A Probabilistic Approach to Extract Qualitative Knowledge for Early Prediction of Gestational Diabetes.
Ontology highlight
ABSTRACT:
SUBMITTER: Karanam A
PROVIDER: S-EPMC8274548 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Gestational diabetes mellitus (GDM) is conventionally confirmed with oral glucose tolerance test (OGTT) in 24 to 28 weeks of gestation, but it is still uncertain whether it can be predicted with secondary use of electronic health records (EHRs) in early pregnancy. To this purpose, the cost-sensitive hybrid model (CSHM) and five conventional machine learning methods are used to construct the predictive models, capturing the future risks of GDM in the temporally aggregated EHRs. The experimental data sources from a nested case-control study cohort, containing 33,935 gestational women in West China Second Hospital. After data cleaning, 4,378 cases and 50 attributes are stored and collected for the data set. Through selecting the most feasible method, the cost parameter of CSHM is adapted to deal with imbalance of the dataset. In the experiment, 3940 samples are used for training and the rest 438 samples for testing. Although the accuracy of positive samples is barely acceptable (62.16%), the results suggest that the vast majority (98.4%) of those predicted positive instances are real positives. To our knowledge, this is the first study to apply machine learning models with EHRs to predict GDM, which will facilitate personalized medicine in maternal health management in the future.
| S-EPMC5703904 | biostudies-other
Project description:AimsThe heterogeneity in Gestational Diabetes Mellitus (GDM) risk factors among different populations impose challenges in developing a generic prediction model. This study evaluates the predictive ability of existing UK NICE guidelines for assessing GDM risk in Singaporean women, and used machine learning to develop a non-invasive predictive model.MethodsData from 909 pregnancies in Singapore's most deeply phenotyped mother-offspring cohort study, Growing Up in Singapore Towards healthy Outcomes (GUSTO), was used for predictive modeling. We used a CatBoost gradient boosting algorithm, and the Shapley feature attribution framework for model building and interpretation of GDM risk attributes.ResultsUK NICE guidelines showed poor predictability in Singaporean women [AUC:0.60 (95% CI 0.51, 0.70)]. The non-invasive predictive model comprising of 4 non-invasive factors: mean arterial blood pressure in first trimester, age, ethnicity and previous history of GDM, greatly outperformed [AUC:0.82 (95% CI 0.71, 0.93)] the UK NICE guidelines.ConclusionsThe UK NICE guidelines may be insufficient to assess GDM risk in Asian women. Our non-invasive predictive model outperforms the current state-of-the-art machine learning models to predict GDM, is easily accessible and can be an effective approach to minimize the economic burden of universal testing & GDM associated healthcare in Asian populations.
| S-EPMC7612635 | biostudies-literature
Project description:All obese women are categorised as being of equally high risk of gestational diabetes (GDM) whereas the majority do not develop the disorder. Lifestyle and pharmacological interventions in unselected obese pregnant women have been unsuccessful in preventing GDM. Our aim was to develop a prediction tool for early identification of obese women at high risk of GDM to facilitate targeted interventions in those most likely to benefit. Clinical and anthropometric data and non-fasting blood samples were obtained at 15+0-18+6 weeks' gestation in 1303 obese pregnant women from UPBEAT, a randomised controlled trial of a behavioural intervention. Twenty one candidate biomarkers associated with insulin resistance, and a targeted nuclear magnetic resonance (NMR) metabolome were measured. Prediction models were constructed using stepwise logistic regression. Twenty six percent of women (n = 337) developed GDM (International Association of Diabetes and Pregnancy Study Groups criteria). A model based on clinical and anthropometric variables (age, previous GDM, family history of type 2 diabetes, systolic blood pressure, sum of skinfold thicknesses, waist:height and neck:thigh ratios) provided an area under the curve of 0.71 (95%CI 0.68-0.74). This increased to 0.77 (95%CI 0.73-0.80) with addition of candidate biomarkers (random glucose, haemoglobin A1c (HbA1c), fructosamine, adiponectin, sex hormone binding globulin, triglycerides), but was not improved by addition of NMR metabolites (0.77; 95%CI 0.74-0.81). Clinically translatable models for GDM prediction including readily measurable variables e.g. mid-arm circumference, age, systolic blood pressure, HbA1c and adiponectin are described. Using a ?35% risk threshold, all models identified a group of high risk obese women of whom approximately 50% (positive predictive value) later developed GDM, with a negative predictive value of 80%. Tools for early pregnancy identification of obese women at risk of GDM are described which could enable targeted interventions for GDM prevention in women who will benefit the most.
