Journal of Clinical Monitoring and Computing最新文献

Intraoperative hypotension (IOH) is associated with morbidity and mortality. The Hypotension Prediction Index (HPI), a machine learning-based tool, offers the opportunity for a proactive approach by predicting hypotensive events. This single center, single blind randomized clinical trial aimed to evaluate the hypothesis that an HPI software-guided approach to IOH management during prone position spine surgery could reduce its incidence compared to our standard care practices. 85 adult patients undergoing spine fusion surgery in the prone position were enrolled. Patients were randomized with a 1:1 allocation ratio. Participants were blinded to their group allocation. In the intervention group, the HPI software was actively used to guide IOH management. In the control group, HPI software readings were blinded, and standard care was administered. The primary outcome was the comparison of time-weighted average (TWA) of IOH between the two groups. Secondary outcomes included a comparison of the incidence of postoperative in-hospital events related to IOH between groups. 77 patients were included in the final analysis (39 in the intervention group), as 8 patients were excluded due to technical issues. No statistically significant difference was found between the intervention and control groups in the TWA of IOH (0.10 mmHg [0.05, 0.23] vs. 0.15 mmHg [0.09, 0.37], p-value 0.088). However, the total duration of hypotensive events per patient was significantly lower in the intervention group (4 min [0.5, 12.2] vs. 11.2 min [2.6, 20.1]; p-value 0.019). Postoperative complication rates did not differ significantly between the two groups. HPI-guided management did not significantly reduce the TWA of IOH compared to standard care in patients undergoing prone-position spine surgery. Complication rates were similar between the two groups.Clinical Trial Registration: This trial was registered with ClinicalTrials.gov (registration number: NCT05341167).

Purpose: Vital sign monitoring plays a pivotal role in assessing and managing the clinical condition of vulnerable newborn infants in the delivery room and in the neonatal intensive care unit (NICU), with advancements in technology over the last years paving the way for newer and less invasive monitoring techniques.

Methods: We conducted a narrative review of the literature in PubMed, Embase, GoogleScholar, and ClinicalTrials.gov. to describe newer technologies in neonatal monitoring of heart rate and oxygen saturation including secondary data-use, focusing also on promising studies which are currently underway.

Results: Innovations such as photoplethysmography, wireless skin sensors, spectroscopy and tremolo sonification can provide a continuous and comprehensive assessment of neonatal vital sign monitoring, including heart rate and oxygen saturations, allowing for the enhancement of early detection of potential complications. Moreover advanced mathematical models, such as heart rate characteristic variability and closed loop automated systems, have shown promise in processing and storing vast amounts of data, aiding in the early prediction of adverse clinical outcomes, supporting decision-making and guiding the development of future studies.

Conclusion: As the field of vital sign monitoring in the NICU continues to evolve, it is essential to address challenges related to novel modalities, data privacy, algorithm accuracy, and seamless integration into existing healthcare systems. By harnessing the potential of innovative technologies, the future of vital sign monitoring in the NICU promises improved neonatal outcomes, enhanced healthcare delivery and facilitation of individualisation of care.

Purpose: The analgesia nociception index (ANI), also referred to as the high frequency variability index (HFVI), is reported to be an objective measure of nociception. This study investigated changes in ANI after peripheral nerve blocks (PNB) under general anesthesia. Understanding these changes could enhance assessment of PNB efficacy before emergence from general anesthesia.

Methods: This study enrolled 30 patients undergoing elective upper limb surgery. After surgery, median and maximum ANI values were recorded during two periods: a 5-minute period before PNB and a 20-minute period after PNB. The numeric rating scale (NRS) for pain was assessed twice: immediately after emergence from general anesthesia (N1) and the maximum pain experienced by the following morning after PNB effects subsided (N2). The difference in ANI before and after PNB was tested using the Wilcoxon signed-rank test. Statistical significance was set at P < 0.05.

Results: The ANI significantly increased after PNB in both the median (pre vs. post PNB value: 53.5 [44.0-68.0] vs. 59.0 [47.0-78.3], median [interquartile range]; P < 0.05) and maximum values (64.0 [56.3-79.5] vs. 74.5 [61.5-85.3]; P < 0.01). Secondary analysis revealed that significant ANI increases in both median (48.0 [42.3-66.5] vs. 61.0 [50.0-76.5]; P < 0.01) and maximum values (58.5 [50.3-75.3] vs. 76.0 [71.8-83.5]; P < 0.01) in the 18 cases with N2 ≥ 4 whereas no statistical differences were observed in the 12 cases with N2 < 4.

Conclusion: The increased ANI value after PNB under propofol anesthesia may be a valuable indicator for assessing PNB efficacy.

