Search Our Scientific Publications & Authors

Publications
find publications by category +
Translate page:

Interpretable Machine Learning Modeling for Ischemic Stroke Outcome Prediction.

Authors:
Mohamed Sobhi Jabal Olivier Joly David Kallmes George Harston Alejandro Rabinstein Thien Huynh Waleed Brinjikji

Front Neurol 2022 19;13:884693. Epub 2022 May 19.

Department of Radiology, Mayo Clinic, Rochester, MN, United States.

Background And Purpose: Mechanical thrombectomy greatly improves stroke outcomes. Nonetheless, some patients fall short of full recovery despite good reperfusion. The purpose of this study was to develop machine learning (ML) models for the pre-interventional prediction of functional outcome at 3 months of thrombectomy in acute ischemic stroke (AIS), using clinical and auto-extractable radiological information consistently available upon first emergency evaluation.

Materials And Methods: A two-center retrospective cohort of 293 patients with AIS who underwent thrombectomy was analyzed. ML models were developed to predict dichotomized modified Rankin score at 90 days (mRS-90) using clinical and imaging features, both separately and combined. Conventional and experimental imaging biomarkers were quantified using automated image-processing software from non-contract computed tomography (CT) and computed tomography angiography (CTA). Shapley Additive Explanation (SHAP) was applied for model interpretability and predictor importance analysis of the optimal model.

Results: Merging clinical and imaging features returned the best results for mRS-90 prediction. The best performing classifier was Extreme Gradient Boosting (XGB) with an area under the receiver operating characteristic curve (AUC) = 84% using selected features. The most important classifying features were age, baseline National Institutes of Health Stroke Scale (NIHSS), occlusion side, degree of brain atrophy [primarily represented by cortical cerebrospinal fluid (CSF) volume and lateral ventricle volume], early ischemic core [primarily represented by e-Alberta Stroke Program Early CT Score (ASPECTS)], and collateral circulation deficit volume on CTA.

Conclusion: Machine learning that is applied to quantifiable image features from CT and CTA alongside basic clinical characteristics constitutes a promising automated method in the pre-interventional prediction of stroke prognosis. Interpretable models allow for exploring which initial features contribute the most to post-thrombectomy outcome prediction overall and for each individual patient outcome.

Download full-text PDF

 Source
http://dx.doi.org/10.3389/fneur.2022.884693DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9160988PMC
May 2022

Publication Analysis

Top Keywords

machine learning
12
[primarily represented
8
ischemic stroke
8
imaging features
8
outcome prediction
8
computed tomography
8
clinical imaging
8
pre-interventional prediction
8
features
6
stroke
6
prediction
5
quantified automated
4
automated image-processing
4
fluid csf
4
cerebrospinal fluid
4
biomarkers quantified
4
imaging biomarkers
4
patient outcome
4
cortical cerebrospinal
4
image-processing software
4

Keyword Occurance

Similar Publications

Chemical named entity recognition in the texts of scientific publications using the naïve Bayes classifier approach.

Authors:
O A Tarasova A V Rudik N Yu Biziukova D A Filimonov V V Poroikov

J Cheminform 2022 Aug 13;14(1):55. Epub 2022 Aug 13.

Laboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry, 10 bldg. 8, Pogodinskaya Str., Moscow, 119121, Russia.

Motivation: Application of chemical named entity recognition (CNER) algorithms allows retrieval of information from texts about chemical compound identifiers and creates associations with physical-chemical properties and biological activities. Scientific texts represent low-formalized sources of information. Most methods aimed at CNER are based on machine learning approaches, including conditional random fields and deep neural networks. Read More

View Article and Full-Text PDF
August 2022
Similar Publications

Neural network methods for diagnosing patient conditions from cardiopulmonary exercise testing data.

Authors:
Donald E Brown Suchetha Sharma James A Jablonski Arthur Weltman

BioData Min 2022 Aug 13;15(1):16. Epub 2022 Aug 13.

Department of Kinesiology, University of Virginia, Charlottesville, VA, USA.

Background: Cardiopulmonary exercise testing (CPET) provides a reliable and reproducible approach to measuring fitness in patients and diagnosing their health problems. However, the data from CPET consist of multiple time series that require training to interpret. Part of this training teaches the use of flow charts or nested decision trees to interpret the CPET results. Read More

View Article and Full-Text PDF
August 2022
Similar Publications

Detection of developmental dysplasia of the hip in X-ray images using deep transfer learning.

Authors:
Mohammad Fraiwan Noran Al-Kofahi Ali Ibnian Omar Hanatleh

BMC Med Inform Decis Mak 2022 Aug 13;22(1):216. Epub 2022 Aug 13.

Department of Internal Medicine, Jordan University of Science and Technology, Irbid, Jordan.

Background: Developmental dysplasia of the hip (DDH) is a relatively common disorder in newborns, with a reported prevalence of 1-5 per 1000 births. It can lead to developmental abnormalities in terms of mechanical difficulties and a displacement of the joint (i.e. Read More

View Article and Full-Text PDF
August 2022
Similar Publications

A method of two-dimensional correlation spectroscopy combined with residual neural network for comparison and differentiation of medicinal plants raw materials superior to traditional machine learning: a case study on Eucommia ulmoides leaves.

Authors:
Lian Li Zhi Min Li Yuan Zhong Wang

Plant Methods 2022 Aug 13;18(1):102. Epub 2022 Aug 13.

Medicinal Plants Research Institute, Yunnan Academy of Agricultural Sciences, Kunming, 650200, People's Republic of China.

Background: Eucommia ulmoides leaf (EUL), as a medicine and food homology plant, is a high-quality industrial raw material with great development potential for a valuable economic crop. There are many factors affecting the quality of EULs, such as different drying methods and regions. Therefore, quality and safety have received worldwide attention, and there is a trend to identify medicinal plants with artificial intelligence technology. Read More

View Article and Full-Text PDF
August 2022
Similar Publications

Using Jupyter Notebooks for re-training machine learning models.

Authors:
Aljoša Smajić Melanie Grandits Gerhard F Ecker

J Cheminform 2022 Aug 13;14(1):54. Epub 2022 Aug 13.

Department of Pharmaceutical Sciences, University of Vienna, Vienna, Austria.

Machine learning (ML) models require an extensive, user-driven selection of molecular descriptors in order to learn from chemical structures to predict actives and inactives with a high reliability. In addition, privacy concerns often restrict the access to sufficient data, leading to models with a narrow chemical space. Therefore, we propose a framework of re-trainable models that can be transferred from one local instance to another, and further allow a less extensive descriptor selection. Read More

View Article and Full-Text PDF
August 2022
Similar Publications
}