Perioperative anaesthetic complications are a major public health concern, as they are associated with increased mortality, prolonged hospital stay, higher healthcare costs, and compromised patient safety. Despite advances in perioperative monitoring and risk stratification, early and personalised identification of patients at risk remains limited. Artificial intelligence (AI) has emerged as a promising approach to improve prediction of perioperative anaesthetic complications, although current evidence is heterogeneous. To synthesise the available evidence on the use of artificial intelligence models to predict perioperative anaesthetic complications in adult surgical patients. A scoping review was conducted following Joanna Briggs Institute methodology and reported according to PRISMA-ScR guidelines. The protocol was registered in the Open Science Framework (DOI: https://doi.org/10.17605/OSF.IO/QU6WY ). PubMed, Scopus, and Web of Science were searched for studies published between 2015 and 2025. Studies applying machine learning, deep learning, or hybrid models to predict perioperative anaesthetic complications were included. Evidence was synthesised using conceptual mapping and thematic analysis. Fifty-one studies were included. Haemodynamic and cardiovascular outcomes, particularly intraoperative hypotension, were most frequently studied, followed by renal, neurological, and respiratory complications, postoperative pain, and perioperative resource utilisation. Most models showed moderate to high predictive performance, while external validation and evaluation of clinical impact were uncommon. Artificial intelligence has substantial potential to support prediction of perioperative anaesthetic complications. However, clinical implementation is limited by methodological weaknesses, including predominantly retrospective designs, limited external validation, and scarce assessment of real-world impact. Prospective multicentre studies are required.

To determine whether the subcutaneous compartment retains an interpretable glucose signal during extreme perioperative perfusion stress and whether agreement with arterial glucose differs by anatomical site. In this prospective mechanistic observational study, 20 adults undergoing pulmonary endarterectomy with deep hypothermic circulatory arrest underwent subcutaneous microdialysis at upper thoracic and periumbilical sites. Recovery-corrected interstitial glucose was converted to calibrated subcutaneous glucose using one-point calibration. Agreement with arterial glucose was evaluated using absolute relative difference (ARD) and repeated-measures Bland-Altman analysis. Exploratory mixed-effects models examined associations of ARD with procedural phase and treatment-related variables. We analysed 743 paired measurements. Overall median ARD was 12.9% (IQR 5.9-21.9), and mean ARD was 17.2% (SD 17.2). The procedural phase was associated with ARD (global P < 0.001), with the greatest discordance during rewarming and early postoperative recovery rather than during the DHCA interval. Agreement was numerically more favourable at the upper thoracic site; however, this between-site difference did not reach statistical significance in the phase-adjusted analysis (P = 0.053). Under recovery-corrected and one-point-calibrated conditions, subcutaneous glucose retained interpretable tracking of arterial glucose during extreme perioperative perfusion stress. These findings argue against a uniform loss of subcutaneous glucose information in this setting and suggest that discordance is phase-dependent and may vary by anatomical site.

To evaluate whether jugular venous NIRS (rSjvO2) and baseline-calibrated cerebral NIRS (cal-rScO2) can serve as surrogates for mixed venous oxygen saturation (SvO2), and whether these inputs can support continuous cardiac output (CO) estimation during off-pump coronary artery bypass grafting (OPCAB). In this prospective observational study, 25 adults undergoing elective OPCAB were enrolled at a single tertiary center. NIRS sensors were placed over the left internal jugular vein (IJV) under ultrasound guidance and over the bilateral forehead. Pulmonary artery catheter measurements served as the reference for SvO2 and thermodilution CO (COTD). Agreement was assessed using Bland-Altman analysis with linear mixed-effects modeling, and trending ability by error grid analysis. CO was estimated using a previously derived modified Fick equation. rSjvO2 showed modest bias versus SvO2 (2.0%) but wide limits of agreement (LoA, - 14.9 to 18.9%). Accuracy varied with jugular anatomy, with the lowest error at an IJV depth of 1.38 cm. Cal-rScO2 showed better agreement (bias 0.8%; LoA, - 7.8 to 9.4%), excellent discrimination for SvO2 <65% (AUC, 0.970), and good trending ability. In contrast, NIRS-based CO estimation showed significant proportional bias, 33.0% percentage error (95% CI, 27.4 to 41.5%), and poor trending ability. Cal-rScO2 appears to be a useful surrogate for SvO2 trending during OPCAB after simple one-point calibration. Jugular NIRS may be useful in selected patients, whereas NIRS-based CO estimation remained clinically insufficient.Trial registration: Clinical Research Information Service (CRIS), Republic of Korea (KCT0007918 November 18, 2022).

