scholarly journals The Relative Contribution of Medical Comorbidities in the OARA Score: A Machine Learning Analysis

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Joshua Chang ◽  
Mary Ziemba-Davis ◽  
Evan R. Deckard ◽  
R. Michael Meneghini
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Medical Condition ◽  
Classification Tree ◽  
Face Validity ◽  
Tree Model ◽  
Relative Contribution ◽  
Ensure Patient Safety ◽  
Study Results ◽  
Same Day Discharge

Background/Objective: The Outpatient Arthroplasty Risk Assessment (OARA) score has been used successfully to identify patients who can safely undergo outpatient primary total joint arthroplasty (TJA) based on medical risk stratification. The targeted score (0 to 79) was conservatively established to ensure patient safety. However, the number of points associated with each of the 52 comorbidities in the OARA score were assigned based on physician experience with early discharge. This study applied machine learning (ML) to empirically identify the relative contribution/importance of each medical comorbidity to safe same-day discharge (SDD). Methods: 3,047 patients who underwent primary unilateral TJA by a single surgeon at a single institution were included in the analysis; 573 were SDDs. Before ML analysis, associations among binary (yes/no) comorbidities were examined using Cramér's V. A CART decision tree model using Gini method was used to develop a model for SDD (yes/no) based on the presence or absence of the comorbidities. Results: To produce interpretable results with acceptable face validity the 52 comorbidities were grouped in 19 common medical categories (heart disease, liver disease, etc.). Although the resulting model was less than perfectly predictive (AROC = 0.652, 95% CI 0.629–0.675), it resulted in an interpretable classification tree identifying heart disease, kidney disease, immunosuppression, chronic sedative use, pulmonary disease, thrombophilia, anemia, and history of stroke, in order, as the most important predictors of SDD. Conclusion: Model limitations expressed as AROC were not unexpected because the relative contribution (expressed as points) of comorbidities to the OARA score are based on physician decision-making, not empirical identification of the importance of each medical condition to safe SDD. Study results moved the goal of empirical classification forward but the low prevalence of many of the comorbidities limited variability and hence model performance and accuracy. Future work with a larger sample is being planned. 

scholarly journals Defining The Best-Fit Machine Learning Classifier Prediction Model For Diagnosis of Heart Disease

2021 ◽  
Author(s):  
Debarati Dey Roy ◽  
Debashis De
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Heart Disease ◽  
Supervised Learning ◽  
Learning Algorithms ◽  
Management Service ◽  
Tree Model ◽  
Data Set ◽  
Death Cases ◽  
Best Fit

Abstract Cardio vascular disease or alternatively heart disease is the primitive cause of death all around the world. Last few decades, it was observed that maximum death cases occurred due to heart failure. The heart failure death cases are associated with many risk factors for example high blood pressure, cholesterol level, sugar level etcetera. Therefore, it is advisable that regular and early diagnosis of these factors may reduce the risk of heart failure and hence achieve prompt disease management service. A commonly used technique to process these enormous medical data is called data mining, which help the researchers in health care domain. Several machine learning algorithms are used to analyses these data and help to design the best-fit model for early detection of heart diseases. This research paper contributes various attributes related to heart mal functioning and build the best-fit model using supervised learning algorithm such as various tree (fine tree, medium tree etc), Gaussian Naïve Bayes, Coarse KNN, Medium Gaussian SVM algorithms. In this paper, we used the data set from Kaggle.com. These data set comprises with total 732 instances along with 5 attributes. All these 5 attributes are to be considered for testing purpose and also to find out the best fit model for prediction of heart disease. In this research article we also compare the various classification models based on supervised learning algorithms. Based on the performance and accuracy rate we therefore, choose ‘Medium Tree’ model as the best-fit model. Maximum accuracy is obtained for ‘Medium Tree’ model. The confusion matrix for each model are calculated and analyze.

scholarly journals A machine learning approach to identify correlates of current e-cigarette use in Canada

2021 ◽  
Author(s):  
Rui Fu ◽  
Nicholas Mitsakakis ◽  
Michael Chaiton
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Electronic Cigarettes ◽  
Classification Tree ◽  
Cigarette Use ◽  
Training Set ◽  
Tree Model ◽  
Cross Sectional ◽  
Classification Tree Model ◽  
Validation Set

