Corrigendum: Integrated analysis of single-cell RNA-seq and chipset data unravels PANoptosis-related genes in sepsis.

[This corrects the article DOI: 10.3389/fimmu.2023.1247131.].

Ubenimex suppresses glycolysis mediated by CD13/Hedgehog signaling to enhance the effect of cisplatin in liver cancer.

Background: Liver cancer ranks third in fatalities among all cancer-related deaths. As a traditional chemotherapy drug, the application of cis-Diamminedichloroplatinum (II) (cisplatin, CDDP) for the treatment of liver cancer is greatly limited by its side effects and high drug resistance. Therefore, we are in urgent need of a more effective and less toxic CDDP therapeutic regimen. Our research aimed to clarify the possible mechanism of ubenimex in enhancing the effect of CDDP on liver cancer. Methods: The underlying mechanism was determined using Cell Counting Kit-8 (CCK-8) assay, flow cytometry, immunofluorescence, enzyme-linked immunosorbent assay (ELISA), transwell assay, wound healing assay and western blot assay. Results: The data indicated that ubenimex suppressed the expression levels of glycolysis-related proteins by decreasing the expression levels of cluster of differentiation 13 (CD13), while overexpression of CD13 could restore the activity of glycolysis. The glycolysis inhibitor 2-deoxy-D-glucose enhanced the antiproliferative effect of ubenimex and CDDP. In addition, the inhibition of the activity levels of the Hedgehog (Hh) pathway members was accompanied by a decrease in CD13 expression, which was reversed following CD13 overexpression. Moreover, ubenimex inhibited the production of lactic acid and adenosine triphosphate (ATP), as well as the expression of key proteins involved in glycolysis, which was similar to the effects caused by the Hh inhibitor cyclopamine. However, the effects of ubenimex were mediated by targeting CD13, while cyclopamine exhibited no effects on CD13, suggesting that Hh signaling occurred in the downstream of CD13. The inhibition of glycolysis by cyclopamine was reduced following CD13 overexpression, which further indicated that ubenimex targeted the CD13/Hh pathway to inhibit glycolysis. Finally, wound healing and transwell assays and cell proliferation and apoptosis analysis demonstrated that ubenimex inhibited glycolysis by alleviating the CD13/Hh pathway, which in turn enhanced the effects of CDDP on inhibiting the progression of liver cancer. Conclusions: Ubenimex inhibits glycolysis by targeting the CD13/Hh pathway, thus playing an anti-tumor role together with CDDP. This study demonstrated the adjuvant effect of ubenimex from the perspective of Hh signal-dependent glycolysis regulation.

Sepsis-associated encephalopathy: From pathophysiology to clinical management.

Sepsis-associated encephalopathy, which presents as delirium and coma, is a significant complication of sepsis characterized by acute brain dysfunction. The presence of inflammatory pathological changes in the brain of sepsis patients and animal models has been recognized since the 1920 s, initially attributed to the entry of microbial toxins into the brain. In the early 2000 s, attention shifted towards the impact of oxidative stress, the cholinergic system, and cytokines on brain function following sepsis onset. More recently, sepsis-associated encephalopathy has been defined as a diffuse brain dysfunction not directly caused by pathogenic infection of the brain. Currently, there is no evidence-based standard for diagnosing sepsis-associated encephalopathy, and clinical management is primarily focused on symptomatic and supportive measures. This review aims to explore the pathophysiology of sepsis-associated encephalopathy and establish the connection between pathophysiological mechanisms and clinical characteristics. We hope that this work will spark the interest of researchers from various fields and contribute to the advancement of sepsis-associated encephalopathy research.

Healthcare services efficiency and its intrinsic drivers in China: based on the three-stage super-efficiency SBM model.

