Towards a multivariate prediction model of pharmacological treatment for women with gestational diabetes mellitus (Preprint)

BACKGROUND Successful management of gestational diabetes mellitus (GDM) reduces the risk of morbidity in women and newborns. A woman’s BG readings and risk factors are used by clinical staff to make decisions regarding the initiation of pharmacological treatment in women with GDM. Mobile-Health (mHealth) solutions allow the real-time follow-up of women with GDM and allow timely treatment and management. Machine learning offers the opportunity to quickly analyse large quantities of data to automatically flag women at risk of requiring pharmacological treatment. OBJECTIVE We sought to assess whether data collected through a mHealth system can be analysed to automatically evaluate the switch to pharmacological treatment from diet-based management of GDM. METHODS We collected data from 3,029 patients to design a machine-learning model that can identify when a woman with GDM needs to switch to medications (Insulin or Metformin) by analysing the data related to blood glucose and other risk factors. RESULTS Through the analysis of 411,785 blood glucose (BG) readings we have designed a machine learning model that can predict the timing of initiation of pharmacological treatment. After one hundred experimental repetitions we have obtained an average performance of 0.80 AUC and an algorithm that allows the flexibility of setting the operating point rather than relying on a static heuristic method, currently used in clinical practice. CONCLUSIONS Using real-time data collected via a mHealth system may further improve the timeliness of intervention and potentially improve patient care. Further real-time clinical testing will enable validating our algorithm using real-world data.

Download Full-text

Accuracy of glycosuria, random blood glucose and risk factors as selective screening tools for gestational diabetes mellitus in comparison with universal diagnosing

BMJ Open Diabetes Research & Care ◽

10.1136/bmjdrc-2017-000493 ◽

2018 ◽

Vol 6 (1) ◽

pp. e000493 ◽

Cited By ~ 5

Author(s):

Faith Agbozo ◽

Abdulai Abubakari ◽

Clement Narh ◽

Albrecht Jahn

Keyword(s):

Diabetes Mellitus ◽

Risk Factors ◽

Blood Glucose ◽

Gestational Diabetes ◽

Gestational Diabetes Mellitus ◽

Test Performance ◽

Gold Standard ◽

Universal Screening ◽

Selective Screening ◽

Random Blood Glucose

ObjectiveDespite the short-term and long-term health implications of gestational diabetes mellitus (GDM), opinions are divided on selective vis-à-vis universal screening. We validated the accuracy of screening tests for GDM.Research design and methodsPregnant women (n=491) were recruited to this prospective, blind comparison with a gold standard study. We did selective screening between 13 and 20 weeks using reagent-strip glycosuria, random capillary blood glucose (RBG) and the presence of ≥1 risk factor(s). Between 20 and 34 weeks, we did universal screening following the ‘one-step’ approach using glycated hemoglobin (HbA1c), fasting venous plasma glucose (FPG), and the 1-hour and the ‘gold standard’ 2-hour oral glucose tolerance test (OGTT). Tests accuracy was estimated following the WHO and the National Institute for Health and Care Excellence (NICE) diagnostic criteria. Overall test performance was determined from the area under the receiver operating characteristic curve (AUC).ResultsGDM prevalence per 2-hour OGTT was 9.0% for the WHO criteria and 14.3% for the NICE criteria. Selective screening using glycosuria, RBG and risk factors missed 97.4%, 87.2% and 45.7% of cases, respectively. FPG threshold ≥5.1 mmol/L had the highest clinically relevant sensitivity (68%) and specificity (81%), but FPG threshold ≥5.6 mmol/L had higher positive predictive value. Although sensitivity of 1-hour OGTT was 39.5%, it had the highest accuracy and diagnostic OR. Regarding test performance, 1-hour OGTT and FPG were very good (AUC>0.8), RBG was poor (AUC≈0.60), whereas HbA1c was invaluable (AUC<0.5).ConclusionsSelective screening using glycosuria and random blood glucose is unnecessary due to its low sensitivity. Fasting glucose ≥5.1 mmol/L could be applicable for screening at the population level. Where 2-hour OGTT is not available, FPG ≥5.6 mmol/L, complemented by the presence of risk factors, could be useful in making therapeutic decision.

