Predicting cerebral infarction in patients with atrial fibrillation using machine learning: The Fushimi AF registry

2021 ◽  
pp. 0271678X2110638
Author(s):  
Hidehisa Nishi ◽  
Naoya Oishi ◽  
Hisashi Ogawa ◽  
Kishida Natsue ◽  
Kento Doi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Cerebral Infarction ◽  
Validation Cohort ◽  
Learning Algorithm ◽  
Anticoagulation Therapy ◽  
Area Under The Curve ◽  
Discrimination Performance ◽  
Gradient Boosting ◽  
Derivation Cohort

The CHADS2 and CHA2DS2-VASc scores are widely used to assess ischemic risk in the patients with atrial fibrillation (AF). However, the discrimination performance of these scores is limited. Using the data from a community-based prospective cohort study, we sought to construct a machine learning-based prediction model for cerebral infarction in patients with AF, and to compare its performance with the existing scores. All consecutive patients with AF treated at 81 study institutions from March 2011 to May 2017 were enrolled (n = 4396). The whole dataset was divided into a derivation cohort (n = 1005) and validation cohort (n = 752) after excluding the patients with valvular AF and anticoagulation therapy. Using the derivation cohort dataset, a machine learning model based on gradient boosting tree algorithm (ML) was built to predict cerebral infarction. In the validation cohort, the receiver operating characteristic area under the curve of the ML model was higher than those of the existing models according to the Hanley and McNeil method: ML, 0.72 (95%CI, 0.66–0.79); CHADS2, 0.61 (95%CI, 0.53–0.69); CHA2DS2-VASc, 0.62 (95%CI, 0.54–0.70). As a conclusion, machine learning algorithm have the potential to perform better than the CHADS2 and CHA2DS2-VASc scores for predicting cerebral infarction in patients with non-valvular AF.

scholarly journals Predicting 1-Hour Thrombolysis Effect of r-tPA in Patients With Acute Ischemic Stroke Using Machine Learning Algorithm

2022 ◽  
Vol 12 ◽  
Author(s):  
Bin Zhu ◽  
Jianlei Zhao ◽  
Mingnan Cao ◽  
Wanliang Du ◽  
Liuqing Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Learning Algorithm ◽  
Degradation Products ◽  
Early Stage ◽  
Area Under The Curve ◽  
Recursive Feature Elimination ◽  
Gradient Boosting ◽  
Data Sets

Background: Thrombolysis with r-tPA is recommended for patients after acute ischemic stroke (AIS) within 4.5 h of symptom onset. However, only a few patients benefit from this therapeutic regimen. Thus, we aimed to develop an interpretable machine learning (ML)–based model to predict the thrombolysis effect of r-tPA at the super-early stage.Methods: A total of 353 patients with AIS were divided into training and test data sets. We then used six ML algorithms and a recursive feature elimination (RFE) method to explore the relationship among the clinical variables along with the NIH stroke scale score 1 h after thrombolysis treatment. Shapley additive explanations and local interpretable model–agnostic explanation algorithms were applied to interpret the ML models and determine the importance of the selected features.Results: Altogether, 353 patients with an average age of 63.0 (56.0–71.0) years were enrolled in the study. Of these patients, 156 showed a favorable thrombolysis effect and 197 showed an unfavorable effect. A total of 14 variables were enrolled in the modeling, and 6 ML algorithms were used to predict the thrombolysis effect. After RFE screening, seven variables under the gradient boosting decision tree (GBDT) model (area under the curve = 0.81, specificity = 0.61, sensitivity = 0.9, and F1 score = 0.79) demonstrated the best performance. Of the seven variables, activated partial thromboplastin clotting time (time), B-type natriuretic peptide, and fibrin degradation products were the three most important clinical characteristics that might influence r-tPA efficiency.Conclusion: This study demonstrated that the GBDT model with the seven variables could better predict the early thrombolysis effect of r-tPA.

scholarly journals Machine Learning Prediction of Stroke Mechanism in Embolic Strokes of Undetermined Source