BACKGROUND: The purpose of this study is to examine the development of healthcare services efficiency in China since the reform of the healthcare system. By examining the development environment of healthcare services in China and examining the driving factors affecting the efficiency of healthcare services, we provide a reference for the future high-quality development of healthcare services in China. METHODS: A three-stage super-efficient slack-based measure (SBM) model with undesirable outputs was used to measure the efficiency of healthcae services in 31 Chinese provinces from 2009 to 2021, and a global Malmquist-Luenberger (GML) index was used to assess their spatiotemporal evolution characteristics and internal influencing mechanisms of healthcare services efficiency. RESULTS: The empirical results showed that the efficiency of China's healthcare services changed significantly from 2009-2014 and then remained stable. During the study period, the efficiency of healthcare services in the eastern region was higher than the national level, while it was lower in the western region. The results of the analysis of environmental factors indicated that an increase in population density reduced the redundancy of healthcare input resources and that economic development as well as an increase in government subsidies, contributed to an increase in the redundancy of healthcare input resources. The main contribution to the growth of healthcare sercices efficiency in China came from the technological innovation effect, and the growth was most significant in the western region. CONCLUSION: From 2009 to 2021, the efficiency of national healthcare services generally showed a slow upward trend, and the efficiency of healthcare services varied widely among regions. Under the existing environmental constraints, relevant departments in each region should strengthen technological innovation in healthcare services, completely focus on the regional catch-up effect, and promote the balanced development of regional health.

Optimization of central venous pressure during the perioperative period is associated with improved prognosis of high-risk operation patients.

Background: While central venous pressure (CVP) measurement is used to guide fluid management for high-risk surgical patients during the perioperative period, its relationship to patient prognosis is unknown. Methods: This single-center, retrospective observational study enrolled patients undergoing high-risk surgery from February 1, 2014 to November 31, 2020, who were admitted to the surgical intensive care unit (ICU) directly after surgery. Patients were divided into the following three groups according to the first CVP measurement (CVP1) after admission to the ICU: low, CVP1 <8 mmHg; moderate, 8 mmHg≤ CVP1 ≤ 12 mmHg; and high, CVP1 >12 mmHg. Perioperative fluid balance, 28-day mortality, length of stay in the ICU, and hospitalization and surgical complications were compared across groups. Results: Of the 775 high-risk surgical patients enrolled in the study, 228 were included in the analysis. Median (interquartile range) positive fluid balance during surgery was lowest in the low CVP1 group and highest in the high CVP1 group (low CVP1: 770 [410, 1205] mL; moderate CVP1: 1070 [685, 1500] mL; high CVP1: 1570 [1008, 2000] mL; all P <0.001). The volume of positive fluid balance during the perioperative period was correlated with CVP1 (r=0.336, P <0.001). The partial arterial pressure of oxygen(PaO2)/fraction of inspired oxygen(FiO2) ratio was significantly lower in the high CVP1 group than in the low and moderate CVP1 groups (low CVP1: 400.0 [299.5, 443.3] mmHg; moderate CVP1: 362.5 [330.0, 434.9] mmHg; high CVP1: 335.3 [254.0, 363.5] mmHg; all P <0.001). The incidence of postoperative acute kidney injury (AKI) was lowest in the moderate CVP1 group (low CVP1: 9.2%; moderate CVP1: 2.7%; high CVP1: 16.0%; P=0.007). The proportion of patients receiving renal replacement therapy was highest in the high CVP1 group (low CVP1: 1.5%; moderate CVP1: 0.9%; high CVP1: 10.0%; P=0.014). Logistic regression analysis showed that intraoperative hypotension and CVP1 >12 mmHg were risk factors for AKI within 72 h after surgery (adjusted odds ratio[aOR]=3.875, 95% confidence interval[CI]: 1.378-10.900, P=0.010 and aOR=1.147, 95%CI: 1.006-1.309, P=0.041). Conclusions: CVP that is either too high or too low increases the incidence of postoperative AKI. Sequential fluid therapy based on CVP after patients are transferred to the ICU post-surgery does not reduce the risk of organ dysfunction caused by an excessive amount of intraoperative fluid. However, CVP can be used as a safety limit indicator for perioperative fluid management in high-risk surgical patients.

