ABSTRACT
Objective:To analyze and explore the independent risk factors of 28-day mortality in patients with septic myocardial injury.Methods:A retrospective cohort study was conducted to collect clinical data of 505 patients diagnosed with sepsis related myocardial injury admitted to the intensive care unit (ICU) of the Affiliated Hospital of Jining Medical University from January 2015 to December 2020. According to the 28-day survival status of patients, they were divided into survival group and death group. COX multivariate regression analysis was used to analyze the influencing factors of the 28-day mortality rate of sepsis related myocardial injury patients, and receiver operating characteristic (ROC) curves were drawn to evaluate the effectiveness of independent risk factors in predicting the 28-day mortality rate of sepsis related myocardial injury patients.Results:A total of 505 patients with sepsis myocardial injury were included, of which 282 survived on 28 days and 223 died, with a mortality rate of 44.16%. COX multivariate regression analysis showed that Sequential Organ Failure Assessment (SOFA) score, Acute Physiology and Chronic Health Evaluation Ⅱ (APACHE Ⅱ) score, blood lactate (LAC), oxygenation index (PaO 2/FiO 2), admission heart rate, and albumin were independent risk factors for sepsis associated myocardial injury mortality at 28 days (all P<0.05). ROC curve analysis showed that the area under the ROC curve (AUC) of SOFA score was 0.766 2, and the 95% confidence interval (95% CI) was 0.724 5-0.807 9; The predictive value of 28-day mortality in sepsis associated myocardial injury patients was superior to APACHE Ⅱ score, LAC, PaO 2/FiO 2, admission heart rate, and albumin [The AUC values were 0.754 1(0.711 5-0.796 7), 0.752 6(0.710 1-0.795 1), 0.697 0(0.649 7-0.744 2), 0.623 2(0.573 7-0.672 7), and 0.620 3(0.570 8-0.669 7), respectively]. Conclusions:SOFA score, APACHE Ⅱ score, LAC, PaO 2/FiO 2, admission heart rate, and albumin are independent risk factors for the 28-day mortality rate of sepsis related myocardial injury. Clinical practice should identify these factors early, intervene early, and improve patient prognosis.
ABSTRACT
OBJECTIVE@#To analyze the risk factors of in-hospital death in patients with sepsis in the intensive care unit (ICU) based on machine learning, and to construct a predictive model, and to explore the predictive value of the predictive model.@*METHODS@#The clinical data of patients with sepsis who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical University from April 2015 to April 2021 were retrospectively analyzed,including demographic information, vital signs, complications, laboratory examination indicators, diagnosis, treatment, etc. Patients were divided into death group and survival group according to whether in-hospital death occurred. The cases in the dataset (70%) were randomly selected as the training set for building the model, and the remaining 30% of the cases were used as the validation set. Based on seven machine learning models including logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost) and artificial neural network (ANN), a prediction model for in-hospital mortality of sepsis patients was constructed. The receiver operator characteristic curve (ROC curve), calibration curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the seven models from the aspects of identification, calibration and clinical application, respectively. In addition, the predictive model based on machine learning was compared with the sequential organ failure assessment (SOFA) and acute physiology and chronic health evaluation II (APACHE II) models.@*RESULTS@#A total of 741 patients with sepsis were included, of which 390 were discharged after improvement, 351 died in hospital, and the in-hospital mortality was 47.4%. There were significant differences in gender, age, APACHE II score, SOFA score, Glasgow coma score (GCS), heart rate, oxygen index (PaO2/FiO2), mechanical ventilation ratio, mechanical ventilation time, proportion of norepinephrine (NE) used, maximum NE, lactic acid (Lac), activated partial thromboplastin time (APTT), albumin (ALB), serum creatinine (SCr), blood urea nitrogen (BUN), blood uric acid (BUA), pH value, base excess (BE), and K+ between the death group and the survival group. ROC curve analysis showed that the area under the curve (AUC) of RF, XGBoost, LR, ANN, DT, SVM, KNN models, SOFA score, and APACHE II score for predicting in-hospital mortality of sepsis patients were 0.871, 0.846, 0.751, 0.747, 0.677, 0.657, 0.555, 0.749 and 0.760, respectively. Among all the models, the RF model had the highest precision (0.750), accuracy (0.785), recall (0.773), and F1 score (0.761), and best discrimination. The calibration curve showed that the RF model performed best among the seven machine learning models. DCA curve showed that the RF model exhibited greater net benefit as well as threshold probability compared to other models, indicating that the RF model was the best model with good clinical utility.@*CONCLUSIONS@#The machine learning model can be used as a reliable tool for predicting in-hospital mortality in sepsis patients. RF models has the best predictive performance, which is helpful for clinicians to identify high-risk patients and implement early intervention to reduce mortality.
