Effect of hyperbilirubinemia on the accuracy of continuous non-invasive hemoglobin measurements in liver transplantation recipients.

This study evaluated the effect of hyperbilirubinemia on the accuracy of continuous non-invasive hemoglobin (SpHb) measurements in liver transplantation recipients. Overall, 1465 SpHb and laboratory hemoglobin (Hb) measurement pairs (n = 296 patients) were analyzed. Patients were grouped into normal (< 1.2 mg/dL), mild-to-moderate (1.2-3.0 mg/dL), and severe (> 3.0 mg/dL) hyperbilirubinemia groups based on the preoperative serum total bilirubin levels. Bland-Altman analysis showed a bias of 0.20 (95% limit of agreement, LoA: - 2.59 to 3.00) g/dL, 0.98 (95% LoA: - 1.38 to 3.35) g/dL, and 1.23 (95% LoA: - 1.16 to 3.63) g/dL for the normal, mild-to-moderate, and severe groups, respectively. The four-quadrant plot showed reliable trending ability in all groups (concordance rate > 92%). The rates of possible missed transfusion (SpHb > 7.0 g/dL for Hb < 7.0 g/dL) were higher in the hyperbilirubinemia groups (2%, 7%, and 12% for the normal, mild-to-moderate, and severe group, respectively. all P < 0.001). The possible over-transfusion rate was less than 1% in all groups. In conclusion, the use of SpHb in liver transplantation recipients with preoperative hyperbilirubinemia requires caution due to the positive bias and high risk of missed transfusion. However, the reliable trending ability indicated its potential use in clinical settings.

Automatic segmentation of atrial fibrillation and flutter in single-lead electrocardiograms by self-supervised learning and Transformer architecture.

OBJECTIVES: Automatic detection of atrial fibrillation and flutter (AF/AFL) is a significant concern in preventing stroke and mitigating hemodynamic instability. Herein, we developed a Transformer-based deep learning model for AF/AFL segmentation in single-lead electrocardiograms (ECGs) by self-supervised learning with masked signal modeling (MSM). MATERIALS AND METHODS: We retrieved data from 11 open-source databases on PhysioNet; 7 of these databases included labeled ECGs, while the other 4 were without labels. Each database contained ECG recordings with durations of ≥30 s. A total of 24 intradialytic ECGs with paroxysmal AF/AFL during 4 h of hemodialysis sessions at Seoul National University Hospital were used for external validation. The model was pretrained by predicting masked areas of ECG signals and fine-tuned by predicting AF/AFL areas. Cross-database validation was used for evaluation, and the intersection over union (IOU) was used as a main performance metric in external database validation. RESULTS: In the 7 labeled databases, the areas marked as AF/AFL constituted 41.1% of the total ECG signals, ranging from 0.19% to 51.31%. In the evaluation per ECG segment, the model achieved IOU values of 0.9254 and 0.9477 for AF/AFL segmentation and other segmentation tasks, respectively. When applied to intradialytic ECGs with paroxysmal AF/AFL, the IOUs for the segmentation of AF/AFL and non-AF/AFL were 0.9896 and 0.9650, respectively. Model performance by different training procedure indicated that pretraining with MSM and the application of an appropriate masking ratio both contributed to the model performance. It also showed higher IOUs of AF/AFL labels than in previous studies when training and test databases were matched. CONCLUSION: The present model with self-supervised learning by MSM performs robustly in segmenting AF/AFL.

Real-time machine learning model to predict in-hospital cardiac arrest using heart rate variability in ICU.

Predicting in-hospital cardiac arrest in patients admitted to an intensive care unit (ICU) allows prompt interventions to improve patient outcomes. We developed and validated a machine learning-based real-time model for in-hospital cardiac arrest predictions using electrocardiogram (ECG)-based heart rate variability (HRV) measures. The HRV measures, including time/frequency domains and nonlinear measures, were calculated from 5 min epochs of ECG signals from ICU patients. A light gradient boosting machine (LGBM) algorithm was used to develop the proposed model for predicting in-hospital cardiac arrest within 0.5-24 h. The LGBM model using 33 HRV measures achieved an area under the receiver operating characteristic curve of 0.881 (95% CI: 0.875-0.887) and an area under the precision-recall curve of 0.104 (95% CI: 0.093-0.116). The most important feature was the baseline width of the triangular interpolation of the RR interval histogram. As our model uses only ECG data, it can be easily applied in clinical practice.

