2012 the als predic on prize als predic on prize setup

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: d to observe drug effect Predic-on Progression: How? The PRO ­ACT Database   Pooled Resource Open ­Access ALS Clinical Trials   8500 de ­iden-fied pa-ent records from completed clinical trials   Largest ALS pa-ent data set ever assembled   Demographics, Medical and family history data   Func-onal measures (ALSFRS, lung capacity)   Vital signs (weight, height, respiratory rate)   Lab data (blood chemistry, hematology, and urinalysis)   Released to the public in Dec. 2012 The ALS Predic-on Prize ALS Predic-on Prize: Setup   The Contest Data •  918 training pa-ents   12 months of data (demographic, ALSFRS, vital sta-s-cs, lab tests)   Time series: roughly monthly measurements, unequally spaced •  279 test pa-ents   First 3 months of data available at test ;me   Challenge: Given first 3 months of pa-ent data, predict progression of ALS over subsequent 9 months   Measure: ALS Func-onal Ra-ng Scale (ALSFRS) score •  Rate of progression = slope of ALSFRS score ALSFRS score Target for Predic-on Months Target for Predic-on   Issues: Timing of future visits unknown; Slope unstable   Open Ques;on: Be^er targets for predic;on? •  Es-mate ALSFRS score as a func-on of -me? •  Classify pa-ent as slow or fast progressor? ALSFRS score ALSFRS (m2) − ALSFRS (m1) slope = m2 − m1 m1 First visit a_er 3 months m2 First visit a_er 12 months Months ALS Progression Types fast non ­linear slow The Difficulty of Predic-on ALS Predic-on Prize: Evalua-on   Contest run on Innocen;ve prize plaporm •  Hosts science compe--ons •  See also Kaggle, Challenge.gov   Contestants uploaded code to Innocen-ve server •  Code had to be wriqen in R! •  Max running -me: 6 hours   Leaderboard displayed error on test set •  Max # submissions: 100   Er...
View Full Document

This note was uploaded on 02/03/2014 for the course STATS 202 taught by Professor Taylor during the Fall '09 term at Stanford.

Ask a homework question - tutors are online