Stephen Bacchi1, Toby Zerner2, Luke Oakden-Rayner3, Timothy Kleinig2, Sandy Patel4, Jim Jannes2. 1. Royal Adelaide Hospital, Australia. Electronic address: stephen.bacchi@sa.gov.au. 2. Royal Adelaide Hospital, Australia; Faculty of Health and Medical Sciences, University of Adelaide, Australia. 3. Royal Adelaide Hospital, Australia; Faculty of Health and Medical Sciences, University of Adelaide, Australia; Australian Institute for Machine Learning, University of Adelaide, Australia. 4. Royal Adelaide Hospital, Australia.
Abstract
RATIONALE AND OBJECTIVES: Intravenous thrombolysis decision-making and obtaining of consent would be assisted by an individualized risk-benefit ratio. Deep learning (DL) models may be able to assist with this patient selection. MATERIALS AND METHODS: Clinical data regarding consecutive patients who received intravenous thrombolysis across two tertiary hospitals over a 7-year period were extracted from existing databases. The noncontrast computed tomography brain scans for these patients were then retrieved with hospital picture archiving and communication systems. Using a combination of convolutional neural networks (CNN) and artificial neural networks (ANN) several models were developed to predict either improvement in the National Institutes of Health Stroke Scale of ≥4 points at 24 hours ("NIHSS24"), or modified Rankin Scale 0-1 at 90 days ("mRS90"). The developed CNN and ANN were then applied to a test set. The THRIVE, HIAT, and SPAN-100 scores were also calculated for the patients in the test set and used to predict NIHSS24 and mRS90. RESULTS: Data from 204 individuals were included in the project. The best performing DL model for prediction of mRS90 was a combination CNN + ANN based on clinical data and computed tomography brain (accuracy = 0.74, F1 score = 0.69). The best performing model for NIHSS24 prediction was also the combination CNN + ANN (accuracy = 0.71, F1 score = 0.74). CONCLUSION: DL models may aid in the prediction of functional thrombolysis outcomes. Further investigation with larger datasets and additional imaging sequences is indicated.
RATIONALE AND OBJECTIVES: Intravenous thrombolysis decision-making and obtaining of consent would be assisted by an individualized risk-benefit ratio. Deep learning (DL) models may be able to assist with this patient selection. MATERIALS AND METHODS: Clinical data regarding consecutive patients who received intravenous thrombolysis across two tertiary hospitals over a 7-year period were extracted from existing databases. The noncontrast computed tomography brain scans for these patients were then retrieved with hospital picture archiving and communication systems. Using a combination of convolutional neural networks (CNN) and artificial neural networks (ANN) several models were developed to predict either improvement in the National Institutes of Health Stroke Scale of ≥4 points at 24 hours ("NIHSS24"), or modified Rankin Scale 0-1 at 90 days ("mRS90"). The developed CNN and ANN were then applied to a test set. The THRIVE, HIAT, and SPAN-100 scores were also calculated for the patients in the test set and used to predict NIHSS24 and mRS90. RESULTS: Data from 204 individuals were included in the project. The best performing DL model for prediction of mRS90 was a combination CNN + ANN based on clinical data and computed tomography brain (accuracy = 0.74, F1 score = 0.69). The best performing model for NIHSS24 prediction was also the combination CNN + ANN (accuracy = 0.71, F1 score = 0.74). CONCLUSION: DL models may aid in the prediction of functional thrombolysis outcomes. Further investigation with larger datasets and additional imaging sequences is indicated.
Authors: B Jiang; G Zhu; Y Xie; J J Heit; H Chen; Y Li; V Ding; A Eskandari; P Michel; G Zaharchuk; M Wintermark Journal: AJNR Am J Neuroradiol Date: 2021-01-07 Impact factor: 3.825
Authors: Julie Adhya; Charles Li; Laura Eisenmenger; Russell Cerejo; Ashis Tayal; Michael Goldberg; Warren Chang Journal: Neuroradiol J Date: 2021-04-28
Authors: J E Soun; D S Chow; M Nagamine; R S Takhtawala; C G Filippi; W Yu; P D Chang Journal: AJNR Am J Neuroradiol Date: 2020-11-26 Impact factor: 3.825
Authors: Lucas A Ramos; Manon Kappelhof; Hendrikus J A van Os; Vicky Chalos; Katinka Van Kranendonk; Nyika D Kruyt; Yvo B W E M Roos; Aad van der Lugt; Wim H van Zwam; Irene C van der Schaaf; Aeilko H Zwinderman; Gustav J Strijkers; Marianne A A van Walderveen; Mariekke J H Wermer; Silvia D Olabarriaga; Charles B L M Majoie; Henk A Marquering Journal: Front Neurol Date: 2020-10-15 Impact factor: 4.003