Buchumschlag

Medical transformer for multimodal survival prediction in intensive care: integration of imaging and non-imaging data

When clinicians assess the prognosis of patients in intensive care, they take imaging and non-imaging data into account. In contrast, many traditional machine learning models rely on only one of these modalities, limiting their potential in medical applications. This work proposes and evaluates a tr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Khader, Firas (VerfasserIn) , Kather, Jakob Nikolas (VerfasserIn) , Müller-Franzes, Gustav (VerfasserIn) , Wang, Tianci (VerfasserIn) , Han, Tianyu (VerfasserIn) , Tayebi Arasteh, Soroosh (VerfasserIn) , Hamesch, Karim (VerfasserIn) , Bressem, Keno (VerfasserIn) , Haarburger, Christoph (VerfasserIn) , Stegmaier, Johannes (VerfasserIn) , Kuhl, Christiane (VerfasserIn) , Nebelung, Sven (VerfasserIn) , Truhn, Daniel (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 2023
In: Scientific reports
Year: 2023, Jahrgang: 13, Pages: 1-11
ISSN:2045-2322
DOI:10.1038/s41598-023-37835-1
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.1038/s41598-023-37835-1
Verlag, kostenfrei, Volltext: https://www.nature.com/articles/s41598-023-37835-1
Volltext
Verfasserangaben:Firas Khader, Jakob Nikolas Kather, Gustav Müller-Franzes, Tianci Wang, Tianyu Han, Soroosh Tayebi Arasteh, Karim Hamesch, Keno Bressem, Christoph Haarburger, Johannes Stegmaier, Christiane Kuhl, Sven Nebelung & Daniel Truhn
Beschreibung
Zusammenfassung:When clinicians assess the prognosis of patients in intensive care, they take imaging and non-imaging data into account. In contrast, many traditional machine learning models rely on only one of these modalities, limiting their potential in medical applications. This work proposes and evaluates a transformer-based neural network as a novel AI architecture that integrates multimodal patient data, i.e., imaging data (chest radiographs) and non-imaging data (clinical data). We evaluate the performance of our model in a retrospective study with 6,125 patients in intensive care. We show that the combined model (area under the receiver operating characteristic curve [AUROC] of 0.863) is superior to the radiographs-only model (AUROC = 0.811, p < 0.001) and the clinical data-only model (AUROC = 0.785, p < 0.001) when tasked with predicting in-hospital survival per patient. Furthermore, we demonstrate that our proposed model is robust in cases where not all (clinical) data points are available.
Beschreibung:Veröffentlicht: 01. Juli 2023
Gesehen am 30.08.2023
Beschreibung:Online Resource
ISSN:2045-2322
DOI:10.1038/s41598-023-37835-1

Ähnliche Einträge