Feature extraction from customer reviews using enhanced rules.

Opinion mining is gaining significant research interest, as it directly and indirectly provides a better avenue for understanding customers, their sentiments toward a service or product, and their purchasing decisions. However, extracting every opinion feature from unstructured customer review documents is challenging, especially since these reviews are often written in native languages and contain grammatical and spelling errors. Moreover, existing pattern rules frequently exclude features and opinion words that are not strictly nouns or adjectives. Thus, selecting suitable features when analyzing customer reviews is the key to uncovering their actual expectations. This study aims to enhance the performance of explicit feature extraction from product review documents. To achieve this, an approach that employs sequential pattern rules is proposed to identify and extract features with associated opinions. The improved pattern rules total 41, including 16 new rules introduced in this study and 25 existing pattern rules from previous research. An average calculated from the testing results of five datasets showed that the incorporation of this study's 16 new rules significantly improved feature extraction precision by 6%, recall by 6% and F-measure value by 5% compared to the contemporary approach. The new set of rules has proven to be effective in extracting features that were previously overlooked, thus achieving its objective of addressing gaps in existing rules. Therefore, this study has successfully enhanced feature extraction results, yielding an average precision of 0.91, an average recall value of 0.88, and an average F-measure of 0.89.

Assessing Complex Left Ventricular Adaptations in Aortic Stenosis Using Personalized 3D + time Cardiac MRI Modeling.

Left ventricular adaptations can be a complex process under the influence of aortic stenosis (AS) and comorbidities. This study proposed and assessed the feasibility of using a motion-corrected personalized 3D + time LV modeling technique to evaluate the adaptive and maladaptive LV response to aid treatment decision-making. A total of 22 AS patients were analyzed and compared against 10 healthy subjects. The 3D + time analysis showed a highly distinct and personalized pattern of remodeling in individual AS patients which is associated with comorbidities and fibrosis. Patients with AS alone showed better wall thickening and synchrony than those comorbid with hypertension. Ischemic heart disease in AS caused impaired wall thickening and synchrony and systolic function. Apart from showing significant correlations to echocardiography and clinical MRI measurements (r: 0.70-0.95; p < 0.01), the proposed technique helped in detecting subclinical and subtle LV dysfunction, providing a better approach to evaluate AS patients for specific treatment, surgical planning, and follow-up recovery.

A novel approach for heart disease prediction using strength scores with significant predictors.

BACKGROUND: Cardiovascular disease is the leading cause of death in many countries. Physicians often diagnose cardiovascular disease based on current clinical tests and previous experience of diagnosing patients with similar symptoms. Patients who suffer from heart disease require quick diagnosis, early treatment and constant observations. To address their needs, many data mining approaches have been used in the past in diagnosing and predicting heart diseases. Previous research was also focused on identifying the significant contributing features to heart disease prediction, however, less importance was given to identifying the strength of these features. METHOD: This paper is motivated by the gap in the literature, thus proposes an algorithm that measures the strength of the significant features that contribute to heart disease prediction. The study is aimed at predicting heart disease based on the scores of significant features using Weighted Associative Rule Mining. RESULTS: A set of important feature scores and rules were identified in diagnosing heart disease and cardiologists were consulted to confirm the validity of these rules. The experiments performed on the UCI open dataset, widely used for heart disease research yielded the highest confidence score of 98% in predicting heart disease. CONCLUSION: This study managed to provide a significant contribution in computing the strength scores with significant predictors in heart disease prediction. From the evaluation results, we obtained important rules and achieved highest confidence score by utilizing the computed strength scores of significant predictors on Weighted Associative Rule Mining in predicting heart disease.

Feature selection and risk prediction for patients with coronary artery disease using data mining.

