MIDO GDM: an innovative artificial intelligence-based prediction model for the development of gestational diabetes in Mexican women.

Given the barriers to early detection of gestational diabetes mellitus (GDM), this study aimed to develop an artificial intelligence (AI)-based prediction model for GDM in pregnant Mexican women. Data were retrieved from 1709 pregnant women who participated in the multicenter prospective cohort study 'Cuido mi embarazo'. A machine-learning-driven method was used to select the best predictive variables for GDM risk: age, family history of type 2 diabetes, previous diagnosis of hypertension, pregestational body mass index, gestational week, parity, birth weight of last child, and random capillary glucose. An artificial neural network approach was then used to build the model, which achieved a high level of accuracy (70.3%) and sensitivity (83.3%) for identifying women at high risk of developing GDM. This AI-based model will be applied throughout Mexico to improve the timing and quality of GDM interventions. Given the ease of obtaining the model variables, this model is expected to be clinically strategic, allowing prioritization of preventative treatment and promising a paradigm shift in prevention and primary healthcare during pregnancy. This AI model uses variables that are easily collected to identify pregnant women at risk of developing GDM with a high level of accuracy and precision.

Diagnostic Accuracy of Capillary Blood Glucometer Testing for Gestational Diabetes.

Purpose: Few pregnant women in low-resource settings are screened for gestational diabetes mellitus (GDM) using the gold standard oral glucose tolerance test (OGTT). This study compared capillary blood glucose testing with 2-h plasma glucose measurements obtained using the 75-g OGTT to screen for GDM at primary healthcare clinics in Mexico. Patients and Methods: Pregnant women who participated in a previous prospective multicenter longitudinal cohort study and who had not been previously diagnosed with diabetes were included. Participants were evaluated using the plasmatic 2-h 75-g OGTT with simultaneous capillary blood glucose measurements using a glucometer. The study endpoint was the comparability of the glucometer results to the gold standard OGTT when collected simultaneously. Sensitivity, specificity, and area under the curve of the glucose measurements obtained for capillary blood compared with venous plasma (gold standard) were calculated to determine diagnostic accuracy. Results: The study included 947 pregnant women who had simultaneous glucose measurements available (blood capillary [glucometer] and venous blood OGTT). Overall, capillary blood glucose testing was very sensitive (89.47%); the specificity was 66.58% and the area under the curve (95% confidence interval) was 0.78 (0.74-0.81). The sensitivity, specificity and area under the curve of each capillary measurement were: 89.47%, 66.58% and 0.78 (0.74-0.82) for the fasting measurement, 91.53%, 93.24% and 0.92 (0.88-0.96) for the one-hour measurement, and 89.80%, 93.32%, 0.91 (0.87-0.95) for the second-hour measurement, respectively. No adverse events were reported. Conclusion: Capillary OGTT is a valid alternative to the gold standard OGTT for screening of GDM in low-resource situations or in situations where there are other limitations to performing the OGTT as part of primary healthcare services.

Comorbilidades y características clínicas asociadas a la mortalidad hospitalaria por COVID-19 en el estado de Hidalgo, México / Comorbidities and clinical characteristics associated with hospital mortality, due to COVID-19, in the state of Hidalgo, Mexico / Comorbidades e características clínicas associadas à mortalidade hospitalar por COVID-19, no estado de Hidalgo, México

Resumen: Introducción: La enfermedad por COVID-19 ha tenido gran impacto en nuestro país; aunque se han documentado diversas variables que contribuyen al pronóstico sobre la mortalidad y/o enfermedad grave en pacientes, es necesario generar información que dé cuenta de las especificidades estatales para contribuir a la toma de decisiones ante una inminente saturación hospitalaria. Objetivo: Identificar las comorbilidades y características clínicas asociadas a la mortalidad por COVID-19, en pacientes hospitalizados en el estado de Hidalgo, México. Material y métodos: Se realizó un estudio descriptivo y retrospectivo. Como fuente de información se utilizó la base de datos abiertos COVID-19 de la Dirección General de Epidemiología de la Secretaría de Salud de México para realizar tres tipos de regresión: probit, logit y Gauss. El modelo gaussiano fue el de mejor ajuste. Resultados: Se analizaron 3,880 casos (1,696 defunciones y 2,184 recuperados) y se identificaron cuatro comorbilidades asociadas a la mortalidad por COVID-19: obesidad, hipertensión, diabetes e insuficiencia renal crónica (IRC) así como dos características clínicas: sexo y edad. Conclusiones: La hipertensión, obesidad, diabetes e IRC aumentan la probabilidad de defunción. Entre las comorbilidades la IRC es la de mayor peso. De las características clínicas analizadas, se encontró asociación con el sexo y la edad, donde la edad es la variable de mayor peso en el modelo.

Abstract: Introduction: The COVID-19 disease has had a great impact on our country; Although various variables that contribute to the prognosis of mortality and/or serious illness in patients have been documented, it is necessary to generate information that accounts for state specificities to contribute to decision-making in the face of imminent hospital saturation. Objective: To identify the comorbidities and clinical characteristics associated with mortality from COVID-19, in hospitalized patients in the state of Hidalgo, Mexico. Material and method: A descriptive and retrospective study was carried out. As a source of information, the COVID-19 open database of the General Directorate of Epidemiology of the Mexican Ministry of Health was used to perform three types of regression: probit, logit and Gaussian. The Gaussian model was the one with the best fit. Results: 3,880 cases (1,696 deaths and 2,184 recovered) were analyzed and 4 comorbidities associated with mortality from COVID-19 were identified: obesity, hypertension, diabetes, and chronic kidney failure (CRF), as well as 2 clinical characteristics: sex and age. Conclusions: Hypertension, obesity, diabetes and CRF increase the probability of death. Among the comorbidities, CRF is the one with the greatest weight. Of the clinical characteristics analyzed, an association was found with sex and age, where age is the variable with the greatest weight in the model.

Resumo: Introdução: A doença COVID-19 teve um grande impacto no nosso país; Embora tenham sido documentadas diversas variáveis ​​que contribuem para o prognóstico de mortalidade e/ou doença grave em pacientes, é necessário gerar informações que contemplem as especificidades estaduais para contribuir na tomada de decisão diante da iminente saturação hospitalar. Objetivo: Identificar as comorbidades e características clínicas associadas à mortalidade por COVID-19, em pacientes hospitalizados no estado de Hidalgo, México. Material e métodos: Foi realizado um estudo descritivo e retrospectivo. Como fonte de informação, o banco de dados aberto COVID-19 da Direção Geral de Epidemiologia do Ministério da Saúde do México foi usado para realizar três tipos de regressão: probit, logit e gaussiana. O modelo gaussiano foi o que melhor se ajustou. Resultados: foram analisados 3,880 casos (1,696 óbitos e 2,184 recuperados) e identificadas 4 comorbidades associadas à mortalidade por COVID-19: obesidade, hipertensão, diabetes e insuficiência renal crônica (IRC), além de 2 características clínicas: sexo e idade. Conclusões: Hipertensão, obesidade, diabetes e IRC aumentam a probabilidade de morte. Dentre as comorbidades, a IRC é a de maior peso. Das características clínicas analisadas, foi encontrada associação com sexo e idade, sendo a idade a variável com maior peso no modelo.