| S-EPMC5145208 | biostudies-literature
Project description:BackgroundOur study aimed to reveal the relationship of maternal pentraxin 3 (PTX3)'s serum concentrations in early pregnancy with gestational diabetes mellitus (GDM) and to explore its potential in the prediction of GDM.MethodsTotally 824 pregnant women were enrolled and divided into a GDM group and a normal glucose tolerance (NGT) group, whose maternal fasting serum PTX3 levels, plasma glucose and insulin were collected. The beta cell function index and quantitative insulin sensitivity check index (QUICKI) was calculated and a homeostatic model assessment of insulin resistance (HOMA-IR) was used with SPSS 22 software used for statistical analysis.ResultsOf all subjects, 13.59% developed GDM. Compared to the NGT group, the PTX3 level was increased in the GDM group (1.48 vs. 1.52 ng/mL, P<0.05), and independently associated with the prediction of GDM (4.209, 95% CI, 1.756-10.091) (P=0.001). The area under receiver operating characteristic curve (AUROC) of the combined screening of PTX3 for GDM was incremented to 0.657 by the addition of maternal characteristics, and it reached a maximum of 0.743 in further combination with biochemical markers.ConclusionsSerum PTX3 levels in early pregnancy may provide a useful approach for early prediction of GDM.
| S-EPMC6990028 | biostudies-literature
Project description:The knowledge of the tertiary structure of RNA loops is important for understanding their functions. In this work we develop an efficient approach named RNApps, specifically designed for predicting the tertiary structure of RNA loops, including hairpin loops, internal loops, and multi-way junction loops. It includes a probabilistic coarse-grained RNA model, an all-atom statistical energy function, a sequential Monte Carlo growth algorithm, and a simulated annealing procedure. The approach is tested with a dataset including nine RNA loops, a 23S ribosomal RNA, and a large dataset containing 876 RNAs. The performance is evaluated and compared with a homology modeling based predictor and an ab initio predictor. It is found that RNApps has comparable performance with the former one and outdoes the latter in terms of structure predictions. The approach holds great promise for accurate and efficient RNA tertiary structure prediction.
| S-EPMC4975501 | biostudies-literature
Project description:AimsTo evaluate the clinical utility of first and second trimester prenatal screening biomarkers for early pregnancy prediction of gestational diabetes mellitus (GDM) risk in nulliparous women.MethodsWe conducted a population-based cohort study of nulliparous women participating in the California Prenatal Screening Program from 2009 to 2011 (n = 105,379). GDM was ascertained from hospital discharge records or birth certificates. Models including maternal characteristics and prenatal screening biomarkers were developed and validated. Risk stratification and reclassification were performed to assess clinical utility of the biomarkers.ResultsDecreased levels of first trimester pregnancy-associated plasma protein A (PAPP-A) and increased levels of second trimester unconjugated estriol (uE3) and dimeric inhibin A (INH) were associated with GDM. The addition of PAPP-A only and PAPP-A, uE3, and INH to maternal characteristics resulted in small, yet significant, increases in area under the receiver operating characteristic curve (AUC) (maternal characteristics only: AUC 0.714 (95% CI 0.703-0.724), maternal characteristics + PAPP-A: AUC 0.718 (95% CI 0.707-0.728), maternal characteristics + PAPP-A, uE3, and INH: AUC 0.722 (0.712-0.733)); however, no net improvement in classification was observed.ConclusionsPAPP-A, uE3, and INH have limited clinical utility for prediction of GDM risk in nulliparous women. Utility of other readily accessible clinical biomarkers in predicting GDM risk warrants further investigation.
| S-EPMC7269799 | biostudies-literature
Project description:Background/aimsTo develop an early prediction model for gestational diabetes mellitus (GDM) using machine learning and to evaluate whether the inclusion of nonalcoholic fatty liver disease (NAFLD)-associated variables increases the performance of model.MethodsThis prospective cohort study evaluated pregnant women for NAFLD using ultrasound at 10-14 weeks and screened them for GDM at 24-28 weeks of gestation. The clinical variables before 14 weeks were used to develop prediction models for GDM (setting 1, conventional risk factors; setting 2, addition of new risk factors in recent guidelines; setting 3, addition of routine clinical variables; setting 4, addition of NALFD-associated variables, including the presence of NAFLD and laboratory results; and setting 5, top 11 variables identified from a stepwise variable selection method). The predictive models were constructed using machine learning methods, including logistic regression, random forest, support vector machine, and deep neural networks.ResultsAmong 1,443 women, 86 (6.0%) were diagnosed with GDM. The highest performing prediction model among settings 1-4 was setting 4, which included both clinical and NAFLD-associated variables (area under the receiver operating characteristic curve [AUC] 0.563-0.697 in settings 1-3 vs. 0.740-0.781 in setting 4). Setting 5, with top 11 variables (which included NAFLD and hepatic steatosis index), showed similar predictive power to setting 4 (AUC 0.719-0.819 in setting 5, P=not significant between settings 4 and 5).ConclusionWe developed an early prediction model for GDM using machine learning. The inclusion of NAFLDassociated variables significantly improved the performance of GDM prediction. (ClinicalTrials.gov Identifier: NCT02276144).
