PPCRKB: a risk factor knowledge base of postoperative pulmonary complications.

Postoperative pulmonary complications (PPCs) are highly heterogeneous disorders with diverse risk factors frequently occurring after surgical interventions, resulting in significant financial burdens, prolonged hospitalization and elevated mortality rates. Despite the existence of multiple studies on PPCs, a comprehensive knowledge base that can effectively integrate and visualize the diverse risk factors associated with PPCs is currently lacking. This study aims to develop an online knowledge platform on risk factors for PPCs (Postoperative Pulmonary Complications Risk Factor Knowledge Base, PPCRKB) that categorizes and presents the risk and protective factors associated with PPCs, as well as to facilitate the development of individualized prevention and management strategies for PPCs based on the needs of each investigator. The PPCRKB is a novel knowledge base that encompasses all investigated potential risk factors linked to PPCs, offering users a web-based platform to access these risk factors. The PPCRKB contains 2673 entries, 915 risk factors that have been categorized into 11 distinct groups. These categories include habit and behavior, surgical factors, anesthetic factors, auxiliary examination, environmental factors, clinical status, medicines and treatment, demographic characteristics, psychosocial factors, genetic factors and miscellaneous factors. The PPCRKB holds significant value for PPC research. The inclusion of both quantitative and qualitative data in the PPCRKB enhances the ability to uncover new insights and solutions related to PPCs. It could provide clinicians with a more comprehensive perspective on research related to PPCs in future. Database URL: http://sysbio.org.cn/PPCs.

A simple machine learning model for the prediction of acute kidney injury following noncardiac surgery in geriatric patients: a prospective cohort study.

BACKGROUND: Surgery in geriatric patients often poses risk of major postoperative complications. Acute kidney injury (AKI) is a common complication following noncardiac surgery and is associated with increased mortality. Early identification of geriatric patients at high risk of AKI could facilitate preventive measures and improve patient prognosis. This study used machine learning methods to identify important features and predict AKI following noncardiac surgery in geriatric patients. METHODS: The data for this study were obtained from a prospective cohort. Patients aged ≥ 65 years who received noncardiac surgery from June 2019 to December 2021 were enrolled. Data were split into training set (from June 2019 to March 2021) and internal validation set (from April 2021 to December 2021) by time. The least absolute shrinkage and selection operator (LASSO) regularization algorithm and the random forest recursive feature elimination algorithm (RF-RFE) were used to screen important predictors. Models were trained through extreme gradient boosting (XGBoost), random forest, and LASSO. The SHapley Additive exPlanations (SHAP) package was used to interpret the machine learning model. RESULTS: The training set included 6753 geriatric patients. Of these, 250 (3.70%) patients developed AKI. The XGBoost model with RF-RFE selected features outperformed other models with an area under the precision-recall curve (AUPRC) of 0.505 (95% confidence interval [CI]: 0.369-0.626) and an area under the receiver operating characteristic curve (AUROC) of 0.806 (95%CI: 0.733-0.875). The model incorporated ten predictors, including operation site and hypertension. The internal validation set included 3808 geriatric patients, and 96 (2.52%) patients developed AKI. The model maintained good predictive performance with an AUPRC of 0.431 (95%CI: 0.331-0.524) and an AUROC of 0.845 (95%CI: 0.796-0.888) in the internal validation. CONCLUSIONS: This study developed a simple machine learning model and a web calculator for predicting AKI following noncardiac surgery in geriatric patients. This model may be a valuable tool for guiding preventive measures and improving patient prognosis. TRIAL REGISTRATION: The protocol of this study was approved by the Committee of Ethics from West China Hospital of Sichuan University (2019-473) with a waiver of informed consent and registered at www.chictr.org.cn (ChiCTR1900025160, 15/08/2019).

Combination of Creatinine with Inflammatory Biomarkers (PCT, CRP, hsCRP) for Predicting Postoperative ICU Admissions for Elderly Patients.

