Association of preoperative antiviral treatment with incidences of post-hepatectomy liver failure in hepatitis B virus-related hepatocellular carcinoma.

BACKGROUND: Post-hepatectomy liver failure (PHLF) is a common consequence of radical partial hepatectomy in hepatocellular carcinoma (HCC). AIMS: To investigate the relationship between preoperative antiviral therapy and PHLF, as well as assess the potential efficacy of hepatitis B virus (HBV) DNA level in predicting PHLF. METHODS: A retrospective study was performed involving 1301 HCC patients with HBV who underwent radical hepatectomy. Receiver operating characteristic (ROC) analysis was used to assess the capacity of HBV DNA to predict PHLF and establish the optimal cutoff value for subsequent analyses. Logistic regression analyses were performed to assess the independent risk factors of PHLF. The increase in the area under the ROC curve, categorical net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were used to quantify the efficacy of HBV DNA level for predicting PHLF. The P < 0.05 was considered statistically significant. RESULTS: Logistic regression analyses showed that preoperative antiviral therapy was independently associated with a reduced risk of PHLF (P < 0.05). HBV DNA level with an optimal cutoff value of 269 IU/mL (P < 0.001) was an independent risk factor of PHLF. All the reference models by adding the variable of HBV DNA level had an improvement in area under the curve, categorical NRI, and IDI, particularly for the fibrosis-4 model, with values of 0.729 (95%CI: 0.705-0.754), 1.382 (95%CI: 1.341-1.423), and 0.112 (95%CI: 0.110-0.114), respectively. All the above findings were statistically significant. CONCLUSION: In summary, preoperative antiviral treatment can reduce the incidence of PHLF, whereas an increased preoperative HBV DNA level has a correlative relationship with an increased susceptibility to PHLF.

Inflammatory Markers Showed Significant Incremental Value for Predicting Post-Hepatectomy Liver Failure in Hepatocellular Carcinoma Patients.

BACKGROUND: Post-hepatectomy liver failure (PHLF) remains a complication with the potential risk of mortality for hepatocellular carcinoma (HCC) patients. The systemic inflammatory response (SIR) has been demonstrated to be associated with a bad prognosis of liver cirrhosis and tumors. This study aims to evaluate the incremental prognostic value of inflammatory markers in predicting PHLF in patients with HCC. METHODS: Clinical characteristics and variables were retrospectively collected in 2824 patients diagnosed with HCC who underwent radical hepatectomy from the First Medical Center of the General Hospital of the People's Liberation Army. A recently published prognostic model for PHLF was used as the reference model. The increase in AUC (ΔAUC), integrated discrimination improvement (IDI), and the continuous version of the net reclassification improvement (NRI) were applied for quantifying the incremental value of adding the inflammatory markers to the reference model. A p value < 0.05 was considered statistically significant. RESULTS: The reference PHLF model showed acceptable prediction performance in the current cohort, with an AUC of 0.7492 (95%CI, 0.7191-0.7794). The calculated ΔAUC associated with procalcitonin (PCT) was the only one that was statistically significant (p < 0.05), with a value of 0.0044, and demonstrated the largest magnitude of the increase in AUC. The continuous NRI value associated with the systemic immune-inflammation index (SII) was 35.79%, second only to GPS (46.07%). However, the inflammatory markers of the new models with statistically significant IDI only included WBC count, lymphocyte count, and SII. IDI associated with SII, meanwhile, was the maximum (0.0076), which was consistent with the performance of using the ΔAUC (0.0044) to assess the incremental value of each inflammatory variable. CONCLUSIONS: Among a wide range of inflammatory markers, only PCT and SII have potential incremental prognostic value for predicting PHLF in patients with radical resectable HCC.

Artificial Intelligence-Assisted Left Ventricular Diastolic Function Assessment and Grading: Multiview Versus Single View.