Subject(s)
Humans , Hospital Mortality , Retrospective Studies , ROC Curve , Prognosis , Sepsis/diagnosis , Intensive Care UnitsABSTRACT
Objective:To analyze the risk factors of acute kidney injury (AKI) in patients with septic shock in intensive care unit (ICU), construct a predictive model, and explore the predictive value of the predictive model.Methods:The clinical data of patients with septic shock who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical College from April 2015 to June 2019 were retrospectively analyzed. According to whether the patients had AKI within 7 days of admission to the ICU, they were divided into AKI group and non-AKI group. 70% of the cases were randomly selected as the training set for building the model, and the remaining 30% of the cases were used as the validation set. XGBoost model was used to integrate relevant parameters to predict the risk of AKI in patients with septic shock. The predictive ability was assessed through receiver operator characteristic curve (ROC curve), and was correlated with acute physiology and chronic health evaluationⅡ(APACHEⅡ), sequential organ failure assessment (SOFA), procalcitonin (PCT) and other comparative verification models to verify the predictive value.Results:A total of 303 patients with septic shock were enrolled, including 153 patients with AKI and 150 patients without AKI. The incidence of AKI was 50.50%. Compared with the non-AKI group, the AKI group had higher APACHEⅡscore, SOFA score and blood lactate (Lac), higher dose of norepinephrine (NE), higher proportion of mechanical ventilation, and tachycardiac. In the XGBoost prediction model of AKI risk in septic shock patients, the top 10 features were serum creatinine (SCr) level at ICU admission, NE use, drinking history, albumin, serum sodium, C-reactive protein (CRP), Lac, body mass index (BMI), platelet count (PLT), and blood urea nitrogen (BUN) levels. Area under the ROC curve (AUC) of the XGBoost model for predicting the risk of AKI in patients with septic shock was 0.816, with a sensitivity of 73.3%, a specificity of 71.7%, and an accuracy of 72.5%. Compared with the APACHEⅡscore, SOFA score and PCT, the performance of the model improved significantly. The calibration curve of the model showed that the goodness of fit of the XGBoost model was higher than the other scores (the calibration curve had the lowest score, with a score of 0.205).Conclusion:Compared with the commonly used clinical scores, the XGBoost model can more accurately predict the risk of AKI in patients with septic shock, which helps to make appropriate diagnosis, treatment and follow-up strategies while predicting the prognosis of patients.