INTRODUCTION: The number of elderly patients who require surgery as their primary treatment has increased rapidly in recent years. Among 300 million people globally who underwent surgery every year, patients aged 65 years and over accounted for more than 30% of cases. Despite medical advances, older patients remain at higher risk of postoperative complications. Early diagnosis and effective prediction are essential requirements for preventing serious postoperative complications. In this study, we aim to provide new biomarker combinations to predict the incidence of postoperative intensive care unit (ICU) admissions > 24 h in elderly patients. METHODS: This investigation was conducted as a nested case-control study, incorporating 413 participants aged ≥ 65 years who underwent non-cardiac, non-urological elective surgeries. These individuals underwent a 30-day postoperative follow-up. Before surgery, peripheral venous blood was collected for analyzing serum creatinine (Scr), procalcitonin (PCT), C-reactive protein (CRP), and high-sensitivity CRP (hsCRP). The efficacy of these biomarkers in predicting postoperative complications was evaluated using receiver operating characteristic (ROC) curve analysis and area under the curve (AUC) values. RESULTS: Postoperatively, 10 patients (2.42%) required ICU admission. Regarding ICU admissions, the AUCs with 95% confidence intervals (CIs) for the biomarker combinations of Scr × PCT and Scr × CRP were 0.750 (0.655-0.845, P = 0.007) and 0.724 (0.567-0.882, P = 0.015), respectively. Furthermore, cardiovascular events were observed in 14 patients (3.39%). The AUC with a 95% CI for the combination of Scr × CRP in predicting cardiovascular events was 0.688 (0.560-0.817, P = 0.017). CONCLUSION: The innovative combinations of biomarkers (Scr × PCT and Scr × CRP) demonstrated efficacy as predictors for postoperative ICU admissions in elderly patients. Additionally, the Scr × CRP also had a moderate predictive value for postoperative cardiovascular events. TRIAL REGISTRATION: China Clinical Trial Registry, ChiCTR1900026223.

Metabolic change in monocytes and postoperative morbidity after major abdominal surgery in elderly patients: A prospective cohort study.

Background: Postoperative complications in aging patients remain a significant cause of increased costs, hospital length of stay, and patient distress. Although alterations in energy metabolism have been closely linked to aging process and surgery, it is still unclear whether metabolic changes during surgery is associated with postoperative complications in elderly patients. This study was conducted to investigate whether metabolic changes during surgery predicts postoperative complications in elderly patients. Methods: We conducted a prospective single-center observational cohort study. 244 adults (aged ≥65 years) who were scheduled for elective major non-cardiac surgery were recruited. Blood samples for each patient were taken before and after surgery. All patients were randomly divided into two groups (122 in each group), then oxygen consumption rate (OCR) or extracellular acidification rate (ECAR) was measured on isolated monocytes in each group. Results: 14 of 110 (12.7%) patients went through OCR measurement and 15 of 122 patients (12.3%) went through ECAR measurement experienced moderate to severe complications. Overall, there was an intensification of glycolysis in monocytes after surgery. Among all variables, only the change (preoperative -postoperative) of glycolytic reserve (GR)/glycolysis (G) and GR/non-glycolytic acidification (NG) were predictors of moderate to severe complications (AUC = 0.70; 95% CI, 0.56-0.81; P = 0.019 and AUC = 0.67; 95% CI, 0.55-0.80; P = 0.031). Decreased postoperative GR/G were associated with worse postoperative complications (RR = 9.08; 95% CI, 1.23-66.81; P = 0.024). Conclusions: Compared with mitochondria function, the change of glycolytic function in monocyte was more valuable in predicting postoperative complications after major abdominal surgery. Our study gave us a new insight into identifying patients at high risk in aging patients.

Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications.

BACKGROUND: Timely detection of modifiable risk factors for postoperative pulmonary complications (PPCs) could inform ventilation strategies that attenuate lung injury. We sought to develop, validate, and internally test machine learning models that use intraoperative respiratory features to predict PPCs. METHODS: We analysed perioperative data from a cohort comprising patients aged 65 yr and older at an academic medical centre from 2019 to 2023. Two linear and four nonlinear learning models were developed and compared with the current gold-standard risk assessment tool ARISCAT (Assess Respiratory Risk in Surgical Patients in Catalonia Tool). The Shapley additive explanation of artificial intelligence was utilised to interpret feature importance and interactions. RESULTS: Perioperative data were obtained from 10 284 patients who underwent 10 484 operations (mean age [range] 71 [65-98] yr; 42% female). An optimised XGBoost model that used preoperative variables and intraoperative respiratory variables had area under the receiver operating characteristic curves (AUROCs) of 0.878 (0.866-0.891) and 0.881 (0.879-0.883) in the validation and prospective cohorts, respectively. These models outperformed ARISCAT (AUROC: 0.496-0.533). The intraoperative dynamic features of respiratory dynamic system compliance, mechanical power, and driving pressure were identified as key modifiable contributors to PPCs. A simplified model based on XGBoost including 20 variables generated an AUROC of 0.864 (0.852-0.875) in an internal testing cohort. This has been developed into a web-based tool for further external validation (https://aorm.wchscu.cn/). CONCLUSIONS: These findings suggest that real-time identification of surgical patients' risk of postoperative pulmonary complications could help personalise intraoperative ventilatory strategies and reduce postoperative pulmonary complications.

