Big data and targeted machine learning in action to assist medical decision in the ICU: the past, the present and the future

Romain Pirracchio (1, 2) , Mittchell J. Cohen (3) , Ivana Malenica (4) , Jonathan Cohen (4) , Antoine Chambaz (5) , Maxime Canesson (6, 7) , Christine Lee (6) , Matthieu Resche-Rigon (8) , Alan Hubbard (9)

1 Service d'Anesthésie-Réanimation [CHU HEGP]
2 UC San Francisco - University of California [San Francisco]
3 University of Colorado [Denver]
4 LBNL - Lawrence Berkeley National Laboratory [Berkeley]
5 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5
6 UCLA - University of California [Los Angeles]
7 UC Irvine - University of California [Irvine]
8 Biostatistique et épidemiologie clinique
9 Division of Biostatistics [Berkeley]

Historically, personalized medicine has been synonymous with pharmacogenomics and oncology. We argue for a new paradigm in personalized medicine that capitalizes on more detailed patient-level data and modern targeted machine learning procedures that may be more applicable to critically ill patients. We discuss how advances in data technology and statistics are providing new opportunities for asking more targeted questions regarding patient treatment, and how this can be applied in the intensive care unit to better predict patient-centered outcomes, help in the discovery of new treatment regimens associated with improved outcomes, and ultimately how these rules can be learned in realtime for the patient.

Domaines: Statistiques [math.ST]; Médecine humaine et pathologie

Romain Pirracchio, Mittchell J. Cohen, Ivana Malenica, Jonathan Cohen, Antoine Chambaz, et al.. Big data and targeted machine learning in action to assist medical decision in the ICU: the past, the present and the future. Anaesthesia Critical Care & Pain Medicine, In press. ⟨hal-01869319⟩