Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study
Abstract Background Gestational diabetes (GDM) is prevalent and benefits from timely and effective treatment, given the short window to impact glycemic control. Clinicians face major barriers to choosing effectively among treatment modalities [medical nutrition therapy (MNT) with or without pharmaco...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-09-01
|
| Series: | BMC Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12916-022-02499-7 |
| _version_ | 1811267374625587200 |
|---|---|
| author | Lauren D. Liao Assiamira Ferrara Mara B. Greenberg Amanda L. Ngo Juanran Feng Zhenhua Zhang Patrick T. Bradshaw Alan E. Hubbard Yeyi Zhu |
| author_facet | Lauren D. Liao Assiamira Ferrara Mara B. Greenberg Amanda L. Ngo Juanran Feng Zhenhua Zhang Patrick T. Bradshaw Alan E. Hubbard Yeyi Zhu |
| author_sort | Lauren D. Liao |
| collection | DOAJ |
| description | Abstract Background Gestational diabetes (GDM) is prevalent and benefits from timely and effective treatment, given the short window to impact glycemic control. Clinicians face major barriers to choosing effectively among treatment modalities [medical nutrition therapy (MNT) with or without pharmacologic treatment (antidiabetic oral agents and/or insulin)]. We investigated whether clinical data at varied stages of pregnancy can predict GDM treatment modality. Methods Among a population-based cohort of 30,474 pregnancies with GDM delivered at Kaiser Permanente Northern California in 2007–2017, we selected those in 2007–2016 as the discovery set and 2017 as the temporal/future validation set. Potential predictors were extracted from electronic health records at different timepoints (levels 1–4): (1) 1-year preconception to the last menstrual period, (2) the last menstrual period to GDM diagnosis, (3) at GDM diagnosis, and (4) 1 week after GDM diagnosis. We compared transparent and ensemble machine learning prediction methods, including least absolute shrinkage and selection operator (LASSO) regression and super learner, containing classification and regression tree, LASSO regression, random forest, and extreme gradient boosting algorithms, to predict risks for pharmacologic treatment beyond MNT. Results The super learner using levels 1–4 predictors had higher predictability [tenfold cross-validated C-statistic in discovery/validation set: 0.934 (95% CI: 0.931–0.936)/0.815 (0.800–0.829)], compared to levels 1, 1–2, and 1–3 (discovery/validation set C-statistic: 0.683–0.869/0.634–0.754). A simpler, more interpretable model, including timing of GDM diagnosis, diagnostic fasting glucose value, and the status and frequency of glycemic control at fasting during one-week post diagnosis, was developed using tenfold cross-validated logistic regression based on super learner-selected predictors. This model compared to the super learner had only a modest reduction in predictability [discovery/validation set C-statistic: 0.825 (0.820–0.830)/0.798 (95% CI: 0.783–0.813)]. Conclusions Clinical data demonstrated reasonably high predictability for GDM treatment modality at the time of GDM diagnosis and high predictability at 1-week post GDM diagnosis. These population-based, clinically oriented models may support algorithm-based risk-stratification for treatment modality, inform timely treatment, and catalyze more effective management of GDM. |
| first_indexed | 2024-04-12T21:01:18Z |
| format | Article |
| id | doaj.art-6b3772ccdb2147bab910d58532331352 |
| institution | Directory Open Access Journal |
| issn | 1741-7015 |
| language | English |
| last_indexed | 2024-04-12T21:01:18Z |
| publishDate | 2022-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medicine |
| spelling | doaj.art-6b3772ccdb2147bab910d585323313522022-12-22T03:16:50ZengBMCBMC Medicine1741-70152022-09-0120111310.1186/s12916-022-02499-7Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort studyLauren D. Liao0Assiamira Ferrara1Mara B. Greenberg2Amanda L. Ngo3Juanran Feng4Zhenhua Zhang5Patrick T. Bradshaw6Alan E. Hubbard7Yeyi Zhu8Division of Biostatistics, School of Public Health, University of CaliforniaDivision of Research, Kaiser Permanente Northern CaliforniaDepartment of Obstetrics and Gynecology, Kaiser Permanente Northern CaliforniaDivision of Research, Kaiser Permanente Northern CaliforniaDivision of Research, Kaiser Permanente Northern CaliforniaDepartment of Civil and Environmental Engineering, Stanford UniversityDivision of Epidemiology, School of Public Health, University