{"id":{"repo_id":"bradford","oai_identifier":"oai:bradscholars.brad.ac.uk:10454/19893.2"},"canonical_url":"https://search.dev.ndltd.org/etd/bradford/oai:bradscholars.brad.ac.uk:10454/19893.2","repository":{"repo_id":"bradford","name":"University of Bradford","base_url":"https://bradscholars.brad.ac.uk/oai/request"},"display":{"title":"Prediction of Large for Gestational Age Infants in Ethnically Diverse Datasets Using Machine Learning Techniques. Development of 3rd Trimester Machine Learning Prediction Models and Identification of Important Features Using Dimensionality Reduction Techniques","abstract":"Background: Large-for-gestational-age (LGA) is a common pregnancy complication, associated with high maternal BMI and diabetes. Despite its gravity, standard prediction methods, such as ultrasounds are inaccurate. Objective: application of machine learning methods to develop LGA prediction models for ethnically diverse datasets and provide a benchmark for future LGA prediction work. Methods: Two retrospective datasets were used: Born In Bradford (BiB) and NHS, each including a large percentage of women of South Asian ethnicity. After appropriate data preparation, LGA classification models were developed, and imbalanced learning strategies were applied. Additionally, using data reduction, important features within the datasets were reported. Results: Baseline BiB models achieved 9% sensitivity, 56% precision, and 26% F0.5, BiB-GDM (containing only GDM women) models achieved 41% sensitivity, 60% precision, and 55% F0.5. Applying random undersampling increased sensitivity scores to 72% for BiB models and 80% for BiB-GDM. Cost sensitive learning methods achieved 36% F0.5 score for BiB models and 57% for BiB-GDM models. Threshold tuning improved the F0.5 scores models to 47% and 66 % in BiB and BiB-GDM, respectively. Using data reduction, important features were the minimum and maximum Abdominal Circumference (AC) and Estimated Foetal Weight (EFW) ultrasound measurements in BiB-GDM dataset. While they were the mean and proportion of high Blood Glucose (BG) measurements in the NHS dataset. Conclusions: machine learning algorithms are not superior to Logistic Regression in LGA predictive performance. Threshold tuning was an appropriate method for handling data imbalance and maximising F0.5 scores. Finally, ultrasound measurements and BG self-monitoring data were important features in LGA prediction.","abstract_html":"Background: Large-for-gestational-age (LGA) is a common pregnancy complication, associated with high maternal BMI and diabetes. Despite its gravity, standard prediction methods, such as ultrasounds are inaccurate. Objective: application of machine learning methods to develop LGA prediction models for ethnically diverse datasets and provide a benchmark for future LGA prediction work. Methods: Two retrospective datasets were used: Born In Bradford (BiB) and NHS, each including a large percentage of women of South Asian ethnicity. After appropriate data preparation, LGA classification models were developed, and imbalanced learning strategies were applied. Additionally, using data reduction, important features within the datasets were reported. Results: Baseline BiB models achieved 9% sensitivity, 56% precision, and 26% F0.5, BiB-GDM (containing only GDM women) models achieved 41% sensitivity, 60% precision, and 55% F0.5. Applying random undersampling increased sensitivity scores to 72% for BiB models and 80% for BiB-GDM. Cost sensitive learning methods achieved 36% F0.5 score for BiB models and 57% for BiB-GDM models. Threshold tuning improved the F0.5 scores models to 47% and 66 % in BiB and BiB-GDM, respectively. Using data reduction, important features were the minimum and maximum Abdominal Circumference (AC) and Estimated Foetal Weight (EFW) ultrasound measurements in BiB-GDM dataset. While they were the mean and proportion of high Blood Glucose (BG) measurements in the NHS dataset. Conclusions: machine learning algorithms are not superior to Logistic Regression in LGA predictive performance. Threshold tuning was an appropriate method for handling data imbalance and maximising F0.5 scores. Finally, ultrasound measurements and BG self-monitoring data were important features in LGA prediction.","abstract_has_math":false,"creators":["Sabouni, Sumaia"],"institution":"University of Bradford","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Graham, Anne M.","Qahwaji, Rami","Poterlowicz, Krzysztof"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-07-24T01:13:22Z","subjects":["Large for gestational age","Gestational diabetes","Macrosomia","Obesity","Machine learning","Prediction","Class imbalance","Algorithms","Ethnically diverse datasets"],"languages":["en"],"rights":["\"Creative
The University of Bradford theses are licenced under a Creative Commons Licence."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://bradscholars.brad.ac.uk/handle/10454/19893.2","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Graham, Anne M.","Qahwaji, Rami","Poterlowicz, Krzysztof"]},{"key":"dc:creator","label":"Author","values":["Sabouni, Sumaia"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-08T09:26:27Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-04-24T14:33:42Z","2025-04-08T09:26:27Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["School of Chemistry & Biosciences. Faculty of Life Sciences"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Bradford"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["PhD"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Large for gestational age","Gestational diabetes","Macrosomia","Obesity","Machine learning","Prediction","Class imbalance","Algorithms","Ethnically diverse datasets"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["\"Creative