ABSTRACT
Objective:To investigate the changes of quadriceps femoris thickness with the length of stay in intensive care unit (ICU) in patients with sepsis, and to evaluate the diagnostic value of muscle changes in mortality.Methods:A prospective study was conducted, and 92 patients with sepsis who were admitted to the ICU of the Affiliated Hospital of Jining Medical College from January 2020 to December 2021 were enrolled. The thickness of quadriceps femoris [including the quadriceps femoris muscle thickness at the midpoint of the anterior superior iliac spine and the upper edge of the patella (M-QMLT), and at the middle and lower 1/3 of the patella (T-QMLT)] measured by ultrasound 1 day (D1), 3 days (D3), and 7 days (D7) after admission to the ICU were collected. The atrophy rate of quadriceps femoris was calculated 3 and 7 days after admission to the ICU compared with 1 day [(D3-D1)/D1 and (D7-D1)/D1, (TD3-TD1)/TD1 and (TD7-TD1)/TD1, respectively]. The demographic information, underlying diseases, vital signs when admission to the ICU and in-hospital mortality of all patients were recorded, and the differences of the above indicators between the two groupswere compared. Multivariate Logistic regression was used to analyze the influence of quadriceps femoris muscle thickness and atrophy rate on in-hospital mortality of septic patients. The receiver operator characteristic curve (ROC curve) was drawn to analyze the predictive value of quadriceps femoris muscle thickness and atrophy rate on in-hospital mortality of septic patients.Results:A total of 92 patients with severe sepsis were included, of which 41 patients died in hospital, 51 patients discharged. The in-hospital mortality was 44.6%. The muscle thickness of quadriceps femoris in severe septic patients decreased with the prolongation of ICU stay, and there was no significant difference between the two groups at the first and third day of ICU admission. The muscle thickness of quadriceps femoris at different measuring positions in the survival group was significantly greater than those in the death group 7 days after admission to the ICU [M-QMLT D7 (cm): 0.50±0.26 vs. 0.39±0.19, T-QMLT D7 (cm): 0.58±0.29 vs. 0.45±0.21, both P < 0.05]. The atrophy rate of quadriceps femoris muscle thickness at different measuring positions 3 and 7 days after admission to ICU in the survival group was significantly lower than those in the death group [(D3-D1)/D1: (8.33±3.44)% vs. (9.74±3.91)%, (D7-D1)/D1: (12.21±4.76)% vs. (19.80±6.15)%, (TD3-TD1)/TD1: (7.83±4.26)% vs. (10.51±4.75)%, (TD7-TD1)/TD1: (11.10±5.46)% vs. (20.22±6.05)%, all P < 0.05]. Multivariate Logistic regression analysis showed that M-QMLT D7, T-QMLT D7, (D3-D1)/D1, (D7-D1)/D1, (TD3-TD1)/TD1, (TD7-TD1)/TD1 were independent risk factors for in-hospital mortality (all P < 0.05). The results were stable after adjusting for confounding factors. ROC curve analysis showed that (TD7-TD1)/TD1 [area under the ROC curve (AUC) was 0.853, 95% confidence interval (95% CI) was 0.773-0.934] was superior to (D7-D1)/D1, T-QMLT D7, M-QMLT D7, (TD3-TD1)/TD1 and (D3-D1)/D1 [AUC was 0.821 (0.725-0.917), 0.692 (0.582-0.802), 0.683 (0.573-0.794), 0.680 (0.569-0.791), 0.622 (0.502-0.742)]. Conclusions:For septic patients in ICU, bedside ultrasound monitoring of quadriceps femoris muscle thickness and atrophy rate has a certain predictive value for in-hospital mortality, and a certain guiding significance in clinical treatment and predicting the prognosis of sepsis.
