dermatologists feel threatened there is easy risk of blowback such as being accused of being unsafe for patients.

        • Michigan Iphone app: screen self for skin cancer w/ free iphone app.

        • VisualDx - made and marketed exclusively for physicians. However, a conceptual step could lead to a patient version for submitting images and the organization already has infrastructure, connections, and momentum.

        • patientslikeme.com - already exists, brand recognition, is crowd sourcing patient support groups. Contains 1,000+ conditions, and 156,241 patients when last accessed.