Multicentre validation of a machine learning model for predicting respiratory failure after noncardiac surgery.

BACKGROUND: Postoperative respiratory failure is a serious complication that could benefit from early accurate identification of high-risk patients. We developed and validated a machine learning model to predict postoperative respiratory failure, defined as prolonged (>48 h) mechanical ventilation or reintubation after surgery. METHODS: Easily extractable electronic health record (EHR) variables that do not require subjective assessment by clinicians were used. From EHR data of 307,333 noncardiac surgical cases, the model, trained with a gradient boosting algorithm, utilised a derivation cohort of 99,025 cases from Seoul National University Hospital (2013-9). External validation was performed using three separate cohorts A-C from different hospitals comprising 208,308 cases. Model performance was assessed by area under the receiver operating characteristic (AUROC) curve and area under the precision-recall curve (AUPRC), a measure of sensitivity and precision at different thresholds. RESULTS: The model included eight variables: serum albumin, age, duration of anaesthesia, serum glucose, prothrombin time, serum creatinine, white blood cell count, and body mass index. Internally, the model achieved an AUROC of 0.912 (95% confidence interval [CI], 0.908-0.915) and AUPRC of 0.113. In external validation cohorts A, B, and C, the model achieved AUROCs of 0.879 (95% CI, 0.876-0.882), 0.872 (95% CI, 0.870-0.874), and 0.931 (95% CI, 0.925-0.936), and AUPRCs of 0.029, 0.083, and 0.124, respectively. CONCLUSIONS: Utilising just eight easily extractable variables, this machine learning model demonstrated excellent discrimination in both internal and external validation for predicting postoperative respiratory failure. The model enables personalised risk stratification and facilitates data-driven clinical decision-making.

Intraoperative Normal Saline Administration and Acute Kidney Injury in Patients Undergoing Liver Transplantation.

BACKGROUND: Normal saline is still used in patients undergoing living donor liver transplantation (LDLT) with normonatremia. We investigated whether the normal saline administered during LDLT is associated with the increased risk of acute kidney injury (AKI) compared with the balanced crystalloids. METHODS: We reviewed 1011 cases undergoing LDLT. The primary exposure variable was normal saline administered intraoperatively compared with the balanced crystalloid. To compare the risk of AKI after adjusting for potential confounders of baseline characteristics and surgical parameters, a propensity score matching analysis was performed. As a sensitivity analysis, ordinal logistic regression analysis was performed for AKI using inverse probability of treatment weighting (IPTW). RESULTS: The incidence of AKI was significantly higher in the saline group (n = 88/174, 50.6%) than in the balanced group (n = 67/174, 38.5%) after matching (P = .010). The incidence of stage 2 or 3 AKI was also significantly higher in the saline group (n = 26/174, 14.9%) than in the balanced group (n = 43/174, 24.7%) after matching (P = .022). The length of hospital stay was significantly longer in the saline group than in the balanced group after matching. Ordinal logistic regression analysis using IPTW showed that the saline group showed a significant association of saline administration with the risk of AKI (odds ratio 1.23, 95% CI 1.05-1.28, P = .013). CONCLUSION: Our propensity score analysis using propensity score matching and IPTW showed that normal saline administration during LDLT is associated with a high risk of postoperative AKI and longer hospital stays. However, our results should be interpreted carefully due to the relatively long period of data collection.

Randomized controlled trial of the effect of general anesthetics on postoperative recovery after minimally invasive nephrectomy.

BACKGROUND: General anesthetic techniques can affect postoperative recovery. We compared the effect of propofol-based total intravenous anesthesia (TIVA) and desflurane anesthesia on postoperative recovery. METHODS: In this randomized trial, 150 patients undergoing robot-assisted or laparoscopic nephrectomy for renal cancer were randomly allocated to either the TIVA or desflurane anesthesia (DES) group. Postoperative recovery was evaluated using the Korean version of the Quality of Recovery-15 questionnaire (QoR-15K) at 24 h, 48 h, and 72 h postoperatively. A generalized estimating equation (GEE) was performed to analyze longitudinal QoR-15K data. Fentanyl consumption, pain severity, postoperative nausea and vomiting, and quality of life three weeks after discharge were also compared. RESULTS: Data were analyzed for 70 patients in each group. The TIVA group showed significantly higher QoR-15K scores at 24 and 48 h postoperatively (24 h: DES, 96 [77, 109] vs. TIVA, 104 [82, 117], median difference 8 [95% CI: 1, 15], P = 0.029; 48 h: 110 [95, 128] vs. 125 [109, 130], median difference 8 [95% CI: 1, 15], P = 0.022), however not at 72 h (P = 0.400). The GEE revealed significant effects of group (adjusted mean difference 6.2, 95% CI: 0.39, 12.1, P = 0.037) and time (P < 0.001) on postoperative QoR-15K scores without group-time interaction (P = 0.051). However, there were no significant differences in other outcomes, except for fentanyl consumption, within the first 24 h postoperatively. CONCLUSIONS: Propofol-based TIVA showed only a transient improvement in postoperative recovery than desflurane anesthesia, without significant differences in other outcomes.

