A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses

We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision-making towards short-interval follow-up versus tissue sampling. From a retrospective 2015–2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions was used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keeping a sensitivity over 94%, when externally tested on 236 images from two image sets: (1) 123 lesions (51 malignant and 72 benign) obtained from two ultrasound systems used for training and from a different one, resulting in a positive predictive value (PPV) of 45.9% (95% confidence interval 36.3–55.7%) versus a radiologists’ PPV of 41.5% (p < 0.005), combined with a 98.0% sensitivity (89.6–99.9%); (2) 113 lesions (54 malignant and 59 benign) obtained from two ultrasound systems from vendors different from those used for training, resulting into a 50.5% PPV (40.4–60.6%) versus a radiologists’ PPV of 47.8% (p < 0.005), combined with a 94.4% sensitivity (84.6–98.8%). Errors in BI-RADS 3 category (i.e., assigned by the model as BI-RADS 4) were 0.8% and 2.7% in the Testing set I and II, respectively. The board-certified breast radiologist accepted the BI-RADS classes assigned by the model in 114 masses (92.7%) and modified the BI-RADS classes of 9 breast masses (7.3%). In six of nine cases, the model performed better than the radiologist did, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.

Download Full-text

A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultra-sound-Detected Suspicious Breast Masses

10.1101/2021.12.16.21267907 ◽

2021 ◽

Author(s):

Matteo Interlenghi ◽

Christian Salvatore ◽

Veronica Magni ◽

Gabriele Caldara ◽

Elia Schiavon ◽

...

Keyword(s):

Machine Learning ◽

Majority Vote ◽

Short Interval ◽

Machine Learning Algorithms ◽

Medical Decision ◽

Ultra Sound ◽

Support Vector ◽

Histopathological Diagnosis ◽

Breast Masses ◽

Biopsy Rate

We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision making towards short-interval follow-up versus tissue sampling. From a retrospective 2015-2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions were used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keeping a sensitivity over 94%, when externally tested on 236 images from two image sets: 1) 123 lesions (51 malignant and 72 benign) obtained from the same four ultrasound systems used for training, resulting into a positive predictive value (PPV) of 45.9% (95% confidence interval 36.3-55.7%) versus a radiologists' PPV of 41.5% (p < 0.005), combined with a 98.0% sensitivity (89.6-99.9%); 2) 113 lesions (54 malignant and 59 benign) obtained from two ultrasound systems from vendors different from those used for training, resulting into a 50.5% PPV (40.4-60.6%) versus a radiologists' PPV of 47.8% (p < 0.005), combined with a 94.4% sensitivity (84.6-98.8%). Errors in BI-RADS 3 category (i.e., assigned by the model as BI-RADS 4) were 0.8% and 2.7% in the Testing set I and II, respectively. The board-certified breast radiologist accepted the BI-RADS classes assigned by the model in 114 masses (92.7%) and modified the BI-RADS classes of 9 breast masses (7.3%). In 6 of 9 cases the model performed better than the radiologist, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.

Download Full-text

Machine learning for analysis of active stand responses in older adults with vasovagal syncope

10.1101/2020.12.07.20241109 ◽

2020 ◽

Author(s):

Michelle Kwok ◽

Hugh Nolan ◽

Chie Wei Fan ◽

Clodagh O’Dwyer ◽

Rose A Kenny ◽

...

Keyword(s):

Machine Learning ◽

Older Adults ◽

Cardiac Output ◽

Discriminant Analysis ◽

Majority Vote ◽

Vasovagal Syncope ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Support Vector ◽