The Modulation by Anesthetics and Analgesics of Respiratory Rhythm in the Nervous System.

Rhythmic eupneic breathing in mammals depends on the coordinated activities of the neural system that sends cranial and spinal motor outputs to respiratory muscles. These outputs modulate lung ventilation and adjust respiratory airflow, which depends on the upper airway patency and ventilatory musculature. Anesthetics are widely used in clinical practice worldwide. In addition to clinically necessary pharmacological effects, respiratory depression is a critical side effect induced by most general anesthetics. Therefore, understanding how general anesthetics modulate the respiratory system is important for the development of safer general anesthetics. Currently used volatile anesthetics and most intravenous anesthetics induce inhibitory effects on respiratory outputs. Various general anesthetics produce differential effects on respiratory characteristics, including the respiratory rate, tidal volume, airway resistance, and ventilatory response. At the cellular and molecular levels, the mechanisms underlying anesthetic-induced breathing depression mainly include modulation of synaptic transmission of ligand-gated ionotropic receptors (e.g., γ-aminobutyric acid, N-methyl-D-aspartate, and nicotinic acetylcholine receptors) and ion channels (e.g., voltage-gated sodium, calcium, and potassium channels, two-pore domain potassium channels, and sodium leak channels), which affect neuronal firing in brainstem respiratory and peripheral chemoreceptor areas. The present review comprehensively summarizes the modulation of the respiratory system by clinically used general anesthetics, including the effects at the molecular, cellular, anatomic, and behavioral levels. Specifically, analgesics, such as opioids, which cause respiratory depression and the "opioid crisis", are discussed. Finally, underlying strategies of respiratory stimulation that target general anesthetics and/or analgesics are summarized.

Trajectory of pain threshold and its association with acute pain after thoracic surgery: a prospective observational study.

BACKGROUND: Postoperative analgesic management is an ongoing challenge. The pain threshold (PT) is an objective index that reflects the body's sensitivity to pain and can be used for quantitative pain assessment. We hypothesized that the PT is correlated with postoperative pain and can thus be used to guide postoperative pain management. METHODS: This study involved 93 patients who underwent thoracoscopic surgery from December 2019 to February 2020. The PT was measured with transcutaneous electrical stimulation before surgery (T0) and at 1 h (T1), 6 h (T6), and 24 h (T24) after surgery. The visual analogue scale (VAS) score was used to evaluate the severity of postoperative pain at the same time. The PT variation (PTV) after surgery was calculated as the ratio of the postoperative PT to preoperative PT. RESULTS: The postoperative PT was higher than the preoperative PT and showed a downward trend within 24 h after surgery; the PTV also showed a downward trend within 24 h after surgery. PT-T1 was negatively correlated with VAS-T1 at rest and during motion (rest: VAS-T1r = - 0.274, P = 0.008; motion: VAS-T1r = - 0.298, P = 0.004). PTV-T1 was negatively correlated with VAS-T1 during motion (r = - 0.213, P = 0.04). Lower VAS-T1 scores (< 4) at rest and during motion were associated with higher PT-T1 (rest: t = 2.452, P = 0.016; motion: t = 2.138, P = 0.035). The intraoperative sufentanil dose was associated with a postoperative increase in PTV-T1. Increased rescue analgesic administration was associated with PTV elevation. However, the incidence of dizziness in patients with moderate PTV-T24 was lower than that in patients with high or low PTV-T24 (χ2 = 8.297, P = 0.015). CONCLUSIONS: The postoperative PT was higher than the preoperative PT and showed a downward trend within 24 h after surgery; PTV also showed a downward trend within 24 h after surgery. The PT and PTV were negatively correlated with the pain intensity at rest and during motion and were associated with perioperative analgesic consumption and the incidence of adverse events.

Circulating biomarkers in perioperative management of cancer patients.

