Showing posts with label traitwise. Show all posts
Showing posts with label traitwise. Show all posts

Tuesday, May 24, 2011

Traitwise, PGP, data standards and the OSI model

I spent the day with Jason Bobe of the Personal Genomes Project. PGP is a public effort sequence a large number of genomes. Traitwise has formed a partnership with them to serve as part of the phenotyping solution.

Jason's role at PGP puts him in the center of a growing number of people who have competing desires to control / provide services around personal health (or "quantified self" as some are calling it). Jason therefore is in the unique position to promote and evangelize.

An interesting part of the conversation focused around the need for open standards of public health and trait related data. I used the OSI networking protocol framework as a model of how conceptual standards can be incredibly useful to increase innovation. One of the best things about the OSI model is that it didn't attempt to actually define any standards but rather it serves as a conceptual framework that defines how standards interface with each other. From that model has emerged a number of interoperable standards at all levels and without it we certainly wouldn't live in the networked world we live in.

One of the aspects of the human data problem is privacy which has "levels of data privacy" and this, it occurred to us, was somewhat analogous to the OSI layer framework.

Layer 1 - Raw identifiable data (post-privacy)
Layer 2 - Anonymized raw data (HIPPA compliant)
Layer 3 - Algorithmically open data (sand-boxed, machine readable)
Layer 4 - Aggregated data

Layer 1 data is non-private. It requires a consent certificate of some sort to go along with the data.

Layer 2 data is considered by many scientists to be adequate for protection in many research circumstances and indeed HIPPA seems satisfied with this. However, for open projects such as Traitwise I personally don't think that it suffices as de-anonymization has been shown in many circumstances such as the infamous AOL search records scandal.

Layer 3 is perhaps the most interesting and least discussed. A Layer 3 system would allow an algorithm written by a researcher to run against raw data but within a sandbox that only allows the aggregated results to emerge. I haven't put a huge amount of thought into this, but it seems plausible to write an API that could enforce such constraints. But, even without such an API, a human code reviewer could accomplish the same thing.

Layer 4 is what Traitwise and others are currently focusing on -- aggregated data that is not deanonymizable.

This is just one aspect of the data and communications problem, but it is an important one and it was fun talking to Jason about it today.

Monday, September 13, 2010

Traitwise Beta 2

We're pleased to announce the beta 2 version of our health-engine "Traitwise". We've simplified question making, added discussions, and generally improved a lot of things. Please come and check it out -- and tell your friends and family!

Monday, July 26, 2010

Traitwise coding survey

We're almost ready to release the beta version of our survey engine: As a test of the embedded private surveys, I've created this short 10 question survey for my nerd friends to resolve a couple of hypotheses I have about coding styles and coding experience. So, to all my coding friends -- please take a few seconds to honestly answer this survey and to report any bugs or problems you find in the engine.

Thursday, March 18, 2010

Traitwise alpha general release

We've made a lot of progress on Traitwise our engine for permitting people to ask and answer seemingly random health-related questions. From this public Q&A we find correlations among all the participants and permit you to understand yourself in a larger context. We also hope that in the long term this gigantic dirty database of answers will reveal interesting things about human health. And, even through we've only barely begun to populate the database, already the correlation engine is turning up intriguing things. For example, some I've looked at today...
  • Reporting that you "have trouble regulating your emotions" is strongly correlated to experiencing significant forgetfulness.
  • Experiencing dry mouth is correlated to napping
  • Being irritable is correlated to being clumsy
While some of these might be statistical flukes (we are, after all, already testing about half a million hypothesis!!) the engine will soon be able to crank up the sampling of those high-interest correlations so that we can asertain if these are statistical flukes or not. Of course, this all depends on participantion, so I beg all of my friends to go to and participate as well as forward the link to whomever they can.

Sunday, March 7, 2010

Traitwise alpha -- Call for participation

As many of my friends know, I've been working on a project for sometime that aims to develop a user-friendly interface for answering and creating health-related questions. We are excited to release the alpha version of and hope you'll help us by participating.

Traitwise is about giving us all a voice in our own health care. Not only can you answer questions, but you may develop questions of your own about any health related subject. We would very much appreciate it if you would create an account and then create questions,
especially about specific diseases or conditions based on your own experience -- after all, no one knows better about a condition than those who suffer from it.

The question creation process is very easy, and don't worry about making mistakes -- all questions go through a review process.

If you are interested in creating questions, you may review the question creation guidelines here, which may make the process easier for us:

For those super-technical friends of mine, be sure to check out the "Analytics" page and see a prototype of how it is that our system finds interesting patterns. (Try "sleep" as an example).

Please note that as this is an alpha release and thus there are plenty of bugs to find (please report them on the "Feedback" page) and many features missing. The most important of the missing features is "results" -- that is returning back to you the interesting findings about your health. As it is now, the system mostly takes from you (your answers and questions) but gives back very little (the results). By answering questions, you are helping us to gather a sufficient amount of data that we may fully develop the results pages.

Thank you for all your help!