A novel few shot learning derived architecture for long-term HbA1c prediction

<p dir="ltr">Regular monitoring of glycated hemoglobin (HbA1c) levels is important for the proper management of diabetes. Studies demonstrated that lower levels of HbA1c play an essential role in reducing or delaying microvascular difficulties that arise from diabetes. In addition, t...

Full description

Saved in:
Bibliographic Details
Main Author: Marwa Qaraqe (10135172) (author)
Other Authors: Almiqdad Elzein (13141038) (author), Samir Belhaouari (18418839) (author), Md Shafiq Ilam (19206097) (author), Goran Petrovski (129836) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513510258507776
author Marwa Qaraqe (10135172)
author2 Almiqdad Elzein (13141038)
Samir Belhaouari (18418839)
Md Shafiq Ilam (19206097)
Goran Petrovski (129836)
author2_role author
author
author
author
author_facet Marwa Qaraqe (10135172)
Almiqdad Elzein (13141038)
Samir Belhaouari (18418839)
Md Shafiq Ilam (19206097)
Goran Petrovski (129836)
author_role author
dc.creator.none.fl_str_mv Marwa Qaraqe (10135172)
Almiqdad Elzein (13141038)
Samir Belhaouari (18418839)
Md Shafiq Ilam (19206097)
Goran Petrovski (129836)
dc.date.none.fl_str_mv 2024-01-04T03:00:00Z
dc.identifier.none.fl_str_mv 10.1038/s41598-023-50348-1
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_novel_few_shot_learning_derived_architecture_for_long-term_HbA1c_prediction/26363242
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Machine learning
Biomarkers
Biotechnology
Endocrinology
Engineering
Health care
Mathematics and computing
dc.title.none.fl_str_mv A novel few shot learning derived architecture for long-term HbA1c prediction
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Regular monitoring of glycated hemoglobin (HbA1c) levels is important for the proper management of diabetes. Studies demonstrated that lower levels of HbA1c play an essential role in reducing or delaying microvascular difficulties that arise from diabetes. In addition, there is an association between elevated HbA1c levels and the development of diabetes-related comorbidities. The advanced prediction of HbA1c enables patients and physicians to make changes to treatment plans and lifestyle to avoid elevated HbA1c levels, which can consequently lead to irreversible health complications. Despite the impact of such prediction capabilities, no work in the literature or industry has investigated the futuristic prediction of HbA1c using current blood glucose (BG) measurements. For the first time in the literature, this work proposes a novel FSL-derived algorithm for the long-term prediction of clinical HbA1c measures. More importantly, the study specifically targeted the pediatric Type-1 diabetic population, as an early prediction of elevated HbA1c levels could help avert severe life-threatening complications in these young children. Short-term CGM time-series data are processed using both novel image transformation approaches, as well as using conventional signal processing methods. The derived images are then fed into a convolutional neural network (CNN) adapted from a few-shot learning (FSL) model for feature extraction, and all the derived features are fused together. A novel normalized FSL-distance (FSLD) metric is proposed for accurately separating the features of different HbA1c levels. Finally, a K-nearest neighbor (KNN) model with majority voting is implemented for the final classification task. The proposed FSL-derived algorithm provides a prediction accuracy of 93.2%.</p><h2>Other Information</h2><p dir="ltr">Published in: Scientific Reports<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41598-023-50348-1" target="_blank">https://dx.doi.org/10.1038/s41598-023-50348-1</a></p>
eu_rights_str_mv openAccess
id Manara2_03343b84ff4d19f5a4b8d50ce824c9ed
identifier_str_mv 10.1038/s41598-023-50348-1
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26363242
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A novel few shot learning derived architecture for long-term HbA1c predictionMarwa Qaraqe (10135172)Almiqdad Elzein (13141038)Samir Belhaouari (18418839)Md Shafiq Ilam (19206097)Goran Petrovski (129836)Biomedical and clinical sciencesClinical sciencesHealth sciencesHealth services and systemsInformation and computing sciencesMachine learningBiomarkersBiotechnologyEndocrinologyEngineeringHealth careMathematics and computing<p dir="ltr">Regular monitoring of glycated hemoglobin (HbA1c) levels is important for the proper management of diabetes. Studies demonstrated that lower levels of HbA1c play an essential role in reducing or delaying microvascular difficulties that arise from diabetes. In addition, there is an association between elevated HbA1c levels and the development of diabetes-related comorbidities. The advanced prediction of HbA1c enables patients and physicians to make changes to treatment plans and lifestyle to avoid elevated HbA1c levels, which can consequently lead to irreversible health complications. Despite the impact of such prediction capabilities, no work in the literature or industry has investigated the futuristic prediction of HbA1c using current blood glucose (BG) measurements. For the first time in the literature, this work proposes a novel FSL-derived algorithm for the long-term prediction of clinical HbA1c measures. More importantly, the study specifically targeted the pediatric Type-1 diabetic population, as an early prediction of elevated HbA1c levels could help avert severe life-threatening complications in these young children. Short-term CGM time-series data are processed using both novel image transformation approaches, as well as using conventional signal processing methods. The derived images are then fed into a convolutional neural network (CNN) adapted from a few-shot learning (FSL) model for feature extraction, and all the derived features are fused together. A novel normalized FSL-distance (FSLD) metric is proposed for accurately separating the features of different HbA1c levels. Finally, a K-nearest neighbor (KNN) model with majority voting is implemented for the final classification task. The proposed FSL-derived algorithm provides a prediction accuracy of 93.2%.</p><h2>Other Information</h2><p dir="ltr">Published in: Scientific Reports<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1038/s41598-023-50348-1" target="_blank">https://dx.doi.org/10.1038/s41598-023-50348-1</a></p>2024-01-04T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1038/s41598-023-50348-1https://figshare.com/articles/journal_contribution/A_novel_few_shot_learning_derived_architecture_for_long-term_HbA1c_prediction/26363242CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/263632422024-01-04T03:00:00Z
spellingShingle A novel few shot learning derived architecture for long-term HbA1c prediction
Marwa Qaraqe (10135172)
Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Machine learning
Biomarkers
Biotechnology
Endocrinology
Engineering
Health care
Mathematics and computing
status_str publishedVersion
title A novel few shot learning derived architecture for long-term HbA1c prediction
title_full A novel few shot learning derived architecture for long-term HbA1c prediction
title_fullStr A novel few shot learning derived architecture for long-term HbA1c prediction
title_full_unstemmed A novel few shot learning derived architecture for long-term HbA1c prediction
title_short A novel few shot learning derived architecture for long-term HbA1c prediction
title_sort A novel few shot learning derived architecture for long-term HbA1c prediction
topic Biomedical and clinical sciences
Clinical sciences
Health sciences
Health services and systems
Information and computing sciences
Machine learning
Biomarkers
Biotechnology
Endocrinology
Engineering
Health care
Mathematics and computing