To investigate the relationship between hemoglobin concentration and peripheral perfusion index (PI) in normovolemic, hemodynamically stable patients. This prospective observational study included 90 adult emergency department patients, classified as anemic (n = 45) and non-anemic (n = 45) according to World Health Organization criteria. PI was measured using standardized pulse oximetry conditions. Group comparisons were performed using appropriate statistical tests. The association between hemoglobin and PI was evaluated using Spearman correlation. A multivariable linear regression model with log-transformed PI was used to identify independent predictors, adjusting for clinically relevant variables. Model assumptions and influential observations were assessed. PI values were significantly lower in anemic patients compared with non-anemic patients (median 2.1 vs. 3.5, p < 0.001). Hemoglobin concentration showed a moderate positive correlation with PI (r = 0.425, p < 0.001). In multivariable analysis, hemoglobin remained independently associated with PI (β = 0.306, p = 0.021). The model demonstrated modest explanatory power (adjusted R[2]=0.069). Sensitivity analysis excluding influential observations yielded consistent findings. Hemoglobin level is independently associated with PI in normovolemic patients. Although PI primarily reflects flow-related peripheral perfusion, hemoglobin contributes to its variability. These findings suggest that anemia and peripheral perfusion are interrelated but distinct physiological parameters that should be considered together in clinical interpretation.

Advanced haemodynamic monitoring of cardiac index is restricted to selected high-risk cases, leaving most patients undergoing major surgery without real-time assessment. We aimed to develop and internally validate a simplified bedside score for continuous, minute-by-minute screening of low cardiac index using routinely available parameters. Retrospective single-centre study of adults undergoing major abdominal surgery with advanced haemodynamic monitoring (January 2023 to February 2026). Low cardiac index was defined as pulse contour cardiac index < 2.2 l.min[- 1].m[- 2]. The dataset was split 80/20 at the patient level. Twelve candidate features were ranked using SHapley Additive exPlanations (SHAP) values; the top five were used to fit a generalised linear mixed model, yielding the integer-weighted Low Cardiac Index (LCI) score. A rule-out threshold (sensitivity ≥ 0.90) was selected, and test-set performance was evaluated with patient-level cluster bootstrap. The analysis cohort comprised 136 patients and 42,346 timepoints (15.5% low cardiac index prevalence). The derived formula was LCI score = 57 + (2 × DBP) + (0.5 × Age) + PPV - HR - SBP. At a threshold of ≥ 30, the score achieved an area under the receiver operating characteristic curve of 0.84 (95% confidence interval 0.75, 0.91), sensitivity 0.92 (0.80, 0.99), and negative predictive value 0.97 (0.92, 1.00). Performance was stable across 20 random splits and outperformed individual haemodynamic parameters. The LCI score is a simple bedside rule-out tool for low cardiac index, with a score below 30 yielding a negative predictive value of 0.97. External validation and prospective assessment of clinical impact are warranted.

Arterial pressure waveform analysis has been used to assess hemodynamic status, however, investigations focusing on waveform morphology remain limited. In this study, we examined changes in selected morphological features of the arterial pressure waveform following volume loading versus vasopressor administration in critically ill patients. In this retrospective observational study, we analyzed adult patients admitted to an intensive care unit between April 2022 and June 2023. Participants were included if they exhibited increased mean arterial pressure (MAP) following either blood return during hemodiafiltration discontinuation (Volume group) or intravenous phenylephrine administration (Pressor group). Arterial waveforms were extracted from one minute before to four minutes after the intervention. We compared 21 waveform-derived features and their normalized parameters at peak MAP with baseline values. Pre- and post-intervention differences for each parameter were assessed using the Wilcoxon matched-pairs signed-rank test. The Volume group comprised 26 patients, and the Pressor group included 20 patients. Systolic angle, systolic dP/dt, and systolic area under the curve (AUC) increased in both groups following intervention. After pulse-pressure normalization, however, systolic AUC increased significantly in the Volume group (median paired difference 4.6 [-0.3-10.2] ms, 95% CI 1.9 to 7.9, P = 0.0038) but not in the Pressor group. This elevation in systolic AUC occurred mainly during the systolic descending phase (4.4 [1.1-9.5] ms, 95% CI 2.7 to 9.1, P = 0.00021). The systolic descending duration exhibited a significant prolongation in the Volume group, whereas no significant change was observed in the Pressor group. Arterial waveform morphology exhibited different patterns of change following blood return versus phenylephrine administration, particularly in the systolic descending phase. Waveform morphology analysis may provide complementary physiological information for monitoring the mechanisms underlying hemodynamic changes.