BACKGROUND: Clinical assessment and grading of left ventricular diastolic function (LVDF) requires quantification of multiple echocardiographic parameters interpreted according to established guidelines, which depends on experienced clinicians and is time consuming. The aim of this study was to develop an artificial intelligence (AI)-assisted system to facilitate the clinical assessment of LVDF. METHODS: In total, 1,304 studies (33,404 images) were used to develop a view classification model to select six specific views required for LVDF assessment. A total of 2,238 studies (16,794 two-dimensional [2D] images and 2,198 Doppler images) to develop 2D and Doppler segmentation models, respectively, to quantify key metrics of diastolic function. We used 2,150 studies with definite LVDF labels determined by two experts to train single-view classification models by AI interpretation of strain metrics or video. The accuracy and efficiency of these models were tested in an external data set of 388 prospective studies. RESULTS: The view classification model identified views required for LVDF assessment with good sensitivity (>0.9), and view segmentation models successfully outlined key regions of these views with intersection over union > 0.8 in the internal validation data set. In the external test data set of 388 cases, AI quantification of 2D and Doppler images showed narrow limits of agreement compared with the two experts (e.g., left ventricular ejection fraction, -12.02% to 9.17%; E/e' ratio, -3.04 to 2.67). These metrics were used to detect LV diastolic dysfunction (DD) and grade DD with accuracy of 0.9 and 0.92, respectively. Concerning the single-view method, the overall accuracy of DD detection was 0.83 and 0.75 by strain-based and video-based models, and the accuracy of DD grading was 0.85 and 0.8, respectively. These models could achieve diagnosis and grading of LVDD in a few seconds, greatly saving time and labor. CONCLUSION: AI models successfully achieved LVDF assessment and grading that compared favorably with human experts reading according to guideline-based algorithms. Moreover, when Doppler variables were missing, AI models could provide assessment by interpreting 2D strain metrics or videos from a single view. These models have the potential to save labor and cost and to facilitate work flow of clinical LVDF assessment.

Echocardiography-based AI for detection and quantification of atrial septal defect.

Objectives: We developed and tested a deep learning (DL) framework applicable to color Doppler echocardiography for automatic detection and quantification of atrial septal defects (ASDs). Background: Color Doppler echocardiography is the most commonly used non-invasive imaging tool for detection of ASDs. While prior studies have used DL to detect the presence of ASDs from standard 2D echocardiographic views, no study has yet reported automatic interpretation of color Doppler videos for detection and quantification of ASD. Methods: A total of 821 examinations from two tertiary care hospitals were collected as the training and external testing dataset. We developed DL models to automatically process color Doppler echocardiograms, including view selection, ASD detection and identification of the endpoints of the atrial septum and of the defect to quantify the size of defect and the residual rim. Results: The view selection model achieved an average accuracy of 99% in identifying four standard views required for evaluating ASD. In the external testing dataset, the ASD detection model achieved an area under the curve (AUC) of 0.92 with 88% sensitivity and 89% specificity. The final model automatically measured the size of defect and residual rim, with the mean biases of 1.9 mm and 2.2 mm, respectively. Conclusion: We demonstrated the feasibility of using a deep learning model for automated detection and quantification of ASD from color Doppler echocardiography. This model has the potential to improve the accuracy and efficiency of using color Doppler in clinical practice for screening and quantification of ASDs, that are required for clinical decision making.

Echocardiography-based AI detection of regional wall motion abnormalities and quantification of cardiac function in myocardial infarction.