Owing to the advances in surgical technology, most solid tumours can be controlled by surgical excision. The priority should be tumour control, while some routine perioperative management might influence cancer progression in an unnoticed way. Moreover, it is increasingly recognized that effective perioperative management should include techniques to improve postoperative outcomes. These influences are elucidated by the different functions of circulating biomarkers in cancer patients. Here, circulating biomarkers with two types of clinical functions were reviewed: (i) circulating biomarkers for cancer progression monitoring, for instance, those related to cancer cell malignancy, tumour microenvironment formation, and early metastasis, and (ii) circulating biomarkers with relevance to postoperative outcomes, including systemic inflammation, immunosuppression, cognitive dysfunction, and pain management. This review aimed to provide new perspectives for the perioperative management of patients with cancer and highlight the potential clinical translation value of circulating biomarkers in improving outcomes.

Predictive value of perioperative procalcitonin, C reactive protein and high-sensitivity C reactive protein for the risk of postoperative complications after non-cardiac surgery in elderly patients: a nested case-control study.

OBJECTIVE: Little is known about the correlation between perioperative concentrations of inflammatory biomarkers and postoperative complications. This study explored whether the plasma concentrations and perioperative changes of procalcitonin (PCT), C reactive protein (CRP) and high-sensitivity CRP (hsCRP) could predict the risk of postoperative morbidity in elderly patients undergoing elective non-cardiac surgery. DESIGN: A nested case-control study. SETTING: A tertiary hospital in China. PARTICIPANTS: A total of 498 patients aged ≥65 years from a prospective cohort who underwent elective non-cardiac surgery between June 2020 and April 2021. PRIMARY OUTCOME MEASURES: The primary outcomes were the efficacy of plasma concentrations of PCT, CRP and hsCRP in predicting the risk of Clavien-Dindo Classification (CDC) ≥grade 3 and major complications. The major complications included mortality, an intensive care unit stay length >24 hour, cardiovascular events, acute kidney injury, postoperative cognitive dysfunction and infections. RESULTS: For major complications, the area under the curve (AUC) (95% CI) of PCT-24 hours, PCT change and PCT change rate were 0.750 (0.698 to 0.803), 0.740 (0.686 to 0.795) and 0.711 (0.651 to 0.771), respectively. The AUC (95% CI) of CRP-24 hours, CRP change, CRP change rate and hsCRP baseline were 0.835 (0.789 to 0.881), 0.818 (0.770 to 0.867), 0.691 (0.625 to 0.756) and 0.616 (0.554 to 0.678), respectively. For complications ≥CDC grade 3, the AUC (95% CI) of PCT-24 hours, PCT change and PCT change rate were 0.662 (0.543 to 0.780), 0.643 (0.514 to 0.772) and 0.627 (0.494 to 0.761), respectively. The AUC (95% CI) of CRP-24 hours and hsCRP baseline were 0.649 (0.527 to 0.771) and 0.639 (0.530 to 0.748), respectively. CONCLUSIONS: PCT-24 hours, CRP-24 hours, the change of perioperative PCT and CRP were valuable predictors of major complications occurring within 30 days after non-cardiac surgery in the elderly. TRIAL REGISTRATION NUMBER: China Clinical Trial Registry: ChiCTR1900026223.

Effects of perioperative intravenous glucocorticoids on perioperative neurocognitive disorders in adults after surgery: A PRISMA-compliant meta-analysis of randomized controlled trials.

BACKGROUND: Randomized controlled trials (RCTs) have shown uncertain clinical benefits from perioperative intravenous glucocorticoids for perioperative neurocognitive disorders (PND). Thus, this meta-analysis was performed to evaluate whether perioperative intravenous glucocorticoids can decrease the occurrence of PND among adults undergoing surgery. METHODS: We searched 4 databases (MEDLINE, Embase, CENTRAL and Web of Science) for RCTs that assessed the incidence of PND in adults (aged ≥ 18 years old) after surgery. Two reviewers independently assessed the studies for eligibility, extracted data, and assessed the risk of bias in each study. We assessed the certainty of evidence using GRADEpro software. RESULTS: A total of 10 studies (N = 14,967) were eligible. Compared with controls, glucocorticoids were not associated with reducing the risk of postoperative cognitive dysfunction (POCD) (risk ratio [RR]: 0.79 95% confidence interval [CI]: 0.41-1.55, P = .50, I2 = 85%), risk of postoperative delirium (POD) (RR: 0.87 95% CI: 0.74-1.03, P = .10, I2 = 36%), the length of stay in intensive care unit (ICU) (mean difference [MD] -0.21 95% CI: -1.20 to 0.79, P = .68, I2 = 84%), 30-day mortality (RR: 0.92 95% CI: 0.59-1.46, P = .73, I2 = 0%), or postoperative atrial fibrillation (RR: 0.94 95% CI: 0.86-1.01, P = .11, I2 = 25%). However, there was significant difference between glucocorticoids and control group in the length of hospital stay (LOS) (MD: -0.39 95% CI: -0.62 to -0.16, P = .001, I2 = 0%), and postoperative infections (RR: 0.65 95% CI: 0.56-0.76, P < .00001, I2 = 0%). CONCLUSIONS: Perioperative intravenous glucocorticoids did not reduce the risk of PND in adults after surgery but might be associated with shorter the LOS and lower the incidence of postoperative infections. More, larger, higher-quality RCTs including neurological surgery or hip fracture surgery and different doses of glucocorticoids compared with placebos are needed to explore the intervention effects.

Relationship between depressive symptoms and anemia among the middle-aged and elderly: a cohort study over 4-year period.

BACKGROUND: The association between anemia and depression has been demonstrated in previous studies, but it's still unclear whether depressive symptoms as a hazard factor for anemia. The findings of a large-scale cross-sectional and longitudinal examination of such an association of among the middle-aged and elderly individuals in China were presented in our study. METHODS: The data from China Health and Retirement Longitudinal Study in 2011 and 2015 were evaluated. 10,179 and 5,887 participants were included in cross-sectional and longitudinal study, respectively. According to the World Health Organization, hemoglobin concentrations below 13 g/dL for males and 12 g/dL for females are considered anemia. The research population was separated into two groups based on scores of the 10-item short form of the Center for Epidemiologic Studies Depression Scale (CES-D-10): the group with depressed symptoms had a score of more than 10 points, and the group with depressive disorder had a score of more than 20 points. Multilevel logistic regression analyses were conducted to explore the relationship between anemia and varying degrees of depressive symptoms, utilizing three models based on adjusting for different types of covariates. RESULTS: In our cross-sectional investigation, depression disorders were more likely to link to the occurrence of anemia (OR, 1.34; 95% CI, 1.02-1.77; P = 0.035). Additionally, there seems a linear connection between depression questionnaire scores and hemoglobin concentrations (r = - 0.053, P < 0.001). Depressive symptom was significantly associated with anemia over 4 years of follow-up, and the more intense the depressive symptoms, the greater the danger of anemia (depressive symptoms group: OR, 1.27; 95% CI, 1.02-1.57, P = 0.032; depressive disorder group: OR, 1.59; 95% CI, 1.12-2.25, P = 0.010). CONCLUSIONS: Our findings suggest that depression symptoms seem related to anemia in the middle-aged and elderly in China cross-sectionally and longitudinally, and that the risk of anemia increases with the severity of depressive symptoms.

Development and evaluation of a data-driven integrated management app for perioperative adverse events: protocol for a mixed-design study.

INTRODUCTION: A patient record review study conducted in 2006 in a random sample of 21 Dutch hospitals found that 51%-77% of adverse events are related to perioperative care, while Centers for Disease Control and Prevention data in USA in 2013 estimated that the medical error is the third-leading cause of mortality. To capitalise on the potential of apps to enhance perioperative medical quality, there is a need for interventions developed in consultation with real-world users designed to support integrated management for perioperative adverse events (PAEs). This study aims: (1) to access the knowledge, attitude and practices for PAEs among physicians, nurses and administrators, and to identify the needs of healthcare providers for a mobile-based PAEs tool; (2) to develop a data-driven app for integrated PAE management that meets those needs and (3) to test the usability, clinical efficacy and cost-effectiveness of the developed app. METHODS AND ANALYSIS: We will adopt an embedded mixed-methods research technique; qualitative data will be used to assess user needs and app adoption, while quantitative data will provide crucial insights to establish the demand for the app, and measure the app effects. Phase 1 will enrol surgery-related healthcare providers from the West China Hospital and identify their latent demand for mobile-based PAEs management using a self-designed questionnaire underpinned by the knowledge, attitude and practice model, as well as expert interviews. In phase 2, we will develop the app for integrated PAE management and test its effectiveness and sustainability. In phase 3, the effects on the total number and severity of reported PAEs will be evaluated using Poisson regression with interrupted time-series analysis over a 2-year period, while users' engagement, adherence, process evaluation and cost-effectiveness will be evaluated using quarterly surveys and interviews. ETHICS AND DISSEMINATION: The West China Hospital of Sichuan University's Institutional Review Board authorised this study after approving the study protocol, permission forms and questionnaires (number: 2022-1364). Participants will be provided with study information, and informed written consent will be obtained. Study findings will be disseminated through peer-reviewed publications and conference presentations.