Recruitment maneuvers (RM) can improve oxygenation in patients with acute respiratory distress syndrome (ARDS), but their physiological effects depend on lung recruitability. This secondary analysis of a randomized controlled trial (RCT) evaluated oxygenation, respiratory mechanics, regional ventilation, and cardiorespiratory adverse events responses to a RM followed by electrical impedance tomography (EIT)-guided PEEP titration, using EIT to assess lung recruitability. In this study, fifty patients with moderate-to-severe ARDS underwent a stepwise RM followed by individualized PEEP titration guided by EIT. Lung recruitability was determined using the collapse index at PEEP 6 cmH2O (CLPEEP6), defined as the proportion of collapsed lung at this PEEP level. Patients were classified into high- and low-recruitability groups based on median CLPEEP6 values. Oxygenation (PaO2/FiO2), static compliance (Cstat), driving pressure (Pdriv), regional ventilation distribution, and cardiorespiratory adverse events were compared before and after RM, during subsequent individualized EIT-guided PEEP titration. In patients with high recruitability (CLPEEP6 > 12.5), the PaO2/FiO2 ratio and Cstat increased significantly after RM (PaO2/FiO2: 100.8 ± 30.3 vs. 125.4 ± 38.3 mmHg, p < 0.05; Cstat: 21.5 ± 5.8 vs. 28.0 ± 7.0 mL/cmH2O, p < 0.001), Pdriv decreased (19.1 ± 3.5 vs. 15.6 ± 3.2 cmH2O, p < 0.001). EIT demonstrated a posterior redistribution of ventilation after RM. In contrast, patients with low recruitability (CLPEEP6 ≤ 12.5) showed no significant mechanical or oxygenation improvement and transient hypotension, arrhythmia, and desaturation appeared numerically more common in this group. No barotrauma or cardiac arrest occurred, and ICU mortality was similar between groups. A strategy combining a RM with subsequent individualized EIT-guided PEEP titration was associated with improved oxygenation and lung mechanics in patients with high lung recruitability, whereas patients with low recruitability showed limited physiological benefit, with cardiorespiratory adverse events appearing numerically more frequent. The EIT-derived CLPEEP6 index represents a feasible and clinically applicable https://clinicaltrials.gov/study/NCT06733168.

Early detection of systemic inflammation and sepsis is essential for improving patient outcomes. Heart rate variability (HRV) has been proposed as a non-invasive marker of inflammation; however, its specificity is limited, particularly under anesthesia or sedation. This study introduces the Trend of Sepsis and Inflammation (TSI), a novel index combining HRV and electroencephalogram (EEG)-derived parameters to better isolate inflammation-related autonomic changes.A post-hoc observational analysis was conducted in two cohorts: surgical patients undergoing general anesthesia (N = 41) and septic patients admitted to the intensive care unit (N = 21). Continuous EEG and ECG recordings were obtained using a multimodal monitoring system. HRV parameters from time and frequency domains, together with an EEG-derived Brain Activity Index, were integrated using an Adaptive Neuro-Fuzzy Inference System (ANFIS) to compute the TSI. TSI values were compared across three conditions: awake baseline, post-surgical inflammation, and sepsis. Statistical analysis employed non-parametric tests, while discriminative performance was assessed using prediction probability (Pk) and concordance with predefined interpretation ranges.TSI values increased progressively across conditions. Median values were 2.29 (IQR: 0.00-13.74) at baseline, 24.68 (18.50-32.00) post-surgery, and 65.59 (52.38-76.25) in sepsis, with significant differences (p < 0.0001). The TSI demonstrated strong discriminative ability (Pk = 93.58%) and high overall concordance (92.6%). HRV spectrograms and EEG-compensated analyses supported physiological consistency.The TSI distinguishes between baseline, post-surgical inflammatory, and septic states. By compensating for anesthesia-related autonomic suppression, it provides a continuous, non-invasive measure of inflammatory burden, supporting its potential use in perioperative and critical care settings. Further validation against established biomarkers is warranted.