Download Full-text

Analysis of Association between Caesarean Delivery and Gestational Diabetes Mellitus Using Machine Learning

Proceedings of Engineering and Technology Innovation ◽

10.46604/peti.2020.4740 ◽

2020 ◽

Vol 15 ◽

pp. 08-15

Author(s):

Nisana Siddegowda Prema ◽

Mullur Puttabuddi Pushpalatha

Keyword(s):

Diabetes Mellitus ◽

Machine Learning ◽

Risk Factors ◽

Gestational Diabetes ◽

Gestational Diabetes Mellitus ◽

Cesarean Delivery ◽

Pregnancy Risk ◽

First Time ◽

Primiparous Women ◽

Previous Cesarean

The study aims to analyze the association between gestational diabetes mellitus (GDM) and other risk factors of cesarean delivery using machine learning (ML). The dataset used for the analysis is from the pregnancy risk assessment survey (PRAMS), considered in two scenarios, i.e., all the data is taken, and all the data of the women who developed GDM. Further, the data is developed in two groups Data-I and Data-II by considering multiparous and primiparous women details, respectively. The correlation analysis and major classification algorithms are applied to the data. It is founded that the top risk factors for the first time cesarean delivery are the age, height, weight, race of the women, presence of hypertension and gestational diabetes mellitus. The major risk factor for repeated cesarean delivery is the previous cesarean delivery. The presence of GDM is also one of the risk factors for cesarean delivery.

Download Full-text

Study the Effect of Maternal Factors on Prevalence of Gestational Diabetes Mellitus and Effect of Treatment Types on Serum Blood Glucose

Research Journal of Pharmacy and Technology ◽

10.52711/0974-360x.2021.00917 ◽

2021 ◽

pp. 5264-5269

Author(s):

Shaymaa Hasan Abbas ◽

Sura Abbas Khdair

Keyword(s):

Diabetes Mellitus ◽

Risk Factors ◽

Blood Glucose ◽

Family History ◽

Gestational Diabetes ◽

Gestational Diabetes Mellitus ◽

Blood Glucose Level ◽

Family History Of Diabetes ◽

Treatment Groups ◽

History Of

Introduction: Gestational diabetes mellitus (GDM) is one of the most common medical problems occurred during pregnancy. GDM increase the chance for developing type 2 diabetes meletus by seven times. The overall prevalence of GDM in pregnancy is 1-14% according to the American Diabetes Association. Material and Methods: a self-administered questionnaire was used to collect data. The information was collected from pregnant women with gestational DM to assess some maternal risk factors and compare blood glucose level according to different treatment types for GDM. Results: The present study reported that (40.38%) of GDM patients have advanced age (≥35 yrs.). First pregnancy was a risk factors for GDM and it was reported by (9.62%). History of HT and GDM during prior pregnancies were reported by (11.54%) and (% 34.62) respectively. Hypertension or preeclampsia in the current pregnancy was reported by (3.85%). Positive family history of diabetes was associated with (26.92%) GDM patients. All Patients of the present study reported no previous PCOS and smoking history. Also in this study, 44 patients out of 52 GDM patients use medications to control the glucose intolerance, while other patients control it by diet. There were no statistical differences found between treatment groups in term of blood glucose control. Conclusion: Age, history of GDM in the previous pregnancies and family history of diabetes mellitus were identifiable as a risk factors for GDM and their effect were significant in this study while the effect of other risk factors were non-significant. No statistical differences found between treatment groups in term of blood glucose level control and no group achieved the glycemic target.

Download Full-text

Geographically weighted machine learning model for untangling spatial heterogeneity of type 2 diabetes mellitus (T2D) prevalence in the USA

Scientific Reports ◽

10.1038/s41598-021-85381-5 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Sarah Quiñones ◽

Aditya Goyal ◽

Zia U. Ahmed

Keyword(s):

Diabetes Mellitus ◽

Machine Learning ◽

Risk Factors ◽

Type 2 Diabetes ◽

Type 2 Diabetes Mellitus ◽

Spatial Heterogeneity ◽

Learning Model ◽

Machine Learning Model ◽

Non Parametric

AbstractType 2 diabetes mellitus (T2D) prevalence in the United States varies substantially across spatial and temporal scales, attributable to variations of socioeconomic and lifestyle risk factors. Understanding these variations in risk factors contributions to T2D would be of great benefit to intervention and treatment approaches to reduce or prevent T2D. Geographically-weighted random forest (GW-RF), a tree-based non-parametric machine learning model, may help explore and visualize the relationships between T2D and risk factors at the county-level. GW-RF outputs are compared to global (RF and OLS) and local (GW-OLS) models between the years of 2013–2017 using low education, poverty, obesity, physical inactivity, access to exercise, and food environment as inputs. Our results indicate that a non-parametric GW-RF model shows a high potential for explaining spatial heterogeneity of, and predicting, T2D prevalence over traditional local and global models when inputting six major risk factors. Some of these predictions, however, are marginal. These findings of spatial heterogeneity using GW-RF demonstrate the need to consider local factors in prevention approaches. Spatial analysis of T2D and associated risk factor prevalence offers useful information for targeting the geographic area for prevention and disease interventions.