| S-EPMC8755469 | biostudies-literature
Project description:AIM:To identify differentially expressed proteins (DEPs) in 1st trimester maternal plasma between pregnant women at risk for gestational diabetes mellitus (GDM) and uncomplicated controls. MATERIALS AND METHODS:First-trimester plasma from five women who developed GDM and five from non-diabetic ones were analyzed using isobaric tag for relative and absolute quantitation - labeled proteomics. Enzyme-linked immunosorbent assay was further applied in an independent cohort of 25 GDM cases and 25 controls for verification. RESULTS:Prenylcysteine oxidase 1 (PCYOX1), beta-ala-his dipeptidase (CNDP1), extracellular matrix protein 1 (ECM1), basement membrane-specific heparan sulfate proteoglycan core protein (HSPG2), thrombospondin-4 (TSP-4) demonstrated significant differences in expression between the two groups (p<0.05). DEPs are mainly associated with complement and coagulation cascades. CONCLUSION:The reported plasma proteomic changes represent potential biomarkers for the early identification of women at risk for GDM. Future studies using larger and more diverse cohorts are necessary to assess the clinical utility of these findings.
| S-EPMC7157887 | biostudies-literature
Project description:ObjectivesTo evaluate the influence of genetic variants and clinical characteristics on the risk of gestational diabetes mellitus (GDM) and to construct and verify a prediction model of GDM in early pregnancy.MethodsFour hundred seventy five women with GDM and 487 women without, as a control, were included to construct the prediction model of GDM in early pregnancy. Both groups had complete genotyping results and clinical data. They were randomly divided into a trial cohort (70%) and a test cohort (30%). Then, the model validation cohort, including 985 pregnant women, was used for the external validation of the GDM early pregnancy prediction model.ResultsWe found maternal age, gravidity, parity, BMI and family history of diabetes were significantly associated with GDM (OR > 1; P < 0.001), and assisted reproduction was a critical risk factor for GDM (OR = 1.553, P = 0.055). MTNR1B rs10830963, C2CD4A/B rs1436953 and rs7172432, CMIP rs16955379 were significantly correlated with the incidence of GDM (AOR > 1, P < 0.05). Therefore, these four genetic susceptible single nucleotide polymorphisms (SNPs) and six clinical characteristics were included in the construction of the GDM early pregnancy prediction model. In the trial cohort, a predictive model of GDM in early pregnancy was constructed, in which genetic risk score was independently associated with GDM (AOR = 2.061, P < 0.001) and was the most effective predictor with the exception of family history of diabetes. The ROC-AUC of the prediction model was 0.727 (95% CI 0.690-0.765), and the sensitivity and specificity were 69.9% and 64.0%, respectively. The predictive power was also verified in the test cohort and the validation cohort.ConclusionsBased on the genetic variants and clinical characteristics, this study developed and verified the early pregnancy prediction model of GDM. This model can help screen out the population at high-risk for GDM in early pregnancy, and lifestyle interventions can be performed for them in a timely manner in early pregnancy.
| S-EPMC8785509 | biostudies-literature
Project description:Metabolomic profiling in populations with impaired glucose tolerance has revealed that branched chain and aromatic amino acids (BCAAs) are predictive of type 2 diabetes. Because gestational diabetes mellitus (GDM) shares pathophysiological similarities with type 2 diabetes, the metabolite profile predictive of type 2 diabetes could potentially identify women who will develop GDM.We conducted a nested case-control study of 18- to 40-year-old women who participated in the Massachusetts General Hospital Obstetrical Maternal Study between 1998 and 2007. Participants were enrolled during their first trimester of a singleton pregnancy and fasting serum samples were collected. The women were followed throughout pregnancy and identified as having GDM or normal glucose tolerance (NGT) in the third trimester. Women with GDM (n?=?96) were matched to women with NGT (n?=?96) by age, BMI, gravidity and parity. Liquid chromatography-mass spectrometry was used to measure the levels of 91 metabolites.Data analyses revealed the following characteristics (mean?±?SD): age 32.8?±?4.4 years, BMI 28.3?±?5.6 kg/m(2), gravidity 2?±?1 and parity 1?±?1. Six metabolites (anthranilic acid, alanine, glutamate, creatinine, allantoin and serine) were identified as having significantly different levels between the two groups in conditional logistic regression analyses (p?<?0.05). The levels of the BCAAs did not differ significantly between GDM and NGT.Metabolic markers identified as being predictive of type 2 diabetes may not have the same predictive power for GDM. However, further study in a racially/ethnically diverse population-based cohort is necessary.
| S-EPMC4428592 | biostudies-literature