Unsupervised meta-clustering identifies risk clusters in acute myeloid leukemia based on clinical and genetic profiles.
Jan-Niklas EckardtChristoph RölligKlaus H MetzelerPeter HeisigSebastian StasikJulia-Annabell GeorgiFrank KroschinskyFriedrich StölzelUwe PlatzbeckerKarsten SpiekermannUtz KrugJan BraessDennis GörlichCristina SauerlandBernhard WoermannTobias HeroldWolfgang HiddemannCarsten Muller-TidowHubert ServeClaudia Dorothea BaldusKerstin Schäfer-EckartMartin KaufmannStefan W KrauseMathias HänelWolfgang E BerdelChristoph SchliemannJiri MayerMaher HanounJohannes ScheteligKarsten WendtMartin BornhäuserChristian ThiedeJan Moritz MiddekePublished in: Communications medicine (2023)
Dynamic data-driven models are likely more suitable for risk stratification in the context of increasingly complex medical data than rigid hypothesis-driven models to allow for a more personalized treatment allocation and gain novel insights into disease biology.