of CaliforniaDivision of Biostatistics, School of Public Health, University of CaliforniaDivision of Research, Kaiser Permanente Northern CaliforniaAbstract Background Gestational diabetes (GDM) is prevalent and benefits from timely and effective treatment, given the short window to impact glycemic control. Clinicians face major barriers to choosing effectively among treatment modalities [medical nutrition therapy (MNT) with or without pharmacologic treatment (antidiabetic oral agents and/or insulin)]. We investigated whether clinical data at varied stages of pregnancy can predict GDM treatment modality. Methods Among a population-based cohort of 30,474 pregnancies with GDM delivered at Kaiser Permanente Northern California in 2007–2017, we selected those in 2007–2016 as the discovery set and 2017 as the temporal/future validation set. Potential predictors were extracted from electronic health records at different timepoints (levels 1–4): (1) 1-year preconception to the last menstrual period, (2) the last menstrual period to GDM diagnosis, (3) at GDM diagnosis, and (4) 1 week after GDM diagnosis. We compared transparent and ensemble machine learning prediction methods, including least absolute shrinkage and selection operator (LASSO) regression and super learner, containing classification and regression tree, LASSO regression, random forest, and extreme gradient boosting algorithms, to predict risks for pharmacologic treatment beyond MNT. Results The super learner using levels 1–4 predictors had higher predictability [tenfold cross-validated C-statistic in discovery/validation set: 0.934 (95% CI: 0.931–0.936)/0.815 (0.800–0.829)], compared to levels 1, 1–2, and 1–3 (discovery/validation set C-statistic: 0.683–0.869/0.634–0.754). A simpler, more interpretable model, including timing of GDM diagnosis, diagnostic fasting glucose value, and the status and frequency of glycemic control at fasting during one-week post diagnosis, was developed using tenfold cross-validated logistic regression based on super learner-selected predictors. This model compared to the super learner had only a modest reduction in predictability [discovery/validation set C-statistic: 0.825 (0.820–0.830)/0.798 (95% CI: 0.783–0.813)]. Conclusions Clinical data demonstrated reasonably high predictability for GDM treatment modality at the time of GDM diagnosis and high predictability at 1-week post GDM diagnosis. These population-based, clinically oriented models may support algorithm-based risk-stratification for treatment modality, inform timely treatment, and catalyze more effective management of GDM.https://doi.org/10.1186/s12916-022-02499-7Gestational diabetesMachine learningPharmacologic treatmentPredictionPregnancyRisk stratification |
| spellingShingle | Lauren D. Liao Assiamira Ferrara Mara B. Greenberg Amanda L. Ngo Juanran Feng Zhenhua Zhang Patrick T. Bradshaw Alan E. Hubbard Yeyi Zhu Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study BMC Medicine Gestational diabetes Machine learning Pharmacologic treatment Prediction Pregnancy Risk stratification |
| title | Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study |
| title_full | Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study |
| title_fullStr | Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study |
| title_full_unstemmed | Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study |
| title_short | Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study |
| title_sort | development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning a population based cohort study |
| topic | Gestational diabetes Machine learning Pharmacologic treatment Prediction Pregnancy Risk stratification |
| url | https://doi.org/10.1186/s12916-022-02499-7 |
| work_keys_str_mv | AT laurendliao developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT assiamiraferrara developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT marabgreenberg developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT amandalngo developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT juanranfeng developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT zhenhuazhang developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT patricktbradshaw developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT alanehubbard developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy AT yeyizhu developmentandvalidationofpredictionmodelsforgestationaldiabetestreatmentmodalityusingsupervisedmachinelearningapopulationbasedcohortstudy |