Measuring the efficiency of public hospitals: A multistage data envelopment analysis in Fujian Province, China.

Objective: The present study aimed to evaluate the operational efficiency of public hospitals in Fujian Province and the factors responsible for the inefficiency of these hospitals and provide relevant suggestions for health policymakers in allocating service resources. Method: In the first stage of the research, the variables affecting the efficiency of hospitals were extracted by qualitative and quantitative methods, including literature optimization, gray related analysis and gray clustering evaluation. In the second stage, the data envelopment analysis (DEA) method was used to evaluate the operational efficiency of 49 hospitals of different levels and types selected by sampling in 2020. Finally, a Tobit regression model with introduced institutional factors and background factors was established to study the main influencing factors of hospital inefficiency. Results: In the first stage, 10 input variables and 10 output variables necessary from the mangers' point of view were identified to test efficiency. In the second stage, the average comprehensive TE, PTE, and SE of 49 sample hospitals was 0.802, 0.888, and 0.902, respectively. 22.45% of these hospitals met the effective criteria, i.e., the overall effective rate was 22.45%. The low SE value of the hospital was the main reason hindering the improvement of the comprehensive efficiency value. The overall effective rate of secondary public hospitals (30.77%) was higher than that of tertiary public hospitals (19.44%), and the overall effective rate of public specialized hospitals (30%) was higher than that of general public hospitals (18.92%). Based on the third stage results, the bed occupancy rate (BOR) and the proportion of beds (POB) were major factors affecting the operation efficiency of grade III hospitals (p < 0.01). However, the operating efficiency of grade II hospitals was significantly affected by POB and regional per capita GDP(GDPPC) (p < 0.05). Moreover, the impact of BOR and GDPPC was positive, and POB was negatively correlated with hospital operation efficiency. Conclusions: The study results indicated that the overall operation efficiency of public hospitals in Fujian Province is low. This study revealed that intervention should be strengthened from a policy and management perspective to improve the operation efficiency of public hospitals.

The magnitude, but not the duration of elevated central venous pressure is associated with mortality in sepsis patients: An analysis of the MIMIC-IV database.

BACKGROUND: It is unclear whether the magnitude and duration of elevated central venous pressure (ECVP) greater than ten mmHg has the same impact on mortality in sepsis patients. METHODS: Critically ill patients with sepsis were identified from the Medical Information Mart for Intensive Care (MIMIC)-IV database. The duration and the magnitude of ECVP were calculated. Normalized ECVP load was defined as the ECVP load (the sum of ECVP value times its duration) divided by the total duration of ECVP. The primary endpoint was 28-day mortality. Kaplan-Meier survival analysis was used to compare survival between patients with high or low normalized ECVP load. RESULTS: A total of 1071 sepsis patients were included. Higher normalized ECVP load was associated with higher mortality rate; in contrast, the duration of ECVP was not associated with mortality. A linear relationship between normalized ECVP load and mortality was identified. Patients with higher normalized ECVP load had less urine output and more positive fluid balance. CONCLUSION: The magnitude, but not the duration of ECVP, is associated with mortality in sepsis patients. ECVP should be considered as a valuable and easily accessible safety parameter during fluid resuscitation.

Integrated analysis of single-cell RNA-seq and chipset data unravels PANoptosis-related genes in sepsis.

