Machine Learning-Based Survival Prediction Models for Progression-Free and Overall Survival in Advanced-Stage Hodgkin Lymphoma.

PURPOSE: Patients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS). PATIENTS AND METHODS: This study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort). RESULTS: In total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis. CONCLUSION: The new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.

Role of radiomics in staging liver fibrosis: a meta-analysis.

BACKGROUND: Fibrosis has important pathoetiological and prognostic roles in chronic liver disease. This study evaluates the role of radiomics in staging liver fibrosis. METHOD: After literature search in electronic databases (Embase, Ovid, Science Direct, Springer, and Web of Science), studies were selected by following precise eligibility criteria. The quality of included studies was assessed, and meta-analyses were performed to achieve pooled estimates of area under receiver-operator curve (AUROC), accuracy, sensitivity, and specificity of radiomics in staging liver fibrosis compared to histopathology. RESULTS: Fifteen studies (3718 patients; age 47 years [95% confidence interval (CI): 42, 53]; 69% [95% CI: 65, 73] males) were included. AUROC values of radiomics for detecting significant fibrosis (F2-4), advanced fibrosis (F3-4), and cirrhosis (F4) were 0.91 [95%CI: 0.89, 0.94], 0.92 [95%CI: 0.90, 0.95], and 0.94 [95%CI: 0.93, 0.96] in training cohorts and 0.89 [95%CI: 0.83, 0.91], 0.89 [95%CI: 0.83, 0.94], and 0.93 [95%CI: 0.91, 0.95] in validation cohorts, respectively. For diagnosing significant fibrosis, advanced fibrosis, and cirrhosis the sensitivity of radiomics was 84.0% [95%CI: 76.1, 91.9], 86.9% [95%CI: 76.8, 97.0], and 92.7% [95%CI: 89.7, 95.7] in training cohorts, and 75.6% [95%CI: 67.7, 83.5], 80.0% [95%CI: 70.7, 89.3], and 92.0% [95%CI: 87.8, 96.1] in validation cohorts, respectively. Respective specificity was 88.6% [95% CI: 83.0, 94.2], 88.4% [95% CI: 81.9, 94.8], and 91.1% [95% CI: 86.8, 95.5] in training cohorts, and 86.8% [95% CI: 83.3, 90.3], 94.0% [95% CI: 89.5, 98.4], and 88.3% [95% CI: 84.4, 92.2] in validation cohorts. Limitations included use of several methods for feature selection and classification, less availability of studies evaluating a particular radiological modality, lack of a direct comparison between radiology and radiomics, and lack of external validation. CONCLUSION: Although radiomics offers good diagnostic accuracy in detecting liver fibrosis, its role in clinical practice is not as clear at present due to comparability and validation constraints.

A chest CT-based nomogram for predicting survival in acute myeloid leukemia.

BACKGROUND: The identification of survival predictors is crucial for early intervention to improve outcome in acute myeloid leukemia (AML). This study aim to identify chest computed tomography (CT)-derived features to predict prognosis for acute myeloid leukemia (AML). METHODS: 952 patients with pathologically-confirmed AML were retrospectively enrolled between 2010 and 2020. CT-derived features (including body composition and subcutaneous fat features), were obtained from the initial chest CT images and were used to build models to predict the prognosis. A CT-derived MSF nomogram was constructed using multivariate Cox regression incorporating CT-based features. The performance of the prediction models was assessed with discrimination, calibration, decision curves and improvements. RESULTS: Three CT-derived features, including myosarcopenia, spleen_CTV, and SF_CTV (MSF) were identified as the independent predictors for prognosis in AML (P < 0.01). A CT-MSF nomogram showed a performance with AUCs of 0.717, 0.794, 0.796 and 0.792 for predicting the 1-, 2-, 3-, and 5-year overall survival (OS) probabilities in the validation cohort, which were significantly higher than the ELN risk model. Moreover, a new MSN stratification system (MSF nomogram plus ELN risk model) could stratify patients into new high, intermediate and low risk group. Patients with high MSN risk may benefit from intensive treatment (P = 0.0011). CONCLUSIONS: In summary, the chest CT-MSF nomogram, integrating myosarcopenia, spleen_CTV, and SF_CTV features, could be used to predict prognosis of AML.

Prognosis prediction of procalcitonin within 24 h for acute diquat poisoning.

BACKGROUND: To explore the predictive value of procalcitonin (PCT) within 24 h after poisoning for prognosis of acute diquat poisoning. METHODS: This retrospective study included acute diquat poisoning patients in the Nanyang City Hospital between May 2017 and July 2021. RESULTS: Among the 45 patients included, 27 survived. The maximum PCT value within 24 h after poisoning was significantly higher in the non-survival patients [9.65 (2.63, 22.77) vs. 0.15 (0.10, 0.50) µg/mL, P < 0.001] compared to the survival patients. The area under the ROC curve (AUC) indicated that the maximum PCT value within 24 h had a good predictive value (AUC = 0.905, 95% CI: 0.808-1.000) compared to ingested quantity (AUC = 0.879, 95% CI: 0.776-0.981), serum creatinine (AUC = 0.776, 95% CI: 0.640-0.912), or APACHE II score (AUC = 0.778, 95% CI: 0.631-0.925). The predictive value of maximum PCT value within 24 h was comparable with blood lactate (AUC = 0.904, 95%CI: 0.807-1.000). CONCLUSIONS: The maximum PCT value within 24 h after poisoning might be a good predictor for the prognosis of patients with acute diquat poisoning.

Assessing the risk of concurrent mycoplasma pneumoniae pneumonia in children with tracheobronchial tuberculosis: retrospective study.

Objective: This study aimed to create a predictive model based on machine learning to identify the risk for tracheobronchial tuberculosis (TBTB) occurring alongside Mycoplasma pneumoniae pneumonia in pediatric patients. Methods: Clinical data from 212 pediatric patients were examined in this retrospective analysis. This cohort included 42 individuals diagnosed with TBTB and Mycoplasma pneumoniae pneumonia (combined group) and 170 patients diagnosed with lobar pneumonia alone (pneumonia group). Three predictive models, namely XGBoost, decision tree, and logistic regression, were constructed, and their performances were assessed using the receiver's operating characteristic (ROC) curve, precision-recall curve (PR), and decision curve analysis (DCA). The dataset was divided into a 7:3 ratio to test the first and second groups, utilizing them to validate the XGBoost model and to construct the nomogram model. Results: The XGBoost highlighted eight significant signatures, while the decision tree and logistic regression models identified six and five signatures, respectively. The ROC analysis revealed an area under the curve (AUC) of 0.996 for XGBoost, significantly outperforming the other models (p < 0.05). Similarly, the PR curve demonstrated the superior predictive capability of XGBoost. DCA further confirmed that XGBoost offered the highest AIC (43.226), the highest average net benefit (0.764), and the best model fit. Validation efforts confirmed the robustness of the findings, with the validation groups 1 and 2 showing ROC and PR curves with AUC of 0.997, indicating a high net benefit. The nomogram model was shown to possess significant clinical value. Conclusion: Compared to machine learning approaches, the XGBoost model demonstrated superior predictive efficacy in identifying pediatric patients at risk of concurrent TBTB and Mycoplasma pneumoniae pneumonia. The model's identification of critical signatures provides valuable insights into the pathogenesis of these conditions.

Identifying the predictive role and the related drugs of oxidative stress genes in the hepatocellular carcinoma.

BACKGROUND AND AIMS: Oncogenesis and tumor development have been related to oxidative stress (OS). The potential diagnostic utility of OS genes in hepatocellular carcinoma (HCC), however, remains uncertain. As a result, this work aimed to create a novel OS related-genes signature that could be used to predict the survival of HCC patients and to screen OS related-genes drugs that might be used for HCC treatment. METHODS: We used The Cancer Genome Atlas (TCGA) database and the Gene Expression Omnibus (GEO) database to acquire mRNA expression profiles and clinical data for this research and the GeneCards database to obtain OS related-genes. Following that, biological functions from Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) were performed on differentially expressed OS-related genes (DEOSGs). Subsequently, the prognostic risk signature was constructed based on DEOSGs from the TCGA data that were screened by using univariate cox analysis, and the Least Absolute Shrinkage and Selection Operator (LASSO) regression, and multivariate cox analysis. At the same time, we developed a prognostic nomogram of HCC patients based on risk signature and clinical-pathological characteristics. The GEO data was used for validation. We used the receiver operating characteristic (ROC) curve, calibration curves, and Kaplan-Meier (KM) survival curves to examine the prediction value of the risk signature and nomogram. Finally, we screened the differentially expressed OS genes related drugs. RESULTS: We were able to recognize 9 OS genes linked to HCC prognosis. In addition, the KM curve revealed a statistically significant difference in overall survival (OS) between the high-risk and low-risk groups. The area under the curve (AUC) shows the independent prognostic value of the risk signature model. Meanwhile, the ROC curves and calibration curves show the strong prognostic power of the nomogram. The top three drugs with negative ratings were ZM-336372, lestaurtinib, and flunisolide, all of which inversely regulate different OS gene expressions. CONCLUSION: Our findings indicate that OS related-genes have a favorable prognostic value for HCC, which sheds new light on the relationship between oxidative stress and HCC, and suggests potential therapeutic strategies for HCC patients.

Interpretable machine learning in predicting drug-induced liver injury among tuberculosis patients: model development and validation study.

BACKGROUND: The objective of this research was to create and validate an interpretable prediction model for drug-induced liver injury (DILI) during tuberculosis (TB) treatment. METHODS: A dataset of TB patients from Ningbo City was used to develop models employing the eXtreme Gradient Boosting (XGBoost), random forest (RF), and the least absolute shrinkage and selection operator (LASSO) logistic algorithms. The model's performance was evaluated through various metrics, including the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPR) alongside the decision curve. The Shapley Additive exPlanations (SHAP) method was used to interpret the variable contributions of the superior model. RESULTS: A total of 7,071 TB patients were identified from the regional healthcare dataset. The study cohort consisted of individuals with a median age of 47 years, 68.0% of whom were male, and 16.3% developed DILI. We utilized part of the high dimensional propensity score (HDPS) method to identify relevant variables and obtained a total of 424 variables. From these, 37 variables were selected for inclusion in a logistic model using LASSO. The dataset was then split into training and validation sets according to a 7:3 ratio. In the validation dataset, the XGBoost model displayed improved overall performance, with an AUROC of 0.89, an AUPR of 0.75, an F1 score of 0.57, and a Brier score of 0.07. Both SHAP analysis and XGBoost model highlighted the contribution of baseline liver-related ailments such as DILI, drug-induced hepatitis (DIH), and fatty liver disease (FLD). Age, alanine transaminase (ALT), and total bilirubin (Tbil) were also linked to DILI status. CONCLUSION: XGBoost demonstrates improved predictive performance compared to RF and LASSO logistic in this study. Moreover, the introduction of the SHAP method enhances the clinical understanding and potential application of the model. For further research, external validation and more detailed feature integration are necessary.

Development and application of a deep learning-based comprehensive early diagnostic model for chronic obstructive pulmonary disease.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is a frequently diagnosed yet treatable condition, provided it is identified early and managed effectively. This study aims to develop an advanced COPD diagnostic model by integrating deep learning and radiomics features. METHODS: We utilized a dataset comprising CT images from 2,983 participants, of which 2,317 participants also provided epidemiological data through questionnaires. Deep learning features were extracted using a Variational Autoencoder, and radiomics features were obtained using the PyRadiomics package. Multi-Layer Perceptrons were used to construct models based on deep learning and radiomics features independently, as well as a fusion model integrating both. Subsequently, epidemiological questionnaire data were incorporated to establish a more comprehensive model. The diagnostic performance of standalone models, the fusion model and the comprehensive model was evaluated and compared using metrics including accuracy, precision, recall, F1-score, Brier score, receiver operating characteristic curves, and area under the curve (AUC). RESULTS: The fusion model exhibited outstanding performance with an AUC of 0.952, surpassing the standalone models based solely on deep learning features (AUC = 0.844) or radiomics features (AUC = 0.944). Notably, the comprehensive model, incorporating deep learning features, radiomics features, and questionnaire variables demonstrated the highest diagnostic performance among all models, yielding an AUC of 0.971. CONCLUSION: We developed and implemented a data fusion strategy to construct a state-of-the-art COPD diagnostic model integrating deep learning features, radiomics features, and questionnaire variables. Our data fusion strategy proved effective, and the model can be easily deployed in clinical settings. TRIAL REGISTRATION: Not applicable. This study is NOT a clinical trial, it does not report the results of a health care intervention on human participants.

Conditional survival analysis and real-time prognosis prediction in stage III T3-T4 colon cancer patients after surgical resection: a SEER database analysis.

BACKGROUND: Conditional survival (CS) takes into consideration the duration of survival post-surgery and can provide valuable additional insights. The aim of this study was to investigate the risk factors associated with reduced one-year postoperative conditional survival in patients diagnosed with stage III T3-T4 colon cancer and real-time prognosis prediction. Furthermore, we aim to develop pertinent nomograms and predictive models. METHODS: Clinical data and survival outcomes of patients diagnosed with stage III T3-T4 colon cancer were obtained from the Surveillance, Epidemiology, and End Results (SEER) database, covering the period from 2010 to 2019. Patients were divided into training and validation cohorts at a ratio of 7:3. The training set consisted of a total of 11,386 patients for conditional overall survival (cOS) and 11,800 patients for conditional cancer-specific survival (cCSS), while the validation set comprised 4876 patients for cOS and 5055 patients for cCSS. Univariate and multivariate Cox regression analyses were employed to identify independent risk factors influencing one-year postoperative cOS and cCSS. Subsequently, predictive nomograms for cOS and cCSS at 2-year, 3-year, 4-year, and 5-year intervals were constructed based on the identified prognostic factors. The performance of these nomograms was rigorously assessed through metrics including the concordance index (C-index), calibration curves, and the area under curve (AUC) derived from the receiver operating characteristic (ROC) analysis. Clinical utility was further evaluated using decision curve analysis (DCA). RESULTS: A total of 18,190 patients diagnosed with stage III T3-T4 colon cancer were included in this study. Independent risk factors for one-year postoperative cOS and cCSS included age, pT stage, pN stage, pretreatment carcinoembryonic antigen (CEA) levels, receipt of chemotherapy, perineural invasion (PNI), presence of tumor deposits, the number of harvested lymph nodes, and marital status. Sex and tumor site were significantly associated with one-year postoperative cOS, while radiation therapy was notably associated with one-year postoperative cCSS. In the training cohort, the developed nomogram demonstrated a C-index of 0.701 (95% CI, 0.711-0.691) for predicting one-year postoperative cOS and 0.701 (95% CI, 0.713-0.689) for one-year postoperative cCSS. Following validation, the C-index remained robust at 0.707 (95% CI, 0.721-0.693) for one-year postoperative cOS and 0.700 (95% CI, 0.716-0.684) for one-year postoperative cCSS. ROC and calibration curves provided evidence of the model's stability and reliability. Furthermore, DCA underscored the nomogram's superior clinical utility. CONCLUSIONS: Our study developed nomograms and predictive models for postoperative stage III survival in T3-T4 colon cancer with the aim of accurately estimating conditional survival. Survival bias in our analyses may lead to overestimation of survival outcomes, which may limit the applicability of our findings.

Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis.

BACKGROUND: The continuous monitoring and recording of patients' pain status is a major problem in current research on postoperative pain management. In the large number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps. OBJECTIVE: The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of artificial intelligence models for multilevel pain assessment from facial images. METHODS: The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies, 2nd edition tool. The performance of these studies was assessed by metrics including sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the curve (AUC). The intermodal variability was assessed and presented by forest plots. RESULTS: A total of 45 reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC), ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. In total, 6 studies were included in the meta-analysis. Their combined sensitivity was 98% (95% CI 96%-99%), specificity was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31), and AUC was 0.99 (95% CI 0.99-1). The subgroup analysis showed that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9/45) of studies, there were no applicability concerns. CONCLUSIONS: This review summarizes recent evidence in automatic multilevel pain estimation from facial expressions and compared the test accuracy of results in a meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, suggesting that larger databases and metrics evaluating multiclass classification performance could improve future studies. TRIAL REGISTRATION: PROSPERO CRD42023418181; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=418181.

Non-invasive prediction nomogram for predicting significant fibrosis in patients with metabolic-associated fatty liver disease: a cross-sectional study.

BACKGROUND AND AIM: This study aims to validate the efficacy of the conventional non-invasive score in predicting significant fibrosis in metabolic-associated fatty liver disease (MAFLD) and to develop a non-invasive prediction model for MAFLD. METHODS: This cross-sectional study was conducted among 7701 participants with MAFLD from August 2018 to December 2023. All participants were divided into a training cohort and a validation cohort. The study compared different subgroups' demographic, anthropometric, and laboratory examination indicators and conducted logistic regression analysis to assess the correlation between independent variables and liver fibrosis. Nomograms were created using the logistic regression model. The predictive values of noninvasive models and nomograms were evaluated using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA). RESULTS: Four nomograms were developed for the quantitative analysis of significant liver fibrosis risk based on the multivariate logistic regression analysis results. The nomogram's area under ROC curves (AUC) was 0.710, 0.714, 0.748, and 0.715 in overall MAFLD, OW-MAFLD, Lean-MAFLD, and T2DM-MAFLD, respectively. The nomogram had a higher AUC in all MAFLD participants and OW-MAFLD than the other non-invasive scores. The DCA curve showed that the net benefit of each nomogram was higher than that of APRI and FIB-4. In the validation cohort, the AUCs of the nomograms were 0.722, 0.750, 0.719, and 0.705, respectively. CONCLUSION: APRI, FIB-4, and NFS performed poorly predicting significant fibrosis in patients with MAFLD. The new model demonstrated improved diagnostic accuracy and clinical applicability in identifying significant fibrosis in MAFLD.

Improving predictions: Enhancing in-hospital mortality forecast for ICU patients with sepsis-induced coagulopathy using a stacking ensemble model.

The incidence of sepsis-induced coagulopathy (SIC) is high, leading to increased mortality rates and prolonged hospitalization and intensive care unit (ICU) stays. Early identification of SIC patients at risk of in-hospital mortality can improve patient prognosis. The objective of this study is to develop and validate machine learning (ML) models to dynamically predict in-hospital mortality risk in SIC patients. A ML model is established based on the Medical Information Mart for Intensive Care IV (MIMIC-IV) database to predict in-hospital mortality in SIC patients. Utilizing univariate feature selection for feature screening. The optimal model was determined by calculating the area under the curve (AUC) with a 95% confidence interval (CI). The optimal model was interpreted using Shapley Additive Explanation (SHAP) values. Among the 3112 SIC patients included in MIMIC-IV, a total of 757 (25%) patients experienced mortality during their ICU stay. Univariate feature selection helps us to pick out the 20 most critical variables from the original feature. Among the 10 developed machine learning models, the stacking ensemble model exhibited the highest AUC (0.795, 95% CI: 0.763-0.827). Anion gap and age emerged as the most significant features for predicting the mortality risk in SIC. In this study, an ML model was constructed that exhibited excellent performance in predicting in-hospital mortality risk in SIC patients. Specifically, the stacking ensemble model demonstrated superior predictive ability.

Predictors of Developing a Complex Course of Osteomyelitis in Patients with Sickle Cell Anaemia.

Objectives: Despite the numerous advances in management strategies, treating osteomyelitis in individuals with sickle cell disease (SCD) remains a significant challenge, leading to severe long-term consequences. This study aimed to assess the key factors potentially linked to a complex progression of osteomyelitis in patients diagnosed with SCD. Methods: A cohort of 34 patients was identified and their progress was monitored over a span of 12 months during a 10-year period (2010-2020). The variables under investigation encompassed demographic and clinical traits, laboratory analyses and imaging data, as well as the treatment strategies employed. Results: The risk prediction model pinpointed 5 factors (severity of SCD, involvement of lower limbs, presence of bacteraemia, magnetic resonance image [MRI] findings and utilisation of surgical debridement) that exhibited an area under the curve (AUC) exceeding 0.7. Causative organisms were identified in 9 out of the total 34 patients (26.47%). A total of 17 patients displayed a severe course of SCD (AUC = 7.88), with MRI being highlighted as a valuable contributing factor (AUC = 7.88). Furthermore, 13 patients (38.2%) underwent surgical debridement, a procedure that yielded a statistically significant P value of 0.012 and an AUC of 0.714. Conclusion: Osteomyelitis within the context of severe SCD, particularly when accompanied by lower extremity infection, bacteraemia, positive MRI findings and the need for surgical debridement, emerges as a cluster of risk factors predisposing individuals to osteomyelitis relapse and a more complex disease course.

Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers.

BACKGROUND: This study aimed to develop and validate an interpretable machine-learning model that utilizes clinical features and inflammatory biomarkers to predict the risk of in-hospital mortality in critically ill patients suffering from sepsis. METHODS: We enrolled all patients diagnosed with sepsis in the Medical Information Mart for Intensive Care IV (MIMIC-IV, v.2.0), eICU Collaborative Research Care (eICU-CRD 2.0), and the Amsterdam University Medical Centers databases (AmsterdamUMCdb 1.0.2). LASSO regression was employed for feature selection. Seven machine-learning methods were applied to develop prognostic models. The optimal model was chosen based on its accuracy, F1 score and area under curve (AUC) in the validation cohort. Moreover, we utilized the SHapley Additive exPlanations (SHAP) method to elucidate the effects of the features attributed to the model and analyze how individual features affect the model's output. Finally, Spearman correlation analysis examined the associations among continuous predictor variables. Restricted cubic splines (RCS) explored potential non-linear relationships between continuous risk factors and in-hospital mortality. RESULTS: 3535 patients with sepsis were eligible for participation in this study. The median age of the participants was 66 years (IQR, 55-77 years), and 56% were male. After selection, 12 of the 45 clinical parameters collected on the first day after ICU admission remained associated with prognosis and were used to develop machine-learning models. Among seven constructed models, the eXtreme Gradient Boosting (XGBoost) model achieved the best performance, with an AUC of 0.94 and an F1 score of 0.937 in the validation cohort. Feature importance analysis revealed that Age, AST, invasive ventilation treatment, and serum urea nitrogen (BUN) were the top four features of the XGBoost model with the most significant impact. Inflammatory biomarkers may have prognostic value. Furthermore, SHAP force analysis illustrated how the constructed model visualized the prediction of the model. CONCLUSIONS: This study demonstrated the potential of machine-learning approaches for early prediction of outcomes in patients with sepsis. The SHAP method could improve the interoperability of machine-learning models and help clinicians better understand the reasoning behind the outcome.

Identification of important modules and biomarkers in diabetic cardiomyopathy based on WGCNA and LASSO analysis.

Background: Diabetic cardiomyopathy (DCM) lacks specific and sensitive biomarkers, and its diagnosis remains a challenge. Therefore, there is an urgent need to develop useful biomarkers to help diagnose and evaluate the prognosis of DCM. This study aims to find specific diagnostic markers for diabetic cardiomyopathy. Methods: Two datasets (GSE106180 and GSE161827) from the GEO database were integrated to identify differentially expressed genes (DEGs) between control and type 2 diabetic cardiomyopathy. We assessed the infiltration of immune cells and used weighted coexpression network analysis (WGCNA) to construct the gene coexpression network. Then we performed a clustering analysis. Finally, a diagnostic model was built by the least absolute shrinkage and selection operator (LASSO). Results: A total of 3066 DEGs in the GSE106180 and GSE161827 datasets. There were differences in immune cell infiltration. According to gene significance (GS) > 0.2 and module membership (MM) > 0.8, 41 yellow Module genes and 1474 turquoise Module genes were selected. Hub genes were mainly related to the "proteasomal protein catabolic process", "mitochondrial matrix" and "protein processing in endoplasmic reticulum" pathways. LASSO was used to construct a diagnostic model composed of OXCT1, CACNA2D2, BCL7B, EGLN3, GABARAP, and ACADSB and verified it in the GSE163060 and GSE175988 datasets with AUCs of 0.9333 (95% CI: 0.7801-1) and 0.96 (95% CI: 0.8861-1), respectively. H9C2 cells were verified, and the results were similar to the bioinformatics analysis. Conclusion: We constructed a diagnostic model of DCM, and OXCT1, CACNA2D2, BCL7B, EGLN3, GABARAP, and ACADSB were potential biomarkers, which may provide new insights for improving the ability of early diagnosis and treatment of diabetic cardiomyopathy.

Development and validation a nomogram prediction model for early diagnosis of bloodstream infections in the intensive care unit.

Purpose: This study aims to develop and validate a nomogram for predicting the risk of bloodstream infections (BSI) in critically ill patients based on their admission status to the Intensive Care Unit (ICU). Patients and methods: Patients' data were extracted from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database (training set), the Beijing Friendship Hospital (BFH) database (validation set) and the eICU Collaborative Research Database (eICU-CRD) (validation set). Univariate logistic regression analyses were used to analyze the influencing factors, and lasso regression was used to select the predictive factors. Model performance was assessed using area under receiver operating characteristic curve (AUROC) and Presented as a Nomogram. Various aspects of the established predictive nomogram were evaluated, including discrimination, calibration, and clinical utility. Results: The model dataset consisted of 14930 patients (1444 BSI patients) from the MIMIC-IV database, divided into the training and internal validation datasets in a 7:3 ratio. The eICU dataset included 2100 patients (100 with BSI) as the eICU validation dataset, and the BFH dataset included 419 patients (21 with BSI) as the BFH validation dataset. The nomogram was constructed based on Glasgow Coma Scale (GCS), sepsis related organ failure assessment (SOFA) score, temperature, heart rate, respiratory rate, white blood cell (WBC), red width of distribution (RDW), renal replacement therapy and presence of liver disease on their admission status to the ICU. The AUROCs were 0.83 (CI 95%:0.81-0.84) in the training dataset, 0.88 (CI 95%:0.88-0.96) in the BFH validation dataset, and 0.75 (95%CI 0.70-0.79) in the eICU validation dataset. The clinical effect curve and decision curve showed that most areas of the decision curve of this model were greater than 0, indicating that this model has a certain clinical effectiveness. Conclusion: The nomogram developed in this study provides a valuable tool for clinicians and nurses to assess individual risk, enabling them to identify patients at a high risk of bloodstream infections in the ICU.

The Validation and Determination of Empagliflozin Concentration in the Presence of Grapefruit Juice Using HPLC for Pharmacokinetic Applications.

Type 2 diabetes mellitus is a multifactorial disorder whose primary manifestation usually initiates with elevated blood sugar levels. Several antidiabetic agents are used to manage type 2 diabetes mellitus, of which empagliflozin is an oral sodium-glucose co-transporter (SGLT-2) inhibitor in the kidney. This research aims to develop and validate a simple analytical method for determining empagliflozin levels in biological fluid and to further evaluate grapefruit juice's impact on empagliflozin pharmacokinetics in rats. High-Performance Liquid Chromatography (HPLC) was used to establish a simple, rapid, and accurate method for determining empagliflozin levels in rat plasma, in the presence of grapefruit juice. Four groups of rats (n = 10 rats in each) were used in the preclinical study. Group A (healthy rats) received empagliflozin alone; Group B (healthy rats) received empagliflozin with grapefruit; Group C (diabetic rats) received empagliflozin with grapefruit; and Group D (healthy, negative control) received no medication. The rats (n = 10) were given grapefruit juice instead of water for seven days before receiving the empagliflozin dose (0.16 mg/kg). Some pharmacokinetic parameters for each group were determined. The maximum plasma concentration (Cmax) and area under the curve (AUC) of empagliflozin in Group A without grapefruit intake were 730 ng/mL and 9264.6 ng × h/mL, respectively, with Tmax (2 h). In Group B, Cmax was 1907 ng/mL and AUC was 10,290.75 ng × h/mL in the presence of grapefruit, with Tmax (1 h); whereas, in Group C, the Cmax was 2936 ng/mL and AUC was 18657 ng × h/mL, with Tmax (2 h). In conclusion, our results showed that the co-administration of grapefruit with empagliflozin should be cautiously monitored and avoided, in which grapefruit elevates the plasma level of empagliflozin. This may be attributed to the inhibition of the uridine enzyme in the grapefruit by hesperidin, naringin, and flavonoid.

Clinical pharmacokinetics of atropine oral gel formulation in healthy volunteers.

Sialorrhea or drooling is a common problem in children and adults with neurodevelopmental disorders. It can negatively impact the quality of life due to its physical and psychological manifestations. Providers commonly prescribe atropine eye drops for topical administration to the oral mucosa, as an off-label treatment to manage sialorrhea. However, the off-label use of atropine eye drops can be associated with medication and dosing errors and systemic side effects. To address these limitations of treatment, we developed a mucoadhesive topical oral gel formulation of atropine as an alternative route to off-label administration of atropine eye drops. In this clinical pharmacokinetic (PK) study, we evaluated the safety and PK of atropine gel (0.01% w/w) formulation after single-dose administration to the oral mucosa in 10 healthy volunteers. The PK data showed that after topical administration to the oral mucosa, atropine followed a two-compartment PK profile. The maximum plasma concentration and area under the curve extrapolated to infinite time were 0.14 ng/mL and 0.74 h·ng·mL-1 , respectively. The absorption rate constant calculated by the compartmental analysis was 0.4 h-1 . Safety parameters, such as heart rate, blood pressure, and oxygen saturation, did not significantly change before and after administration of the gel formulation, and no adverse events were observed in all participants who received atropine gel. These data indicate that atropine gel formulation has a satisfactory PK profile, is well-tolerated at the dose studied, and can be further considered for clinical development as a drug product to treat sialorrhea.

Safety, pharmacokinetics, and pharmacodynamics of anti-IL-4Rα antibody SHR-1819 in healthy subjects: A randomized, controlled phase I study.

SHR-1819 is a novel anti-IL-4Rα monoclonal antibody currently under clinical development for use in patients with type 2 inflammatory diseases. In this randomized, double-blind, placebo-controlled, single-dose escalation phase I trial, we evaluated the safety, tolerability, pharmacokinetics, and pharmacodynamics of SHR-1819 in healthy subjects. Subjects received a single subcutaneous injection of SHR-1819 or placebo, with dose escalation starting at 60 mg and subsequently increasing to 120, 240, 360, and 720 mg. A total of 42 eligible subjects were randomized, and 33 received SHR-1819 (1 subject in the 60 mg cohort and 8 subjects each in the 120, 240, 360 , and 720 mg cohorts) and 9 received placebo. SHR-1819 was well-tolerated, with the majority of adverse events being mild in severity. The exposure of SHR-1819 increased in a manner greater than proportionally with a dose range of 120 to 720 mg. The median Tmax was within 4-7 days (60-720 mg), and the mean half-life ranged from 2.88 to 5.97 days (120-720 mg). The clearance rate of SHR-1819 exhibited a decrease with increasing dose level. Administration of SHR-1819 resulted in a certain degree of reduction in the percentage change from baseline in concentrations of inflammatory biomarkers TARC/CCL17 and IgE, while the reduction of TARC/CCL17 concentrations showed a dose-dependent trend. More than half of the total subjects treated with SHR-1819 were reported antidrug antibody-negative. The preliminary data from this phase I study support further development of SHR-1819 for the treatment of type 2 inflammatory diseases.

Dose safety and pharmacodynamics of subcutaneous bupivacaine in a novel extended-release microparticle formulation: A phase 1, dose-ascending study in male volunteers.

A novel microparticle-based extended-release local anaesthetic containing a bupivacaine/poly-lactic-co-glycolic acid (PLGA; LIQ865A) or plain bupivacaine (LIQ865B) was examined in a first-in-human trial. The objectives were to examine the dose safety/tolerability and pharmacodynamics. Randomized subcutaneous injections of LIQ865A (n = 16) or LIQ865B (n = 12) and diluent, contralaterally, were administered in a dose-ascending manner (150- to 600-mg bupivacaine). Subjects were admitted 24 h post-injection and followed for 30 days post-injection. The risk ratios (RRs; 95% CI) of erythematous reactions for LIQ865A versus diluent was 9.00 (1.81-52.23; P = 0.006) and for LIQ865B versus diluent 2.50 (0.69-9.94; P = 0.37). The RR for the development of hematomas (LIQ865A versus diluent) were 3.25 (1.52-8.16; P = 0.004) and 4.00 (0.72-24.89; P = 0.32) (LIQ865B versus diluent). Subcutaneous indurations persisting for 4-13 weeks were seen in 6/16 subjects receiving LIQ865A. One subject receiving LIQ865A (600-mg bupivacaine) developed intermittent central nervous system (CNS) symptoms of local anaesthetic systemic toxicity (85 min to 51 h post-injection) coinciding with plasma peak bupivacaine concentrations (490-533 ng/ml). Both LIQ865 formulations demonstrated dose-dependent hypoesthesia and hypoalgesia. The duration of analgesia ranged between 37 and 86 h. The overall number of local adverse events, however, prohibits clinical application without further pharmacological modifications.