Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches
<b>Background/Objectives:</b> The causes of low milk supply are multifactorial, including factors such as gene mutations, endocrine disorders, and infrequent milk removal. These factors affect the functional capacity of the mammary gland and, potentially, the concentrations of milk compo...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/2/191 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588704839892992 |
|---|---|
| author | Xuehua Jin Ching Tat Lai Sharon L. Perrella Xiaojie Zhou Ghulam Mubashar Hassan Jacki L. McEachran Zoya Gridneva Nicolas L. Taylor Mary E. Wlodek Donna T. Geddes |
| author_facet | Xuehua Jin Ching Tat Lai Sharon L. Perrella Xiaojie Zhou Ghulam Mubashar Hassan Jacki L. McEachran Zoya Gridneva Nicolas L. Taylor Mary E. Wlodek Donna T. Geddes |
| author_sort | Xuehua Jin |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> The causes of low milk supply are multifactorial, including factors such as gene mutations, endocrine disorders, and infrequent milk removal. These factors affect the functional capacity of the mammary gland and, potentially, the concentrations of milk components. This study aimed to investigate the differences in milk composition between mothers with low and normal milk supply and develop predictive machine learning models for identifying low milk supply. <b>Methods:</b> Twenty-four-hour milk production measurements were conducted using the test-weigh method. An array of milk components was measured in 58 women with low milk supply (<600 mL/24 h) and 106 with normal milk supply (≥600 mL/24 h). Machine learning algorithms were employed to develop prediction models integrating milk composition and maternal and infant characteristics. <b>Results:</b> Among the six machine learning algorithms tested, deep learning and gradient boosting machines methods had the best performance metrics. The best-performing model, incorporating 14 milk components and maternal and infant characteristics, achieved an accuracy of 87.9%, an area under the precision-recall curve (AUPRC) of 0.893, and an area under the receiver operating characteristic curve (AUC) of 0.917. Additionally, a simplified model, optimised for clinical applicability, maintained a reasonable accuracy of 78.8%, an AUPRC of 0.776, and an AUC of 0.794. <b>Conclusions:</b> These findings demonstrate the potential of machine learning models to predict low milk supply with high accuracy. Integrating milk composition and maternal and infant characteristics offers a practical approach to identify women at risk of low milk supply, facilitating timely interventions to support breastfeeding and ensure adequate infant nutrition. |
| format | Article |
| id | doaj-art-777f9236279a41a1ad1436d64b4e8e29 |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-777f9236279a41a1ad1436d64b4e8e292025-01-24T13:29:03ZengMDPI AGDiagnostics2075-44182025-01-0115219110.3390/diagnostics15020191Milk Composition Is Predictive of Low Milk Supply Using Machine Learning ApproachesXuehua Jin0Ching Tat Lai1Sharon L. Perrella2Xiaojie Zhou3Ghulam Mubashar Hassan4Jacki L. McEachran5Zoya Gridneva6Nicolas L. Taylor7Mary E. Wlodek8Donna T. Geddes9School of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Physics, Mathematics and Computing, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Molecular Sciences, The University of Western Australia, Crawley, WA 6009, Australia<b>Background/Objectives:</b> The causes of low milk supply are multifactorial, including factors such as gene mutations, endocrine disorders, and infrequent milk removal. These factors affect the functional capacity of the mammary gland and, potentially, the concentrations of milk components. This study aimed to investigate the differences in milk composition between mothers with low and normal milk supply and develop predictive machine learning models for identifying low milk supply. <b>Methods:</b> Twenty-four-hour milk production measurements were conducted using the test-weigh method. An array of milk components was measured in 58 women with low milk supply (<600 mL/24 h) and 106 with normal milk supply (≥600 mL/24 h). Machine learning algorithms were employed to develop prediction models integrating milk composition and maternal and infant characteristics. <b>Results:</b> Among the six machine learning algorithms tested, deep learning and gradient boosting machines methods had the best performance metrics. The best-performing model, incorporating 14 milk components and maternal and infant characteristics, achieved an accuracy of 87.9%, an area under the precision-recall curve (AUPRC) of 0.893, and an area under the receiver operating characteristic curve (AUC) of 0.917. Additionally, a simplified model, optimised for clinical applicability, maintained a reasonable accuracy of 78.8%, an AUPRC of 0.776, and an AUC of 0.794. <b>Conclusions:</b> These findings demonstrate the potential of machine learning models to predict low milk supply with high accuracy. Integrating milk composition and maternal and infant characteristics offers a practical approach to identify women at risk of low milk supply, facilitating timely interventions to support breastfeeding and ensure adequate infant nutrition.https://www.mdpi.com/2075-4418/15/2/191human milklactationbreastfeedingbiomarkersmilk compositionmilk supply |
| spellingShingle | Xuehua Jin Ching Tat Lai Sharon L. Perrella Xiaojie Zhou Ghulam Mubashar Hassan Jacki L. McEachran Zoya Gridneva Nicolas L. Taylor Mary E. Wlodek Donna T. Geddes Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches Diagnostics human milk lactation breastfeeding biomarkers milk composition milk supply |
| title | Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches |
| title_full | Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches |
| title_fullStr | Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches |
| title_full_unstemmed | Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches |
| title_short | Milk Composition Is Predictive of Low Milk Supply Using Machine Learning Approaches |
| title_sort | milk composition is predictive of low milk supply using machine learning approaches |
| topic | human milk lactation breastfeeding biomarkers milk composition milk supply |
| url | https://www.mdpi.com/2075-4418/15/2/191 |
| work_keys_str_mv | AT xuehuajin milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT chingtatlai milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT sharonlperrella milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT xiaojiezhou milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT ghulammubasharhassan milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT jackilmceachran milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT zoyagridneva milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT nicolasltaylor milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT maryewlodek milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches AT donnatgeddes milkcompositionispredictiveoflowmilksupplyusingmachinelearningapproaches |