Search

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 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.

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.

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

The widespread use of remifentanil during total intravenous anesthesia (TIVA) has raised concerns about the risk of postoperative remifentanil-associated pain. Although a recent meta-analysis suggests that remifentanil-associated pain is unlikely to occur in patients with TIVA because of the protective effect of co-administered propofol, the evidence is not conclusive. We retrospectively assessed 635 patients who received robotic thyroid surgery under TIVA to evaluate the risk of remifentanil-associated pain. Postoperative pain was evaluated using 11-point numeric rating scale (NRS). Time dependent Cox proportional hazards regression analysis was used to determine the risk factors of treatment-requiring pain (NRS > 4) during the first 48 postoperative hours. Postoperative pain rapidly decreased, and treatment-requiring pain remained in 12.8% (81 out of 635) of patients at 48 hours postoperatively. After adjusting for the time-dependent analgesic consumption, intraoperative use of remifentanil > 0.2 mcg/kg/min was a positive predictor of postoperative pain with a hazard ratio of 1.296 (95% C.I., 1.014-1.656, P = 0.039) during 48 hours after surgery. In conclusion, excessive use of remifentanil during TIVA was associated with increased risk of pain after robotic thyroid surgery. Prospective trials are required to confirm these results and determine whether decreasing remifentanil consumption below the threshold can reduce postoperative pain.

The benefit of aspirin use after coronary artery bypass graft surgery has been well proven. However, the effect of preoperative aspirin use in patients undergoing off-pump coronary artery bypass graft surgery (OPCAB) has not been evaluated sufficiently. To evaluate platelet function changes during OPCAB due to preoperative aspirin use, we conducted a randomized controlled trial using flow cytometry and the Multiplate® analyzer. Forty-eight patients scheduled for elective OPCAB were randomized to the aspirin continuation (100 mg/day until operative day) and discontinuation (4 days before the operative day) groups. Platelet function was measured using the platelet activation markers CD62P, CD63, and PAC-1 by flow cytometry, and platelet aggregation was measured using the Multiplate® analyzer, after the induction of anesthesia (baseline), at the end of the operation, and 24 and 48 h postoperatively. Findings of conventional coagulation assays, thromboelastography by ROTEM® assays, and postoperative bleeding-related clinical outcomes were compared between groups. No significant change in CD62P, CD63, or PAC-1 was observed at the end of the operation or 24 or 48 h postoperatively compared with baseline in either group. The area under the curve for arachidonic acid-stimulated platelet aggregation, measured by the Multiplate® analyzer, was significantly smaller in the aspirin continuation group (P < 0.01). However, chest tube drainage and intraoperative and postoperative transfusion requirements did not differ between groups. Our study showed that preoperative use of aspirin for OPCAB did not affect perioperative platelet activation, but it impaired platelet aggregation, which did not affect postoperative bleeding, by arachidonic acid.

The discrepancy between spatial orientations of an endoscopic image and a physician's working environment can make it difficult to interpret endoscopic images. In this study, we developed and evaluated a device that corrects the endoscopic image orientation using an accelerometer and gyrosensor. The acceleration of gravity and angular velocity were retrieved from the accelerometer and gyrosensor attached to the handle of the endoscope. The rotational angle of the endoscope handle was calculated using a Kalman filter with transmission delay compensation. Technical evaluation of the orientation correction system was performed using a camera by comparing the optical rotational angle from the captured image with the rotational angle calculated from the sensor outputs. For the clinical utility test, fifteen anesthesiology residents performed a video endoscopic examination of an airway model with and without using the orientation correction system. The participants reported numbers written on papers placed at the left main, right main, and right upper bronchi of the airway model. The correctness and the total time it took participants to report the numbers were recorded. During the technical evaluation, errors in the calculated rotational angle were less than 5 degrees. In the clinical utility test, there was a significant time reduction when using the orientation correction system compared with not using the system (median, 52 vs. 76 seconds; P = .012). In this study, we developed a real-time endoscopic image orientation correction system, which significantly improved physician performance during a video endoscopic exam.

Prolonged air leak (PAL), defined as air leak more than 5 days after lung resection, has been associated with various adverse outcomes. However, studies on intraoperative risk factors for PAL are not sufficient. We investigated whether the intraoperative ventilatory leak (VL) can predict PAL. A retrospective study of 1060 patients with chest tubes after lung resection was conducted. Tidal volume data were retrieved from the electronic anesthesia records. Ventilatory leak (%) was calculated as [(inspiratory tidal volume-expiratory tidal volume)/ inspiratory tidal volume × 100] and was measured after restart of two-lung ventilation. Cox proportional hazards regression analysis was performed using VL as a predictor, and PAL as the dependent outcome. The odds ratio of the VL was then adjusted by adding possible risk factors including patient characteristics, pulmonary function and surgical factors. The incidence of PAL was 18.7%. VL >9.5% was a significant predictor of PAL in univariable analysis. VL remained significant as a predictor of PAL (1.59, 95% CI, 1.37-1.85, P 60 years, body mass index 2.1 hours. C-statistic of the prediction model was 0.80 (95% CI, 0.77-0.82). In conclusion, VL was a quantitative measure of intraoperative air leakage and an independent predictor of postoperative PAL. Monitoring VL during lung resection may be uselful in recommending additional surgical repair or use of adjuncts and thus, help reduce postoperative PAL.