Trial registration number: UMIN000050334.

Date of registration: February 28, 2023.

Processed electroencephalography (EEG) indices used to guide anesthetic dosing in adults are not validated in young infants. Raw EEG can be processed mathematically, yielding quantitative EEG parameters (qEEG). We hypothesized that machine learning combined with qEEG can accurately classify expired sevoflurane concentrations in young infants. Knowledge from this may contribute to development of future infant-specific EEG algorithms. Frontal EEG collected from infants ≤ 3 months were time-matched as one-minute epochs to expired sevoflurane (eSevo). Fifteen qEEG parameters were extracted from each epoch and eight machine learning models combined the qEEG to classify each epoch into one of four eSevo levels (%): 0.1-1.0, 1.0-2.1, 2.1-2.9, and > 2.9. 64 epochs formed the post hoc SHAP dataset to determine the qEEG that contributed most to the model. The remaining epochs were randomly split 50 times into 80/20 training/testing sets. Accuracy and F1-score determined model performance. 42 infants provided 4574 epochs. The top classifiers K-nearest neighbors, default multi-layer perceptron, and support vector machine achieved 67.5-68.7% accuracy. Burst suppression ratio and entropy β were the top contributors to the models. Post hoc analysis performed without burst suppression ratio yielded similar prediction performance. In young infants, machine learning applied to qEEG predicted eSevo levels with moderate success. Burst suppression ratio, the most important contributor, represented an efficient EEG feature that encapsulated underlying EEG changes seen on other qEEG features. These results provided insight into EEG parameter selection and optimal machine learning models used for future development of infant-specific EEG algorithms.

Unobtrusive pulse rate monitoring by continuous video recording, based on remote photoplethysmography (rPPG), might enable early detection of perioperative arrhythmias in general ward patients. However, the accuracy of an rPPG-based machine learning model to monitor the pulse rate during sinus rhythm and arrhythmias is unknown. We conducted a prospective, observational diagnostic study in a cohort with a high prevalence of arrhythmias (patients undergoing elective electrical cardioversion). Pulse rate was assessed with rPPG via a visible light camera and ECG as reference, before and after cardioversion. A cardiologist categorized ECGs into normal sinus rhythm or arrhythmias requiring further investigation. A supervised machine learning model (support vector machine with Gaussian kernel) was trained using rPPG signal features from 60-s intervals and validated via leave-one-subject-out. Pulse rate measurement performance was evaluated with Bland-Altman analysis. Of 72 patients screened, 51 patients were included in the analyses, including 444 60-s intervals with normal sinus rhythm and 1130 60-s intervals of clinically relevant arrhythmias. The model showed robust discrimination (AUC 0.95 [0.93-0.96]) and good calibration. For pulse rate measurement, the bias and limits of agreement for sinus rhythm were 1.21 [- 8.60 to 11.02], while for arrhythmia, they were - 7.45 [- 35.75 to 20.86]. The machine learning model accurately identified sinus rhythm and arrhythmias using rPPG in real-world conditions. Heart rate underestimation during arrhythmias highlights the need for optimization.

Hypotension in perioperative and intensive care settings is a significant risk factor associated with complications such as myocardial infarction and kidney injury thereby increasing perioperative complications and mortality. Continuous blood pressure monitoring is essential, yet challenging due to the invasive nature of current methods. Non-invasive techniques like Electrical Impedance Tomography (EIT) have been explored but face challenges in accurate and consistent blood pressure estimation. A machine learning (ML) approach was used to predict aortic blood pressures from EIT voltage measurements in landrace pigs. A convolutional neural network (CNN) was trained on a dataset of 75 298 heartbeats, to predict systolic (SAP), mean (MAP), and diastolic arterial pressures (DAP) of individuals whose arterial pressures were unknown to the algorithm. The Intraclass Correlation Coefficient (3,1) with absolute agreement (ICC) was calculated and the concordance was estimated, comparing reference blood pressure measurements and ML-derived estimates. A risk classification was estimated for the calculated blood pressure as suggested by Saugel et al. 2018. The ML-model demonstrated moderate correlations with invasive blood pressure measurements (ICC for SAP of 0.530, for MAP of 0.563, and for DAP of 0.521.) with a low risk score for 75.8% of the SAP and 64.2% of MAP estimated blood pressures. ML-techniques using EIT-voltages showed promising preliminary results in non-invasive aortic blood pressure estimation. Despite limitations in the amount of available training data and the experimental setup, this study illustrates the potential of integrating ML in EIT signal processing for real-time, non-invasive blood pressure monitoring.