Predicting optimal endotracheal tube size and depth in pediatric patients using demographic data and machine learning techniques.

BACKGROUND: Use of endotracheal tubes (ETTs) with appropriate size and depth can help minimize intubation-related complications in pediatric patients. Existing age-based formulae for selecting the optimal ETT size present several inaccuracies. We developed a machine learning model that predicts the optimal size and depth of ETTs in pediatric patients using demographic data, enabling clinical applications. METHODS: Data from 37,057 patients younger than 12 years who underwent general anesthesia with endotracheal intubation were retrospectively analyzed. Gradient boosted regression tree (GBRT) model was developed and compared with traditional age-based formulae. RESULTS: The GBRT model demonstrated the highest macro-averaged F1 scores of 0.502 (95% CI 0.486, 0.568) and 0.669 (95% CI 0.640, 0.694) for predicting the uncuffed and cuffed ETT size (internal diameter [ID]), outperforming the age-based formulae that yielded 0.163 (95% CI 0.140, 0.196, P < 0.001) and 0.392 (95% CI 0.378, 0.406, P < 0.001), respectively. In predicting the ETT depth (distance from tip to lip corner), the GBRT model showed the lowest mean absolute error (MAE) of 0.71 cm (95% CI 0.69, 0.72) and 0.72 cm (95% CI 0.70, 0.74) compared to the age-based formulae that showed an error of 1.18 cm (95% CI 1.16, 1.20, P < 0.001) and 1.34 cm (95% CI 1.31, 1.38, P < 0.001) for uncuffed and cuffed ETT, respectively. CONCLUSIONS: The GBRT model using only demographic data accurately predicted the ETT size and depth. If these results are validated, the model may be practical for predicting optimal ETT size and depth for pediatric patients.

Laser guidance for ultrasound-guided radial artery catheterization using smart glasses: a randomized trial.

PURPOSE: The use of smart glasses during ultrasound-guided needle procedures may reduce operators' head movements but has not been shown to improve procedural performance. Laser guidance has been shown to decrease the time required for ultrasound-guided procedures in phantom models but has not been tested clinically. We hypothesized that adding laser guidance to the use of smart glasses for ultrasound-guided radial artery catheterization using the long axis approach would improve performance by relatively inexperienced users unfamilar with these techniques. METHODS: In an unblinded controlled trial, we enrolled 52 patients requiring radial artery catheterization under anesthesia, randomized into two groups: smart glasses only (SO) (control; N = 26) or smart glasses with laser guidance group (SL) (N = 26). We assessed catheterization time (primary outcome), the number of needle redirections, first-pass success rate, and operator satisfaction (100 = most satisfactory; 0 = unsatisfactory). RESULTS: Comparing the SL with the SO group, catheterization time was shorter (median [interquartile range], 13 [9-20] sec vs 24 [18-46] sec, P < 0.001) and the number of needle redirections was lower (0 [0-1] vs 3 [1-3], P < 0.001) while the first-pass success rate (50% vs 12%, P = 0.007) and operator satisfaction score (85 [76-95] vs 52 [44-74], P < 0.001) were higher. CONCLUSION: Laser guidance improved the performance of ultrasound-guided radial artery catheterization using smart glasses in users inexperienced in the long axis in-plane approach. Nevertheless, it is unclear whether these findings are clinically significant. STUDY REGISTRATION DATE: CRIS.nih.go.kr (KCT0007168); registered 8 April 2022.

