Asymmetric Error Control for Binary Classification in Medical Disease Diagnosis

2020 ◽  
Author(s):  
Wasif Bokhari ◽  
Ajay Bansal
Keyword(s):  
Error Control ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Medical Disease

AEC Classifier: A Tree-Based Classifier with Error Control for Medical Disease Diagnosis and Other Applications

2021 ◽  
Vol 15 (02) ◽  
pp. 241-262
Author(s):  
Wasif Bokhari ◽  
Ajay Bansal
Keyword(s):  
Error Control ◽  
Binary Classification ◽  
False Negative ◽  
Disease Diagnosis ◽  
False Negatives ◽  
Medical Disease ◽  
Unique Nature ◽  
Comparable Accuracy ◽  
The Cost ◽  
Roc Score

In medical disease diagnosis, the cost of a false negative could greatly outweigh the cost of a false positive. This is because the former could cost a life, whereas the latter may only cause medical costs and stress to the patient. The unique nature of this problem highlights the need of asymmetric error control for binary classification applications. In this domain, traditional machine learning classifiers may not be ideal as they do not provide a way to control the number of false negatives below a certain threshold. This paper proposes a novel tree-based binary classification algorithm that can control the number of false negatives with a mathematical guarantee, based on Neyman–Pearson (NP) Lemma. This classifier is evaluated on the data obtained from different heart studies and it predicts the risk of cardiac disease, not only with comparable accuracy and AUC-ROC score but also with full control over the number of false negatives. The methodology used to construct this classifier can be expanded to many more use cases, not only in medical disease diagnosis but also beyond as shown from analysis on different diverse datasets.

A Study on Multi Class Classification from Breast Cancer Images using Ensemble Network and Transfer Learning

2020 ◽  
Vol 14 ◽  
Author(s):  
Lahari Tipirneni ◽  
Rizwan Patan
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Feature Descriptors ◽  
Histopathological Images ◽  
Viable Approach ◽  
Multi Class Classification

Abstract:: Millions of deaths all over the world are caused by breast cancer every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increases the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. The current paper presents an ensemble Convolutional neural network for multi class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from publicly available BreakHis dataset and classified between 8 classes. The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification.

scholarly journals Inferring health conditions from fMRI-graph data

2018 ◽  
Author(s):  
PierGianLuca Porta Mana ◽  
Claudia Bachmann ◽  
Abigail Morrison
Keyword(s):  
Binary Classification ◽  
Disease Diagnosis ◽  
Health Condition ◽  
Automated Classification ◽  
Imaging Data ◽  
Data Set ◽  
Sufficient Statistics ◽  
Conjugate Priors ◽  
Healthy Control ◽  
Partial Exchangeability

Automated classification methods for disease diagnosis are currently in the limelight, especially for imaging data. Classification does not fully meet a clinician's needs, however: in order to combine the results of multiple tests and decide on a course of treatment, a clinician needs the likelihood of a given health condition rather than binary classification yielded by such methods. We illustrate how likelihoods can be derived step by step from first principles and approximations, and how they can be assessed and selected, using fMRI data from a publicly available data set containing schizophrenic and healthy control subjects, as a working example. We start from the basic assumption of partial exchangeability, and then the notion of sufficient statistics and the "method of translation" (Edgeworth, 1898) combined with conjugate priors. This method can be used to construct a likelihood that can be used to compare different data-reduction algorithms. Despite the simplifications and possibly unrealistic assumptions used to illustrate the method, we obtain classification results comparable to previous, more realistic studies about schizophrenia, whilst yielding likelihoods that can naturally be combined with the results of other diagnostic tests.

scholarly journals Inferring health conditions from fMRI-graph data

2018 ◽  
Author(s):  
P.G.L. Porta Mana ◽  
C. Bachmann ◽  
A. Morrison
Keyword(s):  
Binary Classification ◽  
Disease Diagnosis ◽  
Health Condition ◽  
Automated Classification ◽  
Imaging Data ◽  
Data Set ◽  
Sufficient Statistics ◽  
Conjugate Priors ◽  
Healthy Control ◽  
Partial Exchangeability

ABSTRACTAutomated classification methods for disease diagnosis are currently in the limelight, especially for imaging data. Classification does not fully meet a clinician’s needs, however: in order to combine the results of multiple tests and decide on a course of treatment, a clinician needs the likelihood of a given health condition rather than binary classification yielded by such methods. We illustrate how likelihoods can be derived step by step from first principles and approximations, and how they can be assessed and selected, using fMRI data from a publicly available data set containing schizophrenic and healthy control subjects, as a working example. We start from the basic assumption of partial exchangeability, and then the notion of sufficient statistics and the “method of translation” (Edgeworth, 1898) combined with conjugate priors. This method can be used to construct a likelihood that can be used to compare different data-reduction algorithms. Despite the simplifications and possibly unrealistic assumptions used to illustrate the method, we obtain classification results comparable to previous, more realistic studies about schizophrenia, whilst yielding likelihoods that can naturally be combined with the results of other diagnostic tests.

scholarly journals Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Atiqur Rahman ◽  
Sanam Shahla Rizvi ◽  
Aurangzeb Khan ◽  
Aaqif Afzaal Abbasi ◽  
Shafqat Ullah Khan ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dimensionality Reduction ◽  
Intelligent System ◽  
Neurological Diseases ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Support Vector ◽  
Svm Classifier ◽  
Linear Discriminant

