Interpretable Detection and Location of Myocardial Infarction Based on Ventricular Fusion Rule Features

Myocardial infarction (MI) is one of the most common cardiovascular diseases threatening human life. In order to accurately distinguish myocardial infarction and have a good interpretability, the classification method that combines rule features and ventricular activity features is proposed in this paper. Specifically, according to the clinical diagnosis rule and the pathological changes of myocardial infarction on the electrocardiogram, the local information extracted from the Q wave, ST segment, and T wave is computed as the rule feature. All samples of the QT segment are extracted as ventricular activity features. Then, in order to reduce the computational complexity of the ventricular activity features, the effects of Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA), and Locality Preserving Projections (LPP) on the extracted ventricular activity features are compared. Combining rule features and ventricular activity features, all the 12 leads features are fused as the ultimate feature vector. Finally, eXtreme Gradient Boosting (XGBoost) is used to identify myocardial infarction, and the overall accuracy rate of 99.86% is obtained on the Physikalisch-Technische Bundesanstalt (PTB) database. This method has a good medical diagnosis basis while improving the accuracy, which is very important for clinical decision-making.

Download Full-text

Structural Damage Classification in a Jacket-Type Wind-Turbine Foundation Using Principal Component Analysis and Extreme Gradient Boosting

Sensors ◽

10.3390/s21082748 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2748

Author(s):

Jersson X. Leon-Medina ◽

Maribel Anaya ◽

Núria Parés ◽

Diego A. Tibaduiza ◽

Francesc Pozo

Keyword(s):

Principal Component Analysis ◽

Feature Extraction ◽

Wind Turbine ◽

Structural Damage ◽

Principal Component ◽

Gradient Boosting ◽

Damage Classification ◽

Linear Feature ◽

Linear Feature Extraction ◽

Extreme Gradient Boosting

Damage classification is an important topic in the development of structural health monitoring systems. When applied to wind-turbine foundations, it provides information about the state of the structure, helps in maintenance, and prevents catastrophic failures. A data-driven pattern-recognition methodology for structural damage classification was developed in this study. The proposed methodology involves several stages: (1) data acquisition, (2) data arrangement, (3) data normalization through the mean-centered unitary group-scaling method, (4) linear feature extraction, (5) classification using the extreme gradient boosting machine learning classifier, and (6) validation applying a 5-fold cross-validation technique. The linear feature extraction capabilities of principal component analysis are employed; the original data of 58,008 features is reduced to only 21 features. The methodology is validated with an experimental test performed in a small-scale wind-turbine foundation structure that simulates the perturbation effects caused by wind and marine waves by applying an unknown white noise signal excitation to the structure. A vibration-response methodology is selected for collecting accelerometer data from both the healthy structure and the structure subjected to four different damage scenarios. The datasets are satisfactorily classified, with performance measures over 99.9% after using the proposed damage classification methodology.

Download Full-text

Prediction of quality of life in people with ALS

ACM SIGAPP Applied Computing Review ◽

10.1145/3477127.3477128 ◽

2021 ◽

Vol 21 (2) ◽

pp. 5-17

Author(s):

Anna Markella Antoniadi ◽

Miriam Galvin ◽

Mark Heverin ◽

Orla Hardiman ◽

Catherine Mooney

Keyword(s):

Quality Of Life ◽

Disease Onset ◽

Model Performance ◽

Sampling Technique ◽

Clinical Decision ◽

Gradient Boosting ◽

Rapid Decline ◽

Extreme Gradient Boosting ◽

Lateral Sclerosis

Amyotrophic Lateral Sclerosis (ALS) is a rare neurodegenerative disease that causes a rapid decline in motor functions and has a fatal trajectory. ALS is currently incurable, so the aim of the treatment is mostly to alleviate symptoms and improve quality of life (QoL) for the patients. The goal of this study is to develop a Clinical Decision Support System (CDSS) to alert clinicians when a patient is at risk of experiencing low QoL. The source of data was the Irish ALS Registry and interviews with the 90 patients and their primary informal caregiver at three time-points. In this dataset, there were two different scores to measure a person's overall QoL, based on the McGill QoL (MQoL) Questionnaire and we worked towards the prediction of both. We used Extreme Gradient Boosting (XGBoost) for the development of the predictive models, which was compared to a logistic regression baseline model. Additionally, we used Synthetic Minority Over-sampling Technique (SMOTE) to examine if that would increase model performance and SHAP (SHapley Additive explanations) as a technique to provide local and global explanations to the outputs as well as to select the most important features. The total calculated MQoL score was predicted accurately using three features - age at disease onset, ALSFRS-R score for orthopnoea and the caregiver's status pre-caregiving - with a F1-score on the test set equal to 0.81, recall of 0.78, and precision of 0.84. The addition of two extra features (caregiver's age and the ALSFRS-R score for speech) produced similar outcomes (F1-score 0.79, recall 0.70 and precision 0.90).

Download Full-text

Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9090507 ◽

2020 ◽

Vol 9 (9) ◽

pp. 507

Author(s):

Sanjiwana Arjasakusuma ◽

Sandiaga Swahyu Kusuma ◽

Stuart Phinn

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Learning Algorithms ◽

Principal Component ◽

Hyperspectral Data ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Forest Height ◽

Extreme Gradient Boosting

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

Download Full-text

Dimensionality Reduction using PCA and K-Means Clustering for Breast Cancer Prediction

Lontar Komputer Jurnal Ilmiah Teknologi Informasi ◽

10.24843/lkjiti.2018.v09.i03.p08 ◽

2018 ◽

pp. 192 ◽

Cited By ~ 2

Author(s):

Ade Jamal ◽

Annisa Handayani ◽

Ali Akbar Septiandri ◽

Endang Ripmiatin ◽

Yunus Effendi

Keyword(s):

Breast Cancer ◽

Principal Component Analysis ◽

Dimensionality Reduction ◽

Principal Component ◽

Component Analysis ◽

Gradient Boosting ◽

Support Vector ◽

Breast Cancer Dataset ◽

Cancer Prediction ◽

Extreme Gradient Boosting

Breast cancer is the most important cause of death among women. A prediction of breast cancer in early stage provides a greater possibility of its cure. It needs a breast cancer prediction tool that can classify a breast tumor whether it was a harmful malignant tumor or un-harmful benign tumor. In this paper, two algorithms of machine learning, namely Support Vector Machine and Extreme Gradient Boosting technique will be compared for classification purpose. Prior to the classification, the number of data attribute will be reduced from the raw data by extracting features using Principal Component Analysis. A clustering method, namely K-Means is also used for dimensionality reduction besides the Principal Component Analysis. This paper will present a comparison among four models based on two dimensionality reduction methods combined with two classifiers which applied on Wisconsin Breast Cancer Dataset. The comparison will be measured by using accuracy, sensitivity and specificity metrics evaluated from the confusion matrices. The experimental results have indicated that the K-Means method, which is not usually used for dimensionality reduction can perform well compared to the popular Principal Component Analysis.

Download Full-text

Vital signs assessed in initial clinical encounters predict COVID-19 mortality in an NYC hospital system

Scientific Reports ◽

10.1038/s41598-020-78392-1 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Elza Rechtman ◽

Paul Curtin ◽

Esmeralda Navarro ◽

Sharon Nirenberg ◽

Megan K. Horton

Keyword(s):

Machine Learning ◽

New York ◽

Clinical Decision Making ◽

Care Delivery ◽

Vital Signs ◽

Clinical Decision ◽

Rapid Identification ◽

Gradient Boosting ◽

Hospital System ◽

Response Strategies

AbstractTimely and effective clinical decision-making for COVID-19 requires rapid identification of risk factors for disease outcomes. Our objective was to identify characteristics available immediately upon first clinical evaluation related COVID-19 mortality. We conducted a retrospective study of 8770 laboratory-confirmed cases of SARS-CoV-2 from a network of 53 facilities in New-York City. We analysed 3 classes of variables; demographic, clinical, and comorbid factors, in a two-tiered analysis that included traditional regression strategies and machine learning. COVID-19 mortality was 12.7%. Logistic regression identified older age (OR, 1.69 [95% CI 1.66–1.92]), male sex (OR, 1.57 [95% CI 1.30–1.90]), higher BMI (OR, 1.03 [95% CI 1.102–1.05]), higher heart rate (OR, 1.01 [95% CI 1.00–1.01]), higher respiratory rate (OR, 1.05 [95% CI 1.03–1.07]), lower oxygen saturation (OR, 0.94 [95% CI 0.93–0.96]), and chronic kidney disease (OR, 1.53 [95% CI 1.20–1.95]) were associated with COVID-19 mortality. Using gradient-boosting machine learning, these factors predicted COVID-19 related mortality (AUC = 0.86) following cross-validation in a training set. Immediate, objective and culturally generalizable measures accessible upon clinical presentation are effective predictors of COVID-19 outcome. These findings may inform rapid response strategies to optimize health care delivery in parts of the world who have not yet confronted this epidemic, as well as in those forecasting a possible second outbreak.

Download Full-text

On the interpretation of serial laboratory measurements in acute myocardial infarction.

Clinical Chemistry ◽

10.1093/clinchem/30.1.69 ◽

1984 ◽

Vol 30 (1) ◽

pp. 69-76 ◽

Cited By ~ 5

Author(s):

A Albert ◽

E K Harris ◽

J P Chapelle ◽

C Heusghem ◽

H E Kulbertus

Keyword(s):

Myocardial Infarction ◽

Acute Myocardial Infarction ◽

Laboratory Tests ◽

Clinical Decision Making ◽

Risk Index ◽

Clinical Decision ◽

Global Evaluation ◽

Dynamic Risk ◽

Specificity And Sensitivity ◽

Patient’S Outcome

Abstract Serial laboratory determinations are now routinely performed on patients admitted to intensive-care units. Adequate interpretation of such cumulative information for clinical decision-making purposes is a challenging problem. We describe a statistical method for predicting--sequentially as the data become available--the patient's outcome, death or survival. Thus, the method goes beyond previously reported techniques that base such prediction on only a single multivariate observation. The method has been applied to daily measurements of serum urea and lactate dehydrogenase, performed during one week on patients hospitalized in the coronary-care unit with acute myocardial infarction. Two baseline variables were also included in the dynamic risk index so derived: the age of the patient and the number of previous myocardial infarctions recorded on admission. We also discuss the problems of selecting the most-predictive laboratory tests and of determining for each test the amount of past data needed to achieve satisfactory prediction. We distinguish between global evaluation of the dynamic risk index obtained (in terms of specificity and sensitivity) and individual interpretation (in terms of posterior/prior probability ratio) of a given risk score for a particular patient. The approach described may contribute to more effective use of results of repeated laboratory tests on critically ill patients.

Download Full-text

Use of an Artificial Neural Network for Data Analysis in Clinical Decision-Making: The Diagnosis of Acute Coronary Occlusion

Neural Computation ◽

10.1162/neco.1990.2.4.480 ◽

1990 ◽

Vol 2 (4) ◽

pp. 480-489 ◽

Cited By ~ 176

Author(s):

William G. Baxt

Keyword(s):

Neural Network ◽

Myocardial Infarction ◽

Acute Myocardial Infarction ◽

Artificial Neural Network ◽

Coronary Occlusion ◽

Clinical Decision Making ◽

Clinical Decision ◽

Acute Coronary Occlusion ◽

Artificial Neural ◽

Better Than

A nonlinear artificial neural network trained by backpropagation was applied to the diagnosis of acute myocardial infarction (coronary occlusion) in patients presenting to the emergency department with acute anterior chest pain. Three-hundred and fifty-six patients were retrospectively studied, of which 236 did not have acute myocardial infarction and 120 did have infarction. The network was trained on a randomly chosen set of half of the patients who had not sustained acute myocardial infarction and half of the patients who had sustained infarction. It was then tested on a set consisting of the remaining patients to which it had not been exposed. The network correctly identified 92% of the patients with acute myocardial infarction and 96% of the patients without infarction. When all patients with the electrocardiographic evidence of infarction were removed from the cohort, the network correctly identified 80% of the patients with infarction. This is substantially better than the performance reported for either physicians or any other analytical approach.

Download Full-text

Pharmacotherapy for acute myocardial infarction

Journal of Korean Medical Association ◽

10.5124/jkma.2021.64.2.139 ◽

2021 ◽

Vol 64 (2) ◽

pp. 139-151

Author(s):

Sung Soo Kim ◽

Hyun Kuk Kim

Keyword(s):

Myocardial Infarction ◽

Acute Myocardial Infarction ◽

Randomized Controlled Trials ◽

Clinical Decision Making ◽

Heart Association ◽

Coronary Intervention ◽

Clinical Decision ◽

Controlled Trials ◽

Randomized Controlled ◽

Consensus Document

Clinical practice guidelines published by the European Society of Cardiology and the American College of Cardiology/ American Heart Association provide recommendations based on evidence, including randomized controlled trials and registry data, for clinicians to enable efficient clinical decision-making and improve prognosis for patients with acute myocardial infarction (AMI). However, there are several differences in practice, health systems, and races between Korea and Western countries; further, many studies on pharmacotherapy were conducted in the prepercutaneous coronary intervention era. An expert consensus document on pharmacotherapy for AMI was recently published following demands for the establishment of Korean guideline reflecting data in the modern percutaneous coronary intervention era. In this review, we summarized AMI guidelines from Europe, America, Japan, and Korea, and analyzed studies on pharmacotherapy for AMI including well-organized randomized controlled trials by Korean researchers and large-sized registry datasets, such as the Korea Acute Myocardial Infarction Registry and the Korean National Health Insurance Service.

Download Full-text

Evaluation of Total Nitrogen in Water via Airborne Hyperspectral Data: Potential of Fractional Order Discretization Algorithm and Discrete Wavelet Transform Analysis

Remote Sensing ◽

10.3390/rs13224643 ◽

2021 ◽

Vol 13 (22) ◽

pp. 4643

Author(s):

Jinhua Liu ◽

Jianli Ding ◽

Xiangyu Ge ◽

Jingzhe Wang

Keyword(s):

Water Quality ◽

Wavelet Transform ◽

Discrete Wavelet Transform ◽

Fractional Order ◽

Total Nitrogen ◽

Hyperspectral Data ◽

Spectral Information ◽

Gradient Boosting ◽

Discrete Wavelet ◽

Extreme Gradient Boosting

Controlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, the complex factors affecting water quality (plant shading and suspended matter in water) make direct estimation extremely challenging. Considering the spectral response mechanisms of emergent plants, we coupled discrete wavelet transform (DWT) and fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), and eXtreme Gradient Boosting (XGBoost)) to mine this potential spectral information. A total of 567 models were developed, and airborne hyperspectral data processed with various DWT scales and FOD techniques were compared. The effective information in the hyperspectral reflectance data were better emphasized after DWT processing. After DWT processing the original spectrum (OR), its sensitivity to TN in water was maximally improved by 0.22, and the correlation between FOD and TN in water was optimally increased by 0.57. The transformed spectral information enhanced the TN model accuracy, especially for FOD after DWT. For RF, 82% of the model R2 values improved by 0.02~0.72 compared to the model using FOD spectra; 78.8% of the bagging values improved by 0.01~0.53 and 65.0% of the XGBoost values improved by 0.01~0.64. The XGBoost model with DWT coupled with grey relation analysis (GRA) yielded the best estimation accuracy, with the highest precision of R2 = 0.91 for L6. In conclusion, appropriately scaled DWT analysis can substantially improve the accuracy of extracting TN from UAV hyperspectral images. These outcomes may facilitate the further development of accurate water quality monitoring in sophisticated global waters from drone or satellite hyperspectral data.

Download Full-text

Abstract 155: Prevalence of Self-Reported Risk Factors for Myocardial Infarction Among Patients With Venous Thromboembolism

Circulation Cardiovascular Quality and Outcomes ◽

10.1161/circoutcomes.6.suppl_1.a155 ◽

2013 ◽

Vol 6 (suppl_1) ◽

Author(s):

Julie Vanderpoel ◽

Brahim Bookhart ◽

Hillary J Gross ◽

Marco DiBonaventura

Keyword(s):

Risk Factors ◽

Myocardial Infarction ◽

Venous Thromboembolism ◽

Potential Risk ◽

Clinical Decision Making ◽

Smoking Status ◽

Patient Characteristics ◽

Clinical Decision ◽

Family Medical History ◽

The Mean

Objective: To identify the prevalence of risk factors that may be associated with a future myocardial infarction (MI) among patients with venous thromboembolism (VTE). Methods: This study was conducted using the 2010 wave of the National Health and Wellness Survey (NHWS). The NHWS is a self-administered, Internet-based questionnaire from a nationwide sample of adults (N=75,000). Only patients with a diagnosis of VTE, defined as a self-reported diagnosis of deep vein thrombosis (DVT), pulmonary embolism (PE), or both, were included in the analysis. Self-reported patient characteristics that may be potential risk factors for MI were collected, including sociodemographic characteristics, family medical history, and health behaviors (such as smoking status), as well as comorbidities. Included risk factors were based on a literature search. The risk factors were not weighted based on the strength of their potential association with a future MI. Thus, risk factors of varying significance were included and weighted equally. Findings: A total of 814 patients with VTE (519 with DVT, 196 with PE, and 99 with DVT and PE) were included in the analysis. Approximately 53% of the patients were female, and the mean age was 57 years. Among these patients, the mean number of reported risk factors that may be associated with a future MI was 5.6. Approximately 23% (n=189) of patients reported ≤3 risk factors, 55% (n=446) of patients had 4-7 risk factors, and 22% (n=179) of patients had ≥8 risk factors. Some of the more commonly reported risk factors included male gender (47%, n=381), obesity (53%, n=428), hypertension (53%, n=427), hyperlipidemia (49%, n=401), type 2 diabetes (21%, n=167), a family history of cardiovascular disease (81%, n=663), and currently smoking (22%, n=175). Conclusions: A high proportion of patients with VTE have risk factors for a future MI. Awareness of the prevalence of MI risk factors among patients with VTE may support optimal clinical decision-making for these patients. Providers should be cognizant of the potential risk for MI among patients with VTE when selecting treatment approaches. Additional research that considers the relative importance of each potential risk factor is needed to elucidate these findings.

Download Full-text