RéSUMé: OBJECTIF: L'utilisation de lunettes intelligentes pendant les procédures de ponctions échoguidées peut réduire les mouvements de la tête des opérateurs et opératrices, mais il n'a pas été démontré qu'elle améliorait les performances procédurales. Il a été démontré que le guidage laser réduisait le temps requis pour les interventions échoguidées sur des modèles fantômes, mais cette modalité n'a pas été testée cliniquement. Nous avons émis l'hypothèse que l'ajout d'un guidage laser à l'utilisation de lunettes intelligentes pour le cathétérisme échoguidé de l'artère radiale en utilisant une approche longitudinale (long axe) améliorerait les performances d'utilisateurs et utilisatrices relativement inexpérimenté·es et peu familier·ères avec ces techniques. MéTHODE: Dans une étude contrôlée sans insu, nous avons recruté et randomisé en deux groupes 52 patient·es nécessitant un cathétérisme de l'artère radiale sous anesthésie : lunettes intelligentes uniquement (LIU) (témoin N = 26) ou lunettes intelligentes avec guidage laser (LIL) (N = 26). Nous avons évalué le temps de cathétérisme (critère d'évaluation principal), le nombre de réorientation d'aiguilles, le taux de réussite au premier passage et la satisfaction de l'opérateur·trice (100 = le plus satisfaisant; 0 = insatisfaisant). RéSULTATS: En comparant le groupe LIL au groupe LIU, le temps de cathétérisme était plus court (médiane [écart interquartile], 13 [9-20] sec vs 24 [18­46] sec, P < 0,001) et le nombre de réorientations d'aiguilles était plus faible (0 [0­1] vs 3 [1­3], P < 0,001), tandis que le taux de réussite au premier passage (50 % vs 12 %, P = 0,007) et le score de satisfaction des opératrices et opérateurs (85 [76­95] vs 52 [44­74], P < 0,001) étaient plus élevés. CONCLUSION: Le guidage laser à l'aide de lunettes intelligentes a amélioré les performances du cathétérisme échoguidé de l'artère radiale chez des utilisateurs et utilisatrices inexpérimenté·es en approche longitudinale. Nous ne pouvons toutefois pas déterminer si ces résultats sont cliniquement significatifs. DATE D'ENREGISTREMENT DE L'éTUDE: CRIS.nih.go.kr (KCT0007168); enregistré le 8 avril 2022.

Serum neutrophil gelatinase-associated lipocalin and lactate level during surgery predict acute kidney injury and early allograft dysfunction after liver transplantation.

Early allograft dysfunction (EAD) and acute kidney injury (AKI) are common and clinically important complications after liver transplantation. Serum lactate level at the end of surgery could predict EAD and neutrophil gelatinase-associated lipocalin (NGAL) is known as a biomarker for AKI after liver transplantation. The authors investigated whether the combination of these two laboratory tests could be used as an early predictor of these two complications of EAD and AKI. We reviewed cases undergoing living donor liver transplantation (n = 353). Lactate-adjusted NGAL level, a combination of these two predictors, was calculated as the sum of each value multiplied by the odds ratio for EAD or AKI. We evaluated whether this combined predictor at the end of surgery is significantly associated with both postoperative AKI or EAD. We compared the area under the receiver operating characteristic curve (AUC) between our multivariable regression models with and without NGAL, lactate, or lactate-adjusted NGAL. NGAL, lactate and lactate-adjusted NGAL are significant predictors for EAD and AKI. The regression model for EAD or AKI including lactate-adjusted NGAL showed a greater AUC (for EAD: odds ratio [OR] 0.88, 95% confidence interval [CI] 0.84-0.91; for AKI: OR 0.89, 95% CI 0.85-0.92) compared to the AUC of the models including lactate (for EAD: OR 0.84, 95% CI 0.81-0.88; for AKI: OR 0.79, 95% CI 0.74-0.83) or NGAL alone (for EAD: OR 0.82, 95% CI 0.77-0.86; for AKI: OR 0.84, 95% CI 0.80-0.88) or the model without lactate or NGAL (for EAD: OR 0.64, 95% CI 0.58-0.69, for AKI: OR 0.75, 95% CI 0.70-0.79). In conclusion, lactate-adjusted NGAL level at the end of surgery could be a reliable combined laboratory predictor for postoperative EAD or AKI after liver transplantation with a greater discriminative ability than lactate or NGAL alone.

Continuous cuffless blood pressure monitoring using photoplethysmography-based PPG2BP-net for high intrasubject blood pressure variations.

