Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers
<h4>Background</h4> Accurate estimates of gestational age (GA) at birth are important for preterm birth surveillance but can be challenging to obtain in low income countries. Our objective was to develop machine learning models to accurately estimate GA shortly after birth using clinical...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9987787/?tool=EBI |
| _version_ | 1827996563322961920 |
|---|---|
| author | Steven Hawken Robin Ducharme Malia S. Q. Murphy Brieanne Olibris A. Brianne Bota Lindsay A. Wilson Wei Cheng Julian Little Beth K. Potter Kathryn M. Denize Monica Lamoureux Matthew Henderson Katelyn J. Rittenhouse Joan T. Price Humphrey Mwape Bellington Vwalika Patrick Musonda Jesmin Pervin A. K. Azad Chowdhury Anisur Rahman Pranesh Chakraborty Jeffrey S. A. Stringer Kumanan Wilson |
| author_facet | Steven Hawken Robin Ducharme Malia S. Q. Murphy Brieanne Olibris A. Brianne Bota Lindsay A. Wilson Wei Cheng Julian Little Beth K. Potter Kathryn M. Denize Monica Lamoureux Matthew Henderson Katelyn J. Rittenhouse Joan T. Price Humphrey Mwape Bellington Vwalika Patrick Musonda Jesmin Pervin A. K. Azad Chowdhury Anisur Rahman Pranesh Chakraborty Jeffrey S. A. Stringer Kumanan Wilson |
| author_sort | Steven Hawken |
| collection | DOAJ |
| description | <h4>Background</h4> Accurate estimates of gestational age (GA) at birth are important for preterm birth surveillance but can be challenging to obtain in low income countries. Our objective was to develop machine learning models to accurately estimate GA shortly after birth using clinical and metabolomic data. <h4>Methods</h4> We derived three GA estimation models using ELASTIC NET multivariable linear regression using metabolomic markers from heel-prick blood samples and clinical data from a retrospective cohort of newborns from Ontario, Canada. We conducted internal model validation in an independent cohort of Ontario newborns, and external validation in heel prick and cord blood sample data collected from newborns from prospective birth cohorts in Lusaka, Zambia and Matlab, Bangladesh. Model performance was measured by comparing model-derived estimates of GA to reference estimates from early pregnancy ultrasound. <h4>Results</h4> Samples were collected from 311 newborns from Zambia and 1176 from Bangladesh. The best-performing model accurately estimated GA within about 6 days of ultrasound estimates in both cohorts when applied to heel prick data (MAE 0.79 weeks (95% CI 0.69, 0.90) for Zambia; 0.81 weeks (0.75, 0.86) for Bangladesh), and within about 7 days when applied to cord blood data (1.02 weeks (0.90, 1.15) for Zambia; 0.95 weeks (0.90, 0.99) for Bangladesh). <h4>Conclusions</h4> Algorithms developed in Canada provided accurate estimates of GA when applied to external cohorts from Zambia and Bangladesh. Model performance was superior in heel prick data as compared to cord blood data. |
| first_indexed | 2024-04-10T05:13:53Z |
| format | Article |
| id | doaj.art-89a231c2041c456d9b2e5027b76fea75 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-10T05:13:53Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-89a231c2041c456d9b2e5027b76fea752023-03-09T05:31:25ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01183Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markersSteven HawkenRobin DucharmeMalia S. Q. MurphyBrieanne OlibrisA. Brianne BotaLindsay A. WilsonWei ChengJulian LittleBeth K. PotterKathryn M. DenizeMonica LamoureuxMatthew HendersonKatelyn J. RittenhouseJoan T. PriceHumphrey MwapeBellington VwalikaPatrick MusondaJesmin PervinA. K. Azad ChowdhuryAnisur RahmanPranesh ChakrabortyJeffrey S. A. StringerKumanan Wilson<h4>Background</h4> Accurate estimates of gestational age (GA) at birth are important for preterm birth surveillance but can be challenging to obtain in low income countries. Our objective was to develop machine learning models to accurately estimate GA shortly after birth using clinical and metabolomic data. <h4>Methods</h4> We derived three GA estimation models using ELASTIC NET multivariable linear regression using metabolomic markers from heel-prick blood samples and clinical data from a retrospective cohort of newborns from Ontario, Canada. We conducted internal model validation in an independent cohort of Ontario newborns, and external validation in heel prick and cord blood sample data collected from newborns from prospective birth cohorts in Lusaka, Zambia and Matlab, Bangladesh. Model performance was measured by comparing model-derived estimates of GA to reference estimates from early pregnancy ultrasound. <h4>Results</h4> Samples were collected from 311 newborns from Zambia and 1176 from Bangladesh. The best-performing model accurately estimated GA within about 6 days of ultrasound estimates in both cohorts when applied to heel prick data (MAE 0.79 weeks (95% CI 0.69, 0.90) for Zambia; 0.81 weeks (0.75, 0.86) for Bangladesh), and within about 7 days when applied to cord blood data (1.02 weeks (0.90, 1.15) for Zambia; 0.95 weeks (0.90, 0.99) for Bangladesh). <h4>Conclusions</h4> Algorithms developed in Canada provided accurate estimates of GA when applied to external cohorts from Zambia and Bangladesh. Model performance was superior in heel prick data as compared to cord blood data.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9987787/?tool=EBI |
| spellingShingle | Steven Hawken Robin Ducharme Malia S. Q. Murphy Brieanne Olibris A. Brianne Bota Lindsay A. Wilson Wei Cheng Julian Little Beth K. Potter Kathryn M. Denize Monica Lamoureux Matthew Henderson Katelyn J. Rittenhouse Joan T. Price Humphrey Mwape Bellington Vwalika Patrick Musonda Jesmin Pervin A. K. Azad Chowdhury Anisur Rahman Pranesh Chakraborty Jeffrey S. A. Stringer Kumanan Wilson Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers PLoS ONE |
| title | Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers |
| title_full | Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers |
| title_fullStr | Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers |
| title_full_unstemmed | Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers |
| title_short | Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers |
| title_sort | development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9987787/?tool=EBI |
| work_keys_str_mv | AT stevenhawken developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT robinducharme developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT maliasqmurphy developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT brieanneolibris developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT abriannebota developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT lindsayawilson developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT weicheng developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT julianlittle developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT bethkpotter developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT kathrynmdenize developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT monicalamoureux developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT matthewhenderson developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT katelynjrittenhouse developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT joantprice developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT humphreymwape developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT bellingtonvwalika developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT patrickmusonda developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT jesminpervin developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT akazadchowdhury developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT anisurrahman developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT praneshchakraborty developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT jeffreysastringer developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers AT kumananwilson developmentandexternalvalidationofmachinelearningalgorithmsforpostnatalgestationalageestimationusingclinicaldataandmetabolomicmarkers |