scholarly journals A stacking-based model for predicting 30-day all-cause hospital readmissions of patients with acute myocardial infarction

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Zhen Zhang ◽  
Hang Qiu ◽  
Weihao Li ◽  
Yucheng Chen
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Decision Tree ◽  
Hospital Readmissions ◽  
Feature Selection Method ◽  
High Risk Group ◽  
Base Layer ◽  
Gradient Boosting ◽  
Support Vector ◽  
Gradient Enhancement

Abstract Background Acute myocardial infarction (AMI) is a serious cardiovascular disease, followed by a high readmission rate within 30-days of discharge. Accurate prediction of AMI readmission is a crucial way to identify the high-risk group and optimize the distribution of medical resources. Methods In this study, we propose a stacking-based model to predict the risk of 30-day unplanned all-cause hospital readmissions for AMI patients based on clinical data. Firstly, we conducted an under-sampling method of neighborhood cleaning rule (NCR) to alleviate the class imbalance and then utilized a feature selection method of SelectFromModel (SFM) to select effective features. Secondly, we adopted a self-adaptive approach to select base classifiers from eight candidate models according to their performances in datasets. Finally, we constructed a three-layer stacking model in which layer 1 and layer 2 were base-layer and level 3 was meta-layer. The predictions of the base-layer were used to train the meta-layer in order to make the final forecast. Results The results show that the proposed model exhibits the highest AUC (0.720), which is higher than that of decision tree (0.681), support vector machine (0.707), random forest (0.701), extra trees (0.709), adaBoost (0.702), bootstrap aggregating (0.704), gradient boosting decision tree (0.710) and extreme gradient enhancement (0.713). Conclusion It is evident that our model could effectively predict the risk of 30-day all cause hospital readmissions for AMI patients and provide decision support for the administration.

AN EFFICIENT MACHINE LEARNING MODEL FOR PREDICTION OF ACUTE MYOCARDIAL INFARCTION

2020 ◽  
Vol 13 ◽  
Author(s):  
Dhilsath Fathima.M ◽  
S. Justin Samuel ◽  
R. Hari Haran
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Logistic Regression ◽  
Decision Tree ◽  
Learning Model ◽  
Training Dataset ◽  
Data Set ◽  
Machine Learning Model ◽  
Proposed Model

Aim: This proposed work is used to develop an improved and robust machine learning model for predicting Myocardial Infarction (MI) could have substantial clinical impact. Objectives: This paper explains how to build machine learning based computer-aided analysis system for an early and accurate prediction of Myocardial Infarction (MI) which utilizes framingham heart study dataset for validation and evaluation. This proposed computer-aided analysis model will support medical professionals to predict myocardial infarction proficiently. Methods: The proposed model utilize the mean imputation to remove the missing values from the data set, then applied principal component analysis to extract the optimal features from the data set to enhance the performance of the classifiers. After PCA, the reduced features are partitioned into training dataset and testing dataset where 70% of the training dataset are given as an input to the four well-liked classifiers as support vector machine, k-nearest neighbor, logistic regression and decision tree to train the classifiers and 30% of test dataset is used to evaluate an output of machine learning model using performance metrics as confusion matrix, classifier accuracy, precision, sensitivity, F1-score, AUC-ROC curve. Results: Output of the classifiers are evaluated using performance measures and we observed that logistic regression provides high accuracy than K-NN, SVM, decision tree classifiers and PCA performs sound as a good feature extraction method to enhance the performance of proposed model. From these analyses, we conclude that logistic regression having good mean accuracy level and standard deviation accuracy compared with the other three algorithms. AUC-ROC curve of the proposed classifiers is analyzed from the output figure.4, figure.5 that logistic regression exhibits good AUC-ROC score, i.e. around 70% compared to k-NN and decision tree algorithm. Conclusion: From the result analysis, we infer that this proposed machine learning model will act as an optimal decision making system to predict the acute myocardial infarction at an early stage than an existing machine learning based prediction models and it is capable to predict the presence of an acute myocardial Infarction with human using the heart disease risk factors, in order to decide when to start lifestyle modification and medical treatment to prevent the heart disease.