Continuous, comfortable, convenient (C3), and accurate blood pressure (BP) measurement and monitoring are needed for early diagnosis of various cardiovascular diseases. To supplement the limited C3 BP measurement of existing cuff-based BP technologies, though they may achieve reliable accuracy, cuffless BP measurement technologies, such as pulse transit/arrival time, pulse wave analysis, and image processing, have been studied to obtain C3 BP measurement. One of the recent cuffless BP measurement technologies, innovative machine-learning and artificial intelligence-based technologies that can estimate BP by extracting BP-related features from photoplethysmography (PPG)-based waveforms have attracted interdisciplinary attention of the medical and computer scientists owing to their handiness and effectiveness for both C3 and accurate, i.e., C3A, BP measurement. However, C3A BP measurement remains still unattainable because the accuracy of the existing PPG-based BP methods was not sufficiently justified for subject-independent and highly varying BP, which is a typical case in practice. To circumvent this issue, a novel convolutional neural network(CNN)- and calibration-based model (PPG2BP-Net) was designed by using a comparative paired one-dimensional CNN structure to estimate highly varying intrasubject BP. To this end, approximately [Formula: see text], [Formula: see text], and [Formula: see text] of 4185 cleaned, independent subjects from 25,779 surgical cases were used for training, validating, and testing the proposed PPG2BP-Net, respectively and exclusively (i.e., subject-independent modelling). For quantifying the intrasubject BP variation from an initial calibration BP, a novel 'standard deviation of subject-calibration centring (SDS)' metric is proposed wherein high SDS represents high intrasubject BP variation from the calibration BP and vice versa. PPG2BP-Net achieved accurately estimated systolic and diastolic BP values despite high intrasubject variability. In 629-subject data acquired after 20 minutes following the A-line (arterial line) insertion, low error mean and standard deviation of [Formula: see text] and [Formula: see text] for highly varying A-line systolic and diastolic BP values, respectively, where their SDSs are 15.375 and 8.745. This study moves one step forward in developing the C3A cuffless BP estimation devices that enable the push and agile pull services.

Machine learning-based prediction of intraoperative hypoxemia for pediatric patients.

BACKGROUND: Reducing the duration of intraoperative hypoxemia in pediatric patients by means of rapid detection and early intervention is considered crucial by clinicians. We aimed to develop and validate a machine learning model that can predict intraoperative hypoxemia events 1 min ahead in children undergoing general anesthesia. METHODS: This retrospective study used prospectively collected intraoperative vital signs and parameters from the anesthesia ventilator machine extracted every 2 s in pediatric patients undergoing surgery under general anesthesia between January 2019 and October 2020 in a tertiary academic hospital. Intraoperative hypoxemia was defined as oxygen saturation <95% at any point during surgery. Three common machine learning techniques were employed to develop models using the training dataset: gradient-boosting machine (GBM), long short-term memory (LSTM), and transformer. The performances of the models were compared using the area under the receiver operating characteristics curve using randomly assigned internal testing dataset. We also validated the developed models using temporal holdout dataset. Pediatric patient surgery cases between November 2020 and January 2021 were used. The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC). RESULTS: In total, 1,540 (11.73%) patients with intraoperative hypoxemia out of 13,130 patients' records with 2,367 episodes were included for developing the model dataset. After model development, 200 (13.25%) of the 1,510 patients' records with 289 episodes were used for holdout validation. Among the models developed, the GBM had the highest AUROC of 0.904 (95% confidence interval [CI] 0.902 to 0.906), which was significantly higher than that of the LSTM (0.843, 95% CI 0.840 to 0.846 P < .001) and the transformer model (0.885, 95% CI, 0.882-0.887, P < .001). In holdout validation, GBM also demonstrated best performance with an AUROC of 0.939 (95% CI 0.936 to 0.941) which was better than LSTM (0.904, 95% CI 0.900 to 0.907, P < .001) and the transformer model (0.929, 95% CI 0.926 to 0.932, P < .001). CONCLUSIONS: Machine learning models can be used to predict upcoming intraoperative hypoxemia in real-time based on the biosignals acquired by patient monitors, which can be useful for clinicians for prediction and proactive treatment of hypoxemia in an intraoperative setting.

Robust R-peak detection in an electrocardiogram with stationary wavelet transformation and separable convolution.