Download Full-text

Effects of Risk Factors for Pregnancy Outcomes of Subsequent Pregnancy Associated with Gestational Diabetes Mellitus: A Retrospective Cohort Study in China.

10.21203/rs.3.rs-962585/v1 ◽

2021 ◽

Author(s):

Weijiao Xu ◽

Xia Xu ◽

Yanni Guo ◽

Jie Liang ◽

Jianying Yan

Keyword(s):

Diabetes Mellitus ◽

Risk Factors ◽

Blood Glucose ◽

Gestational Diabetes ◽

Gestational Diabetes Mellitus ◽

Early Pregnancy ◽

Child Outcomes ◽

Fasting Blood Glucose ◽

Neonatal Outcomes ◽

Lipid Levels

Abstract BackgroundSince the implementation of the three‑child policy in China, the number of high-risk pregnant women has increased, causing serious challenges to health care during pregnancy. In this article, we aimed to investigate the impact of several risk factors for maternal and neonatal outcomes in pregnancies complicated by gestational diabetes mellitus (GDM) and recurrent GDM to formulate a management strategy to minimize the effect of risk factors for gestational diabetes. ResultsPre-pregnancy body mass index (BMI) and gestational weight gain affect maternal and child outcomes in the first and second onset of GDM. Pregnancy interval and fasting blood glucose in early pregnancy influence maternal and child outcomes of recurrent GDM. Maternal lipid levels during early pregnancy have a marked influence on neonatal outcomes in recurrent GDM.ConclusionsOn the basis of this result, weight management should be closely monitored before and during pregnancy. For planning of the second pregnancy with a previous history of GDM, a reasonable time between pregnancies is ideal. Moreover, in the next pregnancy, control of fasting blood glucose and lipid levels during the first trimester is necessary to improve both maternal and child outcomes.

Download Full-text

ОLD VERSUS NEW RUSSIAN CRITERIA FOR GESTATIONAL DIABETES

Arterial’naya Gipertenziya (Arterial Hypertension) ◽

10.18705/1607-419x-2013-19-4-367-373 ◽

2013 ◽

Vol 19 (4) ◽

pp. 367-373

Author(s):

P. V. Popova ◽

A. V. Dronova ◽

E. R. Sadikova ◽

M. P. Parkkinen ◽

M. V. Bolshakova ◽

...

Keyword(s):

Diabetes Mellitus ◽

Risk Factors ◽

Blood Glucose ◽

Gestational Diabetes ◽

Gestational Diabetes Mellitus ◽

Fasting Glucose ◽

Fasting Blood Glucose ◽

Prenatal Visit ◽

Iadpsg Criteria ◽

New Criteria

Objective. To compare the incidence of gestational diabetes mellitus (GDM), risk factors of its development when using the old (WHO, 1999) and the new Russian criteria (2012) and to assess the correspondence between fasting glycaemia and 75-g oral glucose tolerance test (OGTT), under the new criteria.Design and methods. A total of 354 pregnant women were screened for gestational diabetes mellitus by OGTT between weeks 24 and 28 of gestation. Fasting blood glucose at irst prenatal visit was obtained from the medical records. GDM for therapy initiation was diagnosed according to WHO criteria. GDM was also retrospectively deined according to the new IADPSG-criteria (fasting plasma glucose >5,1 and < 7,0 mmol/l at the irst prenatal visit or by OGTT fasting glucose >5,1 and/or ? 10,0 mmol/l after 1 hour and/or ? 8,5 mmol/l after 2 hours at 24–32 gestation week). Results. GDM was detected in 25,1 % according to the old criteria and in 26,8 % women under the new criteria by OGTT. Fasting glucose at the irst prenatal visit between 5,1 mmol/l and 7,0 mmol/l (that is, GDM under the new criteria) was deined in 92 (28,1 %) of 327 women with known fasting blood glucose level. Only in 34 (37 %) of 92 women with fasting glycemia > 5,1 mmol/l at the irst prenatal visit the results of OGTT met the criteria for GDM (IADPSG) at 24–28 weeks gestation. Total incidence of GDM according to the new criteria (at the irst prenatal visit and after 24 weeks of pregnancy) was 43,4 %. Conclusions. Application of the new Russian criteria leads to a signiicant increase in the frequency of GDM, mainly due to the fasting glucose level at the irst prenatal visit. In women with GDM, diagnosed according to the IADPSG-criteria (but not WHO), such risk factors of GDM as heredity for diabetes mellitus and hypertension before pregnancy were more often identiied compared with women without GDM.

Download Full-text