Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Machine learning can identify newly diagnosed patients with CLL at high risk of infection

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. A phenome-wide association and Mendelian Randomisation study of polygenic risk for depression in UK Biobank

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Identification of epilepsy-associated neuronal subtypes and gene expression underlying epileptogenesis

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. An atlas of O-linked glycosylation on peptide hormones reveals diverse biological roles

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Whole genome landscapes of uveal melanoma show an ultraviolet radiation signature in iris tumours

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  5. Author Correction: Mutational and putative neoantigen load predict clinical benefit of adoptive T cell therapy in melanoma

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Vis graf over relationer

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.

OriginalsprogEngelsk
TidsskriftNature Communications
Vol/bind11
Udgave nummer1
Sider (fra-til)363
ISSN2041-1723
DOI
StatusUdgivet - 17 jan. 2020

ID: 59339866