Literature DB >> 32044620

Evaluation of machine learning methods to stroke outcome prediction using a nationwide disease registry.

Ching-Heng Lin1, Kai-Cheng Hsu2, Kory R Johnson3, Yang C Fann4, Chon-Haw Tsai5, Yu Sun6, Li-Ming Lien7, Wei-Lun Chang8, Po-Lin Chen9, Cheng-Li Lin10, Chung Y Hsu11.   

Abstract

INTRODUCTION: Being able to predict functional outcomes after a stroke is highly desirable for clinicians. This allows clinicians to set reasonable goals with patients and relatives, and to reach shared after-care decisions for recovery or rehabilitation. The aim of this study was to apply various machine learning (ML) methods for 90-day stroke outcome predictions, using a nationwide disease registry.
METHODS: This study used the Taiwan Stroke Registry (TSR) which has prospectively collected data from stroke patients since 2006. Three known ML models (support vector machine, random forest, and artificial neural network), and a hybrid artificial neural network were implemented and evaluated by 10-time repeated hold-out with 10-fold cross-validation.
RESULTS: ML techniques present over 0.94 AUC in both ischemic and hemorrhagic stroke using preadmission and inpatient data. By adding follow-up data, the prediction ability improved to 0.97 AUC. We screened 206 clinical variables to identify 17 important features from the ischemic stroke dataset and 22 features from the hemorrhagic stroke dataset without losing much performance. Error analysis revealed that most prediction errors come from more severe stroke patients.
CONCLUSION: The study showed that ML techniques trained from large, cross-reginal registry datasets were able to predict functional outcome after stroke with high accuracy. The follow-up data is important which can further improve the predictive models' performance. With similar performances among different ML techniques, the algorithm's characteristics and performance on severe stroke patients will be the primary focus when we further develop inference models and artificial intelligence tools for potential medical. Published by Elsevier B.V.

Entities:  

Keywords:  Hemorrhagic stroke; Ischemic stroke; Machine learning; Stroke outcome

Mesh:

Year:  2020        PMID: 32044620      PMCID: PMC7245557          DOI: 10.1016/j.cmpb.2020.105381

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  31 in total

Review 1.  Prediction of recovery of motor function after stroke.

Authors:  Cathy Stinear
Journal:  Lancet Neurol       Date:  2010-10-27       Impact factor: 44.182

2.  Predicting outcome of IV thrombolysis-treated ischemic stroke patients: the DRAGON score.

Authors:  D Strbian; A Meretoja; F J Ahlhelm; J Pitkäniemi; P Lyrer; M Kaste; S Engelter; T Tatlisumak
Journal:  Neurology       Date:  2012-02-07       Impact factor: 9.910

3.  Global stroke statistics.

Authors:  Amanda G Thrift; Dominique A Cadilhac; Tharshanah Thayabaranathan; George Howard; Virginia J Howard; Peter M Rothwell; Geoffrey A Donnan
Journal:  Int J Stroke       Date:  2014-01       Impact factor: 5.266

4.  Disability status at 1 month is a reliable proxy for final ischemic stroke outcome.

Authors:  Bruce Ovbiagele; Patrick D Lyden; Jeffrey L Saver
Journal:  Neurology       Date:  2010-08-24       Impact factor: 9.910

5.  Use of the Barthel index and modified Rankin scale in acute stroke trials.

Authors:  G Sulter; C Steen; J De Keyser
Journal:  Stroke       Date:  1999-08       Impact factor: 7.914

Review 6.  Predictors of upper limb recovery after stroke: a systematic review and meta-analysis.

Authors:  Fiona Coupar; Alex Pollock; Phil Rowe; Christopher Weir; Peter Langhorne
Journal:  Clin Rehabil       Date:  2011-10-24       Impact factor: 3.477

7.  Factors influencing stroke survivors' quality of life during subacute recovery.

Authors:  Deborah S Nichols-Larsen; P C Clark; Angelique Zeringue; Arlene Greenspan; Sarah Blanton
Journal:  Stroke       Date:  2005-06-09       Impact factor: 7.914

Review 8.  Sex differences in stroke: epidemiology, clinical presentation, medical care, and outcomes.

