Prediction of mortality in intensive care unit cardiac surgical patients☆☆☆

Hekmat, Khosro; Doerr, Fabian; Kroener, Axel; Heldwein, M.; Bossert, Torsten; Badreldin, Akmal M.A.; Lichtenberg, Artur

doi:10.1016/j.ejcts.2010.01.053

Cited by 35 publications

(42 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Use of a single site is also a limitation because it can decrease the generalizability of the study findings. Inclusion of the APACHE II variable for the entire sample may also be a limitation, because the APACHE II is a poor prognostic indicator among cardiac surgery patients [47][48][49] ; consequently, we eliminated this variable from the main analysis.…”

Section: Limitationsmentioning

confidence: 99%

Vasopressors and Development of Pressure Ulcers in Adult Critical Care Patients

Cox

Roche

2015

American Journal of Critical Care

104

103

View full text Add to dashboard Cite

Background Vasopressors are lifesaving agents used to raise mean arterial pressure in critically ill patients in shock states. The pharmacodynamics of these agents suggest vasopressors may play a role in development of pressure ulcers; however, this aspect has been understudied. Objective To examine associations between type, dose, and duration of vasopressors (norepinephrine, epinephrine, vasopressin, phenylephrine, dopamine) and development of pressure ulcers in medical-surgical and cardiothoracic intensive care unit patients and to examine predictors of the development of pressure ulcers in these patients. Methods A retrospective correlational design was used in a sample of 306 medical-surgical and cardiothoracic intensive care unit patients who received vasopressor agents during 2012. Results Norepinephrine and vasopressin were significantly associated with development of pressure ulcers; vasopressin was the only significant predictor in multivariate analysis. In addition, mean arterial pressure less than 60 mm Hg in patients receiving vasopressors, cardiac arrest, and mechanical ventilation longer than 72 hours were predictive of development of pressure ulcers. Patients with a cardiac diagnosis at the time of admission to the intensive care unit were less likely than patients without such a diagnosis to experience pressure ulcers while in the unit. Conclusion The addition of vasopressin administered concomitantly with a first-line agent (often norepinephrine) may represent the point at which the risk for pressure ulcers escalates and may be an early warning to heighten strategies to prevent pressure ulcers. Conversely, because vasopressors cannot be terminated to avert development of pressure ulcers, these findings may add to the body of knowledge on factors that potentially contribute to the development of unavoidable pressure ulcers.

show abstract

Section: Limitationsmentioning

confidence: 99%

Vasopressors and Development of Pressure Ulcers in Adult Critical Care Patients

Cox

Roche

2015

American Journal of Critical Care

104

103

View full text Add to dashboard Cite

show abstract

“…Of 12 096 patients undergoing cardiac surgery, 2.1% received renal replacement therapy and 3.9% had severe kidney injury [12]. This increased mortality and morbidity is reflected in the observations that postoperative elevated creatinine concentrations and continuous or intermittent renal replacement therapy (Continuous veno-veno hemofiltration or hemodialysis) are associated with greater postoperative mortality [13]. AKI, defined as a 25% reduction in glomerular filtration rate (GFR), occurs in more than 30% of cardiac surgery patients.…”

Section: Cardiac Surgerymentioning

confidence: 98%

Renal dysfunction and fluid and electrolyte disturbances

Hashem

Weissman

2011

Current Opinion in Critical Care

View full text Add to dashboard Cite

show abstract

“…Es por esto que en investigaciones recientes, se han utilizado diversos métodos para mejorar los índices actuales, como regresión logística [8] [9], combinada con redes bayesianas [10] y modelos de cadenas de Markov [11], ensambles de redes neuronales [12], maquinas de vectores de soporte (SVM) [13] y modelos aditivos [14]. Todas estas investigaciones lograron mejorar los índices ya existentes y mas usados, y algunas de ellas como [14] fueron probadas en entornos clínicos reales.…”

Section: Introductionunclassified

“…Todas estas investigaciones lograron mejorar los índices ya existentes y mas usados, y algunas de ellas como [14] fueron probadas en entornos clínicos reales.…”

Section: Introductionunclassified

Desarrollo de un algoritmo para determinar el riesgo de muerte en pacientes dentro de una Unidad de Cuidado Intensivo utilizando Regresión Múltiple no Lineal

García¹,

Aguilar²,

Padilla³

2014

prospect

View full text Add to dashboard Cite

RESUMENLos sistemas de clasificación de la severidad de la enfermedad han sido utilizados por décadas por médicos en todo el mundo dentro de la Unidad de Cuidado Intensivo, como un indicativo del estado de salud del paciente y la probabilidad del riesgo de muerte del mismo. A pesar de la aceptación de dichos sistemas de clasificación, se ha demostrado que no tienen los resultados más precisos, es por esta razón que los científicos e ingenieros han probado diversas técnicas para buscar mejorar dichos sistemas. En este artículo se presentan los resultados del desarrollo de un algoritmo para la determinación del riesgo de muerte utilizando regresión múltiple no lineal y su comparación con los resultados obtenidos con el sistema de clasificación tradicional SAPS I. Partiendo de una base de datos de mediciones de parámetros fisiológicos para 4000 pacientes, se realiza un procesamiento extendido de la misma, aplicándosele análisis de datos y probándose las técnicas de regresión múltiple no lineal: Árbol de regresión, Regresión logística, Máquina de Vector de Soporte y Redes Neuronales Artificiales. Los mejores resultados se obtuvieron con la técnica Máquina de Vector de Soporte, logrando superar el desempeño del sistema SAPS I.Palabras clave: Parámetros fisiológicos, Regresión Múltiple no Lineal, Riesgo de muerte, Sistemas de clasificación de la severidad de la enfermedad, Unidad de Cuidado Intensivo. ABSTRACTSystems for scoring the severity of illness had been used for decades on the Intensive Care Unit (ICU) of Health Care Institutions as indicators of the patient's health and risk of death. Even after being accepted worldwide, it has been proved that these systems have limitations and do not provide the most accurate results, it is because of this that scientists and engineers have tried different techniques in order to improve these systems. This article presents the results of the development of an algorithm that uses non-linear multiple regression to establish the death risk for patients in the ICU, and the comparison of those results with the ones given by the SAPS I traditional scoring system. Parting from a database of physiological variables measurements for 4000 patients, an extended processing of this database is made together with data analysis, to finally apply the nonlinear multiple regression techniques: Regression trees, Logistic Regression, Support Vector Machine and Artificial Neural Networks. The best results were obtained with the Support Vector Machine technique, having a better performance in comparison with the SAPS I score.

show abstract

Prediction of mortality in intensive care unit cardiac surgical patients☆☆☆

Cited by 35 publications

References 23 publications

Vasopressors and Development of Pressure Ulcers in Adult Critical Care Patients

Vasopressors and Development of Pressure Ulcers in Adult Critical Care Patients

Renal dysfunction and fluid and electrolyte disturbances

Desarrollo de un algoritmo para determinar el riesgo de muerte en pacientes dentro de una Unidad de Cuidado Intensivo utilizando Regresión Múltiple no Lineal

Contact Info

Product

Resources

About