Background: The poor prognosis of sepsis warrants the investigation of biomarkers for predicting the outcome. Several studies have indicated that PANoptosis exerts a critical role in tumor initiation and development. Nevertheless, the role of PANoptosis in sepsis has not been fully elucidated. Methods: We obtained Sepsis samples and scRNA-seq data from the GEO database. PANoptosis-related genes were subjected to consensus clustering and functional enrichment analysis, followed by identification of differentially expressed genes and calculation of the PANoptosis score. A PANoptosis-based prognostic model was developed. In vitro experiments were performed to verify distinct PANoptosis-related genes. An external scRNA-seq dataset was used to verify cellular localization. Results: Unsupervised clustering analysis using 16 PANoptosis-related genes identified three subtypes of sepsis. Kaplan-Meier analysis showed significant differences in patient survival among the subtypes, with different immune infiltration levels. Differential analysis of the subtypes identified 48 DEGs. Boruta algorithm PCA analysis identified 16 DEGs as PANoptosis-related signature genes. We developed PANscore based on these signature genes, which can distinguish different PANoptosis and clinical characteristics and may serve as a potential biomarker. Single-cell sequencing analysis identified six cell types, with high PANscore clustering relatively in B cells, and low PANscore in CD16+ and CD14+ monocytes and Megakaryocyte progenitors. ZBP1, XAF1, IFI44L, SOCS1, and PARP14 were relatively higher in cells with high PANscore. Conclusion: We developed a machine learning based Boruta algorithm for profiling PANoptosis related subgroups with in predicting survival and clinical features in the sepsis.

Chinese experts' consensus on the application of intensive care big data.

The development of intensive care medicine is inseparable from the diversified monitoring data. Intensive care medicine has been closely integrated with data since its birth. Critical care research requires an integrative approach that embraces the complexity of critical illness and the computational technology and algorithms that can make it possible. Considering the need of standardization of application of big data in intensive care, Intensive Care Medicine Branch of China Health Information and Health Care Big Data Society, Standard Committee has convened expert group, secretary group and the external audit expert group to formulate Chinese Experts' Consensus on the Application of Intensive Care Big Data (2022). This consensus makes 29 recommendations on the following five parts: Concept of intensive care big data, Important scientific issues, Standards and principles of database, Methodology in solving big data problems, Clinical application and safety consideration of intensive care big data. The consensus group believes this consensus is the starting step of application big data in the field of intensive care. More explorations and big data based retrospective research should be carried out in order to enhance safety and reliability of big data based models of critical care field.

Construction and efficacy evaluation of an early warning scoring system for septic shock in patients with digestive tract perforation: A retrospective cohort study.

Objective: To establish an early warning scoring system for septic shock in patients with digestive tract perforation (DTP) and evaluate its diagnostic efficacy. Methods: Patients with surgically confirmed or clinically diagnosed DTP admitted to the Department of Intensive Care Medicine of Fujian Provincial Hospital from June 2012 to October 2021 were retrospectively analyzed. General demographic characteristics, perforation-related information, vital signs, common laboratory indicators, and common ICU scores (Glasgow Coma Scale score, Acute Physiology and Chronic Health Evaluation-II score,Sequential Organ Failure Assessment score) were collected. The patients were divided into shock group and non-shock group according to whether the patients had septic shock during hospitalization. The risk factors of septic shock were screened by basic statistical analysis and multivariate Logistic regression analysis. The receiver operating characteristic curve was drawn to determine the cut-off value of the continuous indicators and discretized with reference to clinic, and the corresponding score was set according to the ß regression coefficient of each variable. Results: A total of 176 patients with DTP were included. The average age of the patients was 64.13 ± 14.67 years old, and 74.40% were males. The incidence of septic shock was 30.11% (53/176). Multivariate Logistic regression analysis showed that the highest heart rate≥105 beats/min, Glasgow Coma Scale score≤14 points, lactic acid≥5.75 mmol/L, procalcitonin≥41.47 ug/L, C-reactive protein≥222.5 mg/L were independent risk factors for septic shock in patients with DTP. The total score of clinical diagnostic scoring system of septic shock in patients with DTP was 6 points, including the highest heart rate≥105 beats/min (1 point), lactic acid≥5.75 mmol/L (two points), procalcitonin≥41.47 ug/L (one point), C-reactive protein≥222.5 mg/L (1 point), and Glasgow Coma Scale score≤14 points (1 point). The area under ROC curve (AUC) of this scoring system was 0.789 and the 95% confidence interval was 0.717-0.860 (P < 0.001); when the optimal cut-off value was 2.5, the sensitivity and specificity were 54.70 and 87.80%, respectively. Conclusion: This new score system has its certain clinical value and has important guiding significance for clinicians to judge the prognosis of patients with DTP in time.