Stroke ◽  
2020 ◽  
Vol 51 (9) ◽  
Author(s):  
Hooman Kamel ◽  
Babak B. Navi ◽  
Neal S. Parikh ◽  
Alexander E. Merkler ◽  
Peter M. Okin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Cross Validation ◽  
Learning Algorithm ◽  
Random Search ◽  
Model Performance ◽  
Area Under The Curve ◽  
Independent Set ◽  
Predicted Probability ◽  
Using Data

Background and Purpose: One-fifth of ischemic strokes are embolic strokes of undetermined source (ESUS). Their theoretical causes can be classified as cardioembolic versus noncardioembolic. This distinction has important implications, but the categories’ proportions are unknown. Methods: Using data from the Cornell Acute Stroke Academic Registry, we trained a machine-learning algorithm to distinguish cardioembolic versus non-cardioembolic strokes, then applied the algorithm to ESUS cases to determine the predicted proportion with an occult cardioembolic source. A panel of neurologists adjudicated stroke etiologies using standard criteria. We trained a machine learning classifier using data on demographics, comorbidities, vitals, laboratory results, and echocardiograms. An ensemble predictive method including L1 regularization, gradient-boosted decision tree ensemble (XGBoost), random forests, and multivariate adaptive splines was used. Random search and cross-validation were used to tune hyperparameters. Model performance was assessed using cross-validation among cases of known etiology. We applied the final algorithm to an independent set of ESUS cases to determine the predicted mechanism (cardioembolic or not). To assess our classifier’s validity, we correlated the predicted probability of a cardioembolic source with the eventual post-ESUS diagnosis of atrial fibrillation. Results: Among 1083 strokes with known etiologies, our classifier distinguished cardioembolic versus noncardioembolic cases with excellent accuracy (area under the curve, 0.85). Applied to 580 ESUS cases, the classifier predicted that 44% (95% credibility interval, 39%–49%) resulted from cardiac embolism. Individual ESUS patients’ predicted likelihood of cardiac embolism was associated with eventual atrial fibrillation detection (OR per 10% increase, 1.27 [95% CI, 1.03–1.57]; c-statistic, 0.68 [95% CI, 0.58–0.78]). ESUS patients with high predicted probability of cardiac embolism were older and had more coronary and peripheral vascular disease, lower ejection fractions, larger left atria, lower blood pressures, and higher creatinine levels. Conclusions: A machine learning estimator that distinguished known cardioembolic versus noncardioembolic strokes indirectly estimated that 44% of ESUS cases were cardioembolic.

scholarly journals Performance of Machine Learning Algorithms with Different K Values in K-fold CrossValidation

2021 ◽  
Vol 13 (6) ◽  
pp. 61-71
Author(s):  
Isaac Kofi Nti ◽  
◽  
Owusu N yarko-Boateng ◽  
Justice Aning
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Experimental Studies ◽  
Area Under The Curve ◽  
Essential Element ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Machine Learning Algorithm ◽  
K Value

The numerical value of k in a k-fold cross-validation training technique of machine learning predictive models is an essential element that impacts the model’s performance. A right choice of k results in better accuracy, while a poorly chosen value for k might affect the model’s performance. In literature, the most commonly used values of k are five (5) or ten (10), as these two values are believed to give test error rate estimates that suffer neither from extremely high bias nor very high variance. However, there is no formal rule. To the best of our knowledge, few experimental studies attempted to investigate the effect of diverse k values in training different machine learning models. This paper empirically analyses the prevalence and effect of distinct k values (3, 5, 7, 10, 15 and 20) on the validation performance of four well-known machine learning algorithms (Gradient Boosting Machine (GBM), Logistic Regression (LR), Decision Tree (DT) and K-Nearest Neighbours (KNN)). It was observed that the value of k and model validation performance differ from one machine-learning algorithm to another for the same classification task. However, our empirical suggest that k = 7 offers a slight increase in validations accuracy and area under the curve measure with lesser computational complexity than k = 10 across most MLA. We discuss in detail the study outcomes and outline some guidelines for beginners in the machine learning field in selecting the best k value and machine learning algorithm for a given task.

