Scholarlink

<p>Gestational Diabetes Mellitus (GDM) or glucose intolerance when first recognised during the pregnancy is posing significant threats to mother and fetal health. Improved outcomes can be achieved with early diagnosis and special treatment. It reviews the biological, environmental and lifestyle risk factors for gestational diabetes mellitus (GDM) and examines the progress and innovations in screening, prediction and prevention of GDM by an extensive literature search. The incorporation of Big Data, such as data from electronic health records (EHR), wearable glucose monitories, and laboratory experiments, and the combination of this data with advanced machine learning (ML) models to improve the performance of GDM risk estimators receives a lot of attention. The results suggest that the use of Big Data analytics and creation of high advanced machine learning algorithms can allow the possibility of personalised diagnosis and prevention, with potential to reduce risks such as fetal macrosomia and postpartum diabetes type-2. For example, if a patient’s CGM has observed an increasing trend of blood glucose after meal over a few days, an AI-powered application can automatically send a customizable alert to her smartphone, suggesting a particular low glycaemic meal replacement, before her blood sugar levels reach critical limits, based on her BMI and eating habits. The interdisciplinary approach has been seen to foster the growth of AI-based clinical decision support system which enhances the maternal and fetal treatment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A survey on predictive analytics and preventive strategies for gestational diabetes mellitus using big data and machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月19日

查看全文
  • Vandana Jagtap,
  • Shraddha R. Khonde,
  • Shrinivas N. Dharwadkar,
  • Amita Shinde,
  • Vandana V. Kale,
  • Uma Dattasamje,
  • Swapna S. Bhavsar,
  • Girisha R. Bombale,
  • Shilpa Khedkar,
  • Milind P. Gajare,
  • R. N. Yerrawar,
  • S. H. Gawande

摘要

Gestational Diabetes Mellitus (GDM) or glucose intolerance when first recognised during the pregnancy is posing significant threats to mother and fetal health. Improved outcomes can be achieved with early diagnosis and special treatment. It reviews the biological, environmental and lifestyle risk factors for gestational diabetes mellitus (GDM) and examines the progress and innovations in screening, prediction and prevention of GDM by an extensive literature search. The incorporation of Big Data, such as data from electronic health records (EHR), wearable glucose monitories, and laboratory experiments, and the combination of this data with advanced machine learning (ML) models to improve the performance of GDM risk estimators receives a lot of attention. The results suggest that the use of Big Data analytics and creation of high advanced machine learning algorithms can allow the possibility of personalised diagnosis and prevention, with potential to reduce risks such as fetal macrosomia and postpartum diabetes type-2. For example, if a patient’s CGM has observed an increasing trend of blood glucose after meal over a few days, an AI-powered application can automatically send a customizable alert to her smartphone, suggesting a particular low glycaemic meal replacement, before her blood sugar levels reach critical limits, based on her BMI and eating habits. The interdisciplinary approach has been seen to foster the growth of AI-based clinical decision support system which enhances the maternal and fetal treatment.