biostudies-literatureNoren DPNHGRI NIH HHSNCI NIH HHSNLM NIH HHSNational Institutes of Healthe1004890https://www.ebi.ac.uk/biostudies/studies/S-EPMC4924788biostudies-literatureUnknown12(6)Acute Myeloid Leukemia (AML) is a fatal hematological cancer. The genetic abnormalities underlying AML are extremely heterogeneous among patients, making prognosis and treatment selection very difficult. While clinical proteomics data has the potential to improve prognosis accuracy, thus far, the quantitative means to do so have yet to be developed. Here we report the results and insights gained from the DREAM 9 Acute Myeloid Prediction Outcome Prediction Challenge (AML-OPC), a crowdsourcing effort designed to promote the development of quantitative methods for AML prognosis prediction. We identify the most accurate and robust models in predicting patient response to therapy, remission duration, and overall survival. We further investigate patient response to therapy, a clinically actionabPLoS computational biologyA Crowdsourcing Approach to Developing and Assessing Prediction Algorithms for AML Prognosis.PMC4924788P30 CA016672U54 HG007990T15LM007093T15 LM007093Di Camillo BDREAM 9 AML-OPC ConsortiumSanthanam NLin XEstrada AWright WHess KFitzgerald AKrstajic DZuk PAnbrosini GYeung KYKumar SHunter GAHunter GHung LHZolfaghar KXie HCheong JHNaegle KPiraino SWWang TWrzesien MEngquist EOu Yang THBaladandayuthapani VAnastassiou DRudnicki WFlynn JFatemi SAChen GMLi JXie YChen GBucher PCreighton CJSchultz APark SRosciszewski AGuha SRonan TFronczuk MBisberg AJRhrissorrakrai KYang TYang SKim DLiu LStepanov OOehler VGLong BLKim MNorel RKornblau STang HVilar JMLiu YPeabody ANiemiec RNorman TMcMurray JKorra JShay JRrhissorrakrai KSanavia TZang XMorgan DGu WKuh ANoren DPHu CWQutub AACampion LHosseini MAbrams ZHwang THFriend SHPattin ABoutros PCButurovic LMotiwala TXiao GRegan KBatten KDreos RStolovitzky GLescarbeau RYe JfalseA Crowdsourcing Approach to Developing and Assessing Prediction Algorithms for AML Prognosis.Acute Myeloid Leukemia (AML) is a fatal hematological cancer. The genetic abnormalities underlying AML are extremely heterogeneous among patients, making prognosis and treatment selection very difficult. While clinical proteomics data has the potential to improve prognosis accuracy, thus far, the quantitative means to do so have yet to be developed. Here we report the results and insights gained from the DREAM 9 Acute Myeloid Prediction Outcome Prediction Challenge (AML-OPC), a crowdsourcing effort designed to promote the development of quantitative methods for AML prognosis prediction. We identify the most accurate and robust models in predicting patient response to therapy, remission duration, and overall survival. We further investigate patient response to therapy, a clinically actionab2016-01-01T00:00:00Z2016 Jun2025-06-01T01:39:01.629Z2025-06-01T01:39:01.629ZS-EPMC49247882735183610.1371/journal.pcbi.1004890