We developed machine learning (ML) models to perform continuous hourly prediction of arterial blood gas (ABG) and basic metabolic panel (BMP) laboratory values in critically ill patients. We evaluated its impact on prediction of the need for renal replacement therapy (RRT). We compared the performance of the deep learning models using laboratory variables imputed hourly by our ML estimators versus models using laboratory variables imputed by a previous-value baseline. Our ML model incorporated various predictors, including previous laboratory values, administered medications, clinical events, fluid input/output, hemodynamics, and ventilator settings. Accuracy of laboratory imputations were compared using mean absolute error (MAE) and root mean squared error (RMSE). We trained bi-directional long short-term memory models (Bi-LSTM) to predict need for renal replacement therapy (RRT) that differed only in how laboratory variables were imputed over time. We compared performance using area under the receiver operating characteristics curve (AUROC) and area under the precision-recall curve (AUPRC). XGBoost achieved an average error reduction of 33% in MAE and 32% in RMSE across ABG variables, and 19% and 21% across BMP variables, respectively. Bi-LSTM models using our ML-based hourly laboratory estimates (AUROC 0.951, 95% CI 0.942-0.960; AUPRC 0.419, 95% CI 0.375-0.465) outperformed models using previous-value laboratory imputation (AUROC 0.923, 95% CI 0.910-0.935; AUPRC 0.343, 95% CI 0.301-0.386). Our real-time imputation models led to significant error reduction of most ABG and BMP targets, improving deep learning model performance for the need of RRT.

Maintaining mean arterial pressure (MAP) within a predefined target is central to haemodynamic management in surgical and critically ill adults receiving vasopressors. Closed-loop vasopressor (CLV) systems automate titration to optimise blood pressure control, but their clinical effectiveness remains uncertain. We performed a systematic review and meta-analysis comparing CLV with manual titration. This PRISMA 2020-compliant review was prospectively registered in PROSPERO (CRD420250655697). MEDLINE, Embase, Scopus, Web of Science, CENTRAL, and the Cochrane Library were searched (January 2000-June 2025). Randomised controlled trials enrolling adults receiving vasopressors in perioperative or intensive care settings were included. Primary outcomes were time within the MAP target range and time spent in hypotension or hypertension. Risk of bias was assessed using RoB 2.0 and certainty of evidence using GRADE. Random- or fixed-effects models were selected according to heterogeneity. Six randomized controlled trials (215 patients) were included in the systematic review, whereas five perioperative trials contributed to the meta-analysis of haemodynamic control outcomes, and one ICU-based study was summarized narratively because it did not report comparable MAP control endpoints. CLV increased time within the MAP target range (mean difference [MD] 33.94%, 95% CI 20.41-47.46; I[2] = 77%) and reduced time in hypotension (MD - 18.24%, 95% CI - 28.95 to - 7.53; I[2] = 73%). There was no significant difference in time in hypertension, cumulative norepinephrine dose, or major/minor adverse events. ICU length of stay was not pooled because of clinical and methodological heterogeneity. Certainty of evidence ranged from low to high (moderate for haemodynamic control outcomes). CLV systems improved haemodynamic control, primarily in perioperative settings, but heterogeneity and small samples limit confidence in effect size and generalisability. Evidence in critically ill populations remains limited, and larger trials are needed to determine whether improvements in these physiological surrogate endpoints translate into meaningful patient-centred outcomes.