Parkinson’s disease (PD) is one of the most common and serious neurological diseases. Impairments in voice have been reported to be the early biomarkers of the disease. Hence, development of PD diagnostic tool will help early diagnosis of the disease. Additionally, intelligent system developed for binary classification of PD and healthy controls can also be exploited in future as an instrument for prodromal diagnosis. Notably, patients with rapid eye movement (REM) sleep behaviour disorder (RBD) represent a good model as they develop PD with a high probability. It has been shown that slight speech and voice impairment may be a sensitive marker of preclinical PD. In this study, we propose PD detection by extracting cepstral features from the voice signals collected from people with PD and healthy subjects. To classify the extracted features, we propose to use dimensionality reduction through linear discriminant analysis and classification through support vector machine. In order to validate the effectiveness of the proposed method, we also developed ten different machine learning models. It was observed that the proposed method yield area under the curve (AUC) of 88%, sensitivity of 73.33%, and specificity of 84%. Moreover, the proposed intelligent system was simulated using publicly available multiple types of voice database. Additionally, the data were collected from patients under on-state. The obtained results on the public database are promising compared to the previously published work.

ACO_NB-Based Hybrid Prediction Model for Medical Disease Diagnosis

2021 ◽  
pp. 526-536
Author(s):  
Amit Kumar ◽  
Manish Kumar ◽  
Nidhya R.
Keyword(s):  
Prediction Model ◽  
Disease Diagnosis ◽  
Second Phase ◽  
Data Sets ◽  
Feature Subset ◽  
Hybrid Prediction ◽  
Related Data ◽  
Medical Disease ◽  
Proposed Model ◽  
Two Phases

In recent years, a huge increase in the demand of medically related data is reported. Due to this, research in medical disease diagnosis has emerged as one of the most demanding research domains. The research reported in this chapter is based on developing an ACO (ant colony optimization)-based Bayesian hybrid prediction model for medical disease diagnosis. The proposed model is presented in two phases. In the first phase, the authors deal with feature selection by using the application of a nature-inspired algorithm known as ACO. In the second phase, they use the obtained feature subset as input for the naïve Bayes (NB) classifier for enhancing the classification performances over medical domain data sets. They have considered 12 datasets from different organizations for experimental purpose. The experimental analysis advocates the superiority of the presented model in dealing with medical data for disease prediction and diagnosis.

A Hybrid Model for Enhanced Prediction of Medical Diagnosis Based on Discriminative Rule Framing and Correlated Framework Approaches

2015 ◽  
Vol 23 (01) ◽  
pp. 33-48
Author(s):  
B. Gomathy ◽  
S. M. Ramesh ◽  
A. Shanmugam
Keyword(s):  
Medical Diagnosis ◽  
Principal Component ◽  
Disease Diagnosis ◽  
Linear Discriminant ◽  
Medical Disease ◽  
Input Dataset ◽  
Wrong Diagnosis ◽  
The Common ◽  
Independent Features ◽  
Better Than

Medical diagnosis is mostly done by experienced doctors. However, still some of the cases reported of wrong diagnosis and treatment. Patients are needed to take number of clinical tests for disease diagnosis. Most of the cases, all the tests are not contributing towards efficient diagnosis. The medical data are multidimensional and composed of thousands of independent features. So, the multidimensional database need to be analyzed and preprocessed for valuable decision making for medical diagnosis. The aim of this work is to accurately predict the medical disease with a condensed number of attributes. In this approach, the raw input dataset is preprocessed based on the common normalization approach. An association rule is used to find out the frequent used patterns to prune the dataset. Further, base rule can be applied to the pruned dataset. The Payoff and Heuristic rate can be evaluated to predict the risk analysis. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) approaches are used for better feature selection. Classification result is acquired based on minimum and maximum of residual support values. The experimental results show that the proposed scheme, can perform better than the existing algorithms to diagnose the medical disease.

scholarly journals Convolutional-Neural-Network Assisted Segmentation and SVM Classification of Brain Tumor in Clinical MRI Slices

2021 ◽  
Vol 50 (2) ◽  
pp. 342-356
Author(s):  
Venkatesan Rajinikanth ◽  
Seifedine Kadry ◽  
Yunyoung Nam
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Binary Classification ◽  
Brain Mri ◽  
Research Work ◽  
Disease Diagnosis ◽  
Detection Accuracy ◽  
Tumour Segmentation ◽  
Deep Feature Extraction

Due to the increased disease occurrence rates in humans, the need for the Automated Disease Diagnosis (ADD) systems is also raised. Most of the ADD systems are proposed to support the doctor during the screening and decision making process. This research aims at developing a Computer Aided Disease Diagnosis (CADD) scheme to categorize the brain tumour of 2D MRI slices into Glioblastoma/Glioma class with better accuracy. The main contribution of this research work is to develop a CADD system with Convolutional-Neural-Network (CNN) supported segmentation and classification. The proposed CADD framework consist of the following phases; (i) Image collection and resizing, (ii) Automated tumour segmentation using VGG-UNet, (iv) Deep-feature extraction using VGG16 network, (v) Handcrafted feature extraction, (vi) Finest feature choice by firefly-algorithm, and (vii) Serial feature concatenation and binary classification. The merit of the executed CADD is confirmed using an investigation realized using the benchmark as well as clinically collected brain MRI slices. In this work, a binary classification with a 10-fold cross validation is implemented using well known classifiers and the results attained with the SVM-Cubic (accuracy >98%) is superior. This result confirms that the combination of CNN assisted segmentation and classification helps to achieve enhanced disease detection accuracy.

Sign in / Sign up

Export Citation Format

Share Document