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.

Pulmonary artery catheter monitoring versus arterial waveform-based monitoring during liver transplantation: a retrospective cohort study.

Although pulmonary artery catheter (PAC) has been used during liver transplantation surgery, the usefulness of PAC has rarely been investigated. We evaluated whether the use of PAC is associated with better clinical outcomes compared to arterial waveform-based monitoring after liver transplantation. A total of 1565 cases undergoing liver transplantation were reviewed. We determined whether patients received PAC or not and divided our cohort into the PAC with hemodynamic monitoring using PAC and the non-PAC with arterial waveform-based monitoring using FloTrac-Vigileo. Propensity score matching was performed. Acute kidney injury (AKI), early allograft dysfunction (EAD) and 1-year all-cause mortality or graft failure were compared in the matched cohorts. Logistic regression analysis was performed in the inverse probability of treatment-weighted (IPTW) cohort for postoperative EAD and AKI, respectively. Five-year overall survival was compared between the two groups. In the matched cohort, there was no significant difference in the incidence of AKI, EAD, length of hospital or ICU stay, and 1-year all-cause mortality between the groups. In the IPTW cohort, the use of PAC was not a significant predictor for AKI or EAD (AKI: odds ratio (95% confidence interval) of 1.20 (0.47-1.56), p = 0.229; EAD: 0.99 (0.38-1.14), p = 0.323). There was no significant difference in the survival between groups after propensity score matching (Log-rank test p = 0.578). In conclusion, posttransplant clinical outcomes were not significantly different between the groups with and without PAC. Anesthetic management without the use of PAC may be possible in low-risk patients during liver transplantation. The risk should be carefully assessed by considering MELD scores, ischemic time, surgical history, previous treatment of underlying liver disease, and degree of portal and pulmonary hypertension.Registration: https://clinicaltrials.gov/ct2/show/NCT05457114 (registration date: July 15, 2022).

The effect of goal-directed hemodynamic therapy on clinical outcomes in patients undergoing radical cystectomy: a randomized controlled trial.

BACKGROUND: This study investigated the effects of intraoperative goal-directed hemodynamic therapy (GDHT) on postoperative outcomes in patients undergoing open radical cystectomy. METHODS: This prospective, single-center, randomized controlled trial included 82 patients scheduled for open radical cystectomy between September 2018 and November 2021. The GDHT group (n = 39) received the stroke volume index- and cardiac index-based hemodynamic management using advanced hemodynamic monitoring, while the control group (n = 36) received the standard care under the discretion of attending anesthesiologists during surgery. The primary outcome was the incidence of a composite of in-hospital postoperative complications during hospital stays. RESULTS: A total of 75 patients were included in the final analysis. There was no significant difference in the incidence of in-hospital postoperative complications (28/39 [71.8%] vs. 30/36 [83.3%], risk difference [95% CI], -0.12 [-0.30 to 0.07], P = 0.359) between the groups. The amounts of intraoperative fluid administered were similar between the groups (2700 [2175-3250] vs. 2900 [1950-3700] ml, median difference [95% CI] -200 [-875 to 825], P = 0.714). The secondary outcomes, including the incidence of seven major postoperative complications, duration of hospital stay, duration of intensive care unit stay, and grade of complications, were comparable between the two groups. Trends in postoperative estimated glomerular filtration rate, serum creatinine, and C-reactive protein did not differ significantly between the two groups. CONCLUSIONS: Intraoperative GDHT did not reduce the incidence of postoperative in-hospital complications during the hospital stay in patients who underwent open radical cystectomy. TRIAL REGISTRATION: This study was registered at http://www. CLINICALTRIALS: gov (Registration number: NCT03505112; date of registration: 23/04/2018).

