Cargando…

Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage

Objective: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health–economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothes...

Descripción completa

Detalles Bibliográficos
Autores principales: Rusche, Thilo, Wasserthal, Jakob, Breit, Hanns-Christian, Fischer, Urs, Guzman, Raphael, Fiehler, Jens, Psychogios, Marios-Nikos, Sporns, Peter B.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10094957/
https://www.ncbi.nlm.nih.gov/pubmed/37048712
http://dx.doi.org/10.3390/jcm12072631
_version_ 1785023965809344512
author Rusche, Thilo
Wasserthal, Jakob
Breit, Hanns-Christian
Fischer, Urs
Guzman, Raphael
Fiehler, Jens
Psychogios, Marios-Nikos
Sporns, Peter B.
author_facet Rusche, Thilo
Wasserthal, Jakob
Breit, Hanns-Christian
Fischer, Urs
Guzman, Raphael
Fiehler, Jens
Psychogios, Marios-Nikos
Sporns, Peter B.
author_sort Rusche, Thilo
collection PubMed
description Objective: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health–economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothesized that onset prediction of patients with ICH using artificial intelligence (AI) may be more accurate than human readers. Material and Methods: A total of 7421 computed tomography (CT) datasets between January 2007–July 2021 from the University Hospital Basel with confirmed ICH were extracted and an ICH-segmentation algorithm as well as two classifiers (one with radiomics, one with convolutional neural networks) for onset estimation were trained. The classifiers were trained based on the gold standard of 644 datasets with a known onset of >1 and <48 h. The results of the classifiers were compared to the ratings of two radiologists. Results: Both the AI-based classifiers and the radiologists had poor discrimination of the known onsets, with a mean absolute error (MAE) of 9.77 h (95% CI (confidence interval) = 8.52–11.03) for the convolutional neural network (CNN), 9.96 h (8.68–11.32) for the radiomics model, 13.38 h (11.21–15.74) for rater 1 and 11.21 h (9.61–12.90) for rater 2, respectively. The results of the CNN and radiomics model were both not significantly different to the mean of the known onsets (p = 0.705 and p = 0.423). Conclusions: In our study, the discriminatory power of AI-based classifiers and human readers for onset estimation of patients with ICH was poor. This indicates that accurate AI-based onset estimation of patients with ICH based only on CT-data may be unlikely to change clinical decision making in the near future. Perhaps multimodal AI-based approaches could improve ICH onset prediction and should be considered in future studies.
format Online
Article
Text
id pubmed-10094957
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100949572023-04-13 Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage Rusche, Thilo Wasserthal, Jakob Breit, Hanns-Christian Fischer, Urs Guzman, Raphael Fiehler, Jens Psychogios, Marios-Nikos Sporns, Peter B. J Clin Med Brief Report Objective: Intracerebral hemorrhage (ICH) has a high mortality and long-term morbidity and thus has a significant overall health–economic impact. Outcomes are especially poor if the exact onset is unknown, but reliable imaging-based methods for onset estimation have not been established. We hypothesized that onset prediction of patients with ICH using artificial intelligence (AI) may be more accurate than human readers. Material and Methods: A total of 7421 computed tomography (CT) datasets between January 2007–July 2021 from the University Hospital Basel with confirmed ICH were extracted and an ICH-segmentation algorithm as well as two classifiers (one with radiomics, one with convolutional neural networks) for onset estimation were trained. The classifiers were trained based on the gold standard of 644 datasets with a known onset of >1 and <48 h. The results of the classifiers were compared to the ratings of two radiologists. Results: Both the AI-based classifiers and the radiologists had poor discrimination of the known onsets, with a mean absolute error (MAE) of 9.77 h (95% CI (confidence interval) = 8.52–11.03) for the convolutional neural network (CNN), 9.96 h (8.68–11.32) for the radiomics model, 13.38 h (11.21–15.74) for rater 1 and 11.21 h (9.61–12.90) for rater 2, respectively. The results of the CNN and radiomics model were both not significantly different to the mean of the known onsets (p = 0.705 and p = 0.423). Conclusions: In our study, the discriminatory power of AI-based classifiers and human readers for onset estimation of patients with ICH was poor. This indicates that accurate AI-based onset estimation of patients with ICH based only on CT-data may be unlikely to change clinical decision making in the near future. Perhaps multimodal AI-based approaches could improve ICH onset prediction and should be considered in future studies. MDPI 2023-03-31 /pmc/articles/PMC10094957/ /pubmed/37048712 http://dx.doi.org/10.3390/jcm12072631 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Brief Report
Rusche, Thilo
Wasserthal, Jakob
Breit, Hanns-Christian
Fischer, Urs
Guzman, Raphael
Fiehler, Jens
Psychogios, Marios-Nikos
Sporns, Peter B.
Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage
title Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage
title_full Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage
title_fullStr Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage
title_full_unstemmed Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage
title_short Machine Learning for Onset Prediction of Patients with Intracerebral Hemorrhage
title_sort machine learning for onset prediction of patients with intracerebral hemorrhage
topic Brief Report
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10094957/
https://www.ncbi.nlm.nih.gov/pubmed/37048712
http://dx.doi.org/10.3390/jcm12072631
work_keys_str_mv AT ruschethilo machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT wasserthaljakob machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT breithannschristian machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT fischerurs machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT guzmanraphael machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT fiehlerjens machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT psychogiosmariosnikos machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage
AT spornspeterb machinelearningforonsetpredictionofpatientswithintracerebralhemorrhage