The University of Bradford theses are licenced under a Creative Commons Licence."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://bradscholars.brad.ac.uk/handle/10454/19893.2"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Background: Large-for-gestational-age (LGA) is a common pregnancy complication, associated with high maternal BMI and diabetes. Despite its gravity, standard prediction methods, such as ultrasounds are inaccurate. Objective: application of machine learning methods to develop LGA prediction models for ethnically diverse datasets and provide a benchmark for future LGA prediction work. Methods: Two retrospective datasets were used: Born In Bradford (BiB) and NHS, each including a large percentage of women of South Asian ethnicity. After appropriate data preparation, LGA classification models were developed, and imbalanced learning strategies were applied. Additionally, using data reduction, important features within the datasets were reported. Results: Baseline BiB models achieved 9% sensitivity, 56% precision, and 26% F0.5, BiB-GDM (containing only GDM women) models achieved 41% sensitivity, 60% precision, and 55% F0.5. Applying random undersampling increased sensitivity scores to 72% for BiB models and 80% for BiB-GDM. Cost sensitive learning methods achieved 36% F0.5 score for BiB models and 57% for BiB-GDM models. Threshold tuning improved the F0.5 scores models to 47% and 66 % in BiB and BiB-GDM, respectively. Using data reduction, important features were the minimum and maximum Abdominal Circumference (AC) and Estimated Foetal Weight (EFW) ultrasound measurements in BiB-GDM dataset. While they were the mean and proportion of high Blood Glucose (BG) measurements in the NHS dataset. Conclusions: machine learning algorithms are not superior to Logistic Regression in LGA predictive performance. Threshold tuning was an appropriate method for handling data imbalance and maximising F0.5 scores. Finally, ultrasound measurements and BG self-monitoring data were important features in LGA prediction."]},{"key":"dc:title","label":"Title","values":["Prediction of Large for Gestational Age Infants in Ethnically Diverse Datasets Using Machine Learning Techniques. Development of 3rd Trimester Machine Learning Prediction Models and Identification of Important Features Using Dimensionality Reduction Techniques"]}]}],"canonical_facts":{"dc:contributor.advisor":["Graham, Anne M.","Qahwaji, Rami","Poterlowicz, Krzysztof"],"dc:creator":["Sabouni, Sumaia"],"dc:date.accessioned":["2025-04-08T09:26:27Z"],"dc:date.available":["2024-04-24T14:33:42Z","2025-04-08T09:26:27Z"],"dc:date.issued":["2023"],"dc:description.abstract":["Background: Large-for-gestational-age (LGA) is a common pregnancy complication, associated with high maternal BMI and diabetes. Despite its gravity, standard prediction methods, such as ultrasounds are inaccurate. Objective: application of machine learning methods to develop LGA prediction models for ethnically diverse datasets and provide a benchmark for future LGA prediction work. Methods: Two retrospective datasets were used: Born In Bradford (BiB) and NHS, each including a large percentage of women of South Asian ethnicity. After appropriate data preparation, LGA classification models were developed, and imbalanced learning strategies were applied. Additionally, using data reduction, important features within the datasets were reported. Results: Baseline BiB models achieved 9% sensitivity, 56% precision, and 26% F0.5, BiB-GDM (containing only GDM women) models achieved 41% sensitivity, 60% precision, and 55% F0.5. Applying random undersampling increased sensitivity scores to 72% for BiB models and 80% for BiB-GDM. Cost sensitive learning methods achieved 36% F0.5 score for BiB models and 57% for BiB-GDM models. Threshold tuning improved the F0.5 scores models to 47% and 66 % in BiB and BiB-GDM, respectively. Using data reduction, important features were the minimum and maximum Abdominal Circumference (AC) and Estimated Foetal Weight (EFW) ultrasound measurements in BiB-GDM dataset. While they were the mean and proportion of high Blood Glucose (BG) measurements in the NHS dataset. Conclusions: machine learning algorithms are not superior to Logistic Regression in LGA predictive performance. Threshold tuning was an appropriate method for handling data imbalance and maximising F0.5 scores. Finally, ultrasound measurements and BG self-monitoring data were important features in LGA prediction."],"dc:identifier.uri":["https://bradscholars.brad.ac.uk/handle/10454/19893.2"],"dc:language.iso":["en"],"dc:publisher.department":["School of Chemistry & Biosciences. Faculty of Life Sciences"],"dc:publisher.institution":["University of Bradford"],"dc:rights":["\"Creative
The University of Bradford theses are licenced under a Creative Commons Licence."],"dc:subject":["Large for gestational age","Gestational diabetes","Macrosomia","Obesity","Machine learning","Prediction","Class imbalance","Algorithms","Ethnically diverse datasets"],"dc:title":["Prediction of Large for Gestational Age Infants in Ethnically Diverse Datasets Using Machine Learning Techniques. Development of 3rd Trimester Machine Learning Prediction Models and Identification of Important Features Using Dimensionality Reduction Techniques"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["PhD"]},"updated_at":"2026-07-24T01:13:22Z"}