Authors:  Mathew J Reeves; Cheryl D Bushnell; George Howard; Julia Warner Gargano; Pamela W Duncan; Gwen Lynch; Arya Khatiwoda; Lynda Lisabeth
Journal:  Lancet Neurol       Date:  2008-08-21       Impact factor: 44.182

9.  Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy.

Authors:  Hamed Asadi; Richard Dowling; Bernard Yan; Peter Mitchell
Journal:  PLoS One       Date:  2014-02-10       Impact factor: 3.240

10.  Prediction of stroke thrombolysis outcome using CT brain machine learning.

Authors:  Paul Bentley; Jeban Ganesalingam; Anoma Lalani Carlton Jones; Kate Mahady; Sarah Epton; Paul Rinne; Pankaj Sharma; Omid Halse; Amrish Mehta; Daniel Rueckert
Journal:  Neuroimage Clin       Date:  2014-03-30       Impact factor: 4.881

View more
  9 in total

1.  A machine learning approach to identifying important features for achieving step thresholds in individuals with chronic stroke.

Authors:  Allison E Miller; Emily Russell; Darcy S Reisman; Hyosub E Kim; Vu Dinh
Journal:  PLoS One       Date:  2022-06-17       Impact factor: 3.752

2.  Random forest-based prediction of stroke outcome.

Authors:  Carlos Fernandez-Lozano; Pablo Hervella; Virginia Mato-Abad; Manuel Rodríguez-Yáñez; Sonia Suárez-Garaboa; Iria López-Dequidt; Ana Estany-Gestal; Tomás Sobrino; Francisco Campos; José Castillo; Santiago Rodríguez-Yáñez; Ramón Iglesias-Rey
Journal:  Sci Rep       Date:  2021-05-12       Impact factor: 4.379

3.  Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke.

Authors:  Sheng-Feng Sung; Chih-Hao Chen; Ru-Chiou Pan; Ya-Han Hu; Jiann-Shing Jeng
Journal:  J Am Heart Assoc       Date:  2021-11-19       Impact factor: 6.106

4.  Using a Multiclass Machine Learning Model to Predict the Outcome of Acute Ischemic Stroke Requiring Reperfusion Therapy.

Authors:  I-Min Chiu; Wun-Huei Zeng; Chi-Yung Cheng; Shih-Hsuan Chen; Chun-Hung Richard Lin
Journal:  Diagnostics (Basel)       Date:  2021-01-06

Review 5.  Predicting Ischemic Stroke Outcome Using Deep Learning Approaches.

Authors:  Gang Fang; Zhennan Huang; Zhongrui Wang
Journal:  Front Genet       Date:  2022-01-24       Impact factor: 4.599

6.  Early Prediction of Functional Outcomes After Acute Ischemic Stroke Using Unstructured Clinical Text: Retrospective Cohort Study.

Authors:  Sheng-Feng Sung; Cheng-Yang Hsieh; Ya-Han Hu
Journal:  JMIR Med Inform       Date:  2022-02-17

7.  Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms.

Authors:  Yeong Hwan Ryu; Seo Young Kim; Tae Uk Kim; Seong Jae Lee; Soo Jun Park; Ho-Youl Jung; Jung Keun Hyun
Journal:  J Clin Med       Date:  2022-04-18       Impact factor: 4.964

8.  Stacking ensemble learning model to predict 6-month mortality in ischemic stroke patients.

Authors:  Lee Hwangbo; Yoon Jung Kang; Hoon Kwon; Jae Il Lee; Han-Jin Cho; Jun-Kyeung Ko; Sang Min Sung; Tae Hong Lee
Journal:  Sci Rep       Date:  2022-10-17       Impact factor: 4.996

9.  Transforming self-reported outcomes from a stroke register to the modified Rankin Scale: a cross-sectional, explorative study.

Authors:  Tamar Abzhandadze; Malin Reinholdsson; Annie Palstam; Marie Eriksson; Katharina S Sunnerhagen
Journal:  Sci Rep       Date:  2020-10-14       Impact factor: 4.379

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.