scholarly journals Machine Learning Approach for Postprandial Blood Glucose Prediction in Gestational Diabetes Mellitus

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 219308-219321
Author(s):  
Evgenii A. Pustozerov ◽  
Aleksandra S. Tkachuk ◽  
Elena A. Vasukova ◽  
Anna D. Anopova ◽  
Maria A. Kokina ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Postprandial Blood Glucose ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Glucose Prediction

scholarly journals Blood Glucose Level, Gestational Diabetes Mellitus and Maternal Birth Season: A Retrospective Cohort Study

2021 ◽  
Vol 12 ◽  
Author(s):  
Dongjian Yang ◽  
Jingbo Qiu ◽  
An Qin ◽  
Lei Chen ◽  
Ya Yang ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Cohort Study ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Confidence Interval ◽  
Gestational Diabetes Mellitus ◽  
Pregnant Women ◽  
Retrospective Cohort ◽  
Postprandial Blood Glucose ◽  
Birth Season

BackgroundPrevious evidence indicates that birth season is associated with type 2 diabetes in adults. However, information on the association of birth with gestational diabetes mellitus (GDM) is lacking. The present study explores the association between birth seasonality and GDM in East China.MethodsThis retrospective cohort study was conducted at the International Peace Maternal and child health hospital between 2014 and 2019. A total of 79, 292 pregnant women were included in the study after excluding participants with previous GDM, stillbirth, polycystic ovary syndrome, and lack of GDM laboratory records. The multivariate logistic regression model was employed to estimate the odds ratio and 95% confidence interval. After log transformation of blood glucose level, the percentage change and 95% confidence interval were estimated by a multivariate linear model.ResultsThe risk of GDM among pregnant women born in spring, autumn, and winter was not significantly different compared to that among participants born in summer. Pregnant women born in autumn had significantly higher 1-hour postprandial blood glucose (PBG-1h) and 2-hour postprandial blood glucose (PBG-2h) levels than pregnant women born in summer. Compared to pregnant women born in August, the PBG-1h level of pregnant women born in October, November, and December increased significantly, whereas the PBG-2h levels of pregnant women born in November and December increased significantly.ConclusionPregnant women born in autumn exhibit higher postprandial blood glucose levels during pregnancy than in those born in summer. The findings provide evidence that exposure to seasonal changes in early life may influence blood glucose metabolism during pregnancy.

scholarly journals Development and Evaluation of a Mobile Personalized Blood Glucose Prediction System for Patients With Gestational Diabetes Mellitus

2018 ◽  
Vol 6 (1) ◽  
pp. e6 ◽  
Author(s):  
Evgenii Pustozerov ◽  
Polina Popova ◽  
Aleksandra Tkachuk ◽  
Yana Bolotko ◽  
Zafar Yuldashev ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Prediction System ◽  
Glucose Prediction

One-hour versus two-hour postprandial blood glucose measurement in women with gestational diabetes mellitus: which is more predictive?

Endocrine ◽  
2015 ◽  
Vol 52 (3) ◽  
pp. 561-570 ◽  
Author(s):  
A. Seval Ozgu-Erdinc ◽  
Cantekin Iskender ◽  
Dilek Uygur ◽  
Aysegul Oksuzoglu ◽  
K. Doga Seckin ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Blood Glucose Measurement ◽  
Postprandial Blood Glucose ◽  
Glucose Measurement

scholarly journals Effect of Soya based Protein Rich Diet on Glycaemic Parameters and Thyroid Function Tests in Women with Gestational Diabetes Mellitus

2016 ◽  
Vol 23 (2) ◽  
pp. 201-208 ◽  
Author(s):  
Vijaya Sarathi ◽  
Anish Kolly ◽  
Hulivana Boranna Chaithanya ◽  
Chinthamani Suryanarayana Dwarakanath
Keyword(s):  
Diabetes Mellitus ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Dietary Intervention ◽  
Postprandial Blood Glucose ◽  
Complex Carbohydrate ◽  
Carbohydrate Diet ◽  
High Fiber ◽  
Protein Rich

AbstractBackground and Aims: Medical nutrition therapy plays a major role in the management of gestational diabetes mellitus (GDM). However, control of postprandial blood glucose values is often a challenge in Asian Indian GDM women due to high carbohydrate content in Indian diet.Materials and Methods: Women presenting with GDM diagnosis were randomised to high fiber complex carbohydrate diet and soya based protein rich diet (25% of cereal part in the high fiber, complex carbohydrate diet replaced by soya food) groups.Results: At the end of one week after initiation of dietary intervention, patients who received high fiber complex carbohydrate diet (n=30) had significantly higher postprandial blood glucose levels than those who received soya based protein rich diet (n=32). The need for insulin therapy at the end of one week after initiation of dietary intervention (15.62% vs. 40.0%) and at delivery (18.75% vs. 50%) were significantly lower in soya based protein rich diet group. Maternal thyroid function at diagnosis of GDM and delivery and neonatal TSH were not significantly different between the groups.Conclusion: Consumption of soya based protein rich diet reduced the need for insulin therapy in subjects with GDM. Short term consumption of soya food did not alter maternal and neonatal thyroid functions.

