Machine learning-based prediction of clinical outcomes after traumatic brain injury: Hidden information of early physiological time series.

AIMS: To assess the predictive value of early-stage physiological time-series (PTS) data and non-interrogative electronic health record (EHR) signals, collected within 24 h of ICU admission, for traumatic brain injury (TBI) patient outcomes. METHODS: Using data from TBI patients in the multi-center eICU database, we focused on in-hospital mortality, neurological status based on the Glasgow Coma Score (mGCS) motor subscore at discharge, and prolonged ICU stay (PLOS). Three machine learning (ML) models were developed, utilizing EHR features, PTS signals collected 24 h after ICU admission, and their combination. External validation was performed using the MIMIC III dataset, and interpretability was enhanced using the Shapley Additive Explanations (SHAP) algorithm. RESULTS: The analysis included 1085 TBI patients. Compared to individual models and existing scoring systems, the combination of EHR and PTS features demonstrated comparable or even superior performance in predicting in-hospital mortality (AUROC = 0.878), neurological outcomes (AUROC = 0.877), and PLOS (AUROC = 0.835). The model's performance was validated in the MIMIC III dataset, and SHAP algorithms identified six key intervention points for EHR features related to prognostic outcomes. Moreover, the EHR results (All AUROC >0.8) were translated into online tools for clinical use. CONCLUSION: Our study highlights the importance of early-stage PTS signals in predicting TBI patient outcomes. The integration of interpretable algorithms and simplified prediction tools can support treatment decision-making, contributing to the development of accurate prediction models and timely clinical intervention.

Explainable machine learning for predicting neurological outcome in hemorrhagic and ischemic stroke patients in critical care.

Aim: The objective of this study is to develop accurate machine learning (ML) models for predicting the neurological status at hospital discharge of critically ill patients with hemorrhagic and ischemic stroke and identify the risk factors associated with the neurological outcome of stroke, thereby providing healthcare professionals with enhanced clinical decision-making guidance. Materials and methods: Data of stroke patients were extracted from the eICU Collaborative Research Database (eICU-CRD) for training and testing sets and the Medical Information Mart for Intensive Care IV (MIMIC IV) database for external validation. Four machine learning models, namely gradient boosting classifier (GBC), logistic regression (LR), multi-layer perceptron (MLP), and random forest (RF), were used for prediction of neurological outcome. Furthermore, shapley additive explanations (SHAP) algorithm was applied to explain models visually. Results: A total of 1,216 hemorrhagic stroke patients and 954 ischemic stroke patients from eICU-CRD and 921 hemorrhagic stroke patients 902 ischemic stroke patients from MIMIC IV were included in this study. In the hemorrhagic stroke cohort, the LR model achieved the highest area under curve (AUC) of 0.887 in the test cohort, while in the ischemic stroke cohort, the RF model demonstrated the best performance with an AUC of 0.867 in the test cohort. Further analysis of risk factors was conducted using SHAP analysis and the results of this study were converted into an online prediction tool. Conclusion: ML models are reliable tools for predicting hemorrhagic and ischemic stroke neurological outcome and have the potential to improve critical care of stroke patients. The summarized risk factors obtained from SHAP enable a more nuanced understanding of the reasoning behind prediction outcomes and the optimization of the treatment strategy.

Macrophage ß2-AR activation amplifies inflammation in wound healing by upregulating Trem1 via the cAMP/PKA/CREB pathway.

BACKGROUND: Inflammation is an important part of the wound healing process. The stress hormone epinephrine has been demonstrated to modulate the inflammatory response via its interaction with ß2-adrenergic receptor (ß2-AR). However, the precise molecular mechanism through which ß2-AR exerts its influence on inflammation during the wound healing process remains an unresolved question. METHODS: Transcriptome datasets of wound and macrophages from the GEO database were reanalyzed using bioinformatics. The role of ß2-AR in wound healing was explored by a mouse hind paw plantar wound model, and histological analyses were performed to assess wound healing. In vivo and in vitro assays were performed to elucidate the role of ß2-AR on the inflammatory response. Triggering receptor expressed on myeloid cells 1 (Trem1) was knocked down with siRNA on RAW cells and western blot and qPCR assays were performed. RESULTS: Trem1 was upregulated within 24 h of wounding, and macrophage ß2-AR activation also upregulated Trem1. In vivo experiments demonstrated that ß2-AR agonists impaired wound healing, accompanied by upregulation of Trem1 and activation of cAMP/PKA/CREB pathway, as well as by a high level of pro-inflammatory cytokine production. In vitro experiments showed that macrophage ß2-AR activation amplified LPS-induced inflammation, and knockdown of Trem1 reversed this effect. Using activator and inhibitor of cAMP, macrophage ß2-AR activation was confirmed to upregulate Trem1 via the cAMP/PKA/CREB pathway. CONCLUSION: Our study found that ß2-AR agonists increase Trem1 expression in wounds, accompanied by amplification of the inflammatory response, impairing wound healing. ß2-AR activation in RAW cells induces Trem1 upregulation via the cAMP/PKA/CREB pathway and amplifies LPS-induced inflammatory responses.

Prognosis and pain dissection of novel signatures in kidney renal clear cell carcinoma based on fatty acid metabolism-related genes.

Renal cell carcinoma (RCC) is a malignant tumor that is characterized by the accumulation of intracellular lipid droplets. The prognostic value of fatty acid metabolism-related genes (FMGs) in RCC remains unclear. Alongside this insight, we collected data from three RCC cohorts, namely, The Cancer Genome Atlas (TCGA), E-MTAB-1980, and GSE22541 cohorts, and identified a total of 309 FMGs that could be associated with RCC prognosis. First, we determined the copy number variation and expression levels of these FMGs, and identified 52 overall survival (OS)-related FMGs of the TCGA-KIRC and the E-MTAB-1980 cohort data. Next, 10 of these genes-FASN, ACOT9, MID1IP1, CYP2C9, ABCD1, CPT2, CRAT, TP53INP2, FAAH2, and PTPRG-were identified as pivotal OS-related FMGs based on least absolute shrinkage and selection operator and Cox regression analyses. The expression of some of these genes was confirmed in patients with RCC by immunohistochemical analyses. Kaplan-Meier analysis showed that the identified FMGs were effective in predicting the prognosis of RCC. Moreover, an optimal nomogram was constructed based on FMG-based risk scores and clinical factors, and its robustness was verified by time-dependent receiver operating characteristic analysis, calibration curve analysis, and decision curve analysis. We have also described the biological processes and the tumor immune microenvironment based on FMG-based risk score classification. Given the close association between fatty acid metabolism and cancer-related pain, our 10-FMG signature may also serve as a potential therapeutic target with dual effects on ccRCC prognosis and cancer pain and, therefore, warrants further investigation.