Automated Detection of Diabetes From Exhaled Human Breath Using Deep Hybrid Architecture

Bhaskar, Navaneeth; Bairagi, Vinayak K.; Boonchieng, Ekkarat; Munot, Mousami V.

doi:10.1109/access.2023.3278278

Cited by 13 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is defined as the proportion of accurately predicted outcomes to all of the predictions. For every task and model, the Receiver Operating Characteristic (ROC) curves are also evaluated to analyze the performance [24].…”

Section: Evaluation Metricsmentioning

confidence: 99%

A Multi-task CNN Model for Automated Prediction of Isocitrate Dehydrogenase Mutation Status and Grade of Gliomas

Tupe-Waghmare,

Adithya,

Bhaskar

2024

MMEP

View full text Add to dashboard Cite

In this study, we have developed a multi-task model based on Convolutional Neural Network (CNN) to determine the isocitrate dehydrogenase (IDH) status and grade of gliomas brain tumours from T1-weighted (T1), T2-weighted (T2) and Fluid-Attenuated Inversion Recovery (FLAIR) images, both independently and utilizing stacked images. The study used information from the Cancer Genome Atlas (TCGA), which includes scans of grade III & IV tumours. Around 5546 MR images of individual modality and 1942 images of stacked modalities were processed from the original dataset. Popular CNN architectures like MobileNet, EfficientNetB0, EfficientNetB1, EfficientNetB2 and Xception models were implemented and used for the predictive analysis. A multi-task model has been developed to generate the grade and the IDH status from a single input image. Further, a user interface was developed using Python binding for Qt (PyQt) for checking the samples in real time without the help of medical experts. In comparison to all other models taken into account in this study, the EfficientNetB2 CNN model achieved the highest accuracy. For grade classification and IDH status classification on stacked images, the EfficientNetB2 CNN multi-task architecture achieved accuracy values of 99.4% and 99.6%, respectively. Accuracy scores of 99.7% and 99.8%, respectively, are obtained for grade classification and IDH status classification on individual images.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

A Multi-task CNN Model for Automated Prediction of Isocitrate Dehydrogenase Mutation Status and Grade of Gliomas

Tupe-Waghmare,

Adithya,

Bhaskar

2024

MMEP

View full text Add to dashboard Cite

show abstract

“…In (11), the concentration of acetone in the exhaled breath was examined to fi nd type 2 diabetes. A novel sensing module containing an array of sensors was applied to monitor the acetone concentration for detecting diseases.…”

Section: Related Workmentioning

confidence: 99%

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification

Periasamy

2024

BLL

View full text Add to dashboard Cite

Non-invasive diabetes detection refers to the utilization and development of technologies and methods that can monitor and diagnose diabetes without requiring invasive procedures, namely invasive glucose monitoring or blood sampling. The objective is to provide a more convenient and less burdensome approach to screening and management of diabetes. It is noteworthy that while non-invasive method offers promising avenues for diabetes detection, they frequently require validation through clinical studies and might have limitation in terms of reliability and accuracy than classical invasive approaches. In recent times, deep learning (DL) and feature selection (FS) are used to monitor and diagnose diabetes accurately without requiring invasive procedures. This technique combines the FS method with the DL algorithm for making accurate predictions and extracting relevant features from non-invasive data. This article introduces a new Binary Fire Hawks Optimizer with Deep Learning-Driven Non-Invasive Diabetes Detection and Classifi cation (BFHODL-NIDDC) technique. The major intention of the BFHODL-NIDDC technique focuses on the involvement of non-invasive procedures for the detection of diabetes. In the BFHODL-NIDDC technique, data preprocessing is initially performed to preprocess the input data. Next, the BFHO algorithm chooses an optimal subset of features and improves the classifi er results. For the identifi cation of diabetes, multichannel convolutional bidirectional long short-term memory (MC-BLSTM) model is used. At last, the beetle antenna search (BAS) algorithm is used for the hyperparameter selection of the MC-BLSTM method which in turn enhances the detection performance of the MC-BLSTM model. A series of simulations were conducted on the diabetes dataset to assess the diabetes detection performance of the BFHODL-NIDDC technique. The experimental outcomes illustrated better performance of the BFHODL-NIDDC method over other recent approaches in terms of different metrics (Tab. 4, Fig. 9, Ref. 23).

show abstract

“…The gases, particles and volatile organic compounds (VOCs) that make up exhaled breath can reveal a multitude of information about a person's diet, metabolism, health and environmental exposure. VOCs in exhaled breath indicate metabolic activity and can function as biomarkers for certain illnesses [5]. We investigated the possibility of using breath ammonia as a biomarker for the diagnosis of CKD in our method.…”

Section: Introductionmentioning

confidence: 99%

CNN-CatBoost ensemble deep learning model for enhanced disease detection and classification of kidney disease

Bhaskar,

Borhade,

Barekar

et al. 2024

IJEECS

View full text Add to dashboard Cite

An efficient deep-learning prediction model for identifying chronic kidney disease (CKD) from exhaled breath is presented in this paper. The concentration of urea will be higher in CKD patients. Salivary urease breaks down the stored urea into ammonia, which is then excreted through breath. Thus, by monitoring the breath ammonia content, it is possible to identify the presence of high urea levels in the body. In this work, a novel sensing module is developed and applied to measure and assess the amount of ammonia in exhaled breath. Moreover, an effective deep learning prediction model that combines the CatBoost algorithm and convolutional neural network (CNN) is used to automate the prediction of disease. The proposed model, which combines the benefits of gradient-boosting and CNN, attained an exceptional accuracy of 98.37%. Experiments are conducted to evaluate the proposed model using real-time data and to assess how well it performs in comparison with existing deep learning methods. Our study's findings demonstrate that kidney disease can be accurately and noninvasively diagnosed using the proposed approach.

show abstract

Automated Detection of Diabetes From Exhaled Human Breath Using Deep Hybrid Architecture

Cited by 13 publications

References 37 publications

A Multi-task CNN Model for Automated Prediction of Isocitrate Dehydrogenase Mutation Status and Grade of Gliomas

A Multi-task CNN Model for Automated Prediction of Isocitrate Dehydrogenase Mutation Status and Grade of Gliomas

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification

CNN-CatBoost ensemble deep learning model for enhanced disease detection and classification of kidney disease

Contact Info

Product

Resources

About