Amino acid metabolomics and machine learning for assessment of post-hepatectomy liver regeneration.

Objective: Amino acid (AA) metabolism plays a vital role in liver regeneration. However, its measuring utility for post-hepatectomy liver regeneration under different conditions remains unclear. We aimed to combine machine learning (ML) models with AA metabolomics to assess liver regeneration in health and non-alcoholic steatohepatitis (NASH). Methods: The liver index (liver weight/body weight) was calculated following 70% hepatectomy in healthy and NASH mice. The serum levels of 39 amino acids were measured using ultra-high performance liquid chromatography-tandem mass spectrometry analysis. We used orthogonal partial least squares discriminant analysis to determine differential AAs and disturbed metabolic pathways during liver regeneration. The SHapley Additive exPlanations algorithm was performed to identify potential AA signatures, and five ML models including least absolute shrinkage and selection operator, random forest, K-nearest neighbor (KNN), support vector regression, and extreme gradient boosting were utilized to assess the liver index. Results: Eleven and twenty-two differential AAs were identified in the healthy and NASH groups, respectively. Among these metabolites, arginine and proline metabolism were commonly disturbed metabolic pathways related to liver regeneration in both groups. Five AA signatures were identified, including hydroxylysine, L-serine, 3-methylhistidine, L-tyrosine, and homocitrulline in healthy group, and L-arginine, 2-aminobutyric acid, sarcosine, beta-alanine, and L-cysteine in NASH group. The KNN model demonstrated the best evaluation performance with mean absolute error, root mean square error, and coefficient of determination values of 0.0037, 0.0047, 0.79 and 0.0028, 0.0034, 0.71 for the healthy and NASH groups, respectively. Conclusion: The KNN model based on five AA signatures performed best, which suggests that it may be a valuable tool for assessing post-hepatectomy liver regeneration in health and NASH.

Allosterically activating SHP2 by oleanolic acid inhibits STAT3-Th17 axis for ameliorating colitis.

Src homology 2 domain-containing tyrosine phosphatase 2 (SHP2) is an essential tyrosine phosphatase that is pivotal in regulating various cellular signaling pathways such as cell growth, differentiation, and survival. The activation of SHP2 has been shown to have a therapeutic effect in colitis and Parkinson's disease. Thus, the identification of SHP2 activators and a complete understanding of their mechanism is required. We used a two-step screening assay to determine a novel allosteric activator of SHP2 that stabilizes it in an open conformation. Oleanolic acid was identified as a suitable candidate. By binding to R362, K364, and K366 in the active center of the PTP domain, oleanolic acid maintained the active open state of SHP2, which facilitated the binding between SHP2 and its substrate. This oleanolic acid-activated SHP2 hindered Th17 differentiation by disturbing the interaction between STAT3 and IL-6Rα and inhibiting the activation of STAT3. Furthermore, via the activation of SHP2 and subsequent attenuation of the STAT3-Th17 axis, oleanolic acid effectively mitigated colitis in mice. This protective effect was abrogated by SHP2 knockout or administration of the SHP2 inhibitor SHP099. These findings underscore the potential of oleanolic acid as a promising therapeutic agent for treating inflammatory bowel diseases.

Online interpretable dynamic prediction models for clinically significant posthepatectomy liver failure based on machine learning algorithms: A retrospective cohort study.

BACKGROUND: Posthepatectomy liver failure (PHLF) is the leading cause of mortality in patients undergoing hepatectomy. However, practical models for accurately predicting the risk of PHLF are lacking. This study aimed to develop precise prediction models for clinically significant PHLF. METHODS: A total of 226 patients undergoing hepatectomy at a single center were recruited. The study outcome was clinically significant PHLF. Five pre- and postoperative machine learning (ML) models were developed and compared with four clinical scores, namely, the MELD, FIB-4, ALBI, and APRI scores. The robustness of the developed ML models was internally validated using 5-fold cross-validation by calculating the average of the evaluation metrics and was externally validated on an independent temporal dataset, including the area under the curve (AUC) and the area under the precision‒recall curve (AUPRC). SHapley Additive exPlanations analysis was performed to interpret the best performance model. RESULTS: Clinically significant PHLF was observed in 23 of 226 patients (10.2%). The variables in the preoperative model included creatinine, total bilirubin, and Child‒Pugh grade. In addition to the above factors, the extent of resection was also a key variable for the postoperative model. The pre- and postoperative artificial neural network (ANN) models exhibited excellent performance, with mean AUCs of 0.766 and 0.851, respectively, and mean AUPRC values of 0.441 and 0.645, whereas the MELD, FIB-4, ALBI, and APRI scores reached AUCs of 0.714, 0.498, 0.536 and 0.551, respectively, and AUPRC values of 0.204, 0.111, 0.128 and 0.163, respectively. In addition, the AUCs of the pre- and postoperative ANN models were 0.720 and 0.731, respectively, and the AUPRC values were 0.380 and 0.408, respectively, on the temporal dataset. CONCLUSION: Our online interpretable dynamic ML models outperformed common clinical scores and could function as a clinical decision support tool to identify patients at high risk of PHLF pre- and postoperatively.