Diagnosis and ECMO Treatment of a Critically Ill Patient With Disseminated Mycobacterium tuberculosis: A Case Report.

Background: Mycobacterium tuberculosis infection remains a public health concern worldwide. The diagnosis and treatment of disseminated M. tuberculosis is very difficult, so we shared our experiences and lessons learned in this case report. Case Presentation: A 36-year-old female with a history of epilepsy presented to our hospital with fever, upper abdominal pain, muscle soreness in limbs for 7 days, and shortness of breath for 4 days. On admission, she presented with acute respiratory distress syndrome (ARDS) and liver dysfunction. Due to the critical nature of her clinical presentation, the patient was admitted directly to the Intensive Care Unit (ICU), received mechanical ventilation in prone position and VV-ECMO treatment. Her condition improved gradually, and the ECMO was removed after 7 days and she was weaned off the ventilator after 8 days. However, her fever recurred and she underwent PET-CT examination, liver contrast ultrasound, acid-fast staining and second-generation sequencing of cerebrospinal fluid, which confirmed M. tuberculosis infection. Conclusion: This case report briefly described the treatment and diagnosis of a critically ill patient with intra and extra-pulmonary tuberculosis infection. Timely and appropriate treatment is crucial to save lives, but the timing of ECMO treatment needs to be carefully considered for patients with ARDS caused by tuberculosis.

A multicenter prospective cohort study of cardiac ultrasound phenotypes in patients with sepsis: Study protocol for a multicenter prospective cohort trial.

Background: Sepsis-induced cardiomyopathy significantly increased the mortality of patients with sepsis. The diagnostic criteria for septic cardiomyopathy has not been unified, which brings serious difficulties to clinical treatment. This study aimed to provide evidence for the early identification and intervention in patients with sepsis by clarifying the relationship between the ultrasound phenotype of septic cardiomyopathy and the prognosis of patients with sepsis. Methods: This was a multicenter, prospective cohort study. The study population will consist of all eligible consecutive patients with sepsis or septic shock who meet the Sepsis 3.0 diagnostic criteria and were aged ≥18 years. Clinical data and echocardiographic measurements will be recorded within 2 h, at the 24th hour, at the 72nd hour, and on the 7th day after admission. The prevalence of each phenotype will be described as well, and their association with prognosis will be analyzed statistically. Discussion: To achieve early recognition, prevent reinjury, achieve precise treatment, and reduce mortality in patients with sepsis, it is important to identify septic cardiac alterations and classify the phenotypes at all stages of sepsis. First, there is a lack of studies on the prevalence of each phenotype in Chinese populations. Second, each phenotype and its corresponding prognosis are not clear. In addition, the prognosis of patients with normal cardiac ultrasound phenotypes vs. those with suppressed or hyperdynamic cardiac phenotypes is unclear. Finally, this study was designed to collect data at four specific timing, then the timing of occurrence, duration, changes over time, impact to outcomes of each phenotype will probably be found. This study is expected to establish a standard and objective method to assess the ultrasound phenotype of septic cardiomyopathy due to its advantages of visualization, non-invasiveness and reproducibility, and to provide more precise information for the hemodynamic management of septic patients. In addition, this research will promote the clinical application of critical care ultrasound, which will play an important role in medical education and make ultrasound the best method to assess cardiac changes in sepsis. Trial registration: https://clinicaltrials.gov/ct2/show/NCT05161104, identifier NCT05161104.

Clinical characteristics and early prediction of mortality risk in patients with acute organophosphate poisoning-induced shock.

