scholarly journals Early outcome prediction for out-of-hospital cardiac arrest with initial shockable rhythm using machine learning models

Resuscitation ◽  
2021 ◽  
Vol 158 ◽  
pp. 49-56
Author(s):  
Yohei Hirano ◽  
Yutaka Kondo ◽  
Koichiro Sueyoshi ◽  
Ken Okamoto ◽  
Hiroshi Tanaka
Keyword(s):  
Machine Learning ◽  
Cardiac Arrest ◽  
Outcome Prediction ◽  
Learning Models ◽  
Early Outcome ◽  
Shockable Rhythm ◽  
Hospital Cardiac Arrest ◽  
Machine Learning Models

MACHINE LEARNING MODELS SIGNIFICANT IMPROVE OUTCOME PREDICTION AFTER CARDIAC ARREST

2018 ◽  
Vol 71 (11) ◽  
pp. A775
Author(s):  
Shane Nanayakkara ◽  
Sam Fogarty ◽  
Kelvin Ross ◽  
Zoran Milosevic ◽  
Brent Richards ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiac Arrest ◽  
Outcome Prediction ◽  
Learning Models ◽  
Improve Outcome ◽  
Machine Learning Models

scholarly journals Improved outcome prediction of oropharyngeal cancer by combining clinical and MRI features in machine learning models

2021 ◽  
pp. 109701
Author(s):  
Paula Bos ◽  
Michiel W.M. van den Brekel ◽  
Zeno A.R. Gouw ◽  
Abrahim Al-Mamgani ◽  
Marjaneh Taghavi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Oropharyngeal Cancer ◽  
Outcome Prediction ◽  
Learning Models ◽  
Mri Features ◽  
Improved Outcome ◽  
Machine Learning Models

scholarly journals Heart Failure Diagnosis, Readmission, and Mortality Prediction Using Machine Learning and Artificial Intelligence Models

2020 ◽  
Vol 7 (4) ◽  
pp. 212-219 ◽  
Author(s):  
Aixia Guo ◽  
Michael Pasque ◽  
Francis Loh ◽  
Douglas L. Mann ◽  
Philip R. O. Payne
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Outcome Prediction ◽  
Predictive Accuracy ◽  
Imbalanced Data ◽  
Mortality Prediction ◽  
Machine Learning Techniques ◽  
Patient Specific ◽  
Learning Models ◽  
Machine Learning Models

Abstract Purpose of Review One in five people will develop heart failure (HF), and 50% of HF patients die in 5 years. The HF diagnosis, readmission, and mortality prediction are essential to develop personalized prevention and treatment plans. This review summarizes recent findings and approaches of machine learning models for HF diagnostic and outcome prediction using electronic health record (EHR) data. Recent Findings A set of machine learning models have been developed for HF diagnostic and outcome prediction using diverse variables derived from EHR data, including demographic, medical note, laboratory, and image data, and achieved expert-comparable prediction results. Summary Machine learning models can facilitate the identification of HF patients, as well as accurate patient-specific assessment of their risk for readmission and mortality. Additionally, novel machine learning techniques for integration of diverse data and improvement of model predictive accuracy in imbalanced data sets are critical for further development of these promising modeling methodologies.

Abstract 12747: Protein Profiling for Survival Outcome Prediction in Out-of-Hospital Cardiac Arrest Patients

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Chien-Hua Huang ◽  
Min-Shan Tsai ◽  
Wei-Tien Chang ◽  
Hsin-Yun Hsu ◽  
Wen-Jone Chen
Keyword(s):  
Cardiac Arrest ◽  
Outcome Prediction ◽  
Characteristic Curve ◽  
Protein Profiling ◽  
Inflammatory Reactions ◽  
Shockable Rhythm ◽  
Multiple Biomarkers ◽  
High Prediction ◽  
Hospital Cardiac Arrest ◽  
Pai 1

Introduction: Outcome prediction is still a challenge for out-of-hospital cardiac arrest (OHCA) patients in early post-cardiac arrest period. Changes of protein expression after cardiac arrest and resuscitation could be biomarkers for outcomes prediction. Single biomarker can not reach adequate power to predict outcome due to the complexity of pathophysiological cascades in post-cardiac arrest period. Protein profiling can measure multiple biomarkers at a time point and can provide better information for outcome prediction. Hypothesis: Identify the association of survival to discharge outcome and biomarkers changes by protein profiling in cardiac arrest patients Methods: Total 99 adult non-traumatic OHCA patients with sustained ROSC were enrolled for the study. There were 45 patients survival to hospital discharge. Blood were sampled at 24 hours after cardiac arrest. Protein profiling for 21 different biomarkers, which included brain, heart, inflammatory reactions, oxidative stress and coagulation markers, was measured by suspension microarray assay. Clustering analyses were carried out using Multi-Experiment Viewer (MeV v4.8.1). Results: Heat maps were generated to visualize the Log2 values relative to median values of overall patient sample pool. Based on the performed statistical analysis to narrow down the biomarker panel, we investigated samples respectively by employing only the significant parameters for the Hierarchical Clustering (HCL) analysis. Nine candidate biomarkers (IL-6, IL-8, IL-10, MCP-1, MDA-LDL, Cystatin C, PAI-1, NT-Pro-BNP and S100B) identified respectively from samples pools were applied. The discrimination based on the selected parameters was 76.3% to be accurately clustered in HCL analysis. When adding these biomarkers into clinical variables (age, sex, Apache II, hypothermia, shockable rhythm, CPR duration), receiver-operating characteristic curve analysis showed high prediction power for survival to discharge (area under curve = 0.9378, p<0.01) Conclusion: Protein profiling with suspension microarray can demonstrate the pattern of biomarkers in various pathophysiological changes after cardiac arrest. It has the potential to help predicting the outcome in OHCA patients.

Sign in / Sign up

Export Citation Format

Share Document