Background and Objectives: Chronic lower back pain (LBP) is a common clinical disorder. The early identification of patients who will develop chronic LBP would help develop preventive measures and treatment. We aimed to develop machine learning models that can accurately predict the risk of chronic LBP. Materials and Methods: Data from the Sixth Korea National Health and Nutrition Examination Survey conducted in 2014 and 2015 (KNHANES VI-2, 3) were screened for selecting patients with chronic LBP. LBP lasting >30 days in the past 3 months was defined as chronic LBP in the survey. The following classification models with machine learning algorithms were developed and validated to predict chronic LBP: logistic regression (LR), k-nearest neighbors (KNN), naïve Bayes (NB), decision tree (DT), random forest (RF), gradient boosting machine (GBM), support vector machine (SVM), and artificial neural network (ANN). The performance of these models was compared with respect to the area under the receiver operating characteristic curve (AUROC). Results: A total of 6119 patients were analyzed in this study, of which 1394 had LBP. The feature selected data consisted of 13 variables. The LR, KNN, NB, DT, RF, GBM, SVM, and ANN models showed performances (in terms of AUROCs) of 0.656, 0.656, 0.712, 0.671, 0.699, 0.660, 0.707, and 0.716, respectively, with ten-fold cross-validation. Conclusions: In this study, the ANN model was identified as the best machine learning classification model for predicting the occurrence of chronic LBP. Therefore, machine learning could be effectively applied in the identification of populations at high risk of chronic LBP.

Background: The usefulness of the oxygen reserve index (ORi) in reducing hyperoxemia remains unclear. We designed this study to investigate whether fraction of inspired oxygen (FiO₂) adjustment under a combination of ORi and peripheral oxygen saturation (SpO₂) guidance can reduce intraoperative hyperoxemia compared to SpO₂ alone. Methods: In this prospective, double-blind, randomized controlled study, we allocated patients scheduled for laparoscopic gastrectomy to the SpO₂ group (FiO₂ adjusted to target SpO₂ ≥ 98%) or the ORi-SpO₂ group (FiO₂ adjusted to target 0 < 0 ORi < .3 and SpO₂ ≥ 98%). The ORi, SpO₂, FiO₂, arterial partial pressure of oxygen (PaO₂), and incidence of severe hyperoxemia (PaO_{2 ≥} 200 mm Hg) were recorded before and 1, 2, and 3 hours after surgical incision. Data from 32 and 30 subjects in the SpO₂ and ORi-SpO₂ groups, respectively, were analyzed. Results: PaO₂ was higher in the SpO₂ group (250.31 ± 57.39 mm Hg) than in the ORi-SpO₂ group (170.07 ± 49.39 mm Hg) 1 hour after incision (P < .001). PaO₂ was consistently higher in the SpO₂ group than in the ORi-SpO₂ group, over time (P = .045). The incidence of severe hyperoxemia was higher in the SpO₂ group (84.4%) than in the ORi-SpO₂ group (16.7%, P < .001) 1 hour after incision. Higher FiO₂ was administered to the SpO₂ group [52.5 (50–60)] than the ORi-SpO₂ group [40 (35–50), P < .001] 1 hour after incision. SpO₂ was not different between the 2 groups. Conclusion: The combination of ORi and SpO₂ guided FiO₂ adjustment reduced hyperoxemia compared to SpO₂ alone during laparoscopic gastrectomy.

Background: Remimazolam is manifested by rapid action, hemodynamic stability, and fast recovery. Our study aimed to investigate whether the quality of recovery (QoR) after remimazolam anesthesia in patients undergoing transurethral resection of bladder tumor, which is predominantly performed in the elderly population, is not inferior to that after conventional anesthesia using sevoflurane. Methods: Thirty-four patients were randomly allocated into either of group S (n = 17, receiving sevoflurane anesthesia), or group R (n = 17, receiving remimazolam anesthesia). The QoR was assessed by Korean version of QoR-15 questionnaire, on the day before and after the surgery. Scores acquired for each individual item, QoR-15 scores categorized into 5 dimensions (physical comfort, physical independence, psychological support, emotional state, and pain), and overall global score were subjected to comparative analysis. The primary outcome was postoperative global QoR-15, and a noninferiority delta value of 8.0 was employed. Results: The postoperative global QoR-15 in the group S was 141 (134–146), and in the groups R was 133 (128–142) (P = .152). The mean difference of global QoR-15 (group S–group R) was 1.471 (95% confidence interval of −10.204 to 13.146), and the lower 95% confidence interval margin was lower than the noninferiority margin of −8.0. When comparing the QoR-15 sorted by 5 dimensions, pain scored higher in the group S (20 [18–20]) compared to the group R (15 [15–20], P = .032). Conclusion: The postoperative QoR following transurethral resection of bladder tumor was found to be lower in patients anesthetized with remimazolam in comparison to those anesthetized with sevoflurane.

