The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models

Fan, Jiaxin; Chen, Mengying; Luo, Jianchao; Yang, Shusen; Shi, Jiachen; Yao, Qingling; Zhang, Xiaodong; Du, Shuang; Qu, Huiyang; Cheng, Yuxuan; Ma, Shuyin; Zhang, Meijuan; Xu, Xi; Wang, Qian; Zhan, Shuqin

doi:10.1186/s12911-021-01480-3

Cited by 16 publications

(16 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine learning methods have been a powerful tool for precision medicine in stroke [17,[21][22][23][24]26]. Meanwhile, these methods are also applied to different data formats [25,[34][35][36]. Nevertheless, applications of machine learning for TOAST subtypes classification is very scarce.…”

Section: Discussionmentioning

confidence: 99%

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

Zhang

Wang

Pei

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background TOAST subtype classification is important for diagnosis and research of ischemic stroke. Limited by experience of neurologist and time-consuming manual adjudication, it is a big challenge to finish TOAST classification effectively. We propose a novel active deep learning architecture to classify TOAST. Methods To simulate the diagnosis process of neurologists, we drop the valueless features by XGB algorithm and rank the remaining ones. Utilizing active learning framework, we propose a novel causal CNN, in which it combines with a mixed active selection criterion to optimize the uncertainty of samples adaptively. Meanwhile, KL-focal loss derived from the enhancement of Focal loss by KL regularization is introduced to accelerate the iterative fine-tuning of the model. Results To evaluate the proposed method, we construct a dataset which consists of totally 2310 patients. In a series of sequential experiments, we verify the effectiveness of each contribution by different evaluation metrics. Experimental results show that the proposed method achieves competitive results on each evaluation metric. In this task, the improvement of AUC is the most obvious, reaching 77.4. Conclusions We construct a backbone causal CNN to simulate the neurologist process of that could enhance the internal interpretability. The research on clinical data also indicates the potential application value of this model in stroke medicine. Future work we would consider various data types and more comprehensive patient types to achieve fully automated subtype classification.

show abstract

Section: Discussionmentioning

confidence: 99%

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

Zhang

Wang

Pei

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…A certain study by Fan et al [79] shows the comparison of six different ML-based models that are used in the diagnosis or prediction of Carotid Atherosclerosis by combining electronic health record data, like ultrasonography [80] , with ML algorithms like Logistic Regression, Random Forest, Decision Trees, etc. The analysis revealed that Logistic Regression showed the highest predictive ability, which was also verified by tenfold cross-validation, whereas decision trees showed the poorest predictive performance.…”

Section: Applications In the Present Scenariosmentioning

confidence: 99%

“…Patient data analyzed using these algorithms has shown efficient detection and diagnosis, better response to healthcare services, accompanied by the increase in clinical efficiency and resource reallocation (especially in the case of predictive algorithms) [15] , [16] . Very recently, combinations of ML-based algorithms with deep learning and ensemble systems have been successfully implemented in the diagnosis and detection of various traditional diseases like cancer and Alzheimer's disease [63] , [72] , [75] , [79] , [82] , [83] and even in the case of Covid-19 [50] , [86] , [89] , which has been ravaging the world. Some models have also been used to study pathogenesis and other aspects of cellular biology [36] .…”

Section: Future Prospects and Conclusionmentioning

confidence: 99%

Data-driven machine learning: A new approach to process and utilize biomedical data

Srivastava¹,

Jha²

2022

Predictive Modeling in Biomedical Data Mining and Analysis

View full text Add to dashboard Cite

“…Machine learning (ML) has been used and has shown an acceptable performance in predicting the risk of diseases [ 10 , 11 , 12 ]. Therefore, in the current study, we used simple clinical data obtained by an ML model to predict LAAV and aim to examine the feature importance of the ML model to understand its mechanism.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Model-Based Simple Clinical Information to Predict Decreased Left Atrial Appendage Flow Velocity

Li¹,

Dou

Ding

et al. 2022

JPM

View full text Add to dashboard Cite

Background: Transesophageal echocardiography (TEE) is the first technique of choice for evaluating the left atrial appendage flow velocity (LAAV) in clinical practice, which may cause some complications. Therefore, clinicians require a simple applicable method to screen patients with decreased LAAV. Therefore, we investigated the feasibility and accuracy of a machine learning (ML) model to predict LAAV. Method: The analysis included patients with atrial fibrillation who visited the general hospital of PLA and underwent transesophageal echocardiography (TEE) between January 2017 and December 2020. Three machine learning algorithms were used to predict LAAV. The area under the receiver operating characteristic curve (AUC) was measured to evaluate diagnostic accuracy. Results: Of the 1039 subjects, 125 patients (12%) were determined as having decreased LAAV (LAAV < 25 cm/s). Patients with decreased LAAV were fatter and showed a higher prevalence of persistent AF, heart failure, hypertension, diabetes and stroke, and the decreased LAAV group had a larger left atrium diameter and a higher serum level of NT-pro BNP than the control group (p < 0.05). Three machine-learning models (SVM model, RF model, and KNN model) were developed to predict LAAV. In the test data, the RF model performs best (R = 0.608, AUC = 0.89) among the three models. A fivefold cross-validation scheme further verified the predictive ability of the RF model. In the RF model, NT-proBNP was the factor with the strongest impact. Conclusions: A machine learning model (Random Forest model)-based simple clinical information showed good performance in predicting LAAV. The tool for the screening of decreased LAAV patients may be very helpful in the risk classification of patients with a high risk of LAA thrombosis.

show abstract

The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models

Cited by 16 publications

References 41 publications

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

Data-driven machine learning: A new approach to process and utilize biomedical data

Machine Learning Model-Based Simple Clinical Information to Predict Decreased Left Atrial Appendage Flow Velocity

Contact Info

Product

Resources

About