Universität zu Köln

Agius, Rudi, Brieghel, Christian ORCID: 0000-0002-1816-8106, Andersen, Michael A., Pearson, Alexander T., Ledergerber, Bruno, Cozzi-Lepri, Alessandro, Louzoun, Yoram, Andersen, Christen L., Bergstedt, Jacob ORCID: 0000-0002-9279-6936, von Stemann, Jakob H., Jorgensen, Mette, Tang, Man-Hung Eric ORCID: 0000-0002-3483-0219, Fontes, Magnus, Bahlo, Jasmin, Herling, Carmen D., Hallek, Michael, Lundgren, Jens, MacPherson, Cameron Ross, Larsen, Jan ORCID: 0000-0003-1880-1810 and Niemann, Carsten U. (2020). Machine learning can identify newly diagnosed patients with CLL at high risk of infection. Nat. Commun., 11 (1). LONDON: NATURE PUBLISHING GROUP. ISSN 2041-1723

Full text not available from this repository.

Abstract

Infections have become the major cause of morbidity and mortality among patients with chronic lymphocytic leukemia (CLL) due to immune dysfunction and cytotoxic CLL treatment. Yet, predictive models for infection are missing. In this work, we develop the CLL Treatment-Infection Model (CLL-TIM) that identifies patients at risk of infection or CLL treatment within 2 years of diagnosis as validated on both internal and external cohorts. CLL-TIM is an ensemble algorithm composed of 28 machine learning algorithms based on data from 4,149 patients with CLL. The model is capable of dealing with heterogeneous data, including the high rates of missing data to be expected in the real-world setting, with a precision of 72% and a recall of 75%. To address concerns regarding the use of complex machine learning algorithms in the clinic, for each patient with CLL, CLL-TIM provides explainable predictions through uncertainty estimates and personalized risk factors. Chronic lymphocytic leukemia is an indolent disease, and many patients succumb to infection rather than the direct effects of the disease. Here, the authors use medical records and machine learning to predict the patients that may be at risk of infection, which may enable a change in the course of their treatment.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Agius, Rudi UNSPECIFIED UNSPECIFIED UNSPECIFIED Brieghel, Christian UNSPECIFIED orcid.org/0000-0002-1816-8106 UNSPECIFIED Andersen, Michael A. UNSPECIFIED UNSPECIFIED UNSPECIFIED Pearson, Alexander T. UNSPECIFIED UNSPECIFIED UNSPECIFIED Ledergerber, Bruno UNSPECIFIED UNSPECIFIED UNSPECIFIED Cozzi-Lepri, Alessandro UNSPECIFIED UNSPECIFIED UNSPECIFIED Louzoun, Yoram UNSPECIFIED UNSPECIFIED UNSPECIFIED Andersen, Christen L. UNSPECIFIED UNSPECIFIED UNSPECIFIED Bergstedt, Jacob UNSPECIFIED orcid.org/0000-0002-9279-6936 UNSPECIFIED von Stemann, Jakob H. UNSPECIFIED UNSPECIFIED UNSPECIFIED Jorgensen, Mette UNSPECIFIED UNSPECIFIED UNSPECIFIED Tang, Man-Hung Eric UNSPECIFIED orcid.org/0000-0002-3483-0219 UNSPECIFIED Fontes, Magnus UNSPECIFIED UNSPECIFIED UNSPECIFIED Bahlo, Jasmin UNSPECIFIED UNSPECIFIED UNSPECIFIED Herling, Carmen D. UNSPECIFIED UNSPECIFIED UNSPECIFIED Hallek, Michael UNSPECIFIED UNSPECIFIED UNSPECIFIED Lundgren, Jens UNSPECIFIED UNSPECIFIED UNSPECIFIED MacPherson, Cameron Ross UNSPECIFIED UNSPECIFIED UNSPECIFIED Larsen, Jan UNSPECIFIED orcid.org/0000-0003-1880-1810 UNSPECIFIED Niemann, Carsten U. UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-348613
DOI:	10.1038/s41467-019-14225-8
Journal or Publication Title:	Nat. Commun.
Volume:	11
Number:	1
Date:	2020
Publisher:	NATURE PUBLISHING GROUP
Place of Publication:	LONDON
ISSN:	2041-1723
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language CHRONIC LYMPHOCYTIC-LEUKEMIA; IMMUNE FAILURE; OPEN-LABEL; MICROENVIRONMENT; SURVIVAL; CYCLOPHOSPHAMIDE; FLUDARABINE; PROGNOSIS; RITUXIMAB; IBRUTINIB Multiple languages Multidisciplinary Sciences Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/34861