Effect of driving pressure-guided positive end-expiratory pressure on postoperative pulmonary complications in patients undergoing laparoscopic or robotic surgery: a randomised controlled trial.

BACKGROUND: Individualised positive end-expiratory pressure (PEEP) improves respiratory mechanics. However, whether PEEP reduces postoperative pulmonary complications (PPCs) remains unclear. We investigated whether driving pressure-guided PEEP reduces PPCs after laparoscopic/robotic abdominal surgery. METHODS: This single-centre, randomised controlled trial enrolled patients at risk for PPCs undergoing laparoscopic or robotic lower abdominal surgery. The individualised group received driving pressure-guided PEEP, whereas the comparator group received 5 cm H2O fixed PEEP during surgery. Both groups received a tidal volume of 8 ml kg-1 ideal body weight. The primary outcome analysed per protocol was a composite of pulmonary complications (defined by pre-specified clinical and radiological criteria) within 7 postoperative days after surgery. RESULTS: Some 384 patients (median age: 67 yr [inter-quartile range: 61-73]; 66 [18%] female) were randomised. Mean (standard deviation) PEEP in patients randomised to individualised PEEP (n=178) was 13.6 cm H2O (2.1). Individualised PEEP resulted in lower mean driving pressures (14.7 cm H2O [2.6]), compared with 185 patients randomised to standard PEEP (18.4 cm H2O [3.2]; mean difference: -3.7 cm H2O [95% confidence interval (CI): -4.3 to -3.1 cm H2O]; P<0.001). There was no difference in the incidence of pulmonary complications between individualised (25/178 [14.0%]) vs standard PEEP (36/185 [19.5%]; risk ratio [95% CI], 0.72 [0.45-1.15]; P=0.215). Pulmonary complications as a result of desaturation were less frequent in patients randomised to individualised PEEP (8/178 [4.5%], compared with standard PEEP (30/185 [16.2%], risk ratio [95% CI], 0.28 [0.13-0.59]; P=0.001). CONCLUSIONS: Driving pressure-guided PEEP did not decrease the incidence of pulmonary complications within 7 days of laparoscopic or robotic lower abdominal surgery, although uncertainty remains given the lower than anticipated event rate for the primary outcome. CLINICAL TRIAL REGISTRATION: KCT0004888 (http://cris.nih.go.kr, registration date: April 6, 2020).

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.

Development and validation of a reinforcement learning model for ventilation control during emergence from general anesthesia.

Ventilation should be assisted without asynchrony or cardiorespiratory instability during anesthesia emergence until sufficient spontaneous ventilation is recovered. In this multicenter cohort study, we develop and validate a reinforcement learning-based Artificial Intelligence model for Ventilation control during Emergence (AIVE) from general anesthesia. Ventilatory and hemodynamic parameters from 14,306 surgical cases at an academic hospital between 2016 and 2019 are used for training and internal testing of the model. The model's performance is also evaluated on the external validation cohort, which includes 406 cases from another academic hospital in 2022. The estimated reward of the model's policy is higher than that of the clinicians' policy in the internal (0.185, the 95% lower bound for best AIVE policy vs. -0.406, the 95% upper bound for clinicians' policy) and external validation (0.506, the 95% lower bound for best AIVE policy vs. 0.154, the 95% upper bound for clinicians' policy). Cardiorespiratory instability is minimized as the clinicians' ventilation matches the model's ventilation. Regarding feature importance, airway pressure is the most critical factor for ventilation control. In conclusion, the AIVE model achieves higher estimated rewards with fewer complications than clinicians' ventilation control policy during anesthesia emergence.

Autonomic responses during bladder hydrodistention under general versus spinal anaesthesia in patients with interstitial cystitis/bladder pain syndrome: a randomized clinical trial.

Blocking the abrupt increase in systolic blood pressure associated with autonomic response during bladder hydrodistention in patients with interstitial cystitis/bladder pain syndrome (IC/BPS) is essential for patient safety. We conducted this study to compare autonomic responses during bladder hydrodistention in patients with IC/BPS under general and spinal anaesthesia. Thirty-six patients were randomly allocated to a general anaesthesia (GA, n = 18) or a spinal anaesthesia (SA, n = 18) group. Blood pressure and heart rate were measured continuously and ΔSBP, defined as maximum increases in SBP during bladder hydrodistention from baseline, was compared between groups. Heart rate variability was analysed using electrocardiograms. The post-anaesthesia care unit assessed postoperative pain using a numeric (0-10) rating scale. Our analyses yield a significantly greater ΔSBP (73.0 [26.0-86.1] vs. 2.0 [- 4.0 to 6.0] mmHg), a significantly lower root-mean-square of successive differences in heart rate variability after bladder hydrodistention (10.8 [7.7-19.8] vs. 20.6 [15.1-44.7] ms), and significantly higher postoperative pain scores (3.5 [0.0-5.5] vs. 0.0 [0.0-0.0]) in the GA compared to the SA group. These findings suggest that SA has advantages over GA for bladder hydrodistention in preventing an abrupt increase in SBP and postoperative pain in IC/BPS patients.

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.

Association of the perfusion index with postoperative acute kidney injury: a retrospective study.

BACKGROUND: Many studies have examined the risk factors for postoperative acute kidney injury (AKI), but few have focused on intraoperative peripheral perfusion index (PPI) that has recently been shown to be associated with postoperative morbidity and mortality. Therefore, this study aimed to evaluate the relationship between intraoperative PPI and postoperative AKI under the hypothesis that lower intraoperative PPI is associated with AKI occurrence. METHODS: We retrospectively searched electronic medical records to identify patients who underwent surgery at the general surgery department from May 2021 to November 2021. Patient baseline characteristics, pre- and post-operative laboratory test results, comorbidities, intraoperative vital signs, and discharge profiles were obtained from the Institutional Clinical Data Warehouse and VitalDB. Intraoperative PPI was the primary exposure variable, and the primary outcome was postoperative AKI. RESULTS: Overall, 2,554 patients were identified and 1,586 patients were included in our analysis. According to Kidney Disease Improving Global Outcomes (KDIGO) criteria, postoperative AKI occurred in 123 (7.8%) patients. We found that risks of postoperative AKI increased (odds ratio: 2.00, 95% CI [1.16, 3.44], P = 0.012) when PPI was less than 0.5 for more than 10% of surgery time. Other risk factors for AKI occurrence were male sex, older age, higher American Society of Anesthesiologists physical status, obesity, underlying renal disease, prolonged operation time, transfusion, and emergent operation. CONCLUSIONS: Low intraoperative PPI was independently associated with postoperative AKI.

Relationships between common carotid artery blood flow and anesthesia, pneumoperitoneum, and head-down tilt position: a linear mixed-effect analysis.

This study investigated the effects of pneumoperitoneum and the head-down tilt position on common carotid artery (CCA) blood flow in surgical patients. METHODS: This prospective observational study included 20 patients who underwent gynecological surgery. CCA blood flow was measured using Doppler ultrasound at four-time points: awake in the supine position [T1], 3 min after anesthesia induction in the supine position [T2], 3 min after pneumoperitoneum in the supine position [T3], and 3 min after pneumoperitoneum in the head-down tilt position [T4]. Hemodynamic and respiratory parameters were also recorded at each time point. Linear mixed-effect analyses were performed to compare CCA blood flow across the time points and assess its relationship with hemodynamic parameters. RESULTS: Compared with T1, CCA blood flow decreased significantly at T2 (345.4 [288.0-392.9] vs. 293.1 [253.0-342.6], P = 0.048). CCA blood flow were also significantly lower at T3 and T4 compared with T1 (345.4 [288.0-392.9] vs. 283.6 [258.8-307.6] and 287.1 [242.1-321.4], P = 0.005 and 0.016, respectively). CCA blood flow at T3 and T4 did not significantly differ from that at T2. Changes in CCA blood flow were significantly associated with changes in cardiac index and stroke volume index (P = 0.011 and 0.024, respectively). CONCLUSION: CCA blood flow was significantly decreased by anesthesia induction. Inducing pneumoperitoneum, with or without the head-down tilt position, did not further decrease CCA blood flow if the cardiac index remained unchanged. The cardiac index and stroke volume index were significantly associated with CCA blood flow. CLINICAL TRIAL REGISTRATION: Clinicaltrials.gov (NCT04233177, January 18, 2020).

Transverse abdominis plane block compared with patient-controlled epidural analgesia following abdominal surgery: a meta-analysis and trial sequential analysis.

Thoracic epidural analgesia (TEA) and transversus abdominis plane (TAP) block are used for pain control after abdominal surgery. Although there have been several meta-analyses comparing these two techniques, the conclusion was limited by a small number of studies and heterogeneity among studies. Our meta-analysis used the Medline, EMBASE, and Cochrane central library databases from their inception through September 2022. Randomized controlled trials (RCTs) comparing TEA and TAP block were included. The pre-specified primary outcome was the pain score at rest at 12 h postoperatively. Twenty-two RCTs involving 1975 patients were included. Pooled analyses showed the pain score at rest at 12 h postoperatively was significantly different between groups favoring TEA group (Mean difference [MD] 0.58, 95% confidence interval CI - 0.01, 1.15, P = 0.04, I2 = 94%). TEA group significantly reduced the pain score at 48 h at rest (MD 0.59, 95% CI 0.15, 1.03, P = 0.009, I2 = 86%) and at 48 h at movement (MD 0.53, 95% CI 0.07, 0.99, P = 0.03, I2 = 76%). However, there was no significant difference at other time points. Time to ambulation was shorter in TAP block but the incidence of hypotension at 24 h and 72 h was significantly lower in TAP block compared to TEA. Trial sequential analysis showed that the required information size has not yet been reached. Our meta-analysis demonstrated there was no significant or clinically meaningful difference in the postoperative pain scores between TEA and TAP block group. Given the insufficient information size revealed by TSA, the high risk of bias of our included studies, and the significant heterogeneity of our meta-analysis results, our results should be interpreted carefully but it is not likely that the addition of further studies could prove any clinically meaningful difference in pain score between these two techniques.

Impact of hemodynamic instability during cytoreductive surgery on survival in high-grade serous ovarian carcinoma.

BACKGROUND: To evaluate the impact of intraoperative hypotension and hemodynamic instability on survival outcomes in patients with high-grade serous ovarian carcinoma (HGSOC). METHODS: We retrospectively identified patients with HGSOC, who underwent primary or interval debulking surgery between August 2013 and December 2019. We collected anesthesia-related variables, including the arterial blood pressure measurements (at 1-min intervals) during the surgery of patients. The cumulative duration of mean arterial blood pressure (MAP) readings under 65 mmHg and two performance measurements (median performance error [MDPE] and wobble) were calculated. We investigated associations between the factors indicating hemodynamic instability and prognosis. RESULTS: In total, 338 patients were included. Based on the cumulative duration of MAP under 65 mmHg, we divided patients into two groups: ≥30 min and <30 min. The progression-free survival (PFS) was worse in the ≥30 min group (n = 107) than the <30 min group (n = 231) (median, 18.2 vs. 23.7 months; P = 0.014). In multivariate analysis adjusting for confounders, a duration of ≥30 min of MAP under 65 mmHg was identified as an independent poor prognostic factor for PFS (adjusted HR, 1.376; 95% CI, 1.035-1.830; P = 0.028). Shorter PFS was observed in the group with a MDPE <-4.0% (adjusted HR, 1.351; 95% CI, 1.024-1.783; P = 0.033) and a wobble ≥7.5% (adjusted HR, 1.445; 95% CI, 1.100-1.899; P = 0.008). However, no differences were observed in overall survival. CONCLUSION: This study suggests that the three intraoperative variables for hemodynamic instability, cumulative duration of MAP <65 mmHg, MDPE, and wobble, might be novel prognostic biomarkers for disease recurrence in patients with HGSOC.

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.

Radiographic Predictors of Difficult McGrath MAC Videolaryngoscopy in Patient Undergoing Cervical Spine Surgery.

BACKGROUND: McGrath MAC videolaryngoscopy is a useful technique for successful intubation in cervical spine-injured patients with manual in-line stabilization of the neck during intubation. We aimed to identify radiographic predictors of difficult McGrath MAC videolaryngoscopy in patient undergoing cervical spine surgery. METHODS: Patients undergoing cervical spine surgery who were intubated with a McGrath MAC videolaryngoscope under manual in-line stabilization of the neck between June 2016 and August 2018 were included in this study. Data on airway-related variables and radiographic indices obtained from preoperative lateral cervical spine x-ray, magnetic resonance imaging, and computed tomography (CT) scans were retrospectively collected. Patients were divided into difficult and easy McGrath MAC videolaryngoscopic intubation groups on the basis of intubation time and the number of intubation attempts. RESULTS: In total, 183 patients were included in the study of which 33 (18%) showed difficult videolaryngoscopic intubation. In multivariate logistic regression analysis, atlanto-occipital distance (odds ratio [OR], 0.74; 95% confidence interval [CI], 0.62-0.89; P=0.001) on lateral cervical spine x-ray, incisor-C1-C6 angle in neck extension on lateral cervical spine x-ray (OR, 1.12; 95% CI, 1.02-1.22; P=0.015), tongue area/oral cavity area ratio in the mid-sagittal plane of cervical magnetic resonance imaging or computed tomography (OR, 1.12; 95% CI, 1.05-1.19; P<0.001), and interincisor gap (OR, 0.92; 95% CI, 0.86-0.98; P=0.015) were independent risk factors for difficult videolaryngoscopic intubation. CONCLUSIONS: Radiographic variables indicating enlarged tongue relative to the oral cavity and limited neck extension were associated with difficult McGrath MAC videolaryngoscopy in patients undergoing cervical spine surgery with manual in-line cervical stabilization during intubation.

Intraarterial catheter diameter and dynamic response of arterial pressure monitoring system: a randomized controlled trial.

The dynamic response (DR) of the arterial pressure monitoring system (APMS) may depend on the intraarterial catheter (IAC) diameter. We hypothesized that adequate DR would be more common when using a smaller IAC. We compared the DR of the AMPS (Auto Transducer™) between three IACs (BD Angiocath Plus™) with different diameters. 353 neurosurgical patients were randomized into three groups undergoing catheterization with a 20-, 22-, or 24-gauge IAC: 20G (n = 119), 22G (n = 117), and 24G (n = 117) groups, respectively. The DR, which depends on the natural frequency and damping coefficient, was divided into four types: adequate (primary outcome measure), underdamped, overdamped, and unacceptable. The frequency of intraoperative IAC malfunction was noted. Adequate DR was observed more frequently in the 22G and 24G groups than the 20G group (13.7% and 15.4% vs. 4.2%, P = 0.011 and 0.004, respectively). The frequency of underdamped DR was higher in the 20G group than the 24G group (86.6% vs. 69.2%, P = 0.001), whereas overdamped DR was more frequent in the 24G group than the 20G and 22G groups (6.0% vs. 0.0% and 0.0%, P = 0.007 and 0.014, respectively). IAC malfunctioned more frequently during surgery in the 24G group than the 20G and 22G groups (15.4% vs. 0.0% and 1.7%, P < 0.001 and P < 0.001, respectively). The frequency of adequate DR was low regardless of the IAC diameter. Nonetheless, in terms of DR and IAC malfunction, a 22-gauge BD Angiocath Plus™ was more suitable for invasive blood pressure monitoring with Auto Transducer™ than a 20- or 24-gauge BD Angiocath Plus™. Registration Registry: ClinicalTrials.gov. Registration number: NCT03642756. Date of Registration: July 27, 2018.

Effects of External Laryngeal Manipulation on Cervical Spine Motion during Videolaryngoscopic Intubation under Manual In-Line Stabilization: A Randomized Crossover Trial.

We hypothesized that external laryngeal manipulation would reduce cervical spine motion during video laryngoscopic intubation under manual in-line stabilization by reducing the force required to lift the videolaryngoscope. In this randomized crossover trial, 27 neurointerventional patients underwent two consecutive videolaryngoscopic intubation attempts under manual in-line stabilization. External laryngeal manipulation was applied to all patients in either the first or second attempt. In the second attempt, we tried to reproduce the percentage of glottic opening score obtained in the first attempt. Primary outcomes were cervical spine motion during intubation at the occiput-C1, C1-C2, and C2-C5 segments. The intubation success rate (secondary outcome measure) was recorded. Cervical spine motion during intubation at the occiput-C1 segment was significantly smaller with than without external laryngeal manipulation (7.4° ± 4.6° vs. 11.5° ± 4.8°, mean difference -4.1° (98.33% confidence interval -5.8° to -2.3°), p < 0.001), showing a reduction of 35.7%. Cervical spine motion during intubation at the other segments was not significantly different with versus without external laryngeal manipulation. All intubations were achieved successfully regardless of the application of external laryngeal manipulation. External laryngeal manipulation is a useful method to reduce upper cervical spine motion during videolaryngoscopic intubation under manual in-line stabilization.