Dear Western Hemisphere Team,
This week i am on a short holiday break and there is no alternative speaker so we will cancel the PLP TC tomorrow.
Talk to you again in two weeks.
Peter
Dear Western Hemisphere team,
Tomorrow we will have a look at the results of the Proof-of-concept study in Depression patients from the databases we received so far and like to discuss next steps.
Hope to talk to you all tomorrow.
Peter
The recording of today is as always on the Wiki page.
I will contact all the data custodians that participated in the PLP study that did not
join today to discuss the results and next steps.
In the Eastern Hemisphere meeting tomorrow Sungjae will present on distributed logistic regression and I will give an update on the large-scale prediction study.
Talk to you tomorrow.
The Western Hemisphere TC of June 14th is canceled
If you have interesting topics to discuss in an upcoming Western Hemisphere TC let us know.
Sorry for hijacking this thread, but just wanted to share this whitepaper I stumbled on. It’s on a piece of software called Hunchlab that is used by the US police to predict crime and plan deployment.
Some technical details are noteworthy, like their use of time-related features that also make sense for us given the observed temporal dynamics in our data, or the use of a Poisson model to calibrate the predictions. I also like how they offer to measure the performance of the software on the data of a particular police department (‘more [data] is better’, ‘cleaner [data] is better’).
But what I really like about this document is how they present prediction to (power) users: the name Hunchlab to me is a stroke of genius, being quite modest (e.g. in constrast to Precrime) and so not too threatening, but also how they relate the workings of the algorithm to how a police officer would go about trying to predict where crime is most likely to occur next.I think we can learn something here on how we communicate prediction to doctors.
I guess they have the advantage of being able to boost their predictive power by adding true positives to the data after predicting them, if necessary. 
1 Like
Dear all,
On Wednesday in the Eastern Hemisphere meeting Seng Chan You will present results from a study of predicting 5-years risk of cardiovascular disease using a 3-layer GRU model.
Hope you will all join.
Peter
The goal of today’s Western Hemisphere meeting was to brainstorm about the Prediction Tutorial we will prepare for the OHDSI Symposium. Unfortunately, multiple key team members cannot join so we decided to cancel today’s meeting.
The PLP TC tomorrow is cancelled. If team members have topics to share in upcoming TCs let me know,
Dear all,
We will change the frequency of the PLP TCs during the summer period to once a month.
The TC today is cancelled and will have the next TC in two weeks if there are topics to discuss.
Peter and Jenna
The recording and slides of the Eastern TC are on the wiki.
Today I will present results on the learning curve experiment I will submit as an abstract for the OHDSI symposium.
Peter
1 Like
Team,
Tomorrow in the Western PLP TC, Kristin Feeney will present Deloitte’s Deep Learning work.
Please join see wiki for gotomeeting details,
Peter
Thanks Kristin for the nice insights in the work you are doing at Deloitte.
The recording and slides are on the wiki for those that have missed it.
Peter
The PLP TC tomorrow is cancelled since I will be travelling at this time.
Peter
Hi All,
In the Eastern Hemisphere meeting tomorrow Seng Chan You would like to share some work he has done in the area of Deep Learning and wants to discuss integration in the PLP Package.
Peter
Hi All,
Tomorrow we like to talk about an idea we have to use prior knowledge (for example from WikiPedia) when training prediction models. Martijn will share some very preliminary results on this.
I would also like to use some time of this TC to hear if you have ideas for future research directions related to PLP or topics to discuss.
Peter
Hi @Rijnbeek
As you know, Ajou university has two kind of dataset, one from hospital, one from national claim database. All medical services are based on national claim service in Korea. (Virtually all condition, drug and procedure codes in hospital data are included in claim data)
Claim database contains longitudinal medical histories of large population. But it doesn’t have enough measurement data.
Conversely, hospital data contains only hospital-based visit data of small population. But it does have high-resolution measurement data.
In terms of transfer learning, would it be possible to make predicting model pre-trained in claim database and then transfer this knowledge to the predicting model for hospital data?
Chan
Hi Chan,
I have not looked in to transfer learning a lot myself but I do know Nigham is using it for phenotyping:
https://openreview.net/pdf?id=B1_E8xrKe
I am not sure how this would work for your interesting problem.
Peter
Dear All,
Because of the daylight savings time change we will move the Western Hemisphere TC today to one hour earlier for Europe to keep the TC at noon in US.
Today Martijn will present preliminary results on model building that utilized prior knowledge (informed prior).
We would also like to have an interactive discussion about future research directions for PLP after that.
Hope to talk to you later today.
Peter and Jenna