ABSTRACT
Objective:To explore the value of lactic acid (Lac), procalcitonin (PCT), sequential organ failure assessment (SOFA) score and acute physiology and chronic health evaluationⅡ (APACHEⅡ) score in assessing the severity and predicting the prognosis in sepsis shock.Methods:A retrospectively study was conducted. Patients with septic shock hospitalized in the department of critical care medicine of the Affiliated Hospital of Jining Medical University from April 2015 to June 2019 were enrrolled. The patient's gender, age, body mass index (BMI), infection site, organ dysfunction status; Lac, PCT, C-reactive protein (CRP), heart rate and body temperature immediately after admission to the intensive care unit (ICU); APACHEⅡ and SOFA scores within 24 hours, and 28-day prognosis were collected. According to the 28-day prognosis, the patients with septic shock were divided into the survival group and the death group, and the differences in the indicators between the groups were compared. Multivariate Logistic regression analysis was used to screen the risk factors of 28-day death in patients with septic shock; receiver operating characteristic curve (ROC curve) was used to analyze the value of Lac, PCT, SOFA, APACHEⅡ, and age in predicting the 28-day prognosis of patients with septic shock.Results:A total of 303 septic shock patients were enrolled, of which 124 cases survived and 179 died on the 28th day, and the 28-day mortality was 59.08%. ① Compared with the survival group, patients in the death group were older (years old: 66.58±15.22 vs. 61.15±15.68), APACHEⅡ, SOFA, proportion of lung infections, Lac increased [APACHEⅡ score: 22.79±7.62 vs. 17.98±6.88, SOFA score: 9.42±3.51 vs. 5.65±1.59, proportion of lung infections: 53.63% (96/179) vs. 39.52% (49/124), Lac (mmol/L): 5.10±3.72 vs. 3.71±2.56], oxygenation index (PaO 2/FiO 2) and ICU body temperature decreased [PaO 2/FiO 2 (mmHg, 1 mmHg = 0.133 kPa): 198.94±80.15 vs. 220.68±72.06, ICU body temperature (℃): 37.47±1.08 vs. 37.80±1.14], and the differences were statistically significant (all P < 0.05).②Multivariate Logistic regression analysis results: after adjusted for potential confounding factors, APACHEⅡ, PCT, Lac, age and SOFA were independent risk factors for death in patients with septic shock [APACHEⅡ: odds ratio ( OR) =1.05, 95% confidence interval (95% CI) was 1.01-1.10, P = 0.039; PCT: OR = 0.99, 95% CI was 0.98-1.00, P =0.012; Lac: OR = 1.23, 95% CI was 1.08-1.40, P = 0.002; age: OR = 1.03, 95% CI was 1.01-1.05, P =0.009; SOFA score: OR =1.88, 95% CI was 1.59-2.22, P < 0.001]. ③ROC curve analysis showed that APACHEⅡ, Lac, age and SOFA could predict the prognosis of patients with septic shock [APACHEⅡ: the area under the ROC curve (AUC) = 0.682 4, 95% CI was 0.621 7-0.743 1, P = 0.000; when the best cut-off value was 18.500, its sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio and negative likelihood ratio were 72.63%, 54.84%, 69.89%, 58.12%, 1.608 1 and 0.499 2, respectively. Lac: AUC = 0.604 5, 95% CI was 0.540 8-0.668 2, P = 0.002; when the best cut-off value was 3.550 mmol/L, the sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio and negative likelihood ratio were 50.84%, 73.39%, 73.39%, 50.94%, 1.910 3 and 0.669 9, respectively. Age: AUC = 0.599 1, 95% CI was 0.535 4-0.662 7, P = 0.003; when the best cut-off value was 72.500 years old, the sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio and negative likelihood ratio were 42.46%, 75.00%, 71.03%, 47.45%, 1.698 3 and 0.767 2, respectively. SOFA: AUC =0.822 3, 95% CI was 0.776 7-0.867 9, P = 0.000; when the best cut-off value was 7.500, its sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio and negative likelihood ratio were 68.72%, 87.90%, 89.13%, 66.06%, 5.680 4, 0.355 9 respectively]. The combined prediction had a good sensitivity (72.63%) and specificity (84.86%), and AUC (0.876 5) was higher than that of a single variable, suggested that the multivariate combination was more accurate in predicting the short-term outcome of septic shock. Conclusion:Lac, PCT, SOFA score, APACHEⅡ score and age were independent risk factors for death in patients with septic shock, and the accuracy of Lac, SOFA score, APACHEⅡ score and age in predicting short-term prognosis of septic shock was better than that of single variable, and the diagnostic value was higher.
