Comparison among random forest, logistic regression, and existing clinical risk scores for predicting outcomes in patients with atrial fibrillation: A report from the <scp>J‐RHYTHM</scp> registry

Watanabe, Eiichi; Noyama, Shunsuke; Kiyono, Ken; Inoue, Hiroshi; Atarashi, Hirotsugu; Okumura, Ken; Yamashita, Takeshi; Lip, Gregory Y.H.; Kodani, Eitaro; Origasa, Hideki

doi:10.1002/clc.23688

Cited by 12 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the HAS-BLED score’s reliance on labile INR is outdated, given the shift towards DOACs 13 . Our findings of a modest improvement in ML performance over conventional risk scores align with prior studies 16,17 , which consistently demonstrated the poor performance of the HAS-BLED score, with AUC-ROC ranging from 0.50 to 0.64 16,19,20,44,45 . However, these studies were limited by their focus on broader contexts or specific AF subpopulations 18,19 , restricting their applicability to the broader AF population on DOACs in a real-world clinical scenario when first evaluated by a cardiologist for AF management.…”

Section: Discussionsupporting

confidence: 88%

Machine Learning - Based Bleeding Risk Predictions in Atrial Fibrillation Patients on Direct Oral Anticoagulants

Chaudhary,

Nourelahi,

Thoma

et al. 2024

Preprint

View full text Add to dashboard Cite

Importance: Accurately predicting major bleeding events in non-valvular atrial fibrillation (AF) patients on direct oral anticoagulants (DOACs) is crucial for personalized treatment and improving patient outcomes, especially with emerging alternatives like left atrial appendage closure devices. The left atrial appendage closure devices reduce stroke risk comparably but with significantly fewer non-procedural bleeding events. Objective: To evaluate the performance of machine learning (ML) risk models in predicting clinically significant bleeding events requiring hospitalization and hemorrhagic stroke in non-valvular AF patients on DOACs compared to conventional bleeding risk scores (HAS-BLED, ORBIT, and ATRIA) at the index visit to a cardiologist for AF management. Design: Prognostic modeling with retrospective cohort study design using electronic health record (EHR) data, with clinical follow-up at one-, two-, and five-years. Setting: University of Pittsburgh Medical Center (UPMC) system. Participants: 24,468 non-valvular AF patients aged ≥18 years treated with DOACs, excluding those with prior history of significant bleeding, other indications for DOACs, on warfarin or contraindicated to DOACs. Exposure(s): DOAC therapy for non-valvular AF. Main Outcome(s) and Measure(s): The primary endpoint was clinically significant bleeding requiring hospitalization within one year of index visit. The models incorporated demographic, clinical, and laboratory variables available in the EHR at the index visit. Results: Among 24,468 patients, 553 (2.3%) had bleeding events within one year, 829 (3.5%) within two years, and 1,292 (5.8%) within five years of index visit. We evaluated multivariate logistic regression and ML models including random forest, classification trees, k-nearest neighbor, naive Bayes, and extreme gradient boosting (XGBoost) which modestly outperformed HAS-BLED, ATRIA, and ORBIT scores in predicting clinically significant bleeding at 1-year follow-up. The best performing model (random forest) showed area under the curve (AUC-ROC) 0.76 (0.70-0.81), G-Mean score of 0.67, net reclassification index 0.14 compared to 0.57 (0.50-0.63), G-Mean score of 0.57 for HASBLED score, p-value for difference <0.001. The ML models had improved performance compared to conventional risk across time-points of 2-year and 5-years and within the subgroup of hemorrhagic stroke. SHAP analysis identified novel risk factors including measures from body mass index, cholesterol profile, and insurance type beyond those used in conventional risk scores. Conclusions and Relevance: Our findings demonstrate the superior performance of ML models compared to conventional bleeding risk scores and identify novel risk factors highlighting the potential for personalized bleeding risk assessment in AF patients on DOACs.

show abstract

Section: Discussionsupporting

confidence: 88%

Machine Learning - Based Bleeding Risk Predictions in Atrial Fibrillation Patients on Direct Oral Anticoagulants

Chaudhary,

Nourelahi,

Thoma

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…CatBoost is commonly utilized in the fields of business (60), financial assessments (61), Medicare fraud detection (62), environmental science (63,64), and public science (36). According to our review of the literature, in the field of medicine, the random forest model has retained a competitive edge and is often superior in the prediction and classification of medical conditions compared with traditional logistic regression methods and machine learning methods such as neural networks, SVMs, and decision trees (65)(66)(67)(68). In our study, the CatBoost model outperformed the random forest model in classifying nonrecurrent and recurrent stroke.…”

Section: Discussionmentioning

confidence: 99%

Applying Machine Learning to Carotid Sonographic Features for Recurrent Stroke in Patients With Acute Stroke

