Mechanical Learning for Prediction of Sepsis-Associated Encephalopathy.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhao L
PROVIDER: S-EPMC8636425 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveOur study aimed to identify predictors as well as develop machine learning (ML) models to predict the risk of 30-day mortality in patients with sepsis-associated encephalopathy (SAE).Materials and methodsML models were developed and validated based on a public database named Medical Information Mart for Intensive Care (MIMIC)-IV. Models were compared by the area under the curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive values, and Hosmer-Lemeshow good of fit test.ResultsOf 6994 patients in MIMIC-IV included in the final cohort, a total of 1232 (17.62%) patients died following SAE. Recursive feature elimination (RFE) selected 15 variables, including acute physiology score III (APSIII), Glasgow coma score (GCS), sepsis related organ failure assessment (SOFA), Charlson comorbidity index (CCI), red blood cell volume distribution width (RDW), blood urea nitrogen (BUN), age, respiratory rate, PaO2, temperature, lactate, creatinine (CRE), malignant cancer, metastatic solid tumor, and platelet (PLT). The validation cohort demonstrated all ML approaches had higher discriminative ability compared with the bagged trees (BT) model, although the difference was not statistically significant. Furthermore, in terms of the calibration performance, the artificial neural network (NNET), logistic regression (LR), and adapting boosting (Ada) models had a good calibration-namely, a high accuracy of prediction, with P-values of 0.831, 0.119, and 0.129, respectively.ConclusionsThe ML models, as demonstrated by our study, can be used to evaluate the prognosis of SAE patients in the intensive care unit (ICU). Online calculator could facilitate the sharing of predictive models.
| S-EPMC9252033 | biostudies-literature
Project description:Cellular pathophysiology of sepsis associated encephalopathy (SAE) remains poorly characterised. Brain pathology in SAE, which is manifested by impaired perception, consciousness and cognition, results from multifactorial events, including high levels of systemic cytokines, microbial components and endotoxins, which all damage the brain barriers, instigate neuroinflammation and cause homeostatic failure. Astrocytes, being the principal homeostatic cells of the central nervous system contribute to the brain defence against infection. Forming multifunctional anatomical barriers, astroglial cells maintain brain-systemic interfaces and restrict the damage to the nervous tissue. Astrocytes detect, produce and integrate inflammatory signals between immune cells and cells of brain parenchyma, thus regulating brain immune response. In SAE astrocytes are present in both reactive and astrogliopathic states; balance between these states define evolution of pathology and neurological outcomes. In humans pathophysiology of SAE is complicated by frequent presence of comorbidities, as well as age-related remodelling of the brain tissue with senescence of astroglia; these confounding factors further impact upon SAE progression and neurological deficits.
| S-EPMC7089215 | biostudies-literature
Project description:Sepsis is a major cause of death in intensive care units worldwide. The acute phase of sepsis is often accompanied by sepsis-associated encephalopathy, which is highly associated with increased mortality. Moreover, in the chronic phase, more than 50% of surviving patients suffer from severe and long-term cognitive deficits compromising their daily quality of life and placing an immense burden on primary caregivers. Due to a growing number of sepsis survivors, these long-lasting deficits are increasingly relevant. Despite the high incidence and clinical relevance, the pathomechanisms of acute and chronic stages in sepsis-associated encephalopathy are only incompletely understood, and no specific therapeutic options are yet available. Here, we review the emergence of sepsis-associated encephalopathy from initial clinical presentation to long-term cognitive impairment in sepsis survivors and summarize pathomechanisms potentially contributing to the development of sepsis-associated encephalopathy.
| S-EPMC7141293 | biostudies-literature
Project description:BackgroundSepsis-associated encephalopathy (SAE) is defined as diffuse brain dysfunction associated with sepsis and leads to a high mortality rate. We aimed to develop and validate an optimal machine-learning model based on clinical features for early predicting sepsis-associated acute brain injury.MethodsWe analyzed adult patients with sepsis from the Medical Information Mart for Intensive Care (MIMIC III) clinical database. Candidate models were trained using random forest, support vector machine (SVM), decision tree classifier, gradients boosting machine (GBM), multiple layer perception (MLP), extreme gradient boosting (XGBoost), light gradients boosting machine (LGBM) and a conventional logistic regression model. These methods were applied to develop and validate the optimal model based on its accuracy and area under curve (AUC).ResultsIn total, 12,460 patients with sepsis met inclusion criteria, and 6,284 (50.4%) patients suffered from sepsis-associated acute brain injury. Compared other models, the LGBM model achieved the best performance. The AUC for both train set and test set indicated excellent validity (Trainset AUC 0.91, Testset AUC 0.87). Feature importance analysis showed that glucose, age, mean arterial pressure, heart rate, hemoglobin, and length of ICU stay were the top 6 important clinical factors to predict occurrence of sepsis-associated acute brain injury.ConclusionAlmost half of patients admitted to ICU with sepsis had sepsis-associated acute brain injury. The LGBM model better identify patients with sepsis-associated acute brain injury than did other machine-learning models. Glucose, age, and mean arterial pressure were the three most important clinical factors to predict occurrence of sepsis-associated acute brain injury.