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

2020 ◽  
Author(s):  
Carmelo Velardo ◽  
David Clifton ◽  
Steven Hamblin ◽  
Rabia Khan ◽  
Lionel Tarassenko ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Risk Factors ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Real Time ◽  
Pharmacological Treatment ◽  
Learning Model ◽  
Machine Learning Model

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.

scholarly journals Safe threshold of capillary blood glucose for predicting early future neonatal hypoglycaemia in babies born to mothers with gestational diabetes mellitus, an observational, retrospective cohort study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Esther H. G. Park ◽  
Frances O’Brien ◽  
Fiona Seabrook ◽  
Jane Elizabeth Hirst
Keyword(s):  
Diabetes Mellitus ◽  
Cohort Study ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Capillary Blood ◽  
Capillary Blood Glucose ◽  
Neonatal Hypoglycaemia

Abstract Background There is increasing pressure to get women and babies home rapidly after birth. Babies born to mothers with gestational diabetes mellitus (GDM) currently get 24-h inpatient monitoring. We investigated whether a low-risk group of babies born to mothers with GDM could be defined for shorter inpatient hypoglycaemia monitoring. Methods Observational, retrospective cohort study conducted in a tertiary maternity hospital in 2018. Singleton, term babies born to women with GDM and no other risk factors for hypoglycaemia, were included. Capillary blood glucose (BG) testing and clinical observations for signs of hypoglycaemia during the first 24-h after birth. BG was checked in all babies before the second feed. Subsequent testing occurred if the first result was < 2.0 mmol/L, or clinical suspicion developed for hypoglycaemia. Neonatal hypoglycaemia, defined as either capillary or venous glucose ≤ 2.0 mmol/L and/or clinical signs of neonatal hypoglycaemia requiring oral or intravenous dextrose (lethargy, abnormal feeding behaviour or seizures). Results Fifteen of 106 babies developed hypoglycaemia within the first 24-h. Maternal and neonatal characteristics were not predictive. All babies with hypoglycaemia had an initial capillary BG ≤ 2.6 mmol/L (Area under the ROC curve (AUC) 0.96, 95% Confidence Interval (CI) 0.91–1.0). This result was validated on a further 65 babies, of whom 10 developed hypoglycaemia, in the first 24-h of life. Conclusion Using the 2.6 mmol/L threshold, extended monitoring as an inpatient could have been avoided for 60% of babies in this study. Whilst prospective validation is needed, this approach could help tailor postnatal care plans for babies born to mothers with GDM.

Searching for Utopia, the Challenge of Standardized Medical Nutrition Therapy Prescription in Gestational Diabetes Mellitus Management: A Critical Review

2021 ◽  
Author(s):  
Nina Meloncelli ◽  
Shelley A. Wilkinson ◽  
Susan de Jersey
Keyword(s):  
Diabetes Mellitus ◽  
Blood Glucose ◽  
Gestational Diabetes ◽  
Gestational Diabetes Mellitus ◽  
Lifestyle Modification ◽  
Nutrition Therapy ◽  
Medical Nutrition Therapy ◽  
Glucose Levels ◽  
Blood Glucose Levels ◽  
Medical Nutrition

AbstractGestational diabetes mellitus (GDM) is a common pregnancy disorder and the incidence is increasing worldwide. GDM is associated with adverse maternal outcomes which may be reduced with proper management. Lifestyle modification in the form of medical nutrition therapy and physical activity, as well as self-monitoring of blood glucose levels, is the cornerstone of GDM management. Inevitably, the search for the “ultimate” diet prescription has been ongoing. Identifying the amount and type of carbohydrate to maintain blood glucose levels below targets while balancing the nutritional requirements of pregnancy and achieving gestational weight gain within recommendations is challenging. Recent developments in the area of the gut microbiota and its impact on glycemic response add another layer of complexity to the success of medical nutrition therapy. This review critically explores the challenges to dietary prescription for GDM and why utopia may never be found.

scholarly journals Development of Type 2 Diabetes Mellitus Phenotyping Framework Using Expert Knowledge and Machine Learning Approach

2016 ◽  
Vol 11 (4) ◽  
pp. 791-799 ◽  
Author(s):  
Rina Kagawa ◽  
Yoshimasa Kawazoe ◽  
Yusuke Ida ◽  
Emiko Shinohara ◽  
Katsuya Tanaka ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Expert Knowledge ◽  
The Other ◽  
Learning Approach ◽  
Research Subjects ◽  
Machine Learning Approach

Background: Phenotyping is an automated technique that can be used to distinguish patients based on electronic health records. To improve the quality of medical care and advance type 2 diabetes mellitus (T2DM) research, the demand for T2DM phenotyping has been increasing. Some existing phenotyping algorithms are not sufficiently accurate for screening or identifying clinical research subjects. Objective: We propose a practical phenotyping framework using both expert knowledge and a machine learning approach to develop 2 phenotyping algorithms: one is for screening; the other is for identifying research subjects. Methods: We employ expert knowledge as rules to exclude obvious control patients and machine learning to increase accuracy for complicated patients. We developed phenotyping algorithms on the basis of our framework and performed binary classification to determine whether a patient has T2DM. To facilitate development of practical phenotyping algorithms, this study introduces new evaluation metrics: area under the precision-sensitivity curve (AUPS) with a high sensitivity and AUPS with a high positive predictive value. Results: The proposed phenotyping algorithms based on our framework show higher performance than baseline algorithms. Our proposed framework can be used to develop 2 types of phenotyping algorithms depending on the tuning approach: one for screening, the other for identifying research subjects. Conclusions: We develop a novel phenotyping framework that can be easily implemented on the basis of proper evaluation metrics, which are in accordance with users’ objectives. The phenotyping algorithms based on our framework are useful for extraction of T2DM patients in retrospective studies.

Sign in / Sign up

Export Citation Format

Share Document