A nomogram to predict postoperative infection for older hip fracture patients.

INTRODUCTION: Postoperative infection is one of the most common postoperative complications in hip fracture surgery. It is related with increased morbidity and mortality. This study aimed at developing a nomogram to predict the individual probability of postoperative infection to facilitate perioperative decision-making. MATERIALS AND METHODS: In this retrospective study, we included all patients over 65 years old admitted for hip fracture in West China Hospital of Sichuan University from 1 January 2015 to 31 December 2019. Univariate and multivariate logistic regression analyses were used to identify significant predictors. We used all-subsets regression to screen an optimal model, and visualized the model through drawing nomogram. To evaluate the model performance, we applied receiver operating characteristic curve and calibration curve. RESULTS: We enrolled 677 older patients. 136 (20.1%) patients developed postoperative infection during hospitalization. Variables retained in the final model were albumin [odds ratio (OR) 0.90, 95% confidence interval (CI) 0.84-0.96], cholesterol (OR 1.49, 95% CI 1.04-2.15), blood phosphorus (OR 0.16, 95% CI 0.05-0.48), high-density lipoprotein (OR 0.42, 95% CI 0.19-0.89), surgery type (OR 2.27, 95% CI 1.35-3.90), smoking (OR 1.95, 95% CI 1.02-3.66), American Society of Anesthesiologists classification [class III (OR 1.02, 95% CI 0.55-1.93); class IV (OR 1.93, 95% CI 0.76-4.82)], and chronic pulmonary disease (OR 2.16, 95% CI 1.25-3.68). The C-index of the nomogram was 0.752 (95% CI 0.697-0.806). Calibration curve showed good agreement between predicted value and observed outcome. In the validation group, our nomogram showed an area under the receiver operating characteristic curve of 0.723 (95% CI 0.639-0.807). CONCLUSION: Our nomogram showed good discrimination ability in predicting individual probability of postoperative infection among older patients with hip fracture surgery. The nomogram could help clinicians identify patients at high risk of postoperative infection before surgery.

A Curriculum Batching Strategy for Automatic ICD Coding with Deep Multi-Label Classification Models.

The International Classification of Diseases (ICD) has an important role in building applications for clinical medicine. Extremely large ICD coding label sets and imbalanced label distribution bring the problem of inconsistency between the local batch data distribution and the global training data distribution into the minibatch gradient descent (MBGD)-based training procedure for deep multi-label classification models for automatic ICD coding. The problem further leads to an overfitting issue. In order to improve the performance and generalization ability of the deep learning automatic ICD coding model, we proposed a simple and effective curriculum batching strategy in this paper for improving the MBGD-based training procedure. This strategy generates three batch sets offline through applying three predefined sampling algorithms. These batch sets satisfy a uniform data distribution, a shuffling data distribution and the original training data distribution, respectively, and the learning tasks corresponding to these batch sets range from simple to complex. Experiments show that, after replacing the original shuffling algorithm-based batching strategy with the proposed curriculum batching strategy, the performance of the three investigated deep multi-label classification models for automatic ICD coding all have dramatic improvements. At the same time, the models avoid the overfitting issue and all show better ability to learn the long-tailed label information. The performance is also better than a SOTA label set reconstruction model.

Ketamine alleviating depressive-like behaviors is associated with regulation of nNOS-CAPON-Dexras1 complex in chronic unpredictable mild stress rats.

Background: A growing number of studies have demonstrated that ketamine induces rapid and sustained antidepressant action. Neuronal nitric oxide synthase (nNOS) signaling has been explored for the treatment of neuropsychiatric disorders for decades. But the effect of ketamine on nNOS signaling is poorly understood. The aim of the present study was to investigate the effect of ketamine on nNOS signaling in a chronic unpredictable mild stress (CUMS) model of depression. Methods: Forty-eight rats were randomly divided into four groups: the control group of healthy rats (group C), the healthy rats treated with ketamine 10 mg/kg for 3 days (group CK), the rats model of stress-induced depression group (group D), and the depressed group treated with ketamine 10 mg/kg for 3 days (group DK). The sucrose preference test and open field test were used to assess behavioral changes. Immunohistochemistry, immunofluorescence, and real-time PCR analysis were carried out to measure the expression of nNOS, CAPON, and Dexras1 in the prefrontal cortex (PFC) of the CUMS rats. Results: Compared with healthy rats, the total distance traveled, the rearing counts, the sucrose preference percentage (SPP), and CAPON and Dexras1 expression in the PFC significantly decreased, while nNOS expression increased in CUMS rats. After treating with ketamine, the total distance traveled, the rearing counts, the SPP, and CAPON and Dexras1 expression significantly increased, while nNOS expression significantly decreased. Conclusion: The results indicated that ketamine improved the depressive behavior of rats, which may be related to the reduced nNOS expression and enhanced CAPON and Dexras1 expression.

Machine learning prediction of postoperative major adverse cardiovascular events in geriatric patients: a prospective cohort study.

BACKGROUND: Postoperative major adverse cardiovascular events (MACEs) account for more than one-third of perioperative deaths. Geriatric patients are more vulnerable to postoperative MACEs than younger patients. Identifying high-risk patients in advance can help with clinical decision making and improve prognosis. This study aimed to develop a machine learning model for the preoperative prediction of postoperative MACEs in geriatric patients. METHODS: We collected patients' clinical data and laboratory tests prospectively. All patients over 65 years who underwent surgeries in West China Hospital of Sichuan University from June 25, 2019 to June 29, 2020 were included. Models based on extreme gradient boosting (XGB), gradient boosting machine, random forest, support vector machine, and Elastic Net logistic regression were trained. The models' performance was compared according to area under the precision-recall curve (AUPRC), area under the receiver operating characteristic curve (AUROC) and Brier score. To minimize the influence of clinical intervention, we trained the model based on undersampling set. Variables with little contribution were excluded to simplify the model for ensuring the ease of use in clinical settings. RESULTS: We enrolled 5705 geriatric patients into the final dataset. Of those patients, 171 (3.0%) developed postoperative MACEs within 30 days after surgery. The XGB model outperformed other machine learning models with AUPRC of 0.404(95% confidence interval [CI]: 0.219-0.589), AUROC of 0.870(95%CI: 0.786-0.938) and Brier score of 0.024(95% CI: 0.016-0.032). Model trained on undersampling set showed improved performance with AUPRC of 0.511(95% CI: 0.344-0.667, p < 0.001), AUROC of 0.912(95% CI: 0.847-0.962, p < 0.001) and Brier score of 0.020 (95% CI: 0.013-0.028, p < 0.001). After removing variables with little contribution, the undersampling model showed comparable predictive accuracy with AUPRC of 0.507(95% CI: 0.338-0.669, p = 0.36), AUROC of 0.896(95%CI: 0.826-0.953, p < 0.001) and Brier score of 0.020(95% CI: 0.013-0.028, p = 0.20). CONCLUSIONS: In this prospective study, we developed machine learning models for preoperative prediction of postoperative MACEs in geriatric patients. The XGB model showed the best performance. Undersampling method achieved further improvement of model performance. TRIAL REGISTRATION: The protocol of this study was registered at www.chictr.org.cn (15/08/2019, ChiCTR1900025160).

Prediction of intensive care unit admission (>24h) after surgery in elective noncardiac surgical patients using machine learning algorithms.

Background: To develop a highly discriminative machine learning model for the prediction of intensive care unit admission (>24h) using the easily available preoperative information from electronic health records. An accurate prediction model for ICU admission after surgery is of great importance for surgical risk assessment and appropriate utilization of ICU resources. Method: Data were collected retrospectively from a large hospital, comprising 135,442 adult patients who underwent surgery except for cardiac surgery between 1 January 2014, and 31 July 2018 in China. Multiple existing predictive machine learning algorithms were explored to construct the prediction model, including logistic regression, random forest, adaptive boosting, and gradient boosting machine. Four secondary analyses were conducted to improve the interpretability of the results. Results: A total of 2702 (2.0%) patients were admitted to the intensive care unit postoperatively. The gradient boosting machine model attained the highest area under the receiver operating characteristic curve of 0.90. The machine learning models predicted intensive care unit admission better than the American Society of Anesthesiologists Physical Status (area under the receiver operating characteristic curve: 0.68). The gradient boosting machine recognized several features as highly significant predictors for postoperatively intensive care unit admission. By applying subgroup analysis and secondary analysis, we found that patients with operations on the digestive, respiratory, and vascular systems had higher probabilities for intensive care unit admission. Conclusion: Compared with conventional American Society of Anesthesiologists Physical Status and logistic regression model, the gradient boosting machine could improve the performance in the prediction of intensive care unit admission. Machine learning models could be used to improve the discrimination and identify the need for intensive care unit admission after surgery in elective noncardiac surgical patients, which could help manage the surgical risk.

A multicenter prospective study on postoperative pulmonary complications prediction in geriatric patients with deep neural network model.

Aim: Postoperative pulmonary complications (PPCs) can increase the risk of postoperative mortality, and the geriatric population has high incidence of PPCs. Early identification of high-risk geriatric patients is of great value for clinical decision making and prognosis improvement. Existing prediction models are based purely on structured data, and they lack predictive accuracy in geriatric patients. We aimed to develop and validate a deep neural network model based on combined natural language data and structured data for improving the prediction of PPCs in geriatric patients. Methods: We consecutively enrolled patients aged ≥65 years who underwent surgery under general anesthesia at seven hospitals in China. Data from the West China Hospital of Sichuan University were used as the derivation dataset, and a deep neural network model was developed based on combined natural language data and structured data. Data from the six other hospitals were combined for external validation. Results: The derivation dataset included 12,240 geriatric patients, and 1949(15.9%) patients developed PPCs. Our deep neural network model outperformed other machine learning models with an area under the precision-recall curve (AUPRC) of 0.657(95% confidence interval [CI], 0.655-0.658) and an area under the receiver operating characteristic curve (AUROC) of 0.884(95% CI, 0.883-0.885). The external dataset included 7579 patients, and 776(10.2%) patients developed PPCs. In external validation, the AUPRC was 0.632(95%CI, 0.632-0.633) and the AUROC was 0.889(95%CI, 0.888-0.889). Conclusions: This study indicated that the deep neural network model based on combined natural language data and structured data could improve the prediction of PPCs in geriatric patients.

Efficacy of Bioenergetic Health Index to Predict Delirium After Major Abdominal Surgery in Elderly Patients: A Protocol for a Prospective Observational Cohort Study.

Introduction: Postoperative delirium (POD) is a common disorder following surgery, which seriously threatens the quality of patients' life, especially the older people. The multifactorial manner of this syndrome has made it hard to define an ideal method to predict individual risk. Mitochondria play a key role in the process of POD, which include inflammatory on the brain caused by surgeries and aging related neurodegeneration. As BHI (Bioenergetic Health Index) could be calculated in cells isolated from an individual's blood to represent the patient's composite mitochondrial statue, we hypotheses that HBI of monocytes isolated from individual's peripheral blood can predict POD after major non-cardiac surgery in elderly patients. Methods and Analysis: This is a prospective, observational single-blinded study in a single center. 124 patients aged ≥ 65 years and scheduled for major abdominal surgery (>3 h) under general anesthesia will be enrolled. Preoperative and postoperative delirium will be assessed by trained members using Confusion Assessment Method (CAM). For patients unable to speak in the ICU after the surgery, Confusion Assessment Method for the Intensive Care Unit (CAM-ICU) will be used. All patients will undergo venous blood sampling twice to measure BHI (1-2 tubes, 5 ml/tube): before the surgery and 1 day after surgery in wards. After discharge, patients will be contacted by telephone 30 days after surgery to confirm the incidence of post-discharge complications. The severity of complications will be categorized as mild, moderate, severe or fatal using a modified Clavien-Dindo Classification (CDC) scheme. Ethics and Dissemination: The study has been approved by the Ethics Committee on Biomedical Research, West China Hospital of Sichuan University, Sichuan, China (Chairperson Prof Shaolin Deng, No. 2021-502). Study data will be disseminated in manuscripts submitted to peer-reviewed medical journals as well as in abstracts submitted to congresses. Clinical Trial Registration: [www.ClinicalTrials.gov], identifier [ChiCTR2100047554].