Objective: To further get insights of clinical characteristics of acute organophosphate poisoning-induced shock, investigate the relationship between shock and prognosis, and screen risk indicators for prognosis. Methods: A total of 73 patients with acute organophosphate poisoning admitted to our hospital between January 2014 and December 2021 were enrolled in this retrospective study. Patients were divided into the shock group and the non-shock group. The pH value of blood, arterial blood carbon dioxide partial pressure (PaCO2), arterial partial pressure of oxygen (PaO2), base excess (BE), lactic acid (Lac), serum albumin (ALB), total bilirubin (TBIL), alanine aminotransferase (ALT), serum creatinine (Cr), serum potassium (K), serum calcium (Ca), serum sodium (Na), blood chloride (Cl), serum troponin I (cTNI), brain natriuretic peptide (BNP), white blood cell count (WBC), hemoglobin (HGB), platelet count (PLT), and other clinical indicators of patients were recorded. Incidence of shock, time of shock onset, and outcomes of patients were also recorded. Cox proportional hazards regression models were performed for analysis. Results: The incidence of organophosphate poisoning-induced shock was 30.1% (22/73), and 72.7% of shock patients developed shock blood pressure within 6 h. The levels of blood lactate, ALT, Cr, cTNI, BNP, and Cl in the shock group were significantly higher than those in the non-shock group, while the level of Ca and pH value was significantly lower than that in the non-shock group (all p < 0.05). Moreover, compared with patients without shock (2.0%), the mortality rate was significantly increased in patients with shock (36.4%), which was supported by the results from adjusted Cox proportional hazards regression model. We found that shock and elevated serum creatinine were associated with increased risk of death in patients with organophosphate poisoning (shock: HR, 10.9; 95% CI 1.2-96.3; elevated serum creatinine: HR, 1.0, 95% CI 1.0-1.0). Conclusion: This study indicated the association between elevated serum creatinine and increased mortality rates in patients with organophosphate poisoning, highlighting the importance of the comprehensive management of shock, especially the control of renal function, in these poisoning patients.

[Association between early central venous pressure measurement and mortality in patients with sepsis: a data analysis of MIMIC-III database].

OBJECTIVE: To investigate the association between early central venous pressure (CVP) measurement and mortality in patients with sepsis. METHODS: The adult patients with sepsis were identified from the health data of Medical Information Mart for Intensive Care-III v1.4 (MIMIC-III v1.4). Data of all adult patients with sepsis were collected, including gender, age, comorbidities, length of survival, total length of hospital stay and intensive care unit (ICU) stay, sequential organ failure assessment (SOFA) score, vital signs, laboratory test results on the first day, vasoactive agents usage, fluid input, urine output and fluid balance on the first day, need for renal replacement therapy and mechanical ventilation, diagnosis of sepsis, and the time and value of the first CVP measurement in the ICU. Patients were divided into early measurement and control groups based on whether or not they had a CVP measurement within the first 6 hours of ICU stay. According to the time of the first CVP measurement, the patients were subdivided into four subgroups: ≤ 3 hours, 4-6 hours, 7-12 hours and no measurement within 12 hours. The primary endpoint was 28-day mortality. The relationship between initial CVP and mortality was analyzed by Lowess smoothing method. Kaplan-Meier survival analysis and Log-Rank test were performed for univariate analysis. Cox regression analysis was performed for multivariate analysis to estimate the relationship between timeliness of CVP measurement and mortality. RESULTS: A total of 4 733 sepsis patients were enrolled, 1 673 of whom had CVP measured within 6 hours of admission to the ICU, and the other 3 060 patients served as the control group. There were no differences in demographic characteristics and underlying diseases between the two groups, except that the early CVP measurement group had less underlying renal failure compared with control group. The early CVP measurement group had higher lactic acid (Lac) levels and SOFA scores, indicating worse severity of disease as compared with control group. The 28-day mortality in the early CVP measurement group was significantly lower than that in the control group (34.2% vs. 40.7%, P < 0.01). The early CVP measurement group had shorter length of total hospitalization and longer length of ICU stay, higher rate of mechanical ventilation and vasoactive agents dependent, and more fluid input and fluid balanced in the first day of ICU stay compared with control group. Lowess smoothing analysis showed that a "U"-shaped relationship between initial CVP and mortality was identified, suggesting that too high or too low initial CVP was associated with worse survival. Kaplan-Meier survival analysis showed that compared with the patients without early CVP measurement within 12 hours, the cumulative survival rate of patients with CVP measured within 3 hours was significantly higher (66.7% vs. 59.1%; Log-Rank test: χ2 = 15.810, adjusted P < 0.001); while no significant difference was found in patients with CVP measured between 4 hours and 6 hours and between 7 hours and 12 hours compared with the patients without early CVP measurement within 12 hours (64.4%, 60.3% vs. 59.1%; Log-Rank test: χ2 values were 5.630 and 0.100, and adjusted P values were 0.053 and > 0.999, respectively). Cox multivariate analysis showed that the Cox proportional risk model was established by taking patients without CVP measurement within 12 hours as reference, timely CVP measurement after ICU admission was associated with reduced 28-day mortality of patients with sepsis [≤ 3 hours: hazard ratio (HR) = 0.65, 95% confidence interval (95%CI) was 0.55-0.77, P < 0.001; 4-6 hours: HR = 0.72, 95%CI was 0.60-0.87, P = 0.001; 7-12 hours: HR = 0.80, 95%CI was 0.66-0.98, P = 0.032] after the confounding variables (gender, age, SOFA score, initial Lac, renal failure, maximal blood glucose and white blood cell count, and minimal platelet count within 24 hours) were adjusted. CONCLUSIONS: Early CVP measurement is associated with decreased 28-day mortality in patients with sepsis. CVP should be considered as a valuable and easily accessible safety parameter during early fluid resuscitation.