Abstract 014: Evaluation of Readmission after Acute Myocardial Infarction for Patients Included in Medicare’s Hospital Readmissions Reduction Program

2017 ◽  
Vol 10 (suppl_3) ◽  
Author(s):  
Lila M Martin ◽  
Ryan W Thompson ◽  
Timothy G Ferris ◽  
Jagmeet P Singh ◽  
Elizabeth Laikhter ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Hospital Readmissions ◽  
Index Hospitalization ◽  
Readmission Rates ◽  
Troponin Elevation ◽  
Reduction Program ◽  
Improve Accuracy ◽  
Episodes Of Care ◽  
Index Hospital

Introduction: Medicare’s Hospital Readmissions Reduction Program assesses financial penalties for hospitals based on risk-standardized readmission rates after specific episodes of care, including acute myocardial infarction (AMI). Whether the algorithm accurately identifies patients with AMI who have preventable readmission is unknown. Methods: Using administrative data from Medicare, we conducted physician-adjudicated chart reviews of all patients considered 30 day readmissions after AMI attributed to one hospital from July 2012-June 2015. We extracted information about revascularization during index hospitalization. For patients readmitted to the index hospital or an affiliate, we also extracted reason for readmission. Results: Of 199 admissions, 66 (33.2%) received PCI and 19 (9.6%) underwent CABG on index hospitalization. The remainder of patients did not receive any intervention, i.e. 39 patients (19.6%) were declined due to procedural risk, 15 (7.5%) because of goals of care and 14 (7.0%) refused revascularization. Forty-six patients (23.1%) had troponin elevation in the absence of an MI and did not have an indication for revascularization. The most common diagnoses of the 161 (80.9%) patients readmitted to the index hospital or an affiliate were infections and cardiac and non-cardiac chest discomfort (Table 1). Conclusions: Our results demonstrate that many AMI patients who count towards the Medicare penalty do not receive revascularization during the index hospitalization because of high procedural risk or patient preference. Focusing on these patients may improve readmission metric performance. Furthermore, adding administrative codes for prohibitive procedural risk may improve accuracy of the metric as a measure of quality.

Multi-Class Taxonomy of Well Integrity Anomalies Applying Inductive Learning Algorithms: Analytical Approach for Artificial-Lift Wells

2021 ◽  
Author(s):  
Mostafa Sa'eed Yakoot ◽  
Adel Mohamed Salem Ragab ◽  
Omar Mahmoud
Keyword(s):  
Decision Tree ◽  
Confusion Matrix ◽  
Learning Algorithms ◽  
Oil And Gas Industry ◽  
Classification Model ◽  
Gradient Boosting ◽  
Support Vector ◽  
Risk Category ◽  
Well Integrity ◽  
Extreme Gradient Boosting

Abstract Well integrity has become a crucial field with increased focus and being published intensively in industry researches. It is important to maintain the integrity of the individual well to ensure that wells operate as expected for their designated life (or higher) with all risks kept as low as reasonably practicable, or as specified. Machine learning (ML) and artificial intelligence (AI) models are used intensively in oil and gas industry nowadays. ML concept is based on powerful algorithms and robust database. Developing an efficient classification model for well integrity (WI) anomalies is now feasible because of having enormous number of well failures and well barrier integrity tests, and analyses in the database. Circa 9000 dataset points were collected from WI tests performed for 800 wells in Gulf of Suez, Egypt for almost 10 years. Moreover, those data have been quality-controlled and quality-assured by experienced engineers. The data contain different forms of WI failures. The contributing parameter set includes a total of 23 barrier elements. Data were structured and fed into 11 different ML algorithms to build an automated systematic tool for calculating imposed risk category of any well. Comparison analysis for the deployed models was performed to infer the best predictive model that can be relied on. 11 models include both supervised and ensemble learning algorithms such as random forest, support vector machine (SVM), decision tree and scalable boosting techniques. Out of 11 models, the results showed that extreme gradient boosting (XGB), categorical boosting (CatBoost), and decision tree are the most reliable algorithms. Moreover, novel evaluation metrics for confusion matrix of each model have been introduced to overcome the problem of existing metrics which don't consider domain knowledge during model evaluation. The innovated model will help to utilize company resources efficiently and dedicate personnel efforts to wells with the high-risk. As a result, progressive improvements on business, safety, environment, and performance of the business. This paper would be a milestone in the design and creation of the Well Integrity Database Management Program through the combination of integrity and ML.

Abstract 121: Testing Frequency Of Guideline-recommended Diabetes Performance Measures In A Cohort Of Post-acute Myocardial Infarction (AMI) Diabetics.

2014 ◽  
Vol 7 (suppl_1) ◽  
Author(s):  
Sood Kisra ◽  
John Spertus ◽  
Faraz Kureshi ◽  
Philip G Jones ◽  
Mikhail Kosiborod ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Quality Of Care ◽  
Performance Measures ◽  
High Risk Group ◽  
Diabetic Patients ◽  
Testing Frequency ◽  
Patient Reported ◽  
Using Data

Background: Diabetes mellitus (DM) is common among patients hospitalized with acute myocardial infarction (AMI). Although guideline-supported performance measures exist to improve care for each condition, prior work assessing the quality of care for diabetic patients after AMI has focused only on adherence to CAD performance measures. The quality of diabetic care these patients’ receive is unknown. Methods: Using data from a prospective AMI registry (TRIUMPH), we identified patients with known DM and examined whether DM-focused performance measures had been applied over the 12 months after discharge. We focused upon 3 DM guideline-supported performance measures: a dilated eye exam, detailed foot exam, and HgbA1C testing. For this analysis, we conducted univariate statistics to describe the frequencies with which diabetics reported receiving these DM performance measures and 4 CAD performance measures at their 12-month interview. Results: Among 1,343 patients with a known diagnosis of diabetes presenting with an AMI, a total of 791 (58.9%) completed the 12-month follow up interview. The mean age (SD) of the analytic cohort was 6111 years, with 60% being males and 63% Caucasian. The frequencies of reported receipt among the examined DM and CAD performance measures ranged from 57.3%- 82.2%, with ASA being the most common and a dilated eye exam being the least (Figure). Only 47% of patients reported receiving all three DM performance measures over the past 12 months, while 41.1% reported receiving either one or two, and 12% reported receiving none. Conclusion: In a large, multi-center cohort of diabetic AMI survivors we found that patient-reported receipt of 3 DM and 4 CAD performance measures is sub-optimal and there is significant room for improvement. Novel strategies and approaches for assessing the quality of care delivered to post-AMI diabetics in a multidimensional fashion remains vital for improving care and outcomes in this high-risk group of patients. Characters: 1,683 + figure 500. Limit 2,500

scholarly journals P259 Adherence to optimal medical therapy in Asian patients with acute myocardial infarction treated with PCI

2020 ◽  
Vol 41 (Supplement_1) ◽  
Author(s):  
T Koh ◽  
W Huang ◽  
F Gao ◽  
J C Allen ◽  
C Liman ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
High Risk ◽  
Medical Therapy ◽  
Risk Group ◽  
High Risk Group ◽  
Primary Pci ◽  
Post Discharge ◽  
Asian Patients ◽  
Β Blockers

Abstract On Behalf SingCLOUD collaborators Background  Notable regional differences have been observed worldwide in clinical characteristics and outcomes in patients experiencing acute myocardial infarction (AMI). Asian patients present younger and report higher adverse outcomes rates compared to Western cohorts. The reasons are multifactorial, but adherence to medication prescription guidelines is one of the modifiable factors. Purpose  Our aim was to study the effect of physician adherence to Optimal Medical Therapy (OMT) prescription guidelines on a MACE outcome in a high-risk group of Asian AMI patients over 1 year following percutaneous coronary intervention (PCI). Method  Data for this retrospective study was from the Singapore Cardiac Longitudinal Outcomes Database (SingCLOUD) pilot study involving AMI patients surviving primary PCI at two tertiary centers from 2012 to 2013. Guideline-directed OMT adherence was defined as concurrent prescription of at least one statin plus dual antiplatelet therapy (DAPT – aspirin plus P2Y12-I). Prescription of β-blockers and ACE-i/ARBs was also recorded. Prescription status and MACE (repeat MI, stroke, death) was recorded at discharge, 3, 6 and 9 months, and 1 year following the index discharge. The cumulative effect of OMT adherence at 3, 6, 9 months and 1 year post-discharge was studied by comparing risk of first MACE among patient groups with complete, partial and non-adherence to OMT prescription guidelines. Results  2,478 patients, 80.3% males, mean age 60.3 ± 11.7 years were studied. 1094 (44.1%) underwent primary PCI for STEMI. Single drug prescription at discharge for aspirin, P2Y12-I, and statins was 95, 97 and 95.8%, while prescription of β -blockers and ACE-inhibitors was 86.5 and 75.7%. Prescription of statins and aspirin declined gradually while P2Y12-I fell to 67.9% at 6mo and 47.6% at 1 year. Adherence to OMT declined from 92.3% at discharge to 82.1, 58.5, 56.1 and 40.3% at 3, 6, 9 months and 1 year, respectively. Of 342 (13.8%) occurrences of first MACE, 48.5% occurred within 3mo post-discharge. Complete adherence to OMT upon discharge significantly decreased risk of MACE at 3mo (OR = 0.066; 95% CI: 0.054-0.080; p < 0.001) and 12mo (OR = 0.017; 95% CI: 0.010-0.028; p < 0.001) relative to non-adherence. Conclusion  Over the course of a year in this high-risk group of PCI-treated AMI patients, there was a reduction in prescription adherence to the minimally essential OMT. Complete OMT adherence is beneficial in reducing MACE. Interventions targeting reasons for non-adherence are important in improving patient outcomes. Abstract P259 Figure 1 - Medication over 1 year

scholarly journals Machine Learning Framework to Predict Chronic Kidney Disease using Ensemble Algorithm

2020 ◽  
Vol 9 (5) ◽  
pp. 1-6
Keyword(s):  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Random Forest ◽  
Kidney Disease ◽  
Decision Tree ◽  
Performance Metrics ◽  
Weighted Average ◽  
Gradient Boosting ◽  
Support Vector ◽  
The Individual

Chronic Kidney Disease (CKD) is a worldwide concern that influences roughly 10% of the grown-up population on the world. For most of the people the early diagnosis of CKD is often not possible. Therefore, the utilization of present-day Computer aided supported strategies is important to help the conventional CKD finding framework to be progressively effective and precise. In this project, six modern machine learning techniques namely Multilayer Perceptron Neural Network, Support Vector Machine, Naïve Bayes, K-Nearest Neighbor, Decision Tree, Logistic regression were used and then to enhance the performance of the model Ensemble Algorithms such as ADABoost, Gradient Boosting, Random Forest, Majority Voting, Bagging and Weighted Average were used on the Chronic Kidney Disease dataset from the UCI Repository. The model was tuned finely to get the best hyper parameters to train the model. The performance metrics used to evaluate the model was measured using Accuracy, Precision, Recall, F1-score, Mathew`s Correlation Coefficient and ROC-AUC curve. The experiment was first performed on the individual classifiers and then on the Ensemble classifiers. The ensemble classifier like Random Forest and ADABoost performed better with 100% Accuracy, Precision and Recall when compared to the individual classifiers with 99.16% accuracy, 98.8% Precision and 100% Recall obtained from Decision Tree Algorithm

scholarly journals The association of Medicaid expansion and racial/ethnic inequities in access, treatment, and outcomes for patients with acute myocardial infarction

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0241785
Author(s):  
Erica M. Valdovinos ◽  
Matthew J. Niedzwiecki ◽  
Joanna Guo ◽  
Renee Y. Hsia
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Hospital Mortality ◽  
Racial Disparities ◽  
Hospital Admissions ◽  
Hospital Readmissions ◽  
Medicaid Expansion ◽  
Difference In Differences ◽  
Percentage Points ◽  
White Patients

