Comment on “Computer algorithm can match physicians’ decisions about blood transfusions”

Of the 4946 patients who received intra-operative blood transfusions, 3604 cases were classified as appropriate and 1342 as inappropriate by expert anesthesiologists based on guidelines of the World Health Organization. In this study, no splitting procedure is described in the materials and methods...

Full description

Saved in:
Bibliographic Details
Published in:Journal of translational medicine Vol. 19; no. 1; pp. 175 - 2
Main Author: De Bruyne, Sander
Format: Journal Article
Language:English
Published: London BioMed Central 28.04.2021
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Biomedical and Life Sciences
Biomedicine
Blood Transfusion
Blood transfusions
Computers
Decision Making
Humans
Letter to the Editor
Machine learning
Medical laboratories
Medicine/Public Health
Neural networks
Physicians
ISSN:1479-5876, 1479-5876
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Of the 4946 patients who received intra-operative blood transfusions, 3604 cases were classified as appropriate and 1342 as inappropriate by expert anesthesiologists based on guidelines of the World Health Organization. In this study, no splitting procedure is described in the materials and methods section and it is stated that all 4946 data entries were inputted to the model. [...]as can be derived from the supplementary python script, it seems that the model was trained, validated and tested on exactly the same data entries. [...]the reported accuracies in this study are likely biased, have to be interpreted as the results of a potentially overfitted model and cannot be perceived as being per definition valid for independent data samples.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Correspondence-1
content type line 14
content type line 23
ISSN:1479-5876
1479-5876
DOI:10.1186/s12967-021-02841-2