R-peak detection is an essential step in analyzing electrocardiograms (ECGs). Previous deep learning models reported their performance primarily in a single database, and some models did not perform at the highest levels when applied to a database different from the testing database. To achieve high performances in cross-database validations, we developed a novel deep learning model for R-peak detection using stationary wavelet transform (SWT) and separable convolution. Three databases (i.e., the MIT-BIH Arrhythmia [MIT-BIH], the Institute of Cardiological Technics [INCART], and the QT) were used in both the training and testing models, and the MIT-BIH ST Change (MIT-BIH-ST), European ST-T, TELE and MIT-BIH Noise Stress Test (MIT-BIH-NST) databases were further used for testing. The detail coefficient of level 4 decomposition by SWT and the first derivative from filtered ECGs were used for model inputs, and the interval of 150 ms centered at marked peaks was used for labels. Separable convolution with atrous spatial pyramidal pooling was selected as the model's architecture, and noise-augmented waveforms of 5.69 s duration (2048 size in 360 Hz) were used in training. The model performance was evaluated using cross-database validation. The F1 scores of the peak detection model were 0.9994, 0.9985, and 0.9999 in the MIT-BIH, INCART, and QT databases, respectively. When the above three databases were pooled, the F1 scores were 0.9993 for fivefold cross-validation and 0.9991 for cross-database validation. The model performance remained high for MIT-BIH-ST, European ST-T, and TELE, with F1 scores of 0.9995, 0.9988, and 0.9790, respectively. The model performance when trained by severe noise augmentation increased for the MIT-BIH-NST database (F1 scores from 0.9504 to 0.9759) and decreased for the MIT-BIH database (F1 scores from 0.9994 to 0.9991). The present SWT and separable convolution-based model for R-peak detection yields a high performance even for cross-database validations.

Nonclinical safety evaluation of food colorant lac dye via systematic toxicity profiling with assessment of in vivo antigenic potential.

Lac dye is a natural colorant derived mainly from the insect Kerria lacca (Kerr) and has been used in food and beverage as a red-coloring additive. Despite its increasing use for human consumption as an alternative for allergy-associated cochineal, its toxicity profile remained incomplete to sufficiently assess its safety for the intended use. In this study, we evaluated systemic and genetic toxicity by performing acute and subacute oral toxicity studies in Sprague-Dawley (SD) rats using highly purified lac dye (LD) formulated in water and a battery of genotoxicity tests, respectively. To assess antigenic potentials, we carried out an in vivo passive cutaneous anaphylaxis test. A single dose of LD did not cause mortality at 5000 mg/kg body weight (BW), setting oral LD50 of >5000 mg/kg BW in SD rats. In the 90-day study, transient salivation without accompanying histopathological lesions in the salivary glands in 200 and 500 mg/kg BW groups and red-purple pigmentation on the surface of femora and skulls in 500 mg/kg groups were observed as nonadverse effects associated with LD, and no adverse effect was detected in all of the parameters examined, establishing a 500 mg/kg BW as no-observed-adverse-effect-level (NOAEL). Furthermore, LD was not mutagenic nor clastogenic in the genotoxicity tests. When tested for antigenicity, LD did not induce anaphylactic skin responses as opposed to the positive reaction by ovalbumin, suggesting a lack of antigenicity. Taken together, these findings provide extended toxicity information on LD with direct evidence supporting the lack of antigenicity, providing essential guidance for its safe use in humans.

Predicting intraoperative hypotension using deep learning with waveforms of arterial blood pressure, electroencephalogram, and electrocardiogram: Retrospective study.

To develop deep learning models for predicting Interoperative hypotension (IOH) using waveforms from arterial blood pressure (ABP), electrocardiogram (ECG), and electroencephalogram (EEG), and to determine whether combination ABP with EEG or CG improves model performance. Data were retrieved from VitalDB, a public data repository of vital signs taken during surgeries in 10 operating rooms at Seoul National University Hospital from January 6, 2005, to March 1, 2014. Retrospective data from 14,140 adult patients undergoing non-cardiac surgery with general anaesthesia were used. The predictive performances of models trained with different combinations of waveforms were evaluated and compared at time points at 3, 5, 10, 15 minutes before the event. The performance was calculated by area under the receiver operating characteristic (AUROC), area under the precision-recall curve (AUPRC), sensitivity and specificity. The model performance was better in the model using both ABP and EEG waveforms than in all other models at all time points (3, 5, 10, and 15 minutes before an event) Using high-fidelity ABP and EEG waveforms, the model predicted IOH with a AUROC and AUPRC of 0.935 [0.932 to 0.938] and 0.882 [0.876 to 0.887] at 5 minutes before an IOH event. The output of both ABP and EEG was more calibrated than that using other combinations or ABP alone. The results demonstrate that a predictive deep neural network can be trained using ABP, ECG, and EEG waveforms, and the combination of ABP and EEG improves model performance and calibration.