Stand Test

AbstractObjectivesTo assess 1) differences in the hemodynamic response to the active stand test in older adults with a clinical diagnosis of vasovagal syncope compared to age-matched controls 2) if the active stand test combined with machine learning approaches can be used to identify the presence of vasovagal syncope in older adults.ApproachAdults aged 50 and over (Vasovagal Syncope N=46 Age=66.9±10.3; Control N=86 Age=65.3±9.5) completed an active stand test. Multiple features were extracted to characterize the hemodynamic responses to the active stand test and were compared between groups. Classification was performed using machine learning algorithms including linear discriminant analysis, quadratic discriminant analysis, support vector machine and an ensemble majority vote classifier.Main ResultsSubjects with vasovagal syncope demonstrated a higher resting (supine) heart rate (69.8±13.1 bpm vs 63.3±12.1 bpm; P=0.007), a smaller initial systolic blood pressure drop (−20.2±20.1% vs −27.3±17.5%; P=0.005), larger drops in stroke volume (−14.7±24.0% vs −2.7±23.3%; P=0.010) and cardiac output (−6.4±18.5% vs 5.8±22.3%;P<0.001) and a larger increase in total peripheral resistance (8.1±30.4% vs −6.03±22.8%; P=0.002) compared to controls. A majority vote classifier identified the presence of vasovagal syncope with 82.6% sensitivity, 76.8% specificity, and average accuracy of 78.9%.SignificanceOlder adults with vasovagal syncope display a unique hemodynamic and autonomic response to active standing characterized by relative autonomic hypersensitivity and larger drops in cardiac output compared to age-matched controls. With suitable machine learning algorithms, the active stand test holds the potential to be used to screen older adults for reflex syncopes and hypotensive susceptibility potentially reducing test time, cost, and patient discomfort. More broadly this paper presents a machine learning framework to support use of the active stand test for classification of clinical outcomes of interest.

Download Full-text

Predicting Mortality Risk in Patients with COVID-19 Using Artificial Intelligence to Help Medical Decision-Making

10.1101/2020.03.30.20047308 ◽

2020 ◽

Cited By ~ 14

Author(s):

Mohammad Pourhomayoun ◽

Mahdi Shakibi

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Mortality Rate ◽

Mortality Risk ◽

Confusion Matrix ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Medical Decision ◽

Support Vector ◽

Depth Analysis

AbstractIn the wake of COVID-19 disease, caused by the SARS-CoV-2 virus, we designed and developed a predictive model based on Artificial Intelligence (AI) and Machine Learning algorithms to determine the health risk and predict the mortality risk of patients with COVID-19. In this study, we used documented data of 117,000 patients world-wide with laboratory-confirmed COVID-19. This study proposes an AI model to help hospitals and medical facilities decide who needs to get attention first, who has higher priority to be hospitalized, triage patients when the system is overwhelmed by overcrowding, and eliminate delays in providing the necessary care. The results demonstrate 93% overall accuracy in predicting the mortality rate. We used several machine learning algorithms including Support Vector Machine (SVM), Artificial Neural Networks, Random Forest, Decision Tree, Logistic Regression, and K-Nearest Neighbor (KNN) to predict the mortality rate in patients with COVID-19. In this study, the most alarming symptoms and features were also identified. Finally, we used a separate dataset of COVID-19 patients to evaluate our developed model accuracy, and used confusion matrix to make an in-depth analysis of our classifiers and calculate the sensitivity and specificity of our model.

Download Full-text

Using Machine Learning Algorithms on Prediction of Stock Price

Journal of Modeling and Optimization ◽

10.32732/jmo.2020.12.2.84 ◽

2020 ◽

Vol 12 (2) ◽

pp. 84-99

Author(s):

Li-Pang Chen

Keyword(s):

Machine Learning ◽

Stock Price ◽

Short Term Memory ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Support Vector ◽

Short Term ◽

Learning Techniques ◽

Historical Database ◽

Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

Download Full-text

A Comparative Study of Different Machine Learning Algorithms for Disease Prediction

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse/v7i7/0177 ◽

2017 ◽

Vol 7 (7) ◽

pp. 172

Author(s):

Anantvir Singh Romana

Keyword(s):

Machine Learning ◽

Subsequent Treatment ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Support Vector ◽

Disease Prediction ◽

Classification Problems ◽

Learning Techniques ◽

Neural Network Classifiers ◽

Diagnostic Detection

Accurate diagnostic detection of the disease in a patient is critical and may alter the subsequent treatment and increase the chances of survival rate. Machine learning techniques have been instrumental in disease detection and are currently being used in various classification problems due to their accurate prediction performance. Various techniques may provide different desired accuracies and it is therefore imperative to use the most suitable method which provides the best desired results. This research seeks to provide comparative analysis of Support Vector Machine, Naïve bayes, J48 Decision Tree and neural network classifiers breast cancer and diabetes datsets.

Download Full-text

Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

Military Medicine ◽

10.1093/milmed/usaa418 ◽

2021 ◽

Vol 186 (Supplement_1) ◽

pp. 445-451

Author(s):

Yifei Sun ◽

Navid Rashedi ◽

Vikrant Vaze ◽

Parikshit Shah ◽

Ryan Halter ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Real World ◽

Short Term Memory ◽

Model Performance ◽

Learning Technologies ◽

Machine Learning Algorithms ◽

Support Vector ◽

K Nearest Neighbor ◽

Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

Download Full-text

Efficient detection of hacker community based on twitter data using complex networks and machine learning algorithm

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-210458 ◽

2021 ◽

pp. 1-17

Author(s):

Ahmed Al-Tarawneh ◽

Ja’afer Al-Saraireh

Keyword(s):

Machine Learning ◽

Complex Networks ◽

Nearest Neighbor ◽

Learning Algorithm ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Support Vector ◽

K Nearest Neighbor ◽

Efficient Detection ◽

Suggested Keywords

Twitter is one of the most popular platforms used to share and post ideas. Hackers and anonymous attackers use these platforms maliciously, and their behavior can be used to predict the risk of future attacks, by gathering and classifying hackers’ tweets using machine-learning techniques. Previous approaches for detecting infected tweets are based on human efforts or text analysis, thus they are limited to capturing the hidden text between tweet lines. The main aim of this research paper is to enhance the efficiency of hacker detection for the Twitter platform using the complex networks technique with adapted machine learning algorithms. This work presents a methodology that collects a list of users with their followers who are sharing their posts that have similar interests from a hackers’ community on Twitter. The list is built based on a set of suggested keywords that are the commonly used terms by hackers in their tweets. After that, a complex network is generated for all users to find relations among them in terms of network centrality, closeness, and betweenness. After extracting these values, a dataset of the most influential users in the hacker community is assembled. Subsequently, tweets belonging to users in the extracted dataset are gathered and classified into positive and negative classes. The output of this process is utilized with a machine learning process by applying different algorithms. This research build and investigate an accurate dataset containing real users who belong to a hackers’ community. Correctly, classified instances were measured for accuracy using the average values of K-nearest neighbor, Naive Bayes, Random Tree, and the support vector machine techniques, demonstrating about 90% and 88% accuracy for cross-validation and percentage split respectively. Consequently, the proposed network cyber Twitter model is able to detect hackers, and determine if tweets pose a risk to future institutions and individuals to provide early warning of possible attacks.

Download Full-text

Machine Learning Approach for Predicting Lane-Change Maneuvers using the SHRP2 Naturalistic Driving Study Data

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/03611981211003581 ◽

2021 ◽

pp. 036119812110035

Author(s):

Anik Das ◽

Mohamed M. Ahmed

Keyword(s):

Machine Learning ◽

Prediction Accuracy ◽

Machine Learning Algorithms ◽

Support Vector ◽

Lane Change ◽

Adaptive Boosting ◽

Extreme Gradient Boosting ◽

Naturalistic Driving Study ◽

Naturalistic Driving ◽

Change Prediction

Accurate lane-change prediction information in real time is essential to safely operate Autonomous Vehicles (AVs) on the roadways, especially at the early stage of AVs deployment, where there will be an interaction between AVs and human-driven vehicles. This study proposed reliable lane-change prediction models considering features from vehicle kinematics, machine vision, driver, and roadway geometric characteristics using the trajectory-level SHRP2 Naturalistic Driving Study and Roadway Information Database. Several machine learning algorithms were trained, validated, tested, and comparatively analyzed including, Classification And Regression Trees (CART), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Naïve Bayes (NB) based on six different sets of features. In each feature set, relevant features were extracted through a wrapper-based algorithm named Boruta. The results showed that the XGBoost model outperformed all other models in relation to its highest overall prediction accuracy (97%) and F1-score (95.5%) considering all features. However, the highest overall prediction accuracy of 97.3% and F1-score of 95.9% were observed in the XGBoost model based on vehicle kinematics features. Moreover, it was found that XGBoost was the only model that achieved a reliable and balanced prediction performance across all six feature sets. Furthermore, a simplified XGBoost model was developed for each feature set considering the practical implementation of the model. The proposed prediction model could help in trajectory planning for AVs and could be used to develop more reliable advanced driver assistance systems (ADAS) in a cooperative connected and automated vehicle environment.

Download Full-text

Development of Machine Learning Models for Prediction of Smoking Cessation Outcome

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18052584 ◽

2021 ◽

Vol 18 (5) ◽

pp. 2584

Author(s):

Cheng-Chien Lai ◽

Wei-Hsin Huang ◽

Betty Chia-Chen Chang ◽

Lee-Ching Hwang

Keyword(s):

Machine Learning ◽

Smoking Cessation ◽

Success Rate ◽

Prediction Models ◽

Smoking Status ◽

Medical Center ◽

Machine Learning Algorithms ◽

Classification And Regression Tree ◽

Support Vector ◽

Smoking Cessation Outcome

Predictors for success in smoking cessation have been studied, but a prediction model capable of providing a success rate for each patient attempting to quit smoking is still lacking. The aim of this study is to develop prediction models using machine learning algorithms to predict the outcome of smoking cessation. Data was acquired from patients underwent smoking cessation program at one medical center in Northern Taiwan. A total of 4875 enrollments fulfilled our inclusion criteria. Models with artificial neural network (ANN), support vector machine (SVM), random forest (RF), logistic regression (LoR), k-nearest neighbor (KNN), classification and regression tree (CART), and naïve Bayes (NB) were trained to predict the final smoking status of the patients in a six-month period. Sensitivity, specificity, accuracy, and area under receiver operating characteristic (ROC) curve (AUC or ROC value) were used to determine the performance of the models. We adopted the ANN model which reached a slightly better performance, with a sensitivity of 0.704, a specificity of 0.567, an accuracy of 0.640, and an ROC value of 0.660 (95% confidence interval (CI): 0.617–0.702) for prediction in smoking cessation outcome. A predictive model for smoking cessation was constructed. The model could aid in providing the predicted success rate for all smokers. It also had the potential to achieve personalized and precision medicine for treatment of smoking cessation.

Download Full-text

An Estimation of Ship Collision Risk Based on Relevance Vector Machine

Journal of Marine Science and Engineering ◽

10.3390/jmse9050538 ◽

2021 ◽

Vol 9 (5) ◽

pp. 538

Author(s):

Jinwan Park ◽

Jung-Sik Jeong

Keyword(s):

Machine Learning ◽

Decision Making ◽

Risk Estimation ◽

Good Method ◽

Relevance Vector Machine ◽

Machine Learning Algorithms ◽

Support Vector ◽

Collision Risk ◽

Estimation Model ◽

Ship Collision

According to the statistics of maritime collision accidents over the last five years (2016–2020), 95% of the total maritime collision accidents are caused by human factors. Machine learning algorithms are an emerging approach in judging the risk of collision among vessels and supporting reliable decision-making prior to any behaviors for collision avoidance. As the result, it can be a good method to reduce errors caused by navigators’ carelessness. This article aims to propose an enhanced machine learning method to estimate ship collision risk and to support more reliable decision-making for ship collision risk. In order to estimate the ship collision risk, the conventional support vector machine (SVM) was applied. Regardless of the advantage of the SVM to resolve the uncertainty problem by using the collected ships’ parameters, it has inherent weak points. In this study, the relevance vector machine (RVM), which can present reliable probabilistic results based on Bayesian theory, was applied to estimate the collision risk. The proposed method was compared with the results of applying the SVM. It showed that the estimation model using RVM is more accurate and efficient than the model using SVM. We expect to support the reasonable decision-making of the navigator through more accurate risk estimation, thus allowing early evasive actions.

Download Full-text