Arterial Blood Pressure Wave Signal Reconstruction Using Photoplethysmography by CNN-LSTM Model / 生物化学与生物物理进展

ObjectiveDirect continuous monitoring of arterial blood pressure is invasive and continuous monitoring cannot be achieved by traditional cuffed indirect blood pressure measurement methods. Previously, continuous non-invasive arterial blood pressure monitoring was achieved by using photoplethysmography (PPG), but it is discrete values of systolic and diastolic blood pressures rather than continuous values constructing arterial blood pressure waves. This study aimed to reconstruct arterial blood pressure wave signal based on CNN-LSTM using PPG to achieve continuous non-invasive arterial blood pressure monitoring. MethodsA CNN-LSTM hybrid neural network model was constructed, and the PPG and arterial blood pressure wave synchronized recorded signal data from the Medical Information Mart for Intensive Care (MIMIC) were used. The PPG signals were input to this model after noise reduction, normalization, and sliding window segmentation. The corresponding arterial blood pressure waves were reconstructed from PPG by using the CNN-LSTM hybrid model. ResultsWhen using the CNN-LSTM neural network with a window length of 312, the error between the reconstructed arterial blood pressure values and the actual arterial blood pressure values was minimal: the values of mean absolute error (MAE) and root mean square error (RMSE) were 2.79 mmHg and 4.24 mmHg, respectively, and the cosine similarity is the optimal. The reconstructed arterial blood pressure values were highly correlated with the actual arterial blood pressure values, which met the Association for the Advancement of Medical Instrumentation (AAMI) standards. ConclusionCNN-LSTM hybrid neural network can reconstruct arterial blood pressure wave signal using PPG to achieve continuous non-invasive arterial blood pressure monitoring.

Differences in perioperative femoral and radial arterial blood pressure in neonates and infants undergoing cardiac surgery requiring cardiopulmonary bypass / Diferenças na pressão arterial femoral e radial no perioperatório em neonatos e bebês submetidos a cirurgia cardíaca com bypass cardiopulmonar

Abstract Objective: Several reports claim that blood pressure (BP) in the radial artery may underestimate the accurate BP in critically ill patients. Here, the authors evaluated differences in mean blood pressure (MBP) between the radial and femoral artery during pediatric cardiac surgery to determine the effectiveness of femoral arterial BP monitoring. Method: The medical records of children under 1 year of age who underwent open-heart surgery between 2007 and 2013 were retrospectively reviewed. Radial and femoral BP were measured simultaneously, and the differences between these values were analyzed at various times: after catheter insertion, after the initiation of cardiopulmonary bypass (CPB-on), after aortic cross clamping (ACC), after the release of ACC, after weaning from CPB, at arrival in the intensive care unit (ICU), and every 6 h during the first day in the ICU. Results: A total of 121 patients who underwent open-heart surgery met the inclusion criteria. During the intraoperative period, from the beginning to the end of CPB, radial MBPs were significantly lower than femoral MBPs at each time-point measured (p < 0.05). Multivariate analysis showed that longer CPB time (>60 min, odds ratio: 7.47) was a risk factor for lower radial pressure. However, discrepancies between these two values disappeared after arrival in the ICU. There was no incidence of ischemic complications associated with the catheterization of both arteries. Conclusion: The authors suggest that femoral arterial pressure monitoring can be safely performed, even in neonates, and provides more accurate BP values during CPB-on periods, and immediately after weaning from CPB, especially when CPB time was greater than 60 min.

Resumo Objetivo: Diversos relatos alegam que a pressão arterial (PA) na artéria radial poderá subestimar a PA precisa em pacientes gravemente doentes. Aqui, avaliamos diferenças na pressão arterial média (PAM) entre a artéria radial e femoral durante cirurgia cardíaca pediátrica para determinar a eficácia do monitoramento da PA da artéria femoral. Método: Realizamos uma análise retrospectiva de prontuários médicos de crianças com menos de 1 ano de idade submetidas a cirurgia de coração aberto entre 2007 e 2013. As PAs radial e femoral foram auferidas simultaneamente, as diferenças entre esses valores foram analisadas diversas vezes: após a inserção do cateter, após o início do bypass cardiopulmonar (CPB-on), após pinçamento cruzado da aorta (ACC), após a liberação do ACC, após desmame do CPB, na entrada na unidade de terapia intensiva (UTI) e a cada 6 horas durante o primeiro dia na unidade de terapia intensiva (UTI). Resultados: Um total de 121 pacientes submetidos a cirurgia de coração aberto atenderam aos nossos critérios de inclusão. Durante o transoperatório, do início ao término do CPB, as PAMs da artéria radial foram significativamente menores do que as PAMs da artéria femoral em cada ponto de medição (p < 0,05). A análise multivariada mostrou que a duração mais longa do CPB (> 60 minutos, Razão de Chance = 7,47) representou um fator de risco de pressão radial mais baixa. Contudo, as diferenças entre esses dois valores desapareceram após a entrada na UTI. Não houve incidência de complicações isquêmicas associadas à cateterização de ambas as artérias. Conclusão: Sugerimos que o monitoramento da pressão arterial femoral pode ser realizado com segurança, mesmo em neonatos, e fornece valores da PA mais precisos durante períodos de CPBon e imediatamente após o desmame do CPB, principalmente nos casos em que a duração do CPB foi superior a 60 minutos.

A comparative study on invasive and non-invasive blood pressure monitoring for patients after me-chanic valve replacement / 中国实用护理杂志

Objective To investigate the difference between invasive and non-invasive blood pres-sure monitoring for patients after mechanic valve replacement. Methods Invasive or non- invasive blood pressure of 40 patients after mechanic valve replacement were continuously monitored for 24 hours, and the results underwent t test. Results There was a significant difference between invasive and non-invasive blood pressure monitoring for patients within 12 hours after mechanic valve replacement, but no difference was seen between them after 12 hours. Conclusions It can provide more accurate bases by monitoring blood pressure invasively at early stage after mechanic valve replacement, and it can be replaced by non-invasive blood pressure monitoring 12 hours after mechanic valve replacement.

Enflurane Anesthesia Augments the Peripheral Venous Pressure Changes during Non-invasive Blood Pressure Measurement / 대한마취과학회지

BACKGROUND: Venous regurgitation into the infusion line and subsequent occlusion frequently occurs during blood pressure (BP) measurement. The purpose of this study was to obtain the pattern and the actual range of peripheral venous pressure (PVP) change during NIBP measurement before and during enflurane anesthesia. METHODS: Adult size NIBP cuff was placed on the same arm on which IV infusion set was placed. PVP waveforms during BP measurement were recorded from 6 subjects. PVPs were measured before induction and at 30 min after induction of enflurane anesthesia (n=19). As the PVP waveform during NIBP measurement was biphasic in shape, values of baseline PVP (BEFORE), first peak (PEAK1), notch between two peaks (NOTCH), second peak (PEAK2) were measured. Timed control data were obtained from six volunteers. RESULTS: PEAK2 was always higher than PEAK1. Range of peak PVP was 12-130 mmHg (57.6 2.5 mmHg, mean S.E.) and PVP change was augmented during enflurane anesthesia (p<0.05). Enflurane anesthesia accentuated correlationship between mean arterial pressure and PVP. CONCLUSION: Our observation showed that peak PVP occurred during deflation phase and its range of variation was substantial. Changes in the pattern and the autoregulation of PVP by enflurane needs further investigation.