Influence of anesthesia type on post-reperfusion syndrome during liver transplantation: a single-center retrospective study.

BACKGROUND: Post-reperfusion syndrome (PRS) results in sudden hemodynamic instability following graft reperfusion. Although PRS is known to influence outcomes following liver transplantation, little is known regarding the effects of anesthetics on PRS. This study investigated the association between the type of anesthetic agent and PRS in liver transplantation. METHODS: This single-center retrospective cohort study included patients who underwent liver transplantation between June 2016 and December 2019. Patients were divided into sevoflurane and propofol groups according to the anesthetic agent used. Stabilized inverse probability of treatment weighting (IPTW) analysis was performed to investigate the association between PRS identified based on blood pressure recordings and the type of anesthesia. Associations between the anesthetic agent and the duration of hypotension as well as early postoperative outcomes were also investigated. RESULTS: Data were analyzed for 398 patients, 304 (76.4%) and 94 (23.6%) of whom were anesthetized with propofol and sevoflurane, respectively. PRS developed in 40.7% of the 398 patients. Following stabilized IPTW analysis, the association with PRS was lower in the sevoflurane group than in the propofol group (odds ratio, 0.47; P = 0.018). However, there was no association between the type of anesthetic used and early postoperative outcomes. CONCLUSIONS: The association of PRS was lower in the sevoflurane group than in the propofol group. However, there was no association between the type of anesthetic and the early postoperative outcomes. Further studies are required to determine the optimal anesthetic for liver transplantation.

VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.

In modern anesthesia, multiple medical devices are used simultaneously to comprehensively monitor real-time vital signs to optimize patient care and improve surgical outcomes. However, interpreting the dynamic changes of time-series biosignals and their correlations is a difficult task even for experienced anesthesiologists. Recent advanced machine learning technologies have shown promising results in biosignal analysis, however, research and development in this area is relatively slow due to the lack of biosignal datasets for machine learning. The VitalDB (Vital Signs DataBase) is an open dataset created specifically to facilitate machine learning studies related to monitoring vital signs in surgical patients. This dataset contains high-resolution multi-parameter data from 6,388 cases, including 486,451 waveform and numeric data tracks of 196 intraoperative monitoring parameters, 73 perioperative clinical parameters, and 34 time-series laboratory result parameters. All data is stored in the public cloud after anonymization. The dataset can be freely accessed and analysed using application programming interfaces and Python library. The VitalDB public dataset is expected to be a valuable resource for biosignal research and development.

System of integrating biosignals during hemodialysis: the CONTINUAL (Continuous mOnitoriNg viTal sIgN dUring hemodiALysis) registry.

BACKGROUND: Appropriate monitoring of intradialytic biosignals is essential to minimize adverse outcomes because intradialytic hypotension and arrhythmia are associated with cardiovascular risk in hemodialysis patients. However, a continuous monitoring system for intradialytic biosignals has not yet been developed. METHODS: This study investigated a cloud system that hosted a prospective, open-source registry to monitor and collect intradialytic biosignals, which was named the CONTINUAL (Continuous mOnitoriNg viTal sIgN dUring hemodiALysis) registry. This registry was based on real-time multimodal data acquisition, such as blood pressure, heart rate, electrocardiogram, and photoplethysmogram results. RESULTS: We analyzed session information from this system for the initial 8 months, including data for some cases with hemodynamic complications such as intradialytic hypotension and arrhythmia. CONCLUSION: This biosignal registry provides valuable data that can be applied to conduct epidemiological surveys on hemodynamic complications during hemodialysis and develop artificial intelligence models that predict biosignal changes which can improve patient outcomes.

Artificial intelligence in perioperative medicine: a narrative review.

