Desarrollo de un modelo por inteligencia artificial con hemodinamia no invasiva para predecir preeclampsia en embarazos de alto riesgo / Artificial Intelligence Modeling with Non-Invasive Hemodynamics to Predict Preeclampsia in High-Risk Pregnancy

RESUMEN Introducción: la preeclampsia (PE) es la principal causa de morbimortalidad materno-fetal en nuestro país. Alteraciones hemodinámicas precoces durante el embarazo podrían predecir la evolución a PE. El machine learning (ML) permite el hallazgo de patrones ocultos que podrían detectar precozmente el desarrollo de PE. Objetivos: desarrollar un árbol de clasificación con variables de hemodinamia no invasiva para predecir precozmente desarrollo de PE. Material y métodos: estudio observacional prospectivo con embarazadas de alto riesgo (n=1155) derivadas del servicio de Obstetricia desde enero 2016 a octubre 2022 para el muestreo de entrenamiento por ML con árbol de clasificación j48. Se seleccionaron 112 embarazadas entre semanas 10 a 16, sin tratamiento farmacológico y que completaron el seguimiento con el término de su embarazo con evento final combinado (PE): preeclampsia, eclampsia y síndrome HELLP. Se evaluaron simultáneamente con cardiografía de impedancia y velocidad de onda del pulso y con monitoreo ambulatorio de presión arterial de 24 hs (MAPA). Resultados: presentaron PE 17 pacientes (15,18%). Se generó un árbol de clasificación predictivo con las siguientes variables: índice de complacencia arterial (ICA), índice cardíaco (IC), índice de trabajo sistólico (ITS), cociente de tiempos eyectivos (CTE), índice de Heather (IH). Se clasificaron correctamente el 93,75%; coeficiente Kappa 0,70, valor predictivo positivo (VPP) 0,94 y negativo (VPN) 0,35. Precisión 0,94, área bajo la curva ROC 0,93. Conclusión: las variables ICA, IC, ITS, CTE e IH predijeron en nuestra muestra el desarrollo de PE con excelente discriminación y precisión, de forma precoz, no invasiva, segura y con bajo costo.

ABSTRACT Background: Preeclampsia (PE) is the main cause of maternal-fetal morbidity and mortality in our country. Early hemodynamic changes during pregnancy could predict progression to PE. Machine learning (ML) enables the discovery of hidden patterns that could early detect PE development. Objectives: The aim of this study was to build a classification tree with non-invasive hemodynamic variables for the early prediction of PE occurrence. Results: Seventeen patients (15.18%) presented PE. A predictive classification tree was generated with arterial compliance index (ACI), cardiac index (CI), cardiac work index (CWI), ejective time ratio (ETR), and Heather index (HI). A total of 93.75% patients were correctly classified (Kappa 0.70, positive predictive value 0.94 and negative predictive value 0.35; accuracy 0.94, and area under the ROC curve 0.93). Conclusion: ACI, CI, CWI, ETR and HI variables predicted the early development of PE in our sample with excellent discrimination and accuracy, non-invasively, safely and at low cost.

Analysis of Adherence to Antihypertensive Drug Treatment in an Argentinean Cohort

Abstract Background Adherence to antihypertensive medication is a major challenge in the management of hypertension, and non-adherence is an important barrier to effective management of hypertension. Objectives To determine the adherence rate to hypertensive drug treatment and the factors that influence non-adherence in a cohort of the Argentinean population. Methods A multicenter cross-sectional study was conducted in eight cities of Argentina. Consecutive hypertensive patients seen in general practice offices, receiving pharmacological treatment for at least six months were included. Blood pressure measurements were performed by physicians during the patient visit. The level of adherence was assessed using the Morisky questionnaire, and patients were divided into non-adherent and adherent. Continuous variables were compared using independent t-test. Categorical variables were compared using the χ2 test. To identify the variables independently associated with non-adherence, a forward stepwise binary regression logistic model was performed, and the results expressed as odds ratio (OR) with 95% of confidence interval. All tests were two-tailed, and p-values < 0.05 were considered statistically significant. Results A total of 852 individuals (52% women, 62 ± 13 years) were included. The main reason for lack of adherence was forgetfulness of medication intake and errors in the time of intake (~ 40% in both). Individuals with more cardiovascular risk factors (smoking, diabetes, dyslipidemia and previous cardiovascular events) had lower adherence to antihypertensive treatment, and considerably younger (~ five years younger). Conclusions Adherence rate to antihypertensive drug treatment in our study group was higher than the one reported in previous studies, and the main reason for non-adherence was forgetfulness of medication intake. (Int J Cardiovasc Sci. 2020; 33(3):272-277)

Effect of cheese containing Lactobacillus delbrueckii subsp. Lactis CRL 581 on blood pressure in prehypertensive and stage 1 hypertensive subjects / Efecto de un queso con LactobacillusdelbrueckiisubspLactis CRL 581 sobre la hipertensión arterial en individuos con prehipertensión o estadio 1 de hipertensión arterial

Hypertension is one of the main risk factors for cardiovascular disease. Functional foods containing bioactive peptides have been proposed as a strategy to decrease blood pressure (BP) in subjects under no pharmacological treatment. The aim of this study was to compare the effect of low-sodium, low-fat (LSLF) cheese and LSLF cheese containing Lactobacillus delbrueckii subsp. lactis CRL 581 (LSLF581) on BP in pre-hypertensive and stage 1 hypertensive subjects. Sixty-one pre-hypertensive and stage 1 hypertensive subjects assigned to one of twos (LSLF, n= 29 and LSLF581, n= 32) participated in this 12-month prospective, randomized, double-blind, crossover trial. Twenty-four h ambulatory BP monitoring was performed at the beginning and at the end of each four-week study period. Systolic and diastolic BP decreased in both study groups, but differences between groups were not significant (systolic, -1.78 and -0.2 mmHg; diastolic, -1.54 and -0.42 mmHg in LSLF581 and LSLF, respectively). Although our results could not support a BP lowering effect of LSLF581, small BP reductions could favorably prevent cardiovascular disease development.

La hipertensión arterial es uno de los principales factores de riesgo de enfermedad cardiovascular. Los alimentos funcionales que contienen biopéptidos constituyen una estrategia útil para disminuir la presión arterial (PA) en personas que no están bajo tratamiento farmacológico. El objetivo del estudio fue comparar el efecto de un queso bajo en sodio y bajo en grasas (BSBG) y el mismo queso con Lactobacillus delbrueckii subsp. lactis CRL 581 (BSBG581) sobre la PA en personas con prehipertensión y estadio 1 de hipertensión arterial. Realizamos un estudio prospectivo, randomizado, cruzado y doble ciego durante 12 meses en 61 personas con prehipertensión y estadio 1 de hipertensión arterial, asignadas a dos grupos: BSBG (n= 29) y BSBG581 (n= 32). Se realizó monitoreo ambulatorio de la PA (MAPA) durante 24 h al comienzo y al final de cada etapa del estudio (cuatro semanas). La PA sistólica y diastólica disminuyó en ambos grupos, aunque las diferencias entre grupos no fueron significativas (sistólica, -1.78 y -0.2 mmHg; diastólica -1.54 y -0.42 mmHg en BSBG581 y BSBG respectivamente). Aunque nuestros resultados no pueden confirmar el efecto hipotensor del queso BSBG581, las reducciones moderadas de la PA podrían prevenir el desarrollo de enfermedad cardiovascular.