Lung ultrasound score based on the BLUE-plus protocol is associated with the outcomes and oxygenation indices of intensive care unit patients.

PURPOSE: The primary objective was to demonstrate the relationship between lung ultrasound (LUS) manifestations and the outcomes of intensive care unit (ICU) patients. The secondary objective was to determine the characteristics of LUS manifestations in different subgroups of ICU patients. METHODS: This prospective multi-center cohort study was conducted in 17 ICUs. A total of 1702 patients admitted between August 31, 2017 and February 16, 2019 were included. LUS was performed according to the bedside lung ultrasound in emergency (BLUE)-plus protocol, and LUS scores were calculated. Data on the outcomes and oxygenation indices were analyzed and compared between different primary indication groups. RESULTS: The LUS scores were significantly higher for non-survivors than for survivors and were significantly different between the oxygenation index groups, with higher scores in the lower oxygenation index groups. The LUS score was an independent risk factor for the 28-day mortality. The area under the receiver operating characteristic curve was 0.663 for prediction of the 28-day mortality and 0.748 for prediction of an oxygenation index ≤100. CONCLUSIONS: The LUS score based on the BLUE-plus protocol was an independent risk factor for the 28-day mortality and was important for the prediction of an oxygenation index ≤100. An early LUS score within 24 hours of ICU admission helps predicting the outcome of ICU patients.

Machine Learning Approaches-Driven for Mortality Prediction for Patients Undergoing Craniotomy in ICU.

OBJECTIVES: We aimed to predict the mortality of patients with craniotomy in ICU by using predictive models to extract the high-risk factors leading to the death of patients from a retrospective a study. METHODS: Five machine-learning (ML) algorithms were applied for training on mortality predictive models with the data from a surgical intensive care unit (ICU) database of the Fujian Provincial Hospital in China. The accuracy, precision, recall, f1 score and the area under the receiver operator characteristic curve (AUC) were used to evaluate the performance of different models, and the calibration of the model was evaluated by brier score. RESULTS: We demonstrated that eXtreme Gradient Boosting (XGBoost) was more suitable for the task, demonstrating a AUC of 0.84. We analyzed the feature importance with the Local Interpretable Model-agnostic Explanations (LIME) analysis and further identified the high-risk factors of mortality in ICU through this study. CONCLUSIONS: This study established the mortality predictive model of patients who had undergone craniotomy in ICU. Identification of the factors that had great influence on mortality has the potential to provide auxiliary decision support for clinical medical staff on their practices.