Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Comparison of correctly and incorrectly classified patients for in-hospital mortality prediction in the intensive care unit
Norwegian Univ Sci & Technol, Dept Circulat & Med Imaging, Trondheim, Norway..
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH. Norwegian Univ Sci & Technol, Dept Elect Syst, Trondheim, Norway..ORCID-id: 0000-0002-3323-5311
Norwegian Univ Sci & Technol, Dept Elect Syst, Trondheim, Norway..
Norwegian Univ Sci & Technol, Dept Circulat & Med Imaging, Trondheim, Norway.;St Olavs Univ Hosp, Clin Anaesthesia & Intens Care Med, Trondheim, Norway..
2023 (engelsk)Inngår i: BMC Medical Research Methodology, E-ISSN 1471-2288, Vol. 23, nr 1, artikkel-id 102Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Background

The use of machine learning is becoming increasingly popular in many disciplines, but there is still an implementation gap of machine learning models in clinical settings. Lack of trust in models is one of the issues that need to be addressed in an effort to close this gap. No models are perfect, and it is crucial to know in which use cases we can trust a model and for which cases it is less reliable.

Methods

Four different algorithms are trained on the eICU Collaborative Research Database using similar features as the APACHE IV severity-of-disease scoring system to predict hospital mortality in the ICU. The training and testing procedure is repeated 100 times on the same dataset to investigate whether predictions for single patients change with small changes in the models. Features are then analysed separately to investigate potential differences between patients consistently classified correctly and incorrectly.

Results

A total of 34 056 patients (58.4%) are classified as true negative, 6 527 patients (11.3%) as false positive, 3 984 patients (6.8%) as true positive, and 546 patients (0.9%) as false negatives. The remaining 13 108 patients (22.5%) are inconsistently classified across models and rounds. Histograms and distributions of feature values are compared visually to investigate differences between groups.ConclusionsIt is impossible to distinguish the groups using single features alone. Considering a combination of features, the difference between the groups is clearer. Incorrectly classified patients have features more similar to patients with the same prediction rather than the same outcome.

sted, utgiver, år, opplag, sider
Springer Nature , 2023. Vol. 23, nr 1, artikkel-id 102
Emneord [en]
Machine learning, Explainability, Mortality prediction, eICU, SHAP values
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-327383DOI: 10.1186/s12874-023-01921-9ISI: 000974652000002PubMedID: 37095430Scopus ID: 2-s2.0-85153687506OAI: oai:DiVA.org:kth-327383DiVA, id: diva2:1759694
Merknad

QC 20230526

Tilgjengelig fra: 2023-05-26 Laget: 2023-05-26 Sist oppdatert: 2024-01-17bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstPubMedScopus

Person

Salvi, Giampiero

Søk i DiVA

Av forfatter/redaktør
Salvi, Giampiero
Av organisasjonen
I samme tidsskrift
BMC Medical Research Methodology

Søk utenfor DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric

doi
pubmed
urn-nbn
Totalt: 33 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf