AI driven interpretable deep learning based fetal health classification

In this study, a deep learning model is proposed for the classification of fetal health into 3 categories: Normal, suspect, and pathological. The primary objective is to utilize the power of deep learning to improve the efficiency and effectiveness of diagnostic processes. A deep neural network (DNN...

Full description

Saved in:
Bibliographic Details
Main Authors: Gazala Mushtaq, Veningston K
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:SLAS Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2472630324000888
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846117822562828288
author Gazala Mushtaq
Veningston K
author_facet Gazala Mushtaq
Veningston K
author_sort Gazala Mushtaq
collection DOAJ
description In this study, a deep learning model is proposed for the classification of fetal health into 3 categories: Normal, suspect, and pathological. The primary objective is to utilize the power of deep learning to improve the efficiency and effectiveness of diagnostic processes. A deep neural network (DNN) model is proposed for fetal health analysis using data obtained from Cardiotocography (CTG). A dataset containing 21 attributes is used to carry out this work. The model incorporates multiple hidden layers, augmented with batch normalization and dropout layers for improved generalization. This study assesses the model's interpretation ability in fetal health classification using explainable deep learning. This enhances transparency in decision-making of the classifier model by leveraging feature importance and feature saliency analysis, fostering trust and facilitating the clinical adoption of fetal health assessments. Our proposed model demonstrates a remarkable performance with 0.99 accuracy, 0.93 sensitivity, 0.93 specificity, 0.96 AUC, 0.93 precision, and 0.93 F1 scores in classifying fetal health. We also performed comparative analysis with six other models including Logistic Regression, KNN, SVM, Naive Bayes, Random Forest, and Gradient Boosting to assess and compare the effectiveness of our model and the accuracies of 0.89, 0.88, 0.90, 081, 0.93, and 0.93 were achieved respectively by these baseline models. The results revealed that our proposed model outperformed all the baseline models in terms of accuracy. This indicates the potential of deep learning in improving fetal health assessment and contributing to the field of obstetrics by providing a robust tool for early risk detection.
format Article
id doaj-art-998f2f209d5d4631aeb3fb8126b8c59a
institution Kabale University
issn 2472-6303
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series SLAS Technology
spelling doaj-art-998f2f209d5d4631aeb3fb8126b8c59a2024-12-18T08:51:02ZengElsevierSLAS Technology2472-63032024-12-01296100206AI driven interpretable deep learning based fetal health classificationGazala Mushtaq0Veningston K1Corresponding author.; Department of Computer Science and Engineering, National Institute of Technology Srinagar, Jammu and Kashmir 190006, IndiaDepartment of Computer Science and Engineering, National Institute of Technology Srinagar, Jammu and Kashmir 190006, IndiaIn this study, a deep learning model is proposed for the classification of fetal health into 3 categories: Normal, suspect, and pathological. The primary objective is to utilize the power of deep learning to improve the efficiency and effectiveness of diagnostic processes. A deep neural network (DNN) model is proposed for fetal health analysis using data obtained from Cardiotocography (CTG). A dataset containing 21 attributes is used to carry out this work. The model incorporates multiple hidden layers, augmented with batch normalization and dropout layers for improved generalization. This study assesses the model's interpretation ability in fetal health classification using explainable deep learning. This enhances transparency in decision-making of the classifier model by leveraging feature importance and feature saliency analysis, fostering trust and facilitating the clinical adoption of fetal health assessments. Our proposed model demonstrates a remarkable performance with 0.99 accuracy, 0.93 sensitivity, 0.93 specificity, 0.96 AUC, 0.93 precision, and 0.93 F1 scores in classifying fetal health. We also performed comparative analysis with six other models including Logistic Regression, KNN, SVM, Naive Bayes, Random Forest, and Gradient Boosting to assess and compare the effectiveness of our model and the accuracies of 0.89, 0.88, 0.90, 081, 0.93, and 0.93 were achieved respectively by these baseline models. The results revealed that our proposed model outperformed all the baseline models in terms of accuracy. This indicates the potential of deep learning in improving fetal health assessment and contributing to the field of obstetrics by providing a robust tool for early risk detection.http://www.sciencedirect.com/science/article/pii/S2472630324000888Fetal health classificationDeep LearningMachine learningCardiotocography (CTG)
spellingShingle Gazala Mushtaq
Veningston K
AI driven interpretable deep learning based fetal health classification
SLAS Technology
Fetal health classification
Deep Learning
Machine learning
Cardiotocography (CTG)
title AI driven interpretable deep learning based fetal health classification
title_full AI driven interpretable deep learning based fetal health classification
title_fullStr AI driven interpretable deep learning based fetal health classification
title_full_unstemmed AI driven interpretable deep learning based fetal health classification
title_short AI driven interpretable deep learning based fetal health classification
title_sort ai driven interpretable deep learning based fetal health classification
topic Fetal health classification
Deep Learning
Machine learning
Cardiotocography (CTG)
url http://www.sciencedirect.com/science/article/pii/S2472630324000888
work_keys_str_mv AT gazalamushtaq aidriveninterpretabledeeplearningbasedfetalhealthclassification
AT veningstonk aidriveninterpretabledeeplearningbasedfetalhealthclassification