Artificial Intelligence and Gestacional Diabetes

Official title

Artificial Intelligence in Education and Monitoring Women With Gestational Diabetes

Overview

Artificial intelligence (AI) technology can assist medical teams in remote monitoring and continuing education of women with gestational diabetes (GDM), potentially improving adherence to interventions and impacting outcomes. An AI remote monitoring model called "monitoring model for women with GDM using pharmacological therapy," created by the ChamouDr technical team, will be analyzed focusing on disease education, glycemic control monitoring, and therapeutic interventions. Women diagnosed with GDM are invited to participate in the study and sign a free and informed consent form. The AI tool is installed on the pregnant woman's cell phone, who receives instructions to collect capillary blood glucose 6 times a day according to the protocol, at home, and report the results via WhatsApp to the study tool. Algorithm generated by the AI model based on self monitoring of blood glucose (SMBG) informs about diabetes control in the last week. The dashboard is accessible via a web browser, and signals: in green and red for patients with satisfactory and unsatisfactory control, respectively. Thus, the AI model optimizes the team's time in analyzing and treating patients appropriately in a simple, cost-effective, and accessible way.

Detailed description

AI technology can assist medical teams in remote monitoring and continuing education of women with GDM. Objective: To analyze the results of using an AI model in remote monitoring and continuing education of women with GDM and pharmacological treatment, correlating them with clinical outcomes for the mother-fetus binomial. Methods: prospective, longitudinal, interventional clinical study approved by the local ethics committee. Patients signed a consent form to participate. An AI remote monitoring model called "monitoring model for women with GDM using pharmacological therapy," created by the ChamouDr technical team, will be analyzed focusing on disease education, glycemic control monitoring, and therapeutic interventions. The modell uses WhatsApp®, through a structured chatbot and AI resources, to communicate with the participant. Comparative analyses will be conducted between two groups of 100 pregnant women with GDM on insulin therapy, followed in the high-risk prenatal clinic of the Obstetrics Department of a tertiary hospital: case group using the AI model versus control group, composed of patients previously monitored under conventional in-person supervision, without the use of this technology. Algorithm generated by the AI model based on SMBG informs about diabetes control in the last week. The dashboard is accessible via a web browser, and signals: in green and red for patients with satisfactory and unsatisfactory control, respectively. Thus, the AI model optimizes the team's time in analyzing and treating patients appropriately in a simple, cost-effective, and accessible way.

Interventions

• Other monitoring model for women with gestacional diabetes using pharmacological therapy
  Artificial Intelligence modell through WhatsApp® to remote monitoring gestacional diabetes in insulin treatment, focusing on disease education, glycemic control monitoring, and therapeutic interventions.

Primary outcome measures

• fetal death [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy)]
• Fetal birth weight [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy)]
• neonatal hypoglycemia [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy), and Assessment of neonatal blood glucose levels from birth up to 48 hours post-birth.]
• glycemic control [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy)]

Secondary outcome measures (5)

• admission of the newborn to the intensive care unit [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy), and from birth to 48 hours postpartum]
• mother weight gain [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy).]
• gestational age at delivery [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy).]
• route of delivery [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy).]
• Blood pressure [Time frame: From the moment of randomization to delivery (until 40 weeks of pregnancy).]

Eligibility criteria

Inclusion criteria

• Gestacional diabetes women with gestational age of up to 28 weeks and 6 days
• Gestacional diabetes women who sign the free and informed consent form

Exclusion criteria

• Gestational age greater than 28 completed weeks at the first consultation
• Participants with overt DM (fasting glucose > 126 mg/dl or postprandial > 200 mg/dl)
• Unknown outcome.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

Non-randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Treatment

Study locations

Brazil · 1 center

• Fundação Faculdade Regional de Medicina de São José do Rio Preto — São José do Rio Preto

Publications

• Dhombres F, Bonnard J, Bailly K, Maurice P, Papageorghiou AT, Jouannic JM. Contributions of Artificial Intelligence Reported in Obstetrics and Gynecology Journals: Systematic Review. J Med Internet Res. 2022 Apr 20;24(4):e35465. doi: 10.2196/35465. PMID 35297766
• Akazawa M, Hashimoto K. Artificial intelligence in gynecologic cancers: Current status and future challenges - A systematic review. Artif Intell Med. 2021 Oct;120:102164. doi: 10.1016/j.artmed.2021.102164. Epub 2021 Sep 3. PMID 34629152
• Grunebaum A, Chervenak J, Pollet SL, Katz A, Chervenak FA. The exciting potential for ChatGPT in obstetrics and gynecology. Am J Obstet Gynecol. 2023 Jun;228(6):696-705. doi: 10.1016/j.ajog.2023.03.009. Epub 2023 Mar 15. PMID 36924907
• Sweeting A, Wong J, Murphy HR, Ross GP. A Clinical Update on Gestational Diabetes Mellitus. Endocr Rev. 2022 Sep 26;43(5):763-793. doi: 10.1210/endrev/bnac003. PMID 35041752
• Ye W, Luo C, Huang J, Li C, Liu Z, Liu F. Gestational diabetes mellitus and adverse pregnancy outcomes: systematic review and meta-analysis. BMJ. 2022 May 25;377:e067946. doi: 10.1136/bmj-2021-067946. PMID 35613728
• Mistry SK, Das Gupta R, Alam S, Kaur K, Shamim AA, Puthussery S. Gestational diabetes mellitus (GDM) and adverse pregnancy outcome in South Asia: A systematic review. Endocrinol Diabetes Metab. 2021 Oct;4(4):e00285. doi: 10.1002/edm2.285. Epub 2021 Jul 3. PMID 34505412
• Ugwudike B, Kwok M. Update on gestational diabetes and adverse pregnancy outcomes. Curr Opin Obstet Gynecol. 2023 Oct 1;35(5):453-459. doi: 10.1097/GCO.0000000000000901. Epub 2023 Aug 9. PMID 37560815
• HAPO Study Cooperative Research Group; Metzger BE, Lowe LP, Dyer AR, Trimble ER, Chaovarindr U, Coustan DR, Hadden DR, McCance DR, Hod M, McIntyre HD, Oats JJ, Persson B, Rogers MS, Sacks DA. Hyperglycemia and adverse pregnancy outcomes. N Engl J Med. 2008 May 8;358(19):1991-2002. doi: 10.1056/NEJMoa0707943. PMID 18463375

Identifiers

NCT: NCT07345143 · 78204024.6.0000.5415.

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