Background/Objectives: Adult degenerative scoliosis (ADS) is a three-dimensional spinal deformity caused by asymmetric degeneration of intervertebral discs, facet joints, and paraspinal muscles (PSM). Although previous studies have identified bilateral asymmetry in the multifidus (MF), the erector spinae (ES), and psoas (PS), the underlying mechanism remains unclear. This study aims to compare muscle volume (MV), fat infiltration (FI), and degenerative changes on the concave (CC) and convex (CV) sides in symptomatic ADS patients. Methods: This study included patients with ADS who visited Kangbuk Samsung Hospital between 2022 and 2024. MV and FI were measured by CT scans, and facet joint degeneration (FJD), disc degeneration (DD), and foraminal stenosis (FS) were assessed by MRI. The values of CV and CC side were compared. Results: 74 patients were enrolled with a mean age of 71.38 ± 8.6 years. MV of all PSM was significantly lower on the CC side than CV side. FI of ES and MF was significantly higher on the CC side compared to the CV side. Degenerative changes in the intervertebral discs and neural foramen were more severe on the CC side. Conclusions: In patients with ADS, we found that MV was consistently lower on the CC side across all PSM, whereas FI in the MF and ES was higher on the CC side. Degenerative changes in the spine, such as FS and DD, were also more severe on the CC side, although FJD was not. These results suggest that spinal muscle and structural degeneration are not evenly distributed between two sides. Physiotherapy that specifically targets the more affected CC side may offer better outcomes for patients with ADS.

Background: Exposure to environmental cadmium can have harmful effects on the human kidneys. The relationship between the degree of exposure to cadmium and the risk of chronic kidney disease (CKD) in the general population is unclear. Objectives: To investigate the association between blood cadmium levels and CKD risk using samples from the Korea National Health and Nutrition Examination Survey (KNHANES) VII data, which included heavy metal and serum creatinine levels. Methods: We analyzed the data of 4,222 adults from January 1, 2016, to December 31, 2017. Multiple logistic regression analysis was conducted on weighted data using complex sampling to assess the relationship between blood cadmium levels and CKD. We performed a stratified analysis in the presence of comorbidities such as diabetes or hypertension. Results: There was a positive association between blood cadmium level and the risk of CKD in hypertensive or nondiabetic participants after adjustment, but not between blood cadmium level and CKD in normotensive or diabetic participants. The corresponding odds ratios (OR) of cadmium for CKD were 2.70 (95% confidence interval [CI], 1.49–4.90, P = 0.001) in samples with hypertension and 2.40 (95% CI, 1.56–3.70, P < 0.001) in samples without diabetes. Conclusions: Our findings suggest an association between blood cadmium level and the risk of CKD in hypertensive or nondiabetic participants. Additional research is necessary to elucidate the relationship between cadmium exposure and CKD risk, particularly in individuals with comorbidities.

Background and Objectives: Intraoperative hypotension (IOH) is of great importance in preventing diseases such as postoperative myocardial infarction, acute kidney injury, and mortality. This study aimed to develop and validate machine learning and deep learning models that predict IOH using both biosignals and personalized clinical information for each patient. Materials and Methods: In this retrospective observational study, we used the VitalDB open dataset, which included intraoperative biosignals and clinical information from 6388 patients who underwent non-cardiac surgery between June 2016 and August 2017 at Seoul National University Hospital, Seoul, South Korea. The predictive performances of models trained with four waveforms (arterial blood pressure, electrocardiography, photoplethysmography, and capnography) and clinical information were evaluated and compared at time points at 5 min before the hypotensive event. To predict hypotensive events during surgery, we developed two predictive models: machine learning and deep learning. In total, 2611 patients were enrolled in this retrospective study. Machine and deep learning algorithms were developed and validated using raw waveforms and clinical information as inputs. Results: Gradient boosting machine showed predicted IOH with an AUROC and accuracy of 0.94 (0.93–0.95) and 0.88 (0.86–0.89). A hybrid CNN-RNN model also showed similar performance with an AUROC and accuracy of 0.94 (0.93–0.95) and 0.88 (0.87–0.89). Conclusions: This study developed and validated machine and deep learning models to predict IOH using waveform data and covariate values. In the future, we anticipate that the results of our study will contribute to predicting IOH in real time in the operating room and reducing the occurrence of IOH.