| S-EPMC9575145 | biostudies-literature
Project description:Brain dysfunction is frequently observed in sepsis as a consequence of changes in cerebral structure and metabolism, resulting in worse outcome and reduced life-quality of surviving patients. However, the mechanisms of sepsis-associated encephalopathy development and a better characterization of this syndrome in vivo are lacking. Here, we used magnetic resonance imaging (MRI) techniques to assess brain morphology and metabolism in a murine sepsis model (cecal ligation and puncture, CLP). Sham-operated and CLP mice were subjected to a complete MRI session at baseline, 6 and 24 h after surgery. Accumulation of vasogenic edematic fluid at the base of the brain was observed in T(2)-weighted image at 6 and 24 h after CLP. Also, the water apparent diffusion coefficients in both hippocampus and cortex were decreased, suggesting a cytotoxic edema in brains of nonsurvival septic animals. Moreover, the N-acetylaspartate/choline ratio was reduced in brains of septic mice, indicating neuronal damage. In conclusion, noninvasive assessment by MRI allowed the identification of new aspects of brain damage in sepsis, including cytotoxic and vasogenic edema as well as neuronal damage. These findings highlight the potential applications of MRI techniques for the diagnostic and therapeutic studies in sepsis.
| S-EPMC2949132 | biostudies-other
Project description:Sepsis-associated encephalopathy (SAE) is a risk factor for cognitive and memory dysfunction; however, the mechanism remains unclear. Brain-derived neurotrophic factor (BDNF) was reported to have a positive effect on cognition and emotion regulation, but the study of its precursor, proBDNF, has been limited. This study aimed to elucidate the effects and associated mechanisms of hippocampal proBDNF in a lipopolysaccharide (LPS)-induced SAE mouse model. In this study, we found that the mice exhibited cognitive dysfunction on day 7 after LPS injection. The expression of proBDNF and its receptor, p75 NTR , was also increased in the hippocampus, while the levels of BDNF and its receptor, TrkB, were decreased. A co-localization study showed that proBDNF and p75 NTR were mainly co-localized with neurons. Furthermore, LPS treatment reduced the expression of NeuN, Nissl bodies, GluR4, NR1, NR2A, and NR2B in the hippocampus of SAE mice. Furthermore, an intrahippocampal or intraperitoneal injection of anti-proBDNF antibody was able to ameliorate LPS-induced cognitive dysfunction and restore the expression of NeuN, Nissl bodies, GluR4, NR1, NR2A, NR2B, and PSD95. These results indicated that treatment with brain delivery by an intrahippocampal and systemic injection of mAb-proBDNF may represent a potential therapeutic strategy for treating patients with SAE.
| S-EPMC8329425 | biostudies-literature
Project description:Sepsis-associated encephalopathy (SAE) is a major and frequent complication in patients with sepsis resulting in delirium and premature death. Sepsis survivors commonly suffer from long-term cognitive impairment causing immense burden on patients, caregivers, and economic health systems. Underlying pathophysiology of SAE related cognitive deficits is largely unresolved, Thus treatment options are missing. We report that experimental polymicrobial sepsis in mice induces synaptic pathology in the central nervous system underlying defective long-term potentiation and cognitive dysfunction. Analysis of differentially expressed genes revealed severely affected downregulation of genes related to neuronal and synaptic signaling in the brain, e.g. of the activity-regulated cytoskeleton-associated protein (Arc ), of the transcription-regulatory EGR family, and of the dual-specificity phosphatase 6 (Dusp6). On the protein level, ARC expression and mitogen-activated protein (MAP) kinase signaling in the brain was disturbed during SAE. For targeted rescue of dysregulated synaptic signaling and plasticity, we overexpressed ARC in the hippocampus by bilateral in-vivo stereotactic microinjection of an adeno-associated virus containing a neuron-specific plasmid of the Arc transgene. Hereby, defective synaptic plasticity and signaling in the hippocampus were restored and memory function improved. Accordingly, synaptic plasticity, neuronal spine pathology, and memory dysfunction also improved when post-septic mice were subjected to enriched environment demonstrating the potential for activity-induced recovery of long-term cognitive dysfunction. Together, we identified synaptic pathology of neurocognitive dysfunction after severe systemic infection and provide a proof-of-concept approach to interfere with SAE pathomechanisms leading to cognitive improvement.
2021-02-27 | GSE167610 | GEO
Project description:Sepsis-associated encephalopathy (SAE) is common in septic patients and is associated with adverse outcomes. The gut microbiota has been recognized as a key mediator of neurological disease development. However, the exact role of the gut microbiota in regulating SAE remains elusive. Here, we investigated the role of the gut microbiota in SAE and its underlying mechanisms. Cecal ligation and puncture (CLP) was conducted to induce sepsis in mice. Neurological scores were recorded to distinguish SAE-resistant (SER) (score of >6 at 36 h postoperatively) from SAE-susceptible (SES) (score of ≤6 at 36 h postoperatively) mice. 16S rRNA gene sequencing and metabolomics analyses were used to characterize the gut microbiota in the two groups. Fecal microbiota transplantation was performed to validate the role of the gut microbiota in SAE progression. The gut microbiota was more severely disrupted in SES mice than in SER mice after sepsis modeling. Interestingly, mice receiving postoperative feces from SES mice exhibited more severe cortical inflammation than mice receiving feces from SER mice. Indole-3-propionic acid (IPA), a neuroprotective molecule, was more enriched in feces from SER mice than in feces from SES mice. IPA alleviated CLP-induced anxiety and spatial memory impairment in septic mice. Moreover, IPA markedly inhibited NLRP3 inflammasome activation and interleukin-1β (IL-1β) secretion in lipopolysaccharide-stimulated microglia. These responses were attenuated after antagonizing the aryl hydrocarbon receptor. Our study indicates that the variability in sepsis-induced gut dysbiosis mediates the differential susceptibility to SAE in CLP-induced experimental sepsis mice, and microbially derived IPA is possibly involved in SAE development as a neuroprotective compound. IMPORTANCE The bidirectional interactions between the gut microbiota and sepsis-associated encephalopathy (SAE) are not well characterized. We found that the gut microbiota was more severely disturbed in SAE-susceptible (SES) mice than in SAE-resistant (SER) mice after sepsis modeling. Mice gavaged with postoperative feces from SES mice exhibited more severe neuroinflammation than mice gavaged with feces from SER mice. The gut microbiota from SER mice enriched a neuroprotective metabolite, IPA, which appeared to protect mice from SAE. The potential underlying mechanism of the protective effect of IPA may be mediated via the inhibition of NLRP3 inflammasome activation and IL-1β secretion in microglia. These anti-inflammatory effects of IPA may be regulated by aryl hydrocarbon receptors. These results enhance our understanding of the role of the intestinal microbiota in sepsis. In particular, gut microbiota-derived IPA may serve as a potential therapeutic agent to prevent neuroinflammation in SAE.
| S-EPMC9239149 | biostudies-literature
Project description:Sepsis associated encephalopathy (SAE), appears often indicates the deterioration of the sepsis disease and which have high risk of death. Although several mechanism and hypotheses have been proposed and studied, there is no breakthrough in the treatment of SAE. We performed a systematic research to evaluate the effect of intraperitoneal pressure on SAE. A mice model of sepsis was established by intraperitoneal injection of endotoxin. A total of 48 female BALB/c mouse (30 days old) were randomly divided into a control group (n = 12) and an injection of endotoxin referred to bacterial lipopolysaccharide (LPS) group (n = 12). Intraperitoneal hypertension (IAH) referred to IAH group (n = 12), and LPS + IAH group (n = 12). Following sepsis induction, diagnosis, the brains were analyzed for both function and ultrastructural morphology.We determined that IAH exacerbated sepsis induces sepsis-associated encephalopathy when examining low score of neurological function and more delta wave in EEG, increased neuronal edema in LPS + IAH group, as well as an escalation of Bax and Cleaved-caspase-3, Cleaved-parp, and reduction of Bcl-2 and Mfsd2a in LPS + IAH group. Therefore, IAH can exacerbate and increase incident rate of sepsis-related encephalopathy in sepsis mice by promoting neuronal apoptosis and destruction of the blood-brain barrier.
| S-EPMC5970176 | biostudies-literature
Project description:Background: Early detection of pediatric severe sepsis is necessary in order to optimize effective treatment, and new methods are needed to facilitate this early detection. Objective: Can a machine-learning based prediction algorithm using electronic healthcare record (EHR) data predict severe sepsis onset in pediatric populations? Methods: EHR data were collected from a retrospective set of de-identified pediatric inpatient and emergency encounters for patients between 2-17 years of age, drawn from the University of California San Francisco (UCSF) Medical Center, with encounter dates between June 2011 and March 2016. Results: Pediatric patients (n = 9,486) were identified and 101 (1.06%) were labeled with severe sepsis following the pediatric severe sepsis definition of Goldstein et al. (1). In 4-fold cross-validation evaluations, the machine learning algorithm achieved an AUROC of 0.916 for discrimination between severe sepsis and control pediatric patients at the time of onset and AUROC of 0.718 at 4 h before onset. The prediction algorithm significantly outperformed the Pediatric Logistic Organ Dysfunction score (PELOD-2) (p < 0.05) and pediatric Systemic Inflammatory Response Syndrome (SIRS) (p < 0.05) in the prediction of severe sepsis 4 h before onset using cross-validation and pairwise t-tests. Conclusion: This machine learning algorithm has the potential to deliver high-performance severe sepsis detection and prediction through automated monitoring of EHR data for pediatric inpatients, which may enable earlier sepsis recognition and treatment initiation.
| S-EPMC6798083 | biostudies-literature