Objective: To compare the performance of a newly developed deep learning (DL) framework for automatic detection of regional wall motion abnormalities (RWMAs) for patients presenting with the suspicion of myocardial infarction from echocardiograms obtained with portable bedside equipment versus standard equipment. Background: Bedside echocardiography is increasingly used by emergency department setting for rapid triage of patients presenting with chest pain. However, compared to images obtained with standard equipment, lower image quality from bedside equipment can lead to improper diagnosis. To overcome these limitations, we developed an automatic workflow to process echocardiograms, including view selection, segmentation, detection of RWMAs and quantification of cardiac function that was trained and validated on image obtained from bedside and standard equipment. Methods: We collected 4,142 examinations from one hospital as training and internal testing dataset and 2,811 examinations from other hospital as the external test dataset. For data pre-processing, we adopted DL model to automatically recognize three apical views and segment the left ventricle. Detection of RWMAs was achieved with 3D convolutional neural networks (CNN). Finally, DL model automatically measured the size of cardiac chambers and left ventricular ejection fraction. Results: The view selection model identified the three apical views with an average accuracy of 96%. The segmentation model provided good agreement with manual segmentation, achieving an average Dice of 0.89. In the internal test dataset, the model detected RWMAs with AUC of 0.91 and 0.88 respectively for standard and bedside ultrasound. In the external test dataset, the AUC were 0.90 and 0.85. The automatic cardiac function measurements agreed with echocardiographic report values (e. g., mean bias is 4% for left ventricular ejection fraction). Conclusion: We present a fully automated echocardiography pipeline applicable to both standard and bedside ultrasound with various functions, including view selection, quality control, segmentation, detection of the region of wall motion abnormalities and quantification of cardiac function.

Elevated Fasting Blood Glucose Levels Are Associated with Worse Clinical Outcomes in COVID-19 Patients Than in Pneumonia Patients with Bacterial Infections.

Aims: We investigate how fasting blood glucose (FBG) levels affect the clinical severity in coronavirus disease 2019 (COVID-19) patients, pneumonia patients with sole bacterial infection, and pneumonia patients with concurrent bacterial and fungal infections. Methods: We enrolled 2761 COVID-19 patients, 1686 pneumonia patients with bacterial infections, and 2035 pneumonia patients with concurrent infections. We used multivariate logistic regression analysis to assess the associations between FBG levels and clinical severity. Results: FBG levels in COVID-19 patients were significantly higher than in other pneumonia patients during hospitalisation and at discharge (all p < 0.05). Among COVID-19 patients, the odds ratios of acute respiratory distress syndrome (ARDS), respiratory failure (RF), acute hepatitis/liver failure (AH/LF), length of stay, and intensive care unit (ICU) admission were 12.80 (95% CI, 4.80−37.96), 5.72 (2.95−11.06), 2.60 (1.20−5.32), 1.42 (1.26−1.59), and 5.16 (3.26−8.17) times higher in the FBG ≥7.0 mmol/L group than in FBG < 6.1 mmol/L group, respectively. The odds ratios of RF, AH/LF, length of stay, and ICU admission were increased to a lesser extent in pneumonia patients with sole bacterial infection (3.70 [2.21−6.29]; 1.56 [1.17−2.07]; 0.98 [0.88−1.11]; 2.06 [1.26−3.36], respectively). The odds ratios of ARDS, RF, AH/LF, length of stay, and ICU admission were increased to a lesser extent in pneumonia patients with concurrent infections (3.04 [0.36−6.41]; 2.31 [1.76−3.05]; 1.21 [0.97−1.52]; 1.02 [0.93−1.13]; 1.72 [1.19−2.50], respectively). Among COVID-19 patients, the incidence rate of ICU admission on day 21 in the FBG ≥ 7.0 mmol/L group was six times higher than in the FBG < 6.1 mmol/L group (12.30% vs. 2.21%, p < 0.001). Among other pneumonia patients, the incidence rate of ICU admission on day 21 was only two times higher. Conclusions: Elevated FBG levels at admission predict subsequent clinical severity in all pneumonia patients regardless of the underlying pathogens, but COVID-19 patients are more sensitive to FBG levels, and suffer more severe clinical complications than other pneumonia patients.

Cardiac Adaptation to Prolonged High Altitude Migration Assessed by Speckle Tracking Echocardiography.