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. AI models for perioperative risk stratification, intraoperative event prediction, biosignal analyses, and intensive care medicine have been developed in the field of perioperative medicine. Some of these models have been validated using external datasets and randomized controlled trials. Once these models are implemented in electronic health record systems or software medical devices, they could help anesthesiologists improve clinical outcomes by accurately predicting complications and suggesting optimal treatment strategies in real-time. This review provides an overview of the AI techniques used in perioperative medicine and a summary of the studies that have been published using these techniques. Understanding these techniques will aid in their appropriate application in clinical practice.

Development and Validation of an Arterial Pressure-Based Cardiac Output Algorithm Using a Convolutional Neural Network: Retrospective Study Based on Prospective Registry Data.

BACKGROUND: Arterial pressure-based cardiac output (APCO) is a less invasive method for estimating cardiac output without concerns about complications from the pulmonary artery catheter (PAC). However, inaccuracies of currently available APCO devices have been reported. Improvements to the algorithm by researchers are impossible, as only a subset of the algorithm has been released. OBJECTIVE: In this study, an open-source algorithm was developed and validated using a convolutional neural network and a transfer learning technique. METHODS: A retrospective study was performed using data from a prospective cohort registry of intraoperative bio-signal data from a university hospital. The convolutional neural network model was trained using the arterial pressure waveform as input and the stroke volume (SV) value as the output. The model parameters were pretrained using the SV values from a commercial APCO device (Vigileo or EV1000 with the FloTrac algorithm) and adjusted with a transfer learning technique using SV values from the PAC. The performance of the model was evaluated using absolute error for the PAC on the testing dataset from separate periods. Finally, we compared the performance of the deep learning model and the FloTrac with the SV values from the PAC. RESULTS: A total of 2057 surgical cases (1958 training and 99 testing cases) were used in the registry. In the deep learning model, the absolute errors of SV were 14.5 (SD 13.4) mL (10.2 [SD 8.4] mL in cardiac surgery and 17.4 [SD 15.3] mL in liver transplantation). Compared with FloTrac, the absolute errors of the deep learning model were significantly smaller (16.5 [SD 15.4] and 18.3 [SD 15.1], P<.001). CONCLUSIONS: The deep learning-based APCO algorithm showed better performance than the commercial APCO device. Further improvement of the algorithm developed in this study may be helpful for estimating cardiac output accurately in clinical practice and optimizing high-risk patient care.

Perioperative ABO Blood Group Isoagglutinin Titer and the Risk of Acute Kidney Injury after ABO-Incompatible Living Donor Liver Transplantation.

For ABO-incompatible liver transplantation (ABO-i LT), therapeutic plasma exchange (TPE) is performed preoperatively to reduce the isoagglutinin titer of anti-ABO blood type antibodies. We evaluated whether perioperative high isoagglutinin titer is associated with postoperative risk of acute kidney injury (AKI). In 130 cases of ABO-i LT, we collected immunoglobulin (Ig) G and Ig M isoagglutinin titers of baseline, pre-LT, and postoperative peak values. These values were compared between the patients with and without postoperative AKI. Multivariable logistic regression analysis was used to evaluate the association between perioperative isoagglutinin titers and postoperative AKI. Clinical and graft-related outcomes were compared between high and low baseline and postoperative peak isoagglutinin groups. The incidence of AKI was 42.3%. Preoperative baseline and postoperative peak isoagglutinin titers of both Ig M and Ig G were significantly higher in the patients with AKI than those without AKI. Multivariable logistic regression analysis showed that preoperative baseline and postoperative peak Ig M isoagglutinin titers were significantly associated with the risk of AKI (baseline: odds ratio 1.06, 95% confidence interval 1.02 to 1.09; postoperative peak: odds ratio 1.08, 95% confidence interval 1.04 to 1.13). Cubic spline function curves show a positive relationship between the baseline and postoperative peak isoagglutinin titers and the risk of AKI. Clinical outcomes other than AKI were not significantly different according to the baseline and postoperative peak isoagglutinin titers. Preoperative high initial and postoperative peak Ig M isoagglutinin titers were significantly associated with the development of AKI. As the causal relationship between high isoagglutinin titers and risk of AKI is unclear, the high baseline and postoperative isoagglutinin titers could be used simply as a warning sign for the risk of AKI after liver transplantation.

Coagulopathy-independent, bioinspired hemostatic materials: A full research story from preclinical models to a human clinical trial.

