Accuracy, Sensitivity and Specificity Measurement of Various Classification Techniques on Healthcare Data

Gupta, Niyati; Rawal, Arushi; Shiwani, Savita

doi:10.9790/0661-1157073

Cited by 24 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After completing the training and validation set, the confusion matrix was applied to each trained neural network plotted Class 0 as “Non-COVID-19” with 40 images and Class 1 as “COVID-19.” with 35 images. The test images were divided into the following prediction results: TP, TN, FP, and FN [ 24 ]. Figure 8 describes the confusion matrix for DenseNet201, GoogLeNet, ResNet50, ResNet 101, ResNet152, and ResNeXt101.…”

Section: Resultsmentioning

confidence: 99%

Multiclass Convolution Neural Network for Classification of COVID-19 CT Images

Ching

Lai

Chuah

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the late December of 2019, a novel coronavirus was discovered in Wuhan, China. In March 2020, WHO announced this epidemic had become a global pandemic and that the novel coronavirus may be mild to most people. However, some people may experience a severe illness that results in hospitalization or maybe death. COVID-19 classification remains challenging due to the ambiguity and similarity with other known respiratory diseases such as SARS, MERS, and other viral pneumonia. The typical symptoms of COVID-19 are fever, cough, chills, shortness of breath, loss of smell and taste, headache, sore throat, chest pains, confusion, and diarrhoea. This research paper suggests the concept of transfer learning using the deterministic algorithm in all binary classification models and evaluates the performance of various CNN architectures. The datasets of 746 CT images of COVID-19 and non-COVID-19 were divided for training, validation, and testing. Various augmentation techniques were applied to increase the number of datasets except for testing images. The images were then pretrained using CNN to obtain a binary class. ResNeXt101 and ResNet152 have the best F1 score of 0.978 and 0.938, whereas GoogleNet has an F1 score of 0.762. ResNeXt101 and ResNet152 have an accuracy of 97.81% and 93.80%. ResNeXt101, DenseNet201, and ResNet152 have 95.71%, 93.81%, and 90% sensitivity, whereas ResNeXt101, ResNet101, and ResNet152 have 100%, 99.58%, and 98.33 specificity, respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

Multiclass Convolution Neural Network for Classification of COVID-19 CT Images

Ching

Lai

Chuah

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…There are four major parameters that need to be checked to determine how well the test/classifier performed: Precision, Recall (Sensitivity), F1 Score, and Accuracy,[ 11 12 ] which are given as:…”

Section: E Xperimental D Etailsmentioning

confidence: 99%

Enhancing Medical Diagnosis with AI: A Focus on Respiratory Disease Detection

Sharma,

Pandey,

Shah

2023

Indian Journal of Community Medicine

View full text Add to dashboard Cite

Background: Artificial intelligence (AI) is revolutionizing medical diagnosis and healthcare, providing constant support to medical practitioners. Intelligent systems alleviate workload pressure while optimizing practitioner performance. AI and deep learning have also improved medical imaging and audio analysis. Material and Methods: This research focuses on predicting respiratory diseases using audio recordings from an electronic stethoscope. A convolutional neural network (CNN) was trained on a Respiratory Sound Database, augmented to generate 1,428 audio files. Techniques such as pitch shifting, time stretching, noise addition, time and frequency masking, dynamic range compression, and resampling were employed to increase the diversity and size of the training data. Result: Features were extracted from mono audio files, creating a four layer CNN with 90% accuracy. The software, developed using the CNN model and Streamlit python library, offers a new tool for early and accurate diagnosis, reducing the burden on medical practitioners and enhanci ng their performance. The study highlights AI’s potential in respiratory disease detection through audio analysis. Conclusion: The software, developed using the CNN model and Streamlit python library, offers a new tool for early and accurate diagnosis, reducing the burden on medical practitioners and enhancing their performance.

show abstract

“…A metric [23] uses the model to describe the number of real positive cases that were projected to be positive. In other words, it is regarded as a true-positive rate, which measures the likelihood that a condition associated with heart disease would be accurately detected using equation 1.…”

Section: Sensitivitymentioning

confidence: 99%

Stacking Ensemble Machine Learning Algorithm with an Application to Heart Disease Prediction

Fatima,

Kazi,

Tassaddiq

et al. 2023

Contemp. Math.

View full text Add to dashboard Cite

Mathematics and statistics have a significant impact on the advancement of most trending sciences like machine learning, artificial intelligence, and data science. In this article, we use the Stacking Ensemble Machine Learning Algorithm (SEMLA) to predict heart disease, considering accuracy (acc), diagnostic odds ratio (Dor), F1_score, Matthews correlation coefficient (Mcc), receiver operating characteristics-area under curve (roc-auc), and logloss (log_loss). The data is analyzed using classification learning techniques. We have considered sex, age, cholesterol, fasting blood sugar, the highest rate of heartbeat, type of chest pain, resting electrocardiogram (ECG), angina, depression induced by exercise, peak exercise measurement, major vessel number, a disorder in the blood, and a target attribute to represent the presence and absence of disorders. The approach used allows for the prediction of heart disease and the management of worst-case scenarios. In comparison with the existing models, our proposed model has outperformed other models with an accuracy of 97.28%.

show abstract

Accuracy, Sensitivity and Specificity Measurement of Various Classification Techniques on Healthcare Data

Cited by 24 publications

References 4 publications

Multiclass Convolution Neural Network for Classification of COVID-19 CT Images

Multiclass Convolution Neural Network for Classification of COVID-19 CT Images

Enhancing Medical Diagnosis with AI: A Focus on Respiratory Disease Detection

Stacking Ensemble Machine Learning Algorithm with an Application to Heart Disease Prediction

Contact Info

Product

Resources

About