ABSTRACT
Objective:To investigate the relationship between the arterial blood lactic acid level after entering the intensive care unit (ICU) and the 28-day mortality of patients with septic shock.Methods:The clinical data of 303 patients with septic shock hospitalized in the department of critical medicine of the Affiliated Hospital of Jining Medical College from April 2015 to June 2019 were analyzed retrospectively. According to the blood lactate (Lac) level, the patients were divided into <4 mmol/L group ( n=203), 4-10 mmol/L group ( n=69) and >10 mmol/L group ( n=31). The baseline characteristics of the patients were analyzed. Multiple logistic regression analysis was used to analyze the independent influencing factors of the 28-day mortality of patients with septic shock. The receiver operating characteristic (ROC) curve was used to analyze the predictive value of the Lac level after entering the ICU for 28-day mortality, and Kaplan-Meier survival curve was performed according to the best cut-off value. Results:A total of 303 patients with septic shock were included, with 179 died in 28 days, and the total mortality was 59.08%. There were 203, 69, 31 patients in Lac<4 mmol/L, 4-10 mmol/L and >10 mmol/L group, respectively. There were significant differences in Acute Physiology and Chronic Health Evalution Ⅱ (APACHE Ⅱ), Sequential Organ Failure Assessment (SOFA), oxygenation index (PaO 2/FiO 2), abdominal infection, the proportion of vasoactive drugs use among the three groups ( P<0.05). Multiple logistic regression analysis showed that the independent influencing factor of the 28-day mortality of septic shock were age, SOFA, use of mechanical ventilation, lactic acid (Lac). ROC curve analysis showed that the area under the ROC curve (AUC) for predicting 28-day mortality of patients with septic shock was 0.604 5 (95% CI: 0.540 8-0.668 2). When the optimal cut-off value was 3.55 mmol/L, the sensitivity was 0.508 4, the specificity was 0.733 9, the positive likelihood ratio was 1.910 3 and the negative likelihood ratio was 0.669 9. According to the best cut-off value of entrance Lac, patients were divided into high Lac group (≥3.55 mmol/L) and low Lac group (<3.55 mmol/L), and their 28-day mortality rates were 73.39%(91/124) and 49.16%(88/179). Kaplan-Meier survival curve showed that the 28-day cumulative survival rate of the high Lac group was significantly lower than that of the low Lac group ( P<0.001). Multiple logistic regression analysis showed that after adjusting for confounding factors, the 28 d mortality increased to 1.22 times for each increase of 1 mmol/L of Lac [odds ratio ( OR)=1.22, 95% confidence interval (95% CI) was 1.08-1.37, P=0.001 4]. The 28 d mortality in high Lac group was 3.53 times higher than that in low Lac group ( OR=3.53, 95% CI was 1.36-7.09, P=0.000 4). Conclusions:In patients with ICU septic shock, the arterial blood Lac level after admission was associated with 28-day mortality. Patients with septic shock whose arterial blood Lac level exceeded 3.55 mmol/L within 1 hour of entering the room had a significantly increased risk of death.
ABSTRACT
Objective To understand the job well-being status of ICU nurses,and to explore the mediating role of psychological capital in job stress and job well-being.Methods ICU nurses'general data questionnaire,the Nurse Questionnaire Psychological Capital,Chinese Nurses' Work Stressor Scale and Work Well-Being Scale were used to investigate 224 ICU nurses in three grade a general hospitals.Results Total score of psychological capital for ICU nurses was(4.46±0.55)points,the total average working pressure was(2.14±0.37)points,the happiness score was(4.36±0.67)points.Psychological capital and job well-being were positively correlated(r=0.513,P＜0.01),job stress and job well-being was negatively correlated(r =-0.454,P＜ 0.05).The structural equation results showed that psychological capital played an intermediary role in the sense of ICU nurses job stress and job happiness.Conclusions Hospital nursing managers should pay more attention to the mental health of ICU nurses and lower their work stress,so as to improve the work well-being of ICU nurses and improve the quality of ICU nursing.