Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add more filters










Publication year range
1.
Actual. anestesiol. reanim ; 70(4): 209-217, Abr. 2023. ilus, tab, graf
Article in Spanish | IBECS | ID: ibc-218272

ABSTRACT

Antecedentes y objetivo: El propósito del presente estudio fue evaluar si una red neuronal superficial (RN-S) puede detectar y clasificar los cambios en la presión arterial (PA), dependientes del tono vascular mediante un análisis del contorno de la onda de fotopletismografía (FPG). Material y métodos: Las señales de FPG y PA invasivas fueron simultáneamente registradas en 26 pacientes programados para cirugía general. Se estudió la aparición de episodios de hipertensión (presión arterial sistólica (PAS) > 140 mmHg), normotensión e hipotensión (PAS < 90 mmHg). El tono vascular fue clasificado según la FPG en dos formas: 1) Mediante inspección visual de los cambios en la amplitud de la onda de FPG y en la posición de la incisura dícrota; donde las clases I-II representan vasoconstricción (incisura dícrota ubicada a > 50% de la amplitud de FPG en ondas de pequeña amplitud), tono vascular normal de clase III (incisura dícrota ubicada entre 20-50% de la amplitud de FPG en ondas normales) y vasodilatación de clases IV-V-VI (incisura dícrota a < 20% de la amplitud FPG en ondas grandes). 2) Mediante un análisis automatizado basado en RN-S que combina siete parámetros derivados de la onda de FPG. Resultados: La evaluación visual fue precisa en la detección de hipotensión (sensibilidad 91%, especificidad 86% y precisión 88%) e hipertensión (sensibilidad 93%, especificidad 88% y precisión 90%). La normotensión se presentó como clase visual III (III-III) (mediana y 1°- 3° cuartiles), hipotensión como clase V (IV-VI) e hipertensión como clase II (I-III); todos con significancia estadística (p < 0,0001). La RN-S funcionó bien en la clasificación de las condiciones de PA. El porcentaje de datos con clasificación correcta por la RN-S fue del 83% para normotensión, 94% para hipotensión y 90% para hipertensión. Conclusiones: Los cambios en la PA inducidos por alteraciones en el tono vascular fueron clasificados correctamente de forma automática con una RN-S con base en...(AU)


Background: To test whether a Shallow Neural Network (S-NN) can detect and classify vascular tone dependent changes in arterial blood pressure (ABP) by advanced photopletysmographic (PPG) waveform analysis. Methods: PPG and invasive ABP signals were recorded in 26 patients undergoing scheduled general surgery. We studied the occurrence of episodes of hypertension (systolic arterial pressure (SAP) > 140 mmHg), normotension and hypotension (SAP < 90 mmHg). Vascular tone according to PPG was classified in two ways: 1) By visual inspection of changes in PPG waveform amplitude and dichrotic notch position; where Classes I-II represent vasoconstriction (notch placed > 50% of PPG amplitude in small amplitude waves), Class III normal vascular tone (notch placed between 20-50% of PPG amplitude in normal waves) and Classes IV-V-VI vasodilation (notch < 20% of PPG amplitude in large waves). 2) By an automated analysis, using S-NN trained and validated system that combines seven PPG derived parameters. Results: The visual assessment was precise in detecting hypotension (sensitivity 91%, specificity 86% and accuracy 88%) and hypertension (sensitivity 93%, specificity 88% and accuracy 90%). Normotension presented as a visual Class III (III-III) (median and 1st-3rd quartiles), hypotension as a Class V (IV-VI) and hypertension as a Class II (I-III); all p < 0.0001. The automated S-NN performed well in classifying ABP conditions. The percentage of data with correct classification by S-ANN was 83% for normotension, 94% for hypotension, and 90% for hypertension. Conclusions: Changes in ABP were correctly classified automatically by S-NN analysis of the PPG waveform contour.(AU)


Subject(s)
Humans , Female , Middle Aged , Aged , Photoplethysmography , Arterial Pressure , Hypotension , Anesthesia, General/adverse effects
2.
Rev Esp Anestesiol Reanim (Engl Ed) ; 70(4): 209-217, 2023 04.
Article in English | MEDLINE | ID: mdl-36868265

ABSTRACT

BACKGROUND: To test whether a Shallow Neural Network (S-NN) can detect and classify vascular tone dependent changes in arterial blood pressure (ABP) by advanced photopletysmographic (PPG) waveform analysis. METHODS: PPG and invasive ABP signals were recorded in 26 patients undergoing scheduled general surgery. We studied the occurrence of episodes of hypertension (systolic arterial pressure (SAP) >140 mmHg), normotension and hypotension (SAP < 90 mmHg). Vascular tone according to PPG was classified in two ways: 1) By visual inspection of changes in PPG waveform amplitude and dichrotic notch position; where Classes I-II represent vasoconstriction (notch placed >50% of PPG amplitude in small amplitude waves), Class III normal vascular tone (notch placed between 20-50% of PPG amplitude in normal waves) and Classes IV-V-VI vasodilation (notch <20% of PPG amplitude in large waves). 2) By an automated analysis, using S-NN trained and validated system that combines seven PPG derived parameters. RESULTS: The visual assessment was precise in detecting hypotension (sensitivity 91%, specificity 86% and accuracy 88%) and hypertension (sensitivity 93%, specificity 88% and accuracy 90%). Normotension presented as a visual Class III (III-III) (median and 1st-3rd quartiles), hypotension as a Class V (IV-VI) and hypertension as a Class II (I-III); all p < .0001. The automated S-NN performed well in classifying ABP conditions. The percentage of data with correct classification by S-ANN was 83% for normotension, 94% for hypotension, and 90% for hypertension. CONCLUSIONS: Changes in ABP were correctly classified automatically by S-NN analysis of the PPG waveform contour.


Subject(s)
Hypertension , Hypotension , Humans , Arterial Pressure , Photoplethysmography , Hypertension/diagnosis , Hypotension/diagnosis , Neural Networks, Computer
SELECTION OF CITATIONS
SEARCH DETAIL
...