Lin

Law

Yeh

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

BackgroundAlthough carotid sonographic features have been used as predictors of recurrent stroke, few large-scale studies have explored the use of machine learning analysis of carotid sonographic features for the prediction of recurrent stroke.MethodsWe retrospectively collected electronic medical records of enrolled patients from the data warehouse of China Medical University Hospital, a tertiary medical center in central Taiwan, from January 2012 to November 2018. We included patients who underwent a documented carotid ultrasound within 30 days of experiencing an acute first stroke during the study period. We classified these participants into two groups: those with non-recurrent stroke (those who has not been diagnosed with acute stroke again during the study period) and those with recurrent stoke (those who has been diagnosed with acute stroke during the study period). A total of 1,235 carotid sonographic parameters were analyzed. Data on the patients' demographic characteristics and comorbidities were also collected. Python 3.7 was used as the programming language, and the scikit-learn toolkit was used to complete the derivation and verification of the machine learning methods.ResultsIn total, 2,411 patients were enrolled in this study, of whom 1,896 and 515 had non-recurrent and recurrent stroke, respectively. After extraction, 43 features of carotid sonography (36 carotid sonographic parameters and seven transcranial color Doppler sonographic parameter) were analyzed. For predicting recurrent stroke, CatBoost achieved the highest area under the curve (0.844, CIs 95% 0.824–0.868), followed by the Light Gradient Boosting Machine (0.832, CIs 95% 0.813–0.851), random forest (0.819, CIs 95% 0.802–0.846), support-vector machine (0.759, CIs 95% 0.739–0.781), logistic regression (0.781, CIs 95% 0.764–0.800), and decision tree (0.735, CIs 95% 0.717–0.755) models.ConclusionWhen using the CatBoost model, the top three features for predicting recurrent stroke were determined to be the use of anticoagulation medications, the use of NSAID medications, and the resistive index of the left subclavian artery. The CatBoost model demonstrated efficiency and achieved optimal performance in the predictive classification of non-recurrent and recurrent stroke.

show abstract

“…LR utilizes a function of the logistic to create a binary dependent parameter [18]. It is a curve-fitting module in which the dependent value varies in relation to the independent value and the data points are aligned to be as close to the curve as possible [19], [20]. This study, the regularization was carried out with the help of ridge (L2), that reduces the sum of the weight's squares to the greatest extent possible.…”

Section: Logistic Regression (Lr)mentioning

confidence: 99%

“…This work proposed two cases for training and prediction process over three group's image eye diseases; Case 1, Utilised three models, ANN, LR, and KNN, separately for the training and testing process to distinguish the images of two eye diseases, CNV and DME, from the healthy one. Figure 2 illustrate the proposed algorithm for this case, which utilized (6,000) total images (with 2,000 images for each type of eye disease: CNV, DME, and healthy one were chosen for comparison), and the dataset was split into 9:1 ratio for training and testing (The ratio of training 90% with repeat train/test (20), get the highest AC (0.958) for ANN models). For case 2, a new model was presented and we called it the Stacking model.…”

Section: Proposed Algorithmsmentioning

confidence: 99%

Machine learning-based diagnosis of eye-diseases

Yousif,

Tomah,

Mohsin

2023

IJEECS

View full text Add to dashboard Cite

<span>Over the last several years, artificial intelligence (AI) has been substantially utilized in image processing and classification. Several tools are accessible for visualizing, training, and pre-processing image data. One such tool is orange, which has several pre-processing modules and a particular add-on for image processing methods in addition to excellent data visualization. The tool (version 3.32.0) was used in the suggested study to give a comparative and predictive analysis using several classification models. Three main models have been used to train and predict the three groups image eye diseases. The results were compared based on some criteria, including area-under-a-curve (AUC), the accuracy of classification (CA), F1 score, precision, and recall. These models include K-nearest neighbour (KNN), logistic regression (LR), artificial neural networks (ANN) and stacking model. The stacking model, which is a novel model, is also presented in this work by concatenating the output of the parallel form of ANN and KNN models with the LR model. The best performance belonged to the Stacking model, which offers the best detection and prediction results.</span>

show abstract

Comparison among random forest, logistic regression, and existing clinical risk scores for predicting outcomes in patients with atrial fibrillation: A report from the J‐RHYTHM registry

Cited by 12 publications

References 32 publications

Machine Learning - Based Bleeding Risk Predictions in Atrial Fibrillation Patients on Direct Oral Anticoagulants

Machine Learning - Based Bleeding Risk Predictions in Atrial Fibrillation Patients on Direct Oral Anticoagulants

Applying Machine Learning to Carotid Sonographic Features for Recurrent Stroke in Patients With Acute Stroke

Machine learning-based diagnosis of eye-diseases

Contact Info

Product

Resources

About