We investigated whether pre-induction High Frequency Variability Index (HFVI)/Analgesia Nociception Index (ANI) and Nociception Level (NOL) values could predict hypotension during general anesthesia induction in older patients. This prospective observational study included patients aged ≥ 65 years undergoing elective surgery under general anesthesia. After recording HFVI/ANI and NOL values, remifentanil was administered at 0.2 µg/kg/min for 2 min, followed by a rapid intravenous bolus administration of propofol at 2 mg/kg. Noninvasive blood pressure was measured at 1-min intervals over 5 min. Hypotension was defined as mean arterial pressure (MAP) < 65 mmHg. Predictive performance was evaluated using receiver operating characteristic (ROC) curves. Additionally, the area under MAP < 65 mmHg (AUT-65), a continuous metric integrating the depth and duration of hypotension, was calculated and correlated with nociception index values. We analyzed 51 patients (19 men; 22 in the hypotension group and 29 in the nonhypotension group). The hypotension group demonstrated lower HFVI/ANIi values (58.7 ± 11.1 vs. 69.0 ± 15.1, p = 0.010) and higher NOL values (17.2 ± 9.1 vs. 10.7 ± 8.8, p = 0.013). HFVI/ANIi (AUC = 0.72, cutoff = 62.5) and NOL (AUC = 0.71, cutoff = 13.5) moderately predicted hypotension. AUT-65 was significantly correlated with HFVI/ANIi (Spearman rho = - 0.35, p = 0.013) and NOL (rho = 0.47, p = 0.0005). Pre-induction HFVI/ANI and NOL were associated with the occurrence and cumulative burden of post-induction hypotension in patients aged ≥ 65 years, suggesting their potential utility as pre-induction screening tools.Trial registration This study was approved by the Ethics Committee of Yamagata University Hospital on January 18, 2024 (approval number 2023 - 280). Before commencement, the study was registered as a prospective observational study in the UMIN Clinical Trials Registry (UMIN000053529).

Continuous vital sign monitoring (CVSM) is superior to intermittent manual vital sign assessment in detecting deviations, but alert thresholds have limited evidence, as a strong definition of physiologically normal variations are lacking. Consequences of too few alerts are missed detections of oncoming complications, and too many alerts result in over-alerting and over-treatment. This study aimed to describe duration and deviation of vital signs in postoperative patients without complications when monitored continuously. Adult patients admitted to the general ward after major surgery were included. Continuous wireless vital sign monitoring (CVSM) was performed during the early postoperative period, with data collection blinded to ward nurses. For peripheral oxygen saturation (SpO2), systolic blood pressure, heart rate, and respiratory rate, the longest consecutive durations outside predefined thresholds were identified. The primary outcome was the longest consecutive duration of SpO2 < 88%. A total of 600 patients were analyzed and of these, 277 patients had no complications of any kind. The longest sustained episodes with SpO2 < 88% were median 9 min [IQR 2-31 min]. The maximum length of other vital sign sustained deviations had the following median duration in minutes: SpO2 < 92%: 58[6 -129], HR > 110/min: 3 [0-13], HR < 50/min: 0 [0-1], RF > 24/min: 1 [0-4] and RF < 11/min: 4 [2-12]. Sustained episodes of severe desaturations, tachycardia and tachypnea were short, but moderate desaturations frequent. These findings indicate that vital signs in complication free patients should be carefully analyzed when monitored continuously after major surgery.

The framework of fluid responsiveness addresses only whether volume expansion will augment cardiac output, not whether the circulation can accept that volume without producing congestive organ injury. The complementary concept of fluid tolerance has accumulated empirical support over recent years and is integral to understanding patients' fluid status. This narrative review synthesises the physiological basis of fluid responsiveness and fluid tolerance, describes the bedside monitoring tools available to assess each, and considers the clinical implications of their joint interpretation in critical care. We performed a literature search restricted to articles published between 2020 and the date of the search. The retrieved abstracts were evaluated for relevance, and their reference lists were subsequently screened to identify additional pertinent publications. Fluid responsiveness and fluid tolerance are dissociable but physiologically interdependent, sharing determinants such as biventricular function, stressed volume and venous capacitance. Dynamic tests remain the preferred approach for assessing preload responsiveness; each has specific applicability conditions, and many require continuous or rapidly repeated cardiac output monitoring. Emerging tools have been developed to assess fluid tolerance, primarily based on vascular sonography; their interpretation requires concurrent assessment of biventricular function and further validation. Reframing fluid stewardship around the interaction between responsiveness and tolerance shifts the focus from forward-flow alone to net physiological benefit. No single parameter or device fully captures fluid status. An integrated, serial, multi-parametric assessment supported by appropriate monitoring platforms is therefore preferable to reliance on any single measure. At present, these tools support fluid stewardship rather than representing interventions with independently proven survival benefit. Future priorities include defining organ-specific congestion thresholds and testing whether monitoring-informed protocols improve outcomes.