Since the first report of underwater adhesive proteins of marine mussels in 1981, numerous studies have reported mussel-inspired synthetic adhesive polymers. However, none of them have developed up to human-level translational studies. Here, we report a sticky polysaccharide that effectively promotes hemostasis from animal bleeding models to first-in-human hepatectomy. We found that the hemostatic material instantly generates a barrier layer that seals hemorrhaging sites. The barrier is created within a few seconds by in situ interactions with abundant plasma proteins. Therefore, as long as patient blood contains proper levels of plasma proteins, hemostasis should always occur even in coagulopathic conditions. To date, insufficient tools have been developed to arrest coagulopathic bleedings originated from genetic disorders, chronic diseases, or surgical settings such as organ transplantations. Mussel-inspired adhesion chemistry described here provides a useful alternative to the use of fibrin glues up to a human-level biomedical application.

Dextroplantation of Left Liver Graft in Infants.

The position of the left side liver graft is important, and it could lead to complications of the hepatic vein (HV) and portal vein (PV), especially in a small child using a variant left lateral section (vLLS) graft. The purpose of this study was to evaluate the outcome of a novel technique for the implantation of a vLLS graft to the right side (dextroplantation) in infants. For 3 years, 10 consecutive infants underwent dextroplantation using a vLLS graft (group D). The graft was implanted to the right side of the recipient after 90° counterclockwise rotation; the left HV graft was anastomosed to inferior vena cava using the extended right and middle HV stump, and PV was reconstructed using oblique anastomosis without angulation. Surgical outcomes were compared with the historical control group (n = 17, group C) who underwent conventional liver transplantation using a vLLS during infancy. Group D recipients were smaller than group C (body weight <6 kg: 50.0% versus 11.8%; P = 0.03). The rate of graft-to-recipient weight ratio >4% was higher in group D (60.0%) than C (11.8%; P = 0.01). Surgical drains were removed earlier in group D than in group C (15 versus 18 postoperative days [PODs]; P = 0.048). Each group had 1 PV complication (10.0% versus 5.9%); no HV complication occurred in group D, but 3 HV complications (17.6%) occurred in group C (P > 0.05). Hospital stay was shorter in group D than in group C (20 versus 31 PODs; P = 0.02). Dextroplantation of a vLLS graft, even a large-for-size one, was successful in small infants without compromising venous outcomes, compared with conventional vLLS transplantation. We could remove the surgical drains earlier and reduce hospital stays in cases of dextroplantation.

Comparison of bispectral index-guided and fixed-gas concentration techniques in desflurane and remifentanil anesthesia: A randomized controlled trial.

Anesthesia with desflurane and remifentanil can be maintained with either fixed or titrated desflurane concentration. We hypothesized that the fixed-gas concentration (FG) method would reduce the number of anesthetic titrations without hypnotic and hemodynamic instability compared to the bispectral index (BIS)-guided (BG) method. Forty-eight patients were randomly allocated to the FG or BG groups. In the FG group, desflurane vaporizer setting was fixed at 1 age-corrected minimum alveolar concentration (MAC). In the BG group, desflurane was titrated to target a BIS level at 50. Remifentanil was titrated to maintain a systolic arterial pressure (SAP) of 120 mmHg in both groups. Our primary endpoint was the hypnotic stability measured by the wobble of BIS in performance analysis, and the secondary endpoints included the wobble of SAP, mean BIS value during surgery, and the number of anesthetic titrations. The BIS in the FG group showed significantly less wobble (3.9 ± 1.1% vs 5.5 ± 1.5%, P <0.001) but lower value (33 ± 6 vs 46 ± 7, P <0.001) than BG group. The wobble of SAP showed no difference between groups [median (inter-quartile range), 5.0 (4.1-7.5)% vs 5.2 (4.2-8.3)%, P = 0.557]. The numbers of anesthetic titrations in the FG group were significantly lower than the BG group (0 ± 0 vs 8 ± 5, P<0.001 for desflurane, 13 ± 13 vs 22 ± 17, P = 0.047 for remifentanil). Less wobble in BIS and reduced anesthetic titration without hemodynamic instability during the FG technique may be practical in balanced anesthesia using desflurane and remifentanil anesthesia. Clinical trial: This study was registered at ClinicalTrials.gov (NCT02283866).