OBJECTIVE: To explore lung ultrasound radiomics features which related to extravascular lung water index (EVLWI), and to predict EVLWI in critically ill patients based on lung ultrasound radiomics combined with machine learning and validate its effectiveness. METHODS: A retrospective case-control study was conducted. The lung ultrasound videos and pulse indicated continuous cardiac output (PiCCO) monitoring results of critically ill patients admitted to the department of critical care medicine of the First Affiliated Hospital of Guangxi Medical University from November 2021 to October 2022 were collected, and randomly divided into training set and validation set at 8:2. The corresponding images from lung ultrasound videos were obtained to extract radiomics features. The EVLWI measured by PiCCO was regarded as the "gold standard", and the radiomics features of training set was filtered through statistical analysis and LASSO algorithm. Eight machine learning models were trained using filtered radiomics features including random forest (RF), extreme gradient boost (XGBoost), decision tree (DT), Naive Bayes (NB), multi-layer perceptron (MLP), K-nearest neighbor (KNN), support vector machine (SVM), and Logistic regression (LR). Receiver operator characteristic curve (ROC curve) was plotted to evaluate the predictive performance of models on EVLWI in the validation set. RESULTS: A total of 151 samples from 30 patients were enrolled (including 906 lung ultrasound videos and 151 PiCCO monitoring results), 120 in the training set, and 31 in the validation set. There were no statistically significant differences in main baseline data including gender, age, body mass index (BMI), mean arterial pressure (MAP), central venous pressure (CVP), heart rate (HR), cardiac index (CI), cardiac function index (CFI), stroke volume index (SVI), global end diastolic volume index (GEDVI), systemic vascular resistance index (SVRI), pulmonary vascular permeability index (PVPI) and EVLWI. The overall EVLWI range in 151 PiCCO monitoring results was 3.7-25.6 mL/kg. Layered analysis showed that both datasets had EVLWI in the 7-15 mL/kg interval, and there was no statistically significant difference in EVLWI distribution. Two radiomics features were selected by using LASSO algorithm, namely grayscale non-uniformity (weight was -0.006 464) and complexity (weight was -0.167 583), and they were used for modeling. ROC curve analysis showed that the MLP model had better predictive performance. The area under the ROC curve (AUC) of the prediction validation set EVLWI was higher than that of RF, XGBoost, DT, KNN, LR, SVM, NB models (0.682 vs. 0.658, 0.657, 0.614, 0.608, 0.596, 0.557, 0.472). CONCLUSIONS The gray level non-uniformity and complexity of lung ultrasound were the most correlated radiomics features with EVLWI monitored by PiCCO. The MLP model based on gray level non-uniformity and complexity of lung ultrasound can be used for semi-quantitative prediction of EVLWI in critically ill patients.
Humans ; Extravascular Lung Water/diagnostic imaging* ; Retrospective Studies ; Critical Illness ; Case-Control Studies ; Bayes Theorem ; China ; Lung/diagnostic imaging*

Objective: To study the effects on extravascular lung water of lung protective ventilation strategy applying on piglets with acute respiratory distress syndrome (ARDS) induced by paraquat (PQ) under pulse indicating continuous cardiac output (PiCCO) monitoring. Methods: The piglets models with ARDS induced by PQ were established in June 2020 and all of them were received mechanical ventilation and divided into three groups according to tidal volume (V(T)) : small V(T) group (6 ml/kg) , middle V(T) group (10 ml/kg) and large V(T) group (15 ml/kg) , there were 5 piglets in each group. The positive end expiratory pressure (PEEP) were all setup on 10 cmH(2)O. The indexes such as arterial blood gas analysis, oxygenation index (OI) , extravascular lung water index (ELWI) and pulmonary vascular permeability index (PVPI) were monitored at time of before the model was established (baseline) , time of the model was established (t(0)) and 2 h (t(2)) , 4 h (t(4)) , 6 h (t(6)) after mechanical ventilation. Lung tissue were punctured at time of baseline, t(0) and t(6) to be stained by Hematoxylin-eosin (HE) staining and pulmonary pathology were observed under light microscopy. Results: The heart rate (HR) , mean arterial pressure (MAP) and partial pressure of carbon dioxide (PaCO(2)) of all groups were higher than the base value while the pH values, partial pressure of oxygen (PaO(2)) and OI were lower than the base value when the models were established (P<0.05) . After mechanical ventilation, the HR and MAP values of all groups at t(2), t(4) and t(6) were lower than t(0) while the PaCO(2) of t(4) and t(6) were all higher than t(0), the differences were statistically significant (P<0.05) . The PaO(2) and OI of all groups showed a trend of rising at first and then decreasing after mechanical ventilation. The MAP, PaO(2), PaCO(2) and OI of the middle V(T) group and large V(T) group were apparently lower than that of the small V(T) group at t(2), t(4) and t(6) (P<0.05) . The ELWI and PVPI at t(0) of all groups were higher than that of baseline (P<0.05) . The ELWI of the small V(T) group at t(6) were lower than t(0) of the same group and t(6) of the middle V(T) group and large V(T) group (P<0.05) . HE staining showed congestion and edema of alveolar tissue, swelling of capillaries, exudation of red blood cells and widening of alveolar septum in piglets after successful modeling. And further widening of alveolar septum and rupture of alveolar septum could be seen in the lung tissues of each group at t(6), and the injury was the slightest in the small V(T) group. Conclusion: The lung protective ventilation strategy can alleviate the extravascular lung water and ARDS induced by PQ and improve oxygenation.
Animals ; Extravascular Lung Water ; Lung/physiology* ; Paraquat/toxicity* ; Respiration, Artificial/adverse effects* ; Respiratory Distress Syndrome/chemically induced* ; Swine

Adult ; Capillary Permeability ; Extracorporeal Membrane Oxygenation ; Extravascular Lung Water ; Humans ; Lung/diagnostic imaging* ; Prognosis ; Respiratory Distress Syndrome/therapy*

OBJECTIVE: To investigate the value of pulse indicator continuous cardiac output (PiCCO) monitoring in the treatment management of patients with severe heart failure. METHODS: Sixty patients of severe heart failure admitted to intensive care unit (ICU) of Fujian Provincial Hospital from August 2017 to February 2019 were enrolled, and they were divided into control group and treatment group according to random number table method, with 30 in each group. The treatment group used bedside PiCCO to carry out minimally invasive hemodynamics monitoring, according to the monitoring data target guidance for vasoactive drugs and liquid management. The control group was based only on traditional electrocardiogram (ECG) monitoring and lung sound, urine volume of vasoactive drugs and liquid management. The changes of cardiac index (CI), global end diastolic volume index (GEDVI), extravascular lung water index (EVLWI), systemic vascular resistance index (SVRI), invasive mean arterial pressure (MAP) and central venous pressure (CVP) were observed before and 72 hours after treatment in the treatment group. The 7-day total effective rate, the length of ICU stay and 28-day mortality were compared between the two groups. RESULTS: Compared with before treatment, CI and MAP in the treatment group were significantly increased after treatment [CI (mL×s^-1×m^-2): 53.34±16.67 vs. 35.01±13.34, MAP (mmHg, 1 mmHg = 0.133 kPa): 72.6±10.6 vs. 62.5±10.3, both P < 0.05], GEDVI, EVLWI, SVRI, CVP were significantly decreased [GEDVI (mL/m²): 760.3±90.2 vs. 960.2±110.3, EVLWI (mL/kg): 6.5±1.3 vs. 12.5±6.2, SVRI (kPa×s×L^-1×m^-2): 297.3±35.1 vs. 434.1±58.8, CVP (mmHg): 10.1±2.6 vs. 12.2±3.4, all P < 0.05]. Compared with the control group, the 7-day total effective rate of the treatment group was significantly higher (90.0% vs. 80.0%), the length of ICU stay was significantly shorter (days: 8.2±4.5 vs. 10.3±2.5), and the 28-day mortality was significantly lower, with statistically significant difference (all P < 0.05). CONCLUSIONS PiCCO monitoring is a goal-oriented treatment management for patients with severe heart failure, which is helpful to individualized accurate treatment, shorten the length of ICU stay and improve short-term prognosis.
Cardiac Output ; Extravascular Lung Water ; Heart Failure/therapy* ; Heart Rate ; Hemodynamics ; Humans ; Prospective Studies

OBJECTIVETo investigate the effect of atrial fibrillation on the accuracy of parameters monitored by transpulmonary thermodilution method.

METHODSTotally 12 patients from emergency intensive care unit with paroxysmal atrial fibrillation were enrolled. The hemodynamic parameters such as heart rate, mean arterial pressure, cardiac index, systemic vascular resistance index, intrathoracic blood volume index, and extravascular lung water index were monitored by transpulmonary thermodilution method before paroxysmal atrial fibrillation and during atrial fibrillation, the number of B-lines was detected by lung ultrasonography before and during paroxysmal atrial fibrillation. The changes of all the parameters were analyzed.

RESULTSWhen the paroxysmal atrial fibrillation happened, the heart rate increased significantly [(123.3±20.0) beat/min vs. (98.9±12.3) beat/min, P=0.006]; the mean arterial pressure [(86.9±10.2) mmHg vs. (93.0±12.5) mmHg, P=0.058], cardiac index [(2.82±0.62) L/(min·m(2)) vs. (3.31±1.02) L/(min·m(2)), P=0.058] and systemic vascular resistance index [(2254±947) dyn·s·cm(-5)·m(2) vs. (2302±828) dyn·s·cm(-5)·m(2), P=0.351] had no obvious change; however, the intrathoracic blood volume index significantly increased [(1333±90) ml/m(2) vs. (937±111) ml/m(2), P<0.001]; extravascular lung water index also increased significantly [(16.1±1.1) ml/kg vs. (6.5±1.9) ml/kg, P<0.001]. No significant difference was found in the number of B-lines detected by lung ultrasonography before and during atrial fibrillation (10.0±4.2 vs. 9.4±4.4, P=0.180).

CONCLUSIONBoth intrathoracic blood volume and extravascular lung water monitored by transpulmonary thermodilution method were overvalued during paroxysmal atrial fibrillation, which may mislead the clinical judgment and decision-making.

Atrial Fibrillation ; physiopathology ; Blood Pressure ; Blood Volume ; Cardiac Output ; Extravascular Lung Water ; Heart Rate ; Hemodynamics ; Humans ; Intensive Care Units ; Thermodilution ; Vascular Resistance

OBJECTIVETo appraise the significance of extravascular lung water index (EVLWI), pulmonary vascular permeability index (PVPI), and intrathoracic blood volume index (ITBVI) in the differential diagnosis of the type of burn-induced pulmonary edema.

METHODSThe clinical data of 38 patients, with severe burn hospitalized in our burn ICU from December 2011 to September 2014 suffering from the complication of pulmonary edema within one week post burn and treated with mechanical ventilation accompanied by pulse contour cardiac output monitoring, were retrospectively analyzed. The patients were divided into lung injury group ( L, n = 17) and hydrostatic group (H, n = 21) according to the diagnosis of pulmonary edema. EVLWI, PVPI, ITBVI, oxygenation index, and lung injury score ( LIS) were compared between two groups, and the correlations among the former four indexes and the correlations between each of the former three indexes and types of pulmonary edema were analyzed. Data were processed with t test, chi-square test, Mann-Whitney U test, Pearson correlation test, and accuracy test [receiver operating characteristic (ROC) curve].

RESULTSThere was no statistically significant difference in EVLWI between group L and group H, respectively (12.9 ± 3.1) and (12.1 ± 2.1) mL/kg, U = 159.5, P > 0.05. The PVPI and LIS of patients in group L were respectively 2.6 ± 0.5 and (2.1 ± 0.6) points, and they were significantly higher than those in group H [1.4 ± 0.3 and (1.0 ± 0.6) points, with U values respectively 4.5 and 36.5, P values below 0.01]. The ITBVI and oxygenation index of patients in group L were respectively (911 197) mL/m2 and (136 ± 69) mmHg (1 mmHg = 0.133 kPa), which were significantly lower than those in group H [(1,305 ± 168) mL/m2 and (212 ± 60) mmHg, with U values respectively 21.5 and 70.5, P values below 0.01]. In group L, there was obviously positive correlation between EVLWI and PVPI, or EVLWI and ITBVI (with r values respectively 0.553 and 0.807, P < 0.05 or P < 0.01), and there was obviously negative correlation between oxygenation index and EVLWI, or oxygenation index and PVPI (with r values respectively -0.674 and -0.817, P values below 0.01). In group H, there was obviously positive correlation between EVLWI and ITBVI (r = 0.751, P < 0.01) but no obvious correlation between EVLWI and PVPI, oxygenation index and EVLWI, or oxygenation index and PVPI (with r values respectively -0.275, 0.197, and 0:062, P values above 0.05). The total area under ROC curve of PVPI value for differentiating the type of pulmonary edema was 0.987 [with 95% confidence interval (CI) 0.962-1.013, P < 0.01], and 1.9 was the cutoff value with sensitivity of 94.1% and specificity of 95.2% . The total area under ROC curve of ITBVI value for differentiating the type of pulmonary edema was 0.940 (with 95% CI 0.860-1.020, P < 0.01), and 1,077. 5 mL/m2 was the cutoff value with sensitivity of 95.2% and specificity of 88.2%.

CONCLUSIONSEVLWI, PVPI, and ITBVI have an important significance in the differential diagnosis of the type of burn-induced pulmonary edema, and they may be helpful in the early diagnosis and management of burn-induced pulmonary edema.

Blood Gas Analysis ; Blood Volume ; Burns ; complications ; Capillary Permeability ; Diagnosis, Differential ; Extravascular Lung Water ; Humans ; Lung ; blood supply ; Lung Injury ; physiopathology ; therapy ; Monitoring, Physiologic ; Pulmonary Edema ; diagnosis ; etiology ; ROC Curve ; Respiration, Artificial ; Retrospective Studies

Pulmonary edema frequently occurs after severe burn. It not only impairs pulmonary function directly, but also can induce or exacerbate other pulmonary complications such as lung infection, acute lung injury ( ALI), and ARDS. Extravascular lung water (EVLW) is closely related to the pulmonary edema. Dynamical monitor of EVLW has been used to predict and quantify the degree of pulmonary edema clinically. This review focuses on the recent progresses at home and abroad on the formation mechanism, monitoring approach, and prevention and treatment of EVLW after severe burn injury.
Acute Lung Injury ; etiology ; physiopathology ; Burns ; Extravascular Lung Water ; Humans ; Pulmonary Edema ; diagnosis ; etiology ; Severity of Illness Index ; Shock, Septic ; complications ; physiopathology ; Thermodilution ; Trauma Severity Indices

OBJECTIVETo assess the effects of continuous blood purification (CBP) on extravascular lung water and respiratory function in patients with extrapulmonary acute respiratory distress syndrome (ARDSexp).

METHODSThe data of 31 patients with ARDSexp admitted in our department were retrospectively analyzed.Sixteen of the patients received CBP, and the other 15 patients did not (control group). The level of extravascular lung water index (EVLWI), pulmonary vascular permeability index (PVPI), and respiratory function were measured before and after CPB.

RESULTSThe mortality rate was significantly lower in CBP group than in the control group (12.5% vs 33.3%, P<0.05). The patients in CPB group showed markedly earlier and significantly greater improvements in EVLWI, PVPI, PaO2/FiO, and respiratory function than the control patients (P<0.05).

CONCLUSIONCBP can reduce EVLWI and PVPI, improve pulmonary compliance and oxygenation, and reduce mortality rate in patients with ARDSexp.

Capillary Permeability ; Extravascular Lung Water ; Hemofiltration ; Humans ; Lung ; Monitoring, Physiologic ; Respiration ; Respiratory Distress Syndrome, Adult ; Retrospective Studies

OBJECTIVETo observe the best dose of methylprednisolone improving lung injury in swine with paraquat intoxication.

METHODSAcute lung injury (ALI/ARDS) model was made by an intraperitoneal injection of a large dose of 20%PQ solution20 millilitres in swine. Then 24 swine were randomly divided into 4 groups: exposed PQ control group, 5 mg/kg of methylprednisolone group, 15 mg/kg of methylprednisolone group, 30 mg/kg of methylprednisolone group. All groups were based on the conventional rehydration for intervention, Arterial blood samples were collected before modeling and 0, 12, 24, 36 hours after different processing for blood gas analysis. At the same time heart rate (HR), mean arterial pressure (MAP), extravascular lung water index (EVLWI) and pulmonary vascular permeability index (PVPI) were measured by using PICCO (pulse indicator continuous cardiac output), lung tissue was obtained by punctureneedle to produce lung biopsy, then observe the pathological changes of lung tissue in the microscope.

RESULTS1. Comparison between groups: there is no significant difference about extravascular lung water index (EVLWI) and semi-quantitative score of lung tissue pathology in four groups (P > 0.05) before modeling, so is t0, there is significant difference at about extravascular lung water index and semi-quantitative score of lung tissue pathology 12 h, 24 h and 36 h after different processing (P < 0.05). Within the group: EVLWI and semi-quantitative score of Lung tissue pathology in four groups significantly increased when the model was made (P < 0.05), after different processing, EVLWI and semi-quantitative score of Lung tissue pathology in exposed PQ control group kept going up, in other three groups, EVLWI and semi-quantitative score of lung tissue pathology went down first and then went up, there is significant difference compared with t0 (P < 0.05). 2. Comparison between groups: there is no significant difference about oxygenation index in four groups (P > 0.05) before modeling, so is t0, there is significant difference about oxygenation at 12 h, 24 h and 36 h after different processing (P < 0.05). Within the group: oxygenation index in four groups significantly decreased when the model was made (P < 0.05), after different processing, oxygenation index in exposed PQ control group kept going down, in other three groups, it showed a downward trend after the first rise, there is significant difference compared with t0 (P < 0.05). 3. After medication for 36h, correlation analysis showed that EVLWI were negatively associated with oxygenation index (r = -0.427, P = 0.022) and positively associated with semi-quantitative score of Lung tissue pathology (r = 0.903, P = 0.034).

CONCLUSIONMethylprednisolone can obviously relieve lung injury caused by paraquat poisoning and improve oxygenation. After the model was made, within 24 hours, 30 mg/kg of methylprednisolone have advantage for the PQ poisoning swine, but 15mg/kg of methylprednisolone is best for improving lung injury induced by paraquat intoxication within 24 hours to 36 hours.

Acute Lung Injury ; chemically induced ; drug therapy ; Animals ; Blood Gas Analysis ; Capillary Permeability ; Extravascular Lung Water ; Heart Rate ; Lung ; Lung Injury ; Methylprednisolone ; administration & dosage ; therapeutic use ; Paraquat ; toxicity ; Swine

OBJECTIVETo assess the prognostic value of pulse indicator continuous cardiac output (Picco) monitoring combined with plasma microRNA-150 detection in septic shock patients.

METHODSClinical data of 48 patients with septic shock admitted in General Intensive Care Unit (GICU), Shanghai First People's Hospital Songjiang Branch Affiliated to Shanghai Jiaotong University from August 2012 to August 2014 were analyzed retrospectively. The plasma levels of microRNA-150 in 48 patients at admission were assayed by qRT-PCR; and Picco monitoring was performed to record hemodynamic changes. The correlation of microRNA-150 or Picco parameters with prognosis of patients was assessed by univariate analysis and multivariate logistic analysis. Spearman correlation test showed the relationship between microRNA-150 and Picco parameters. Finally, the clinical value of combining microRNA-150 with Picco monitoring to predict the outcome of septic shock patients was analyzed by ROC curves.

RESULTSTwenty-three patients survived and 25 died in 28 d after admission in GICU. Compared with survival patients, microRNA-150 was significantly lower in fatal patients (t=-10.32, P<0.05). Univariate analysis showed that low microRNA-150 level was a risk factor for poor prognosis(OR=2.176,95% CI:1.121-4.223, P<0.05). Compared with fatal cases, the cardiac index of survival patients was higher, while EVLWI and PVPI were lower. MicroRNA-150 level was positively correlated with cardiac index (r=0.712, P<0.05), negatively correlated with EVLWI and PVPI (r=-0.622 and-0.689, both P<0.05). ROC curves showed a satisfactory diagnostic efficiency of combining microRNA-150 with Picco monitoring.

CONCLUSIONLower microRNA-150 may indicate a poor prognosis, and Picco monitoring combined with microRNA 150 detection may improve the prognostic efficiency in septic shock patients.

China ; Death ; Extravascular Lung Water ; Hemodynamics ; Humans ; MicroRNAs ; blood ; Plasma ; chemistry ; Prognosis ; Retrospective Studies ; Risk Factors ; Shock, Septic ; blood ; mortality