Introduction After having an acute myocardial infarction (AMI), racial and ethnic minorities have less access to care, decreased rates of invasive treatments such as percutaneous coronary intervention (PCI), and worse outcomes compared with white patients. The objective of this study was to determine whether the Affordable Care Act’s expansion of Medicaid eligibility was associated with changes in racial disparities in access, treatments, and outcomes after AMI. Methods Quasi-experimental, difference-in-differences-in-differences analysis of non-Hispanic white and minority patients with acute myocardial infarction in California and Florida from 2010–2015, using linear regression models to estimate the difference-in-differences. This population-based sample included all Medicaid and uninsured patients ages 18–64 hospitalized with acute myocardial infarction in California, which expanded Medicaid through the Affordable Care Act beginning as early as July 2011 in certain counties, and Florida, which did not expand Medicaid. The main outcomes included rates of admission to hospitals capable of performing PCI, rates of transfer for patients who first presented to hospitals that did not perform PCI, rates of PCI during hospitalization and rates of early (within 48 hours of admission) PCI, rates of readmission to the hospital within 30 days, and rates of in-hospital mortality. Results A total of 55,991 hospital admissions met inclusion criteria, 32,540 of which were in California and 23,451 were in Florida. Among patients with AMI who initially presented to a non-PCI hospital, the likelihood of being transferred increased by 12 percentage points (95% CI 2 to 21) for minority patients relative to white patients after the Medicaid expansion. The likelihood of undergoing PCI increased by 3 percentage points (95% CI 0 to 5) for minority patients relative to white patients after the Medicaid expansion. We did not find an association between the Medicaid expansion and racial disparities in overall likelihood of admission to a PCI hospital, hospital readmissions, or in-hospital mortality. Conclusions The Medicaid expansion was associated with a decrease in racial disparities in transfers and rates of PCI after AMI. We did not find an association between the Medicaid expansion and admission to a PCI hospital, readmissions, and in-hospital mortality. Additional factors outside of insurance coverage likely continue to contribute to disparities in outcomes after AMI. These findings are crucial for policy makers seeking to reduce racial disparities in access, treatment and outcomes in AMI.

scholarly journals Comparison of Thrombolysis in Myocardial Infarction Score and Heart Score in risk stratification of acute myocardial infarction patients, prognostic accuracy and arrhythmia incidence

2019 ◽  
Vol 7 (9) ◽  
pp. 3300
Author(s):  
Keerthana Batyala ◽  
M. V. Nagabhushana ◽  
Malli Dorasanamma
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
High Risk ◽  
Risk Stratification ◽  
Risk Group ◽  
High Risk Group ◽  
P Value ◽  
Heart Score ◽  
Prognostic Accuracy ◽  
Timi Score

Background: To compare TIMI & HEART SCORE for their risk stratification in Acute Myocardial Infarction Patients,  prognostic accuracy and Arrhythmia incidence.Methods: This observational study is conducted in a Tertiary care hospital over a period of 2 years from August 2017 to July 2019. A total of 100 patients presented to ER with Chest Pain are selected for study. Patients were monitored for a period of one month in ICCU.Results: In present study out of 61 cases with TIMI score ≥5, mortality of 11.5%(7 cases, p value 0.028). Heart score more than 6  constitutes high risk group, out of which mortality was observed in 7.45% cases (p=0.48). Most of the arrhythmias (70.49%) in present study observed in patients with TIMI score ≥5 (High risk group) which is statistically significant with p value 0.002. Most of the arrhythmias in present study observed in patients with HS ≥8 which is not statistically significant with p value 0.135.Conclusions: In present study, overall mortality rate was 7% and these patients who died constitutes to high risk group with TIMI. HEART SCORE identified more patients as low risk compared to TIMI SCORE. TIMI SCORE is a good predictor of arrhythmia incidence.

Sign in / Sign up

Export Citation Format

Share Document