Demystifying machine learning for mortality prediction

J. M. Smit; M. E. van Genderen; M. J.T. Reinders; D. A.M.P.J. Gommers; J. H. Krijthe; J. Van Bommel

doi:10.1186/s13054-021-03868-z

Demystifying machine learning for mortality prediction

J. M. Smit^*, M. E. van Genderen, M. J.T. Reinders, D. A.M.P.J. Gommers, J. H. Krijthe, J. Van Bommel

^*Corresponding author for this work

Intensive Care

Delft University of Technology

Research output: Contribution to journal › Comment/Letter to the editor › Professional

2 Citations (Scopus)

20 Downloads (Pure)

Abstract

With interest, we read the article by Banoei et al. [1] on machine learning (ML) models to predict mortality among COVID-19 patients. They refer to other studies that failed to predict mortality using ‘conventional statistical analysis’, after which they present a linear ML model as a better suited method for such complex medical problems. We feel such a claim creates an image around ML as an alternative technique that offers solutions where statistical modeling fails. However, ML and statistical modeling are tightly interwoven. [...]

Original language	English
Article number	447
Journal	Critical Care
Volume	25
Issue number	1
DOIs	https://doi.org/10.1186/s13054-021-03868-z
Publication status	Published - 23 Dec 2021

Access to Document

10.1186/s13054-021-03868-zLicence: CC BY

s13054-021-03868-zFinal published version, 570 KBLicence: CC BY

Cite this

@article{41bb1eeecfcb4a3d93890dc7111681aa,

title = "Demystifying machine learning for mortality prediction",

abstract = "With interest, we read the article by Banoei et al. [1] on machine learning (ML) models to predict mortality among COVID-19 patients. They refer to other studies that failed to predict mortality using {\textquoteleft}conventional statistical analysis{\textquoteright}, after which they present a linear ML model as a better suited method for such complex medical problems. We feel such a claim creates an image around ML as an alternative technique that offers solutions where statistical modeling fails. However, ML and statistical modeling are tightly interwoven. [...]",

author = "Smit, \{J. M.\} and \{van Genderen\}, \{M. E.\} and Reinders, \{M. J.T.\} and Gommers, \{D. A.M.P.J.\} and Krijthe, \{J. H.\} and \{Van Bommel\}, J.",

year = "2021",

month = dec,

day = "23",

doi = "10.1186/s13054-021-03868-z",

language = "English",

volume = "25",

journal = "Critical Care",

issn = "1364-8535",

publisher = "BioMed Central Ltd.",

number = "1",

}

TY - JOUR

T1 - Demystifying machine learning for mortality prediction

AU - Smit, J. M.

AU - van Genderen, M. E.

AU - Reinders, M. J.T.

AU - Gommers, D. A.M.P.J.

AU - Krijthe, J. H.

AU - Van Bommel, J.

PY - 2021/12/23

Y1 - 2021/12/23

N2 - With interest, we read the article by Banoei et al. [1] on machine learning (ML) models to predict mortality among COVID-19 patients. They refer to other studies that failed to predict mortality using ‘conventional statistical analysis’, after which they present a linear ML model as a better suited method for such complex medical problems. We feel such a claim creates an image around ML as an alternative technique that offers solutions where statistical modeling fails. However, ML and statistical modeling are tightly interwoven. [...]

AB - With interest, we read the article by Banoei et al. [1] on machine learning (ML) models to predict mortality among COVID-19 patients. They refer to other studies that failed to predict mortality using ‘conventional statistical analysis’, after which they present a linear ML model as a better suited method for such complex medical problems. We feel such a claim creates an image around ML as an alternative technique that offers solutions where statistical modeling fails. However, ML and statistical modeling are tightly interwoven. [...]

UR - https://www.scopus.com/pages/publications/85121706123

U2 - 10.1186/s13054-021-03868-z

DO - 10.1186/s13054-021-03868-z

M3 - Comment/Letter to the editor

C2 - 34949229

AN - SCOPUS:85121706123

SN - 1364-8535

VL - 25

JO - Critical Care

JF - Critical Care

IS - 1

M1 - 447

ER -

Demystifying machine learning for mortality prediction

Abstract

Access to Document

Other files and links

Fingerprint

Cite this