Objective: Exposure to high altitudes represents physiological stress that leads to significant changes in cardiovascular properties. However, long-term cardiovascular adaptions to high altitude migration of lowlanders have not been described. Accordingly, we measured changes in cardiovascular properties following prolonged hypoxic exposure in acclimatized Han migrants and Tibetans. Methods: Echocardiographic features of recently adapted Han migrant (3-12 months, n = 64) and highly adapted Han migrant (5-10 years, n = 71) residence in Tibet (4,300 m) using speckle tracking echocardiography were compared to those of age-matched native Tibetans (n = 75) and Han lowlanders living at 1,400 m (n = 60). Results: Short-term acclimatized migrants showed increased estimated pulmonary artery systolic pressure (PASP) (32.6 ± 5.1 mmHg vs. 21.1 ± 4.2 mmHg, p < 0.05), enlarged right ventricles (RVs), and decreased fractional area change (FAC) with decreased RV longitudinal strain (-20 ± 2.8% vs. -25.5 ± 3.9%, p < 0.05). While left ventricular ejection fraction (LVEF) was preserved, LV diameter (41.7 ± 3.1 mm vs. 49.7 ± 4.8 mm, p < 0.05) and LV longitudinal strain (-18.8 ± 3.2% vs. -22.9 ± 3.3%, p < 0.05) decreased. Compared with recent migrants, longer-term migrants had recovered RV structure and functions with slightly improved RV and LV longitudinal strain, though still lower than lowlander controls; LV size remained small with increased mass index (68.3 ± 12.7 vs. 59.3 ± 9.6, p < 0.05). In contrast, native Tibetans had slightly increased PASP (26.1 ± 3.4 mmHg vs. 21.1 ± 4.2 mmHg, p < 0.05) with minimally altered cardiac deformation compared to lowlanders. Conclusion: Right ventricular systolic function is impaired in recent (<1 year) migrants to high altitudes but improved during the long-term dwelling. LV remodeling persists in long-term migrants (>5 years) but without impairment of LV systolic or diastolic function. In contrast, cardiac size, structure, and function of native Tibetans are more similar to those of lowland dwelling Hans.

Self-supervised learning assisted diagnosis for mitral regurgitation severity classification based on color Doppler echocardiography.

BACKGROUND: Mitral regurgitation (MR) is the most common valve lesion worldwide. However, the quantitative assessment of MR severity based on current guidelines is challenging and time-consuming; strict adherence to applying these guidelines is therefore relatively infrequent. We aimed to develop an automatic, reliable and reproducible artificial intelligence (AI) diagnostic system to assist physicians in grading MR severity based on color video Doppler echocardiography via a self-supervised learning (SSL) algorithm. METHODS: We constructed a retrospective cohort of 2,766 consecutive echocardiographic studies of patients with MR diagnosed based on clinical criteria from two hospitals in China. One hundred and forty-eight studies with reference standards were selected in the main analysis and also served as the test set for the AI segmentation model. Five hundred and ninety-two and 148 studies were selected with stratified random sampling as the training and validation datasets, respectively. The self-supervised algorithm captures features and segments the MR jet and left atrium (LA) area, and the output is used to assist physicians in MR severity grading. The diagnostic performance of physicians without and with the support from AI was estimated and compared. RESULTS: The performance of SSL algorithm yielded 89.2% and 85.3% average segmentation dice similarity coefficient (DICE) on the validation and test datasets, which achieved 6.2% and 8.1% improvement compared to Residual U-shape Network (ResNet-UNet), respectively. When physicians were provided the output of algorithm for grading MR severity, the sensitivity increased from 77.0% (95% CI: 70.9-82.1%) to 86.7% (95% CI: 80.3-91.2%) and the specificity was largely unchanged: 91.5% (95% CI: 87.8-94.1%) vs. 90.5% (95% CI: 86.7-93.2%). CONCLUSIONS: This study provides a new, practical, accurate, plug-and-play AI-assisted approach for assisting physicians in MR severity grading that can be easily implemented in clinical practice.

Automated Analysis of Doppler Echocardiographic Videos as a Screening Tool for Valvular Heart Diseases.

