Search

Hypoxemia often occurs in outpatients undergoing anesthesia-assisted esophagogastroduodenoscopy (EGD). However, there is a scarcity in tools to predict the hypoxemia risk. We aimed to solve this problem by developing and validating machine learning (ML) models based on preoperative and intraoperative features. All data were retrospectively collected from June 2021 to February 2022. The most appropriate predictive features were selected by the least absolute shrinkage and selection operator, which were incorporated and modelled by 4 ML algorithms. The area under the precision-recall curve (AUPRC) was used as the main evaluation metric to select the best models, and the selected models were compared with the STOP-BANG score. Their predictive performance was visually interpreted by SHapley Additive exPlanations. The primary endpoint of this study was hypoxemia during the procedure, defined as at least one reading of pulse oximetry < 90% without probes misplacement from the anesthesia induction beginning to the end of EGD, while the secondary endpoint was hypoxemia during induction, from the induction beginning to the start of endoscopic intubation. Of 1160 patients in the derivation cohort, 112 patients (9.6%) developed intraoperative hypoxemia, of which 102 (8.8%) occurred during the induction period. In temporal and external validation, no matter whether based on preoperative variables or still based on preoperative plus intraoperative variables, our models showed excellent predictive performance for the two endpoints, significantly better than STOP-BANG score. In the model interpretation section, preoperative variables (airway assessment indicators, pulse oximeter oxygen saturation and BMI) and intraoperative variables (the induced propofol dose) made the highest contribution to the predictions. To our knowledge, our ML models were the first to predict hypoxemia risk, which achieved excellent overall predictive ability integrating various clinical indicators. These models have the potential to become an effective tool for adjusting sedation strategies flexibly and reducing the workload of anesthesiologists.KEY MESSAGESThis study is the first model employing ML methods based on preoperative and preoperative plus intraoperative variables for predicting the risk of hypoxemia during induction and the whole EGD procedure respectively.Our four models achieved satisfactory predictive performance and outperformed STOP-BANG score in terms of AUPRC in the temporal and external validation cohorts respectively.We found that the relevant variables of airway assessment should be fully taken into account when analyzing the risk factor of hypoxemia, and the effect of patients’ age on their hypoxemia risk should be considered in conjunction with the propofol dose. This study is the first model employing ML methods based on preoperative and preoperative plus intraoperative variables for predicting the risk of hypoxemia during induction and the whole EGD procedure respectively. Our four models achieved satisfactory predictive performance and outperformed STOP-BANG score in terms of AUPRC in the temporal and external validation cohorts respectively. We found that the relevant variables of airway assessment should be fully taken into account when analyzing the risk factor of hypoxemia, and the effect of patients’ age on their hypoxemia risk should be considered in conjunction with the propofol dose.

Additional file 1: Supplementary Table 1 Thirty-eight genes significantly associated with prognosis in LUAD

Additional file 2: Supplementary Table 2 Risk assessment of 20 clinical LUAD patients

Objectives: Paresthesia-free stimulation such as high frequency and burst have been demonstrated as effective therapies for neuropathic pain. The aim of this meta-analysis was to evaluate the efficacy and safety of conventional spinal cord stimulation (SCS) in the treatment of refractory angina pectoris (RAP). Materials and Methods: Relevant randomized controlled trials that investigated SCS for patients with RAP were comprehensively searched in Medline, Pubmed, Embase, and Cochrane Library. Five meta-analyses were performed examining the changes in Canadian Cardiovascular Society classes, exercise time, Visual Analog Scale (VAS) scores of pain, Seattle Angina Questionnaire, and nitroglycerin use in RAP patients after SCS therapy. We analyzed standardized mean differences (MD) and 95% confidence intervals (CIs) for each outcome by Review Manager 5.0 and STATA 12.0. Results: A total of 12 randomized controlled trials involving 476 RAP patients were identified. A trend of reduction in the angina frequency (MD=−9.03, 95% CI, −15.70 to −2.36) and nitroglycerin consumption (MD=−0.64, 95% CI, −0.84 to −0.45) could be observed in the SCS group. Compared with the control group, SCS showed benefit on increasing exercise time (MD=0.49, 95% CI, 0.13-0.85) and treatment satisfaction (MD=6.87, 95% CI, 2.07-11.66) with decreased VAS scores of pain (MD=−0.50, 95% CI, −0.81 to −0.20) and disease perception (MD=−8.34, 95% CI, −14.45 to −2.23). However, the result did not reach the significance level in terms of physical limitation (95% CI, −8.75 to 3.38; P=0.39) or angina stability (95% CI, −7.55 to 3.67; P=0.50). Discussion: The current meta-analysis suggested that SCS was a potential alternative in the treatment of PAP patients. Further investigation for finding the appropriate intensity of stimulation is required before this treatment should be widely recommended and applied.