A Multimodal Ensemble Deep Learning Model for Functional Outcome Prognosis of Stroke Patients
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background and Purpose The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS. Methods We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3–6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3–6. Results Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3–6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004). Conclusion The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.
Abstract
Background and Purpose The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS. Methods We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3–6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3–6. Results Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3–6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004). Conclusion The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.
참고문헌 (42)
- James SL, "Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017 : a systematic analysis for the global burden of disease study 2017", Lancet, 392, pp.1789~1858 (2018)
- Langhammer B, "Factors enhancing activities of daily living after stroke in specialized rehabilitation : an observational multicenter study within the Sunnaas International Network", Eur J Phys Rehabil Med, 53, pp.725~734 (2017)
- Kugler C, "Does age influence early recovery from ischemic stroke? A study from the Hessian Stroke Data Bank", J Neurol, 250, pp.676~681 (2003)
- Venema E, "Selection of patients for intra-arterial treatment for acute ischaemic stroke : development and validation of a clinical decision tool in two randomised trials", BMJ, 357, pp.j1710~ (2017)
- Paker N, "Impact of cognitive impairment on functional outcome in stroke", Stroke Res Treat, 2010, pp.652612~ (2010)
- Molina CA, "Improving the predictive accuracy of recanalization on stroke outcome in patients treated with tissue plasminogen activator", Stroke, 35, pp.151~156 (2004)
- Nichols-Larsen DS, "Factors influencing stroke survivors’ quality of life during subacute recovery", Stroke, 36, pp.1480~1484 (2005)
- Saposnik G, "Stroke prognostication using age and NIH stroke scale : SPAN-100", Neurology, 80, pp.21~28 (2013)
- Boers AMM, "Association of follow-up infarct volume with functional outcome in acute ischemic stroke : a pooled analysis of seven randomized trials", J Neurointerv Surg, 10, pp.1137~1142 (2018)
- Laredo C, "Prognostic significance of infarct size and location : the case of insular stroke", Sci Rep, 8, pp.9498~ (2018)
- Kim YD, "The ischemic stroke predictive risk score predicts early neurological deterioration", J Stroke Cerebrovasc Dis, 25, pp.819~824 (2016)
- Ntaios G, "An integer-based score to predict functional outcome in acute ischemic stroke : the ASTRAL score", Neurology, 78, pp.1916~1922 (2012)
- Jang SK, "Reliability and clinical utility of machine learning to predict stroke prognosis : comparison with logistic regression", J Stroke, 22, pp.403~406 (2020)
- Heo J, "Machine learning-based model for prediction of outcomes in acute stroke", Stroke, 50, pp.1263~1265 (2019)
- van Os HJA, "Predicting outcome of endovascular treatment for acute ischemic stroke : potential value of machine learning algorithms", Front Neurol, 9, pp.784~ (2018)
- Ramos LA, "Predicting poor outcome before endovascular treatment in patients with acute ischemic stroke", Front Neurol, 11, pp.580957~ (2020)
- Alaka SA, "Functional outcome prediction in ischemic stroke : a comparison of machine learning algorithms and regression models", Front Neurol, 11, pp.889~ (2020)
- Hilbert A, "Data-efficient deep learning of radiological image data for outcome prediction after endovascular treatment of patients with acute ischemic stroke", Comput Biol Med, 115, pp.103516~ (2019)
- Samak ZA, "Medical image understanding and analysis. MIUA 2020. Communications in computer and information science (vol 1248)", pp.267~279 (2020), Springer
- Hatami N, "CNN-LSTM based multimodal MRI and clinical data fusion for predicting functional outcome in stroke patients", Annu Int Conf IEEE Eng Med Biol Soc, 2022, pp.3430~3434 (2022)
- Moulton E, "Interpretable deep learning for the prognosis of long-term functional outcome post-stroke using acute diffusion weighted imaging", J Cereb Blood Flow Metab, 43, pp.198~209 (2023)
- van Swieten JC, "Interobserver agreement for the assessment of handicap in stroke patients", Stroke, 19, pp.604~607 (1988)
- Sulter G, "Use of the Barthel index and modified Rankin scale in acute stroke trials", Stroke, 30, pp.1538~1541 (1999)
- Tustison NJ, "N4ITK : improved N3 bias correction", IEEE Trans Med Imaging, 29, pp.1310~1320 (2010)
- Avants BB, "Symmetric diffeomorphic image registration with cross-correlation : evaluating automated labeling of elderly and neurodegenerative brain", Med Image Anal, 12, pp.26~41 (2008)
- Adams HP Jr, "Classification of subtype of acute ischemic stroke. Definitions for use in a multicenter clinical trial. TOAST. Trial of Org 10172 in Acute Stroke Treatment", Stroke, 24, pp.35~41 (1993)
- Xie S, "Aggregated residual transformations for deep neural networks", Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.5987~5995 (2017)
- Woo S, "Computer vision – ECCV 2018. Lecture notes in computer science (vol 11211)", pp.3~19 (2018), Springer
- Cubuk ED, "RandAugment : practical automated data augmentation with a reduced search space", Proceedings of the 2020 IEEE, 2020, 3008~3017
- Lin TY, "Focal loss for dense object detection", IEEE Trans Pattern Anal Mach Intell, 42, pp.318~327 (2020)
- Lundberg SM, "A unified approach to interpreting model predictions", 31st Conference on Neural Information Processing Systems (NIPS 2017), pp.4765~4774 (2017), Advances in Neural Information Processing Systems
- Selvaraju RR, "Grad-CAM : visual explanations from deep networks via gradient-based localization", Int J Comput Vis, 128, pp.336~359 (2020)
- Abadi M, "Tensorflow: a system for large-scale machine learning", Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, pp.265~283 (2016), USENIX Association
- Bradski G, "The opencv library", Dr Dobb’s Journal : Software Tools for the Professional Programmer, 25, pp.120~123 (2000)
- van der Walt S, "Scikit-image : image processing in Python", PeerJ, 2, pp.e453~ (2014)
- Pedregosa F, "Scikit-learn : machine learning in Python", J Mach Learn Res, 12, pp.2825~2830 (2011)
- Jenkinson M, "FSL", Neuroimage, 62, pp.782~790 (2012)
- Corso G, "Outcome predictors in first-ever ischemic stroke patients : a population-based study", Int Sch Res Notices, 2014, pp.904647~ (2014)
- Turhan B, "On the dataset shift problem in software engineering prediction models", Empir Software Eng, 17, pp.62~74 (2012)