Aim: Popularity of electronic cigarettes (i.e. e-cigarettes) is soaring in Canada. Understanding person-level correlates of current e-cigarette use (vaping) is crucial to guide tobacco policy, but prior studies have not fully identified these correlates due to model overfitting caused by multicollinearity. This study addressed this issue by using classification tree, a machine learning algorithm. Methods: This population-based cross-sectional study used the Canadian Tobacco, Alcohol, and Drugs Survey (CTADS) from 2017 that targeted residents aged 15 or older. Forty-six person-level characteristics were first screened in a logistic mixed-effects regression procedure for their strength in predicting vaper type (current vs. former vaper) among people who reported to have ever vaped. A 9:1 ratio was used to randomly split the data into a training set and a validation set. A classification tree model was developed using the cross-validation method on the training set using the selected predictors and assessed on the validation set using sensitivity, specificity and accuracy. Results: Of the 3,059 people with an experience of vaping, the average age was 24.4 years (standard deviation = 11.0), with 41.9% of them being female and 8.5% of them being aboriginal. There were 556 (18.2%) current vapers. The classification tree model performed relatively well and suggested attraction to e-cigarette flavors was the most important correlate of current vaping, followed by young age (< 18) and believing vaping to be less harmful to oneself than cigarette smoking. Conclusions: People who vape due to flavors are associated with very high risk of becoming current vapers. The findings of this study provide evidence that supports the ongoing ban on flavored vaping products in the US and suggests a similar regulatory intervention may be effective in Canada.

scholarly journals Prediction of Heart Disease Severity Measurment Using Deep Learning Techniques

2021 ◽  
Author(s):  
Rina S. Patil ◽  
Mohit Gangwar
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Predictive Accuracy ◽  
Process Efficiency ◽  
Support Vector ◽  
Machine Learning Classification ◽  
Learning Techniques ◽  
Study Results ◽  
Feature Extraction And Selection ◽  
Vector Machines

Machine learning enables AI and is used in data analytics to overcome many challenges. Machine learning was the growing method of predicting outcomes based on existing data. The computer learns characteristics from the test implementation, then applies characteristics to an unknown dataset to predict the result. Classification is an essential technique of machine learning which is widely used for forecasting. Some classification techniques predict with adequate accuracy, while others show a small precision. This research investigates a process called machine learning classification, which combines different classifiers to enhance the precision of weak architectures. Experimentation using this tool was conducted using a database on heart disease. The collecting and measuring data method were designed to decide how to use the ensemble methodology to improve predictive accuracy in cardiovascular disease. This paper aims not only to enhance the precision of poor different classifiers but also to apply the algorithm with a neural network to demonstrate its usefulness in predicting disease in its earliest stages. The study results show that various classification algorithmic strategies, such as support vector machines, successfully improve the forecasting ability of poor classifiers and show satisfactory success in recognizing heart attack risk. Using ML classification, a cumulative improvement in the accuracy was obtained for poor classification models. That process efficiency was further improved with the introduction of feature extraction and selection, and the findings show substantial improvements in predictive power.

A Review on Heart Disease Detection Techniques

2017 ◽  
Vol 7 (7) ◽  
pp. 395
Author(s):  
. Anika ◽  
Navpreet Kaur
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Review Paper ◽  
Vascular Diseases ◽  
Disease Detection ◽  
Automated Classification ◽  
Feature Extraction Method ◽  
Detection Techniques ◽  
Cardio Vascular ◽  
Public Domain Software

The paper exhibits a formal audit on early detection of heart disease which are the major cause of death. Computational science has potential to detect disease in prior stages automatically. With this review paper we describe machine learning for disease detection. Machine learning is a method of data analysis that automates analytical model building.Various techniques develop to predict cardiac disease based on cases through MRI was developed. Automated classification using machine learning. Feature extraction method using Cell Profiler and GLCM. Cell Profiler a public domain software, freely available is flourished by the Broad Institute's Imaging Platform and Glcm is a statistical method of examining texture .Various techniques to detect cardio vascular diseases.

Prediction of Having a Heart Disease Using Machine Learning

2020 ◽  
Author(s):  
Indu Dokare ◽  
Anjali Prithiani ◽  
Hanish Ochani ◽  
Sachin Kanjan ◽  
Dinesh Tarachandani
Keyword(s):  
Machine Learning ◽  
Heart Disease

scholarly journals Feasibility of Using Floor Vibration to Detect Human Falls

2020 ◽  
Vol 18 (1) ◽  
pp. 200
Author(s):  
Yu Shao ◽  
Xinyue Wang ◽  
Wenjie Song ◽  
Sobia Ilyas ◽  
Haibo Guo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Human Body ◽  
Nearest Neighbor ◽  
Body Movement ◽  
Modern Society ◽  
Recognition System ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor ◽  
Study Results ◽  
Floor Vibration

With the increasing aging population in modern society, falls as well as fall-induced injuries in elderly people become one of the major public health problems. This study proposes a classification framework that uses floor vibrations to detect fall events as well as distinguish different fall postures. A scaled 3D-printed model with twelve fully adjustable joints that can simulate human body movement was built to generate human fall data. The mass proportion of a human body takes was carefully studied and was reflected in the model. Object drops, human falling tests were carried out and the vibration signature generated in the floor was recorded for analyses. Machine learning algorithms including K-means algorithm and K nearest neighbor algorithm were introduced in the classification process. Three classifiers (human walking versus human fall, human fall versus object drop, human falls from different postures) were developed in this study. Results showed that the three proposed classifiers can achieve the accuracy of 100, 85, and 91%. This paper developed a framework of using floor vibration to build the pattern recognition system in detecting human falls based on a machine learning approach.

scholarly journals Data mining techniques with machine learning algorithm to predict patients of heart disease

2021 ◽  
Vol 1088 (1) ◽  
pp. 012035
Author(s):  
Mulyawan ◽  
Agus Bahtiar ◽  
Githera Dwilestari ◽  
Fadhil Muhammad Basysyar ◽  
Nana Suarna
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Heart Disease ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Data Mining Techniques

scholarly journals Identification of Circulating Diagnostic Biomarkers for Coronary Microvascular Disease in Postmenopausal Women Using Machine-Learning Techniques

Metabolites ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 339
Author(s):  
Alicia Arredondo Eve ◽  
Elif Tunc ◽  
Yu-Jeh Liu ◽  
Saumya Agrawal ◽  
Huriye Erbak Yilmaz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Postmenopausal Women ◽  
Diagnostic Test ◽  
Microvascular Disease ◽  
Machine Learning Techniques ◽  
Gas Chromatography Mass Spectrometry ◽  
Circulating Biomarkers ◽  
Diagnostic Biomarkers ◽  
Persistent Symptoms

Coronary microvascular disease (CMD) is a common form of heart disease in postmenopausal women. It is not due to plaque formation but dysfunction of microvessels that feed the heart muscle. The majority of the patients do not receive a proper diagnosis, are discharged prematurely and must go back to the hospital with persistent symptoms. Because of the lack of diagnostic biomarkers, in the current study, we focused on identifying novel circulating biomarkers of CMV that could potentially be used for developing a diagnostic test. We hypothesized that plasma metabolite composition is different for postmenopausal women with no heart disease, CAD, or CMD. A total of 70 postmenopausal women, 26 healthy individuals, 23 individuals with CMD and 21 individuals with CAD were recruited. Their full health screening and tests were completed. Basic cardiac examination, including detailed clinical history, additional disease and prescribed drugs, were noted. Electrocardiograph, transthoracic echocardiography and laboratory analysis were also obtained. Additionally, we performed full metabolite profiling of plasma samples from these individuals using gas chromatography-mass spectrometry (GC–MS) analysis, identified and classified circulating biomarkers using machine learning approaches. Stearic acid and ornithine levels were significantly higher in postmenopausal women with CMD. In contrast, valine levels were higher for women with CAD. Our research identified potential circulating plasma biomarkers of this debilitating heart disease in postmenopausal women, which will have a clinical impact on diagnostic test design in the future.

scholarly journals Machine Learning Based Classification Models for Heart Disease Prediction

2021 ◽  
Vol 1916 (1) ◽  
pp. 012092
Author(s):  
N Karthikeyan ◽  
P Padmanaban ◽  
A Prasanth ◽  
D Ragunath
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Disease Prediction ◽  
Classification Models
Sign in / Sign up

Export Citation Format

Share Document