scholarly journals An Autoencoder and Machine Learning Model to Predict Suicidal Ideation with Brain Structural Imaging

2020 ◽  
Vol 9 (3) ◽  
pp. 658 ◽  
Author(s):  
Jun-Cheng Weng ◽  
Tung-Yeh Lin ◽  
Yuan-Hsiung Tsai ◽  
Man Teng Cheok ◽  
Yi-Peng Eve Chang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Suicidal Ideation ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Learning Model ◽  
Supervised Machine Learning ◽  
Gradient Boosting ◽  
Machine Learning Model ◽  
Extreme Gradient Boosting ◽  
Depressive Patients

It is estimated that at least one million people die by suicide every year, showing the importance of suicide prevention and detection. In this study, an autoencoder and machine learning model was employed to predict people with suicidal ideation based on their structural brain imaging. The subjects in our generalized q-sampling imaging (GQI) dataset consisted of three groups: 41 depressive patients with suicidal ideation (SI), 54 depressive patients without suicidal thoughts (NS), and 58 healthy controls (HC). In the GQI dataset, indices of generalized fractional anisotropy (GFA), isotropic values of the orientation distribution function (ISO), and normalized quantitative anisotropy (NQA) were separately trained in different machine learning models. A convolutional neural network (CNN)-based autoencoder model, the supervised machine learning algorithm extreme gradient boosting (XGB), and logistic regression (LR) were used to discriminate SI subjects from NS and HC subjects. After five-fold cross validation, separate data were tested to obtain the accuracy, sensitivity, specificity, and area under the curve of each result. Our results showed that the best pattern of structure across multiple brain locations can classify suicidal ideates from NS and HC with a prediction accuracy of 85%, a specificity of 100% and a sensitivity of 75%. The algorithms developed here might provide an objective tool to help identify suicidal ideation risk among depressed patients alongside clinical assessment.

scholarly journals Machine learning does not improve upon traditional regression in predicting outcomes in atrial fibrillation: an analysis of the ORBIT-AF and GARFIELD-AF registries

EP Europace ◽  
2020 ◽  
Vol 22 (11) ◽  
pp. 1635-1644 ◽  
Author(s):  
Zak Loring ◽  
Suchit Mehrotra ◽  
Jonathan P Piccini ◽  
John Camm ◽  
David Carlson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Regression Models ◽  
Prediction Models ◽  
Area Under The Curve ◽  
Population Based ◽  
Discriminatory Power ◽  
Gradient Boosting ◽  
Stepwise Logistic Regression ◽  
Prediction Modelling

Abstract Aims Prediction models for outcomes in atrial fibrillation (AF) are used to guide treatment. While regression models have been the analytic standard for prediction modelling, machine learning (ML) has been promoted as a potentially superior methodology. We compared the performance of ML and regression models in predicting outcomes in AF patients. Methods and results The Outcomes Registry for Better Informed Treatment of Atrial Fibrillation (ORBIT-AF) and Global Anticoagulant Registry in the FIELD (GARFIELD-AF) are population-based registries that include 74 792 AF patients. Models were generated from potential predictors using stepwise logistic regression (STEP), random forests (RF), gradient boosting (GB), and two neural networks (NNs). Discriminatory power was highest for death [STEP area under the curve (AUC) = 0.80 in ORBIT-AF, 0.75 in GARFIELD-AF] and lowest for stroke in all models (STEP AUC = 0.67 in ORBIT-AF, 0.66 in GARFIELD-AF). The discriminatory power of the ML models was similar or lower than the STEP models for most outcomes. The GB model had a higher AUC than STEP for death in GARFIELD-AF (0.76 vs. 0.75), but only nominally, and both performed similarly in ORBIT-AF. The multilayer NN had the lowest discriminatory power for all outcomes. The calibration of the STEP modelswere more aligned with the observed events for all outcomes. In the cross-registry models, the discriminatory power of the ML models was similar or lower than the STEP for most cases. Conclusion When developed from two large, community-based AF registries, ML techniques did not improve prediction modelling of death, major bleeding, or stroke.