Incorporating preoperative frailty to assist in early prediction of postoperative pneumonia in elderly patients with hip fractures: an externally validated online interpretable machine learning model.

BACKGROUND: This study aims to implement a validated prediction model and application medium for postoperative pneumonia (POP) in elderly patients with hip fractures in order to facilitate individualized intervention by clinicians. METHODS: Employing clinical data from elderly patients with hip fractures, we derived and externally validated machine learning models for predicting POP. Model derivation utilized a registry from Nanjing First Hospital, and external validation was performed using data from patients at the Fourth Affiliated Hospital of Nanjing Medical University. The derivation cohort was divided into the training set and the testing set. The least absolute shrinkage and selection operator (LASSO) and multivariable logistic regression were used for feature screening. We compared the performance of models to select the optimized model and introduced SHapley Additive exPlanations (SHAP) to interpret the model. RESULTS: The derivation and validation cohorts comprised 498 and 124 patients, with 14.3% and 10.5% POP rates, respectively. Among these models, Categorical boosting (Catboost) demonstrated superior discrimination ability. AUROC was 0.895 (95%CI: 0.841-0.949) and 0.835 (95%CI: 0.740-0.930) on the training and testing sets, respectively. At external validation, the AUROC amounted to 0.894 (95% CI: 0.821-0.966). The SHAP method showed that CRP, the modified five-item frailty index (mFI-5), and ASA body status were among the top three important predicators of POP. CONCLUSION: Our model's good early prediction ability, combined with the implementation of a network risk calculator based on the Catboost model, was anticipated to effectively distinguish high-risk POP groups, facilitating timely intervention.

Nanoassembly-Mediated Exendin-4 Derivatives to Decrease Renal Retention.

An Exendin-4 analogue that was conjugated with 68Ga exhibited an excellent diagnostic effect on insulinoma in clinical practice. On account of its low molecular weight and short hydration radius, 68Ga-Exendin-4 showed high accumulation in kidney tissues. Nanoparticle-mediated strategies have attracted much attention due to polyvalent properties and the size amplification effect. In this study, Exendin-4 derivatives of radionuclide nanodevices were developed and evaluated. The Exendin-4 derivatives consisting of a ternary block recombinant protein were purified by an inverse transition cycle (ITC) and allowed to self-assemble into a nanodevice under physiological conditions. Our results showed that the nanoassemblies of Exendin-4 derivatives formed homogeneous spherical nanoparticles, exhibited outstanding affinity for insulinoma cells, and could be deposited in insulinoma tissues in vivo. The nanoassembly-mediated Exendin-4 derivatives showed fivefold reduced renal retention and exhibited an outstanding tumor-suppression effect.

Identification of two distinct head and neck squamous cell carcinoma subtypes based on fatty acid metabolism-related signatures: Implications for immunotherapy and chemotherapy.

The dysregulation of lipid metabolism is a critical factor in the initiation and progression of tumors. In this investigation, we aim to characterize the molecular subtypes of head and neck squamous cell carcinoma (HNSCC) based on their association with fatty acid metabolism and develop a prognostic risk model. The transcriptomic and clinical data about HNSCC were obtained from public databases. Clustering analysis was conducted on fatty acid metabolism genes (FAMG) associated with prognosis, utilizing the non-negative matrix factorization algorithm. The immune infiltration, response to immune therapy, and drug sensitivity between molecular subtypes were evaluated. Differential expression genes were identified between subtypes, and a prognostic model was constructed using Cox regression analyses. A nomogram for HNSCC was constructed and evaluated. Thirty FAMGs have been found to exhibit differential expression in HNSCC, out of which three are associated with HNSCC prognosis. By performing clustering analysis on these 3 genes, 2 distinct molecular subtypes of HNSCC were identified that exhibit significant heterogeneity in prognosis, immune landscape, and treatment response. Using a set of 7778 genes that displayed differential expression between the 2 molecular subtypes, a prognostic risk model for HNSCC was constructed comprising 11 genes. This model has the ability to stratify HNSCC patients into high-risk and low-risk groups, which exhibit significant differences in prognosis, immune infiltration, and immune therapy response. Moreover, our data suggest that this risk model is negatively correlated with B cells and most T cells, but positively correlated with macrophages, mast cells, and dendritic cells. Ultimately, we constructed a nomogram incorporating both the risk signature and radiotherapy, which has demonstrated exceptional performance in predicting prognosis for HNSCC patients. A molecular classification system and prognostic risk models were developed for HNSCC based on FAMGs. This study revealed the potential involvement of FAMGs in modulating tumor immune microenvironment and response to treatment.

Ice sheet and precession controlled subarctic Pacific productivity and upwelling over the last 550,000 years.

The polar oceans play a vital role in regulating atmospheric CO2 concentrations (pCO2) during the Pleistocene glacial cycles. However, despite being the largest modern reservoir of respired carbon, the impact of the subarctic Pacific remains poorly understood due to limited records. Here, we present high-resolution, 230Th-normalized export productivity records from the subarctic northwestern Pacific covering the last five glacial cycles. Our records display pronounced, glacial-interglacial cyclicity superimposed with precessional-driven variability, with warm interglacial climate and high boreal summer insolation providing favorable conditions to sustain upwelling of nutrient-rich subsurface waters and hence increased export productivity. Our transient model simulations consistently show that ice sheets and to a lesser degree, precession are the main drivers that control the strength and latitudinal position of the westerlies. Enhanced upwelling of nutrient/carbon-rich water caused by the intensification and poleward migration of the northern westerlies during warmer climate intervals would have led to the release of previously sequestered CO2 from the subarctic Pacific to the atmosphere. Our results also highlight the significant role of the subarctic Pacific in modulating pCO2 changes during the Pleistocene climate cycles, especially on precession timescale ( ~ 20 kyr).

A machine learning stacking model accurately estimating gastric fluid volume in patients undergoing elective sedated gastrointestinal endoscopy.

BACKGROUND: The current point-of-care ultrasound (POCUS) assessment of gastric fluid volume primarily relies on the traditional linear approach, which often suffers from moderate accuracy. This study aimed to develop an advanced machine learning (ML) model to estimate gastric fluid volume more accurately. METHODS: We retrospectively analyzed the clinical data and POCUS data (D1: craniocaudal diameter, D2: anteroposterior diameter) of 1386 patients undergoing elective sedated gastrointestinal endoscopy (GIE) at Nanjing First Hospital to predict gastric fluid volume using ML techniques, including six different ML models and a stacking model. We evaluated the models using the adjusted Coefficient of Determination (R2), mean absolute error (MAE) and root mean square error (RMSE). The SHapley Additive exPlanations (SHAP) method was used to interpret the importance of the variables. Finally, a web calculator was constructed to facilitate its clinical application. RESULTS: The stacking model (Linear regression + Multilayer perceptron) performed best, with the highest adjusted R2 of 0.718 (0.632 to 0.804). The mean prediction bias was 4 ml (MAE: 4.008 (3.68 to 4.336)), which is better than that of the linear model. D1 and D2 ranked high in the SHAP plot and performed better in the right lateral decubitus (RLD) than in the supine position. The web calculator can be accessed at https://cheason.shinyapps.io/Stacking_regressor/. CONCLUSION: The stacking model and its web calculator can serve as practical tools for accurately estimating gastric fluid volume in patients undergoing elective sedated GIE. It is recommended that anesthesiologists measure D1 and D2 in the patient's RLD position.

Hypoxia-derived molecular subtype and gene signature characterize prognoses and therapeutic responses in head and neck squamous cell carcinoma.

Intratumoral hypoxia is widely associated with the development of malignancy, treatment resistance, and worse prognoses. This study aims to investigate the role of hypoxia-related genes (HRG) in the immune landscape, treatment response, and prognosis of head and neck squamous cell carcinoma (HNSCC). The transcriptome and clinical data of HNSCC were downloaded from TCGA and GEO databases, and HNSCC molecular subtypes were identified using non-negative matrix factorization (NMF) clustering. Prognostic models were constructed using univariate, Lasso, and multivariate Cox regression analyses. The relationship between HRGs and immune cell infiltration, immune therapy response, and drug sensitivity was evaluated, and a nomogram was constructed. 47 HRGs were differentially expressed in HNSCC, among which 10 genes were significantly associated with HNSCC prognosis. Based on these 10 genes, 2 HNSCC molecular subtypes were identified, which showed significant heterogeneity in terms of prognosis, immune infiltration, and treatment response. A total of 3280 differentially expressed genes were identified between the subtypes. After univariate, Lasso, and multivariate Cox regression analysis, 18 genes were selected to construct a novel prognostic model, which showed a significant correlation with B cells, T cells, and macrophages. Using this model, HNSCC was classified into high-risk and low-risk groups, which exhibited significant differences in terms of prognosis, immune cell infiltration, immune therapy response, and drug sensitivity. Finally, a nomogram based on this model and radiotherapy was constructed, which showed good performance in predicting HNSCC prognosis and guiding personalized treatment strategies. The decision curve analysis demonstrated its better clinical applicability compared to other strategies. HRGs can identify 2 HNSCC molecular subtypes with significant heterogeneity, and the HRG-derived risk model has the potential for prognostic prediction and guiding personalized treatment strategies.

Machine learning-based risk prediction of hypoxemia for outpatients undergoing sedation colonoscopy: a practical clinical tool.

OBJECTIVES: Hypoxemia as a common complication in colonoscopy under sedation and may result in serious consequences. Unfortunately, a hypoxemia prediction model for outpatient colonoscopy has not been developed. Consequently, the objective of our study was to develop a practical and accurate model to predict the risk of hypoxemia in outpatient colonoscopy under sedation. METHODS: In this study, we included patients who received colonoscopy with anesthesia in Nanjing First Hospital from July to September 2021. Risk factors were selected through the least absolute shrinkage and selection operator (LASSO). Prediction models based on logistic regression (LR), random forest classifier (RFC), extreme gradient boosting (XGBoost), support vector machine (SVM), and stacking classifier (SCLF) model were implemented and assessed by standard metrics such as the area under the receiver operating characteristic curve (AUROC), sensitivity and specificity. Then choose the best model to develop an online tool for clinical use. RESULTS: We ultimately included 839 patients. After LASSO, body mass index (BMI) (coefficient = 0.36), obstructive sleep apnea-hypopnea syndrome (OSAHS) (coefficient = 1.32), basal oxygen saturation (coefficient = -0.14), and remifentanil dosage (coefficient = 0.04) were independent risk factors for hypoxemia. The XGBoost model with an AUROC of 0.913 showed the best performance among the five models. CONCLUSION: Our study selected the XGBoost as the first model especially for colonoscopy, with over 95% accuracy and excellent specificity. The XGBoost includes four variables that can be quickly obtained. Moreover, an online prediction practical tool has been provided, which helps screen high-risk outpatients with hypoxemia swiftly and conveniently.

Colonoscopy under sedation is an effective technique for the inspection and treatment of alimentary canal diseases, but hypoxemia associated with this process cannot be ignored, since prolonged or severe hypoxemia may result in several serious consequences.We wanted to develop a practical and accurate model to predict the risk of hypoxemia for outpatient colonoscopy under sedation, which could help clinicians make more accurate and objective judgments to prevent patients from being harmed.A total of 839 patients were included in our study and we constructed five machine learning models and selected the best one, which demonstrated satisfactory performance. On this basis, a user-friendly data interface has been developed for convenient application. Clinicians can log in to this interface at any time and it will automatically calculate the patient's risk of hypoxemia when entering patient information.This study offers evidence that machine learning algorithms can accurately predict the risk of hypoxemia for outpatient colonoscopy under sedation and the model we developed is a practical and interpretable tool that could be used as a clinical decision-making aid.

Prediction of medial knee contact force using multisource fusion recurrent neural network and transfer learning.

Estimation of knee contact force (KCF) during gait provides essential information to evaluate knee joint function. Machine learning has been employed to estimate KCF because of the advantages of low computational cost and real-time. However, the existing machine learning models do not adequately consider gait-related data's temporal-dependent, multidimensional, and highly heterogeneous nature. This study is aimed at developing a multisource fusion recurrent neural network to predict the medial condyle KCF. First, a multisource fusion long short-term memory (MF-LSTM) model was established. Then, we developed a transfer learning strategy based on the MF-LSTM model for subject-specific medial KCF prediction. Four subjects with instrumented tibial prostheses were obtained from the literature. The results showed that the MF-LSTM model could predict medial KCF to a certain high level of accuracy (the mean of ρ = 0.970). The transfer learning model improved the prediction accuracy (the mean of ρ = 0.987). This study shows that the MF-LSTM model is a powerful and accurate computational tool for medial KCF prediction. Introducing transfer learning techniques could further improve the prediction performance for the target subject. This coupling strategy can help clinicians accurately estimate and track joint contact forces in real time.

Online interpretable dynamic prediction models for postoperative delirium after cardiac surgery under cardiopulmonary bypass developed based on machine learning algorithms: A retrospective cohort study.

OBJECTIVE: Postoperative delirium (POD) is strongly associated with poor early and long-term prognosis in cardiac surgery patients with cardiopulmonary bypass (CPB). This study aimed to develop dynamic prediction models for POD after cardiac surgery under CPB using machine learning (ML) algorithms. METHODS: From July 2021 to June 2022, clinical data were collected from patients undergoing cardiac surgery under CPB at Nanjing First Hospital. A dataset from the same center (October 2022 to November 2022) was also used for temporal external validation. We used ML and deep learning to build models in the training set, optimized parameters in the test set, and finally validated the best model in the validation set. The SHapley Additive exPlanations (SHAP) method was introduced to explain the best models. RESULTS: Of the 885 patients enrolled, 221 (25.0%) developed POD. 22 (22.0%) of 100 validation cohort patients developed POD. The preoperative and postoperative artificial neural network (ANN) models exhibited optimal performance. The validation results demonstrated satisfactory predictive performance of the ANN model, with area under the receiver operator characteristic curve (AUROC) values of 0.776 and 0.684 for the preoperative and postoperative models, respectively. Based on the ANN algorithm, we constructed dynamic, highly accurate, and interpretable web risk calculators for POD. CONCLUSIONS: We successfully developed online interpretable dynamic ANN models as clinical decision aids to identify patients at high risk of POD before and after cardiac surgery to facilitate early intervention or care.

Accurately predicting the risk of unfavorable outcomes after endovascular coil therapy in patients with aneurysmal subarachnoid hemorrhage: an interpretable machine learning model.

BACKGROUND: Despite endovascular coiling as a valid modality in treatment of aneurysmal subarachnoid hemorrhage (aSAH), there is a risk of poor prognosis. However, the clinical utility of previously proposed early prediction tools remains limited. We aimed to develop a clinically generalizable machine learning (ML) models for accurately predicting unfavorable outcomes in aSAH patients after endovascular coiling. METHODS: Functional outcomes at 6 months after endovascular coiling were assessed via the modified Rankin Scale (mRS) and unfavorable outcomes were defined as mRS 3-6. Five ML algorithms (logistic regression, random forest, support vector machine, deep neural network, and extreme gradient boosting) were used for model development. The area under precision-recall curve (AUPRC) and receiver operating characteristic curve (AUROC) was used as main indices of model evaluation. SHapley Additive exPlanations (SHAP) method was applied to interpret the best-performing ML model. RESULTS: A total of 371 patients were eventually included into this study, and 85.4% of them had favorable outcomes. Among the five models, the DNN model had a better performance with AUPRC of 0.645 (AUROC of 0.905). Postoperative GCS score, size of aneurysm, and age were the top three powerful predictors. The further analysis of five random cases presented the good interpretability of the DNN model. CONCLUSION: Interpretable clinical prediction models based on different ML algorithms have been successfully constructed and validated, which would serve as reliable tools in optimizing the treatment decision-making of aSAH. Our DNN model had better performance to predict the unfavorable outcomes at 6 months in aSAH patients compared with Yan's nomogram model.

Development and validation of a novel nomogram model to assess the risk of gastric contents in outpatients undergoing elective sedative gastrointestinal endoscopy procedures.

BACKGROUND: Gastric contents may contribute to patients' aspiration during anesthesia. Ultrasound can accurately assess the risk of gastric contents in patients undergoing sedative gastrointestinal endoscopy (GIE) procedures, but its efficiency is limited. Therefore, developing an accurate and efficient model to predict gastric contents in outpatients undergoing elective sedative GIE procedures is greatly desirable. METHODS: This study retrospectively analyzed 1501 patients undergoing sedative GIE procedures. Gastric contents were observed under direct gastroscopic vision and suctioned through the endoscope. High-risk gastric contents were defined as having solid content or liquid volume > 25 ml and pH < 2.5; otherwise, they were considered low-risk gastric contents. Univariate analysis and multivariate analysis were used to select the independent risk factors to predict high-risk gastric contents. Based on the selected independent risk factors, we assigned values to each independent risk factor and established a novel nomogram. The performance of the nomogram was verified in the testing cohort by the metrics of discrimination, calibration, and clinical usefulness. In addition, an online accessible web calculator was constructed. RESULTS: We found BMI, cerebral infarction, cirrhosis, male, age, diabetes, and gastroesophageal reflux disease were risk factors for gastric contents. The AUROCs were 0.911 and 0.864 in the development and testing cohort, respectively. Moreover, the nomogram showed good calibration ability. Decision curve analysis and Clinical impact curve demonstrated that the predictive nomogram was clinically useful. The website of the nomogram was https://medication.shinyapps.io/dynnomapp/. CONCLUSIONS: This study demonstrates that clinical variables can be combined with algorithmic techniques to predict gastric contents in outpatients. Nomogram was constructed from routine variables, and the web calculator had excellent clinical applicability to assess the risk of gastric contents accurately and efficiently in outpatients, assist anesthesiologists in assessment and identify the most appropriate patients for ultrasound.

A convenient machine learning model to predict full stomach and evaluate the safety and comfort improvements of preoperative oral carbohydrate in patients undergoing elective painless gastrointestinal endoscopy.

BACKGROUND AND AIMS: Assessment of the patient's gastric contents is the key to avoiding aspiration incidents, however, there is no effective method to determine whether elective painless gastrointestinal endoscopy (GIE) patients have a full stomach or an empty stomach. And previous studies have shown that preoperative oral carbohydrates (POCs) can improve the discomfort induced by fasting, but there are different perspectives on their safety. This study aimed to develop a convenient, accurate machine learning (ML) model to predict full stomach. And based on the model outcomes, evaluate the safety and comfort improvements of POCs in empty- and full stomach groups. METHODS: We enrolled 1386 painless GIE patients between October 2022 and January 2023 in Nanjing First Hospital, and 1090 patients without POCs were used to construct five different ML models to identify full stomach. The metrics of discrimination and calibration validated the robustness of the models. For the best-performance model, we further interpreted it through SHapley Additive exPlanations (SHAP) and constructed a web calculator to facilitate clinical use. We evaluated the safety and comfort improvements of POCs by propensity score matching (PSM) in the two groups, respectively. RESULTS: Random Forest (RF) model showed the greatest discrimination with the area under the receiver operating characteristic curve (AUROC) 0.837 [95% confidence interval (CI): 79.1-88.2], F1 71.5%, and best calibration with a Brier score of 15.2%. The web calculator can be visited at https://medication.shinyapps.io/RF_model/. PSM results demonstrated that POCs significantly reduced the full stomach incident in empty stomach group (p < 0.05), but no differences in full stomach group (p > 0.05). Comfort improved in both groups and was more significant in empty stomach group. CONCLUSIONS: The developed convenient RF model predicted full stomach with high accuracy and interpretability. POCs were safe and comfortably improved in both groups, with more benefit in empty stomach group. These findings may guide the patients' gastrointestinal preparation.

This study is the first model utilizing advanced ML techniques based on multiple clinical variables to identify full stomach. The model is suitable for patient-rich outpatient clinics, primary hospitals, remote regions, and specific clinical settings where POCUS is not available.The developed convenient RF model predicted full stomach with high accuracy and interpretability. The test cohort AUROC was 0.837. We further established an online accessible individualized risk calculator and provided waterfall plots to increase the interpretability of each prediction.The propensity score matching (PSM) showed that preoperative oral carbohydrate (POCs) were safe and comfortably improved in both groups, with more benefit in empty stomach group. These findings may provide information for anesthesiologists to guide patients on POCs.

A novel interpretative tool for early prediction of low cardiac output syndrome after valve surgery: online machine learning models.

OBJECTIVE: Low cardiac output syndrome (LCOS) is a severe complication after valve surgery, with no uniform standard for early identification. We developed interpretative machine learning (ML) models for predicting LCOS risk preoperatively and 0.5 h postoperatively for intervention in advance. METHODS: A total of 2218 patients undergoing valve surgery from June 2019 to Dec 2021 were finally enrolled to construct preoperative and postoperative models. Logistic regression, support vector machine (SVM), random forest classifier, extreme gradient boosting, and deep neural network were executed for model construction, and the performance of models was evaluated by area under the curve (AUC) of the receiver operating characteristic and calibration curves. Our models were interpreted through SHapley Additive exPlanations, and presented as an online tool to improve clinical operability. RESULTS: The SVM algorithm was chosen for modeling due to better AUC and calibration capability. The AUCs of the preoperative and postoperative models were 0.786 (95% CI 0.729-0.843) and 0.863 (95% CI 0.824-0.902), and the Brier scores were 0.123 and 0.107. Our models have higher timeliness and interpretability, and wider coverage than the vasoactive-inotropic score, and the AUC of the postoperative model was significantly higher. Our preoperative and postoperative models are available online at http://njfh-yxb.com.cn:2022/lcos. CONCLUSIONS: The first interpretable ML tool with two prediction periods for online early prediction of LCOS risk after valve surgery was successfully built in this study, in which the SVM model has the best performance, reserving enough time for early precise intervention in critical care.

Dynamic and visual nomograms to online predict unfavorable outcome of mechanical thrombectomy for acute basilar artery occlusion.

BACKGROUND: The evidence of mechanical thrombectomy (MT) in basilar artery occlusion (BAO) was limited. This study aimed to develop dynamic and visual nomogram models to predict the unfavorable outcome of MT in BAO online. METHODS: BAO patients treated with MT were screened. Preoperative and postoperative nomogram models were developed based on clinical parameters and imaging features. An independent dataset was collected to perform external validation. Web-based calculators were constructed to provide convenient access. RESULTS: A total of 127 patients were included in the study, and 117 of them were eventually included in the analysis. The nomogram models showed robust discrimination, with an area under the receiver operating characteristic (ROC) of 0.841 (preoperative) and 0.916 (postoperative). The calibration curves showed good agreement. The preoperative predictors of an unfavorable outcome were previous stroke, the National Institutes of Health Stroke Scale (NIHSS) at admission, and the posterior circulation Alberta Stroke Program Early Computed Tomography Score (pc-ASPECTS). The postoperative predictors were previous stroke, NIHSS at 24 h, and pc-ASPECTS. CONCLUSION: Dynamic and visual nomograms were constructed and validated for the first time for BAO patients treated with MT, which provided precise predictions for the risk of an unfavorable outcome. The preoperative model may assist clinicians in selecting eligible patients, and the postoperative model may facilitate individualized poststroke management.

A risk prediction model based on machine learning for postoperative cognitive dysfunction in elderly patients with non-cardiac surgery.

BACKGROUND: Early identification of elderly patients undergoing non-cardiac surgery who may be at high risk for postoperative cognitive dysfunction (POCD) can increase the chances of prevention for them, as extra attention and limited resources can be allocated more to these patients. AIM: We performed this analysis with the aim of developing a simple, clinically useful machine learning (ML) model to predict the probability of POCD at 3 months in elderly patients after non-cardiac surgery. METHODS: We collected information on patients who received surgical treatment at Nanjing First Hospital from May 2020 to May 2021. We used LASSO regression to select key features and built 5 ML models to assess the risk of POCD at 3 months in elderly patients after non-cardiac surgery. The Shapley Additive exPlanations (SHAP) and methods were introduced to interpret the best model. RESULTS: A total of 415 patients with non-cardiac surgery were included. The support vector machine (SVM) was the best-performing model of the five ML models. The model showed excellent performance compared to the other four models. The SHAP results showed that VAS score, age, intraoperative hypotension, and preoperative hemoglobin were the four most important features, indicating that the SVM model had good interpretability and reliability. The website of the web-based calculator was https://modricreagan-non-3-pocd-9w2q78.streamlit.app/ . CONCLUSION: Based on six important perioperative variables, we successfully established a series of ML models for predicting POCD occurrence at 3 months after surgery in elderly non-cardiac patients, with SVM model being the best-performing model. Our models are expected to serve as decision aids for clinicians to monitor screened high-risk patients more closely or to consider further interventions.