Coronary artery disease (CAD) is an important cause of mortality across the globe. Early risk prediction of CAD would be able to reduce the death rate by allowing early and targeted treatments. In healthcare, some studies applied data mining techniques and machine learning algorithms on the risk prediction of CAD using patient data collected by hospitals and medical centers. However, most of these studies used all the attributes in the datasets which might reduce the performance of prediction models due to data redundancy. The objective of this research is to identify significant features to build models for predicting the risk level of patients with CAD. In this research, significant features were selected using three methods (i.e., Chi-squared test, recursive feature elimination, and Embedded Decision Tree). Synthetic Minority Over-sampling Technique (SMOTE) oversampling technique was implemented to address the imbalanced dataset issue. The prediction models were built based on the identified significant features and eight machine learning algorithms, utilizing Acute Coronary Syndrome (ACS) datasets provided by National Cardiovascular Disease Database (NCVD) Malaysia. The prediction models were evaluated and compared using six performance evaluation metrics, and the top-performing models have achieved AUC more than 90%. Graphical abstract.

Phenotyping of hypertensive heart disease and hypertrophic cardiomyopathy using personalized 3D modelling and cardiac cine MRI.

Differential diagnosis of hypertensive heart disease (HHD) and hypertrophic cardiomyopathy (HCM) is clinically challenging but important for treatment management. This study aims to phenotype HHD and HCM in 3D + time domain by using a multiparametric motion-corrected personalized modeling algorithm and cardiac magnetic resonance (CMR). 44 CMR data, including 12 healthy, 16 HHD and 16 HCM cases, were examined. Multiple CMR phenotype data consisting of geometric and dynamic variables were extracted globally and regionally from the models over a full cardiac cycle for comparison against healthy models and clinical reports. Statistical classifications were used to identify the distinctive characteristics and disease subtypes with overlapping functional data, providing insights into the challenges for differential diagnosis of both types of disease. While HCM is characterized by localized extreme hypertrophy of the LV, wall thickening/contraction/strain was found to be normal and in sync, though it was occasionally exaggerated at normotrophic/less severely hypertrophic regions during systole to preserve the overall ejection fraction (EF) and systolic functionality. Additionally, we observed that hypertrophy in HHD could also be localized, although at less extreme conditions (i.e. more concentric). While fibrosis occurs mostly in those HCM cases with aortic obstruction, only minority of HHD patients were found affected by fibrosis. We demonstrate that subgroups of HHD (i.e. preserved and reduced EF: HHDpEF & HHDrEF) have different 3D + time CMR characteristics. While HHDpEF has cardiac functions in normal range, dilation and heart failure are indicated in HHDrEF as reflected by low LV wall thickening/contraction/strain and synchrony, as well as much reduced EF.

Assessment of infarct-specific cardiac motion dysfunction using modeling and multimodal magnetic resonance merging.

PURPOSE: To propose a cardiac motion tracking model that evaluates wall motion abnormality in postmyocardial infarction patients. Correlation between the motion parameter of the model and left ventricle (LV) function was also determined. MATERIALS AND METHODS: Twelve male patients with post-ST elevation myocardial infarction (post-STEMI) and 10 healthy controls of the same gender were recruited to undergo cardiac magnetic resonance imaging (MRI) using a 1.5T scanner. Using an infarct-specific LV division approach, the late gadolinium enhancement (LGE) MRI images were used to divide the LV on the tagged MRI images into infarct, adjacent, and remote sectors. Motion tracking was performed using the infarct-specific two-parameter empirical deformable model (TPEDM). The match quality was defined as the position error computed using root-mean-square (RMS) distance between the estimated and expert-verified tag intersections. The position errors were compared with the ones from our previously published fixed-sector TPEDM. Cine MRI images were used to calculate regional ejection fraction (REF). Correlation between the end-systolic contraction parameter (αES ) with REF was determined. RESULTS: The position errors in the proposed model were significantly lower than the fixed-sector model (P < 0.01). The median position errors were 0.82 mm versus 1.23 mm. The αES correlates significantly with REF (r = 0.91, P < 0.01). CONCLUSION: The infarct-specific TPEDM combines the morphological and functional information from LGE and tagged MRI images. It was shown to outperform the fixed-sector model in assessing regional LV dysfunction. The significant correlation between αES and REF added prognostic value because it indicated an impairment of cardiac function with the increase of infarct transmurality. LEVEL OF EVIDENCE: 3 J. Magn. Reson. Imaging 2017;45:525-534.