scholarly journals Early Prediction of Seven-Day Mortality in Intensive Care Unit Using a Machine Learning Model: Results from the SPIN-UTI Project

2021 ◽  
Vol 10 (5) ◽  
pp. 992
Author(s):  
Martina Barchitta ◽  
Andrea Maugeri ◽  
Giuliana Favara ◽  
Paolo Marco Riela ◽  
Giovanni Gallo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Intensive Care Units ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Support Vector ◽  
Icu Admission ◽  
Risk Of Death ◽  
Saps Ii ◽  
Svm Algorithm

Patients in intensive care units (ICUs) were at higher risk of worsen prognosis and mortality. Here, we aimed to evaluate the ability of the Simplified Acute Physiology Score (SAPS II) to predict the risk of 7-day mortality, and to test a machine learning algorithm which combines the SAPS II with additional patients’ characteristics at ICU admission. We used data from the “Italian Nosocomial Infections Surveillance in Intensive Care Units” network. Support Vector Machines (SVM) algorithm was used to classify 3782 patients according to sex, patient’s origin, type of ICU admission, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II, presence of invasive devices, trauma, impaired immunity, antibiotic therapy and onset of HAI. The accuracy of SAPS II for predicting patients who died from those who did not was 69.3%, with an Area Under the Curve (AUC) of 0.678. Using the SVM algorithm, instead, we achieved an accuracy of 83.5% and AUC of 0.896. Notably, SAPS II was the variable that weighted more on the model and its removal resulted in an AUC of 0.653 and an accuracy of 68.4%. Overall, these findings suggest the present SVM model as a useful tool to early predict patients at higher risk of death at ICU admission.

scholarly journals Development of a machine learning model for predicting pediatric mortality in the early stages of intensive care unit admission

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bongjin Lee ◽  
Kyunghoon Kim ◽  
Hyejin Hwang ◽  
You Sun Kim ◽  
Eun Hee Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Validation Cohort ◽  
External Validation ◽  
Learning Model ◽  
Derivation Cohort ◽  
Icu Admission ◽  
Early Stages ◽  
Machine Learning Model

AbstractThe aim of this study was to develop a predictive model of pediatric mortality in the early stages of intensive care unit (ICU) admission using machine learning. Patients less than 18 years old who were admitted to ICUs at four tertiary referral hospitals were enrolled. Three hospitals were designated as the derivation cohort for machine learning model development and internal validation, and the other hospital was designated as the validation cohort for external validation. We developed a random forest (RF) model that predicts pediatric mortality within 72 h of ICU admission, evaluated its performance, and compared it with the Pediatric Index of Mortality 3 (PIM 3). The area under the receiver operating characteristic curve (AUROC) of RF model was 0.942 (95% confidence interval [CI] = 0.912–0.972) in the derivation cohort and 0.906 (95% CI = 0.900–0.912) in the validation cohort. In contrast, the AUROC of PIM 3 was 0.892 (95% CI = 0.878–0.906) in the derivation cohort and 0.845 (95% CI = 0.817–0.873) in the validation cohort. The RF model in our study showed improved predictive performance in terms of both internal and external validation and was superior even when compared to PIM 3.

Clinical Score and Machine Learning-Based Model to Predict Diagnosis of Primary Aldosteronism in Arterial Hypertension

Hypertension ◽  
2021 ◽  
Vol 78 (5) ◽  
pp. 1595-1604
Author(s):  
Fabrizio Buffolo ◽  
Jacopo Burrello ◽  
Alessio Burrello ◽  
Daniel Heinrich ◽  
Christian Adolf ◽  
...  
Keyword(s):  
Machine Learning ◽  
Arterial Hypertension ◽  
Primary Aldosteronism ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Clinical Score ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Individual Risk ◽  
The Individual

Primary aldosteronism (PA) is the cause of arterial hypertension in 4% to 6% of patients, and 30% of patients with PA are affected by unilateral and surgically curable forms. Current guidelines recommend screening for PA ≈50% of patients with hypertension on the basis of individual factors, while some experts suggest screening all patients with hypertension. To define the risk of PA and tailor the diagnostic workup to the individual risk of each patient, we developed a conventional scoring system and supervised machine learning algorithms using a retrospective cohort of 4059 patients with hypertension. On the basis of 6 widely available parameters, we developed a numerical score and 308 machine learning-based models, selecting the one with the highest diagnostic performance. After validation, we obtained high predictive performance with our score (optimized sensitivity of 90.7% for PA and 92.3% for unilateral PA [UPA]). The machine learning-based model provided the highest performance, with an area under the curve of 0.834 for PA and 0.905 for diagnosis of UPA, with optimized sensitivity of 96.6% for PA, and 100.0% for UPA, at validation. The application of the predicting tools allowed the identification of a subgroup of patients with very low risk of PA (0.6% for both models) and null probability of having UPA. In conclusion, this score and the machine learning algorithm can accurately predict the individual pretest probability of PA in patients with hypertension and circumvent screening in up to 32.7% of patients using a machine learning-based model, without omitting patients with surgically curable UPA.

Abstract WP406: Training and Validation of Deepmedic Machine Learning Tool for Automated Hematoma Segmentation and Volume Analysis on CT Using Multicenter Data

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Sean Nurmsoo ◽  
Alessandro Guida ◽  
Alex Wong ◽  
Richard I Aviv ◽  
Andrew Demchuk ◽  
...  
Keyword(s):  
Machine Learning ◽  
Validation Cohort ◽  
Learning Algorithm ◽  
Intraclass Correlation ◽  
Ct Scans ◽  
Dice Similarity Coefficient ◽  
Machine Learning Algorithm ◽  
Manual Segmentation ◽  
Training Cohort ◽  
Volume Calculation

Introduction: We sought to train and validate an automated machine learning algorithm for ICH segmentation and volume calculation using multicenter data. Methods: An open-source 3D deep machine learning algorithm “DeepMedic” was trained using manually segmented ICH from 208 CT scans (129 patients) from the multicenter PREDICT study. The algorithm was then validated with 125 manually segmented CT scans (48 patients) from the SPOTLIGHT study. Manual segmentation was performed with Quantomo semi-automated software. ABC/2 was measured for all studies by two neuroradiologists. Accuracy of DeepMedic segmentation was assessed using the Dice similarity coefficient. Analysis was stratified by presence of IVH. Intraclass correlation (ICC) with 95% confidence intervals (CI) assessed agreement between manual vs. DeepMedic segmentation volume; and manual segmentation and ABC/2 volume. Bland-Altman charts were analyzed for ABC/2 and DeepMedic vs. manual segmentation volumes. Results: DeepMedic demonstrated high segmentation accuracy in the training cohort (median Dice 0.96; IQR 0.95 - 0.97) and in the validation cohort (median Dice 0.91; IQR 0.86 - 0.94). Dice coefficients were not significantly different between patients with IVH in the training cohort; however was significantly worse in the validation cohort in patients with IVH (Wilcoxon p<0.001). Agreement was significantly better between DeepMedic and manual segmentation (PREDICT: ICC 0.99 [95%CI 0.99 -1.00]; SPOTLIGHT: ICC 0.98 [95%CI 0.97 - 0.99]) than between ABC/2 and manual segmentation (PREDICT: ICC 0.92 [95%CI 0.89 - 0.95]; SPOTLIGHT: ICC 0.95 [95%CI 0.93-0.97]). Improved accuracy of DeepMedic was demonstrated in Bland-Altman charts (Fig 1). Conclusion: ICH machine learning segmentation with DeepMedic is feasible and accurate; and demonstrates greater agreement with manual segmentation compared to ABC/2 volumes. Accuracy of the machine learning algorithm however is limited in patients with IVH.

Sign in / Sign up

Export Citation Format

Share Document