OBJECTIVES: This study sought to develop a deep learning (DL) framework to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs). BACKGROUND: Although advances in DL have been applied to the interpretation of echocardiograms, such techniques have not been reported for interpretation of color Doppler videos for diagnosing VHDs. METHODS: The authors developed a 3-stage DL framework for automatic screening of echocardiographic videos for mitral stenosis (MS), mitral regurgitation (MR), aortic stenosis (AS), and aortic regurgitation (AR) that classifies echocardiographic views, detects the presence of VHDs, and, when present, quantifies key metrics related to VHD severities. The algorithm was trained (n = 1,335), validated (n = 311), and tested (n = 434) using retrospectively selected studies from 5 hospitals. A prospectively collected set of 1,374 consecutive echocardiograms served as a real-world test data set. RESULTS: Disease classification accuracy was high, with areas under the curve of 0.99 (95% CI: 0.97-0.99) for MS; 0.88 (95% CI: 0.86-0.90) for MR; 0.97 (95% CI: 0.95-0.99) for AS; and 0.90 (95% CI: 0.88-0.92) for AR in the prospective test data set. The limits of agreement (LOA) between the DL algorithm and physician estimates of metrics of valve lesion severities compared to the LOAs between 2 experienced physicians spanned from -0.60 to 0.77 cm2 vs -0.48 to 0.44 cm2 for MV area; from -0.27 to 0.25 vs -0.23 to 0.08 for MR jet area/left atrial area; from -0.86 to 0.52 m/s vs -0.48 to 0.54 m/s for peak aortic valve blood flow velocity (Vmax); from -10.6 to 9.5 mm Hg vs -10.2 to 4.9 mm Hg for average peak aortic valve gradient; and from -0.39 to 0.32 vs -0.31 to 0.32 for AR jet width/left ventricular outflow tract diameter. CONCLUSIONS: The proposed deep learning algorithm has the potential to automate and increase efficiency of the clinical workflow for screening echocardiographic images for the presence of VHDs and for quantifying metrics of disease severity.

High Fasting Blood Glucose Level With Unknown Prior History of Diabetes Is Associated With High Risk of Severe Adverse COVID-19 Outcome.

Background: We aimed to understand how glycaemic levels among COVID-19 patients impact their disease progression and clinical complications. Methods: We enrolled 2,366 COVID-19 patients from Huoshenshan hospital in Wuhan. We stratified the COVID-19 patients into four subgroups by current fasting blood glucose (FBG) levels and their awareness of prior diabetic status, including patients with FBG<6.1mmol/L with no history of diabetes (group 1), patients with FBG<6.1mmol/L with a history of diabetes diagnosed (group 2), patients with FBG≥6.1mmol/L with no history of diabetes (group 3) and patients with FBG≥6.1mmol/L with a history of diabetes diagnosed (group 4). A multivariate cause-specific Cox proportional hazard model was used to assess the associations between FBG levels or prior diabetic status and clinical adversities in COVID-19 patients. Results: COVID-19 patients with higher FBG and unknown diabetes in the past (group 3) are more likely to progress to the severe or critical stage than patients in other groups (severe: 38.46% vs 23.46%-30.70%; critical 7.69% vs 0.61%-3.96%). These patients also have the highest abnormal level of inflammatory parameters, complications, and clinical adversities among all four groups (all p<0.05). On day 21 of hospitalisation, group 3 had a significantly higher risk of ICU admission [14.1% (9.6%-18.6%)] than group 4 [7.0% (3.7%-10.3%)], group 2 [4.0% (0.2%-7.8%)] and group 1 [2.1% (1.4%-2.8%)], (P<0.001). Compared with group 1 who had low FBG, group 3 demonstrated 5 times higher risk of ICU admission events during hospitalisation (HR=5.38, 3.46-8.35, P<0.001), while group 4, where the patients had high FBG and prior diabetes diagnosed, also showed a significantly higher risk (HR=1.99, 1.12-3.52, P=0.019), but to a much lesser extent than in group 3. Conclusion: Our study shows that COVID-19 patients with current high FBG levels but unaware of pre-existing diabetes, or possibly new onset diabetes as a result of COVID-19 infection, have a higher risk of more severe adverse outcomes than those aware of prior diagnosis of diabetes and those with low current FBG levels.

Assisting scalable diagnosis automatically via CT images in the combat against COVID-19.

The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance.

The Preference, Effect, and Prognosis of Intra-Aortic Balloon Counterpulsation in Acute Myocardial Infarction Complicated by Cardiogenic Shock Patients: A Retrospective Cohort Study.

BACKGROUNDS: Intra-aortic balloon counterpulsation is increasingly used in acute myocardial infarction complicated by cardiogenic shock. The aim of this study was to explore the preference, effect, and prognosis of intra-aortic balloon counterpulsation in acute myocardial infarction complicated by cardiogenic shock patients. METHODS: Data of acute myocardial infarction complicated by cardiogenic shock patients at the Fourth Medical Center of PLA General Hospital were collected retrospectively. A propensity score was calculated with a logistic regression which contained clinically meaningful variables and variables selected by Lasso and then used to match the control group. The cumulative incidence curve and Gray's test were employed to analyse the effect and prognosis of intra-aortic balloon counterpulsation on mortality. RESULTS: A total of 1962 acute myocardial infarction cases admitted between May 2015 and November 2018 were identified, and 223 cases with acute myocardial infarction complicated by cardiogenic shock were included as the study cohort, which contained 34 cases that received IABP and 189 cases that did not receive IABP. Patients with higher alanine aminotransferase (OR = 1.93, 95% CI 1.29-2.98), higher triglyceride (OR = 3.71, 95% CI 1.87-7.95), and higher blood glucose (OR = 1.08, 95% CI 0.99-1.18) had a higher probability of receiving intra-aortic balloon counterpulsation. In the propensity score matching analysis, 34 cases received intra-aortic balloon counterpulsation and 102 matched controls were included in the comparison. By comparing the cumulative incidence of in-hospital mortality, there was no statistically significant difference between the intra-aortic balloon counterpulsation group and matched control group (P = 0.454). CONCLUSION: The use of intra-aortic balloon counterpulsation may not improve the prognosis of the acute myocardial infarction complicated by cardiogenic shock patients.

Calpain inhibition ameliorates scald burn-induced acute lung injury in rats.

BACKGROUND: The molecular pattern of severe burn-induced acute lung injury, characterized by cell structure damage and leukocyte infiltration, remains unknown. This study aimed to determine whether calpain, a protease involved in both processes, mediates severe burn-induced acute lung injury. METHODS: Rats received full-thickness scald burns covering 30% of the total body surface area, followed by instant fluid resuscitation. MDL28170 (Tocris Bioscience), an inhibitor of calpain, was given intravenously 1 h before or after the scald burn. The histological score, wet/dry weight ratio, and caspase-3 activity were examined to evaluate the degree of lung damage. Calpain activity and its source were detected by an assay kit and immunofluorescence staining. The proteolysis of membrane skeleton proteins α-fodrin and ankyrin-B, which are substrates of calpain, was measured by Western blot. RESULTS: Time-course studies showed that tissue damage reached a peak between 1 and 6 h post-scald burn and gradually diminished at 24 h. More importantly, calpain activity reached peak levels at 1 h and was maintained until 24 h, paralleled by lung damage to some extent. Western blot showed that the levels of the proteolyzed forms of α-fodrin and ankyrin-B correlated well with the degree of damage. MDL28170 at a dose of 3 mg/kg b. w. given 1 h before burn injury not only antagonized the increase in calpain activity but also ameliorated scald burn-induced lung injury, including the degradation of α-fodrin and ankyrin-B. Immunofluorescence images revealed calpain 1 and CD45 double-positive cells in the lung tissue of rats exposed to scald burn injury, suggesting that leukocytes were a dominant source of calpain. Furthermore, this change was blocked by MDL28170. Finally, MDL28170 given at 1 h post-scald burn injury significantly ameliorated the wet/dry weight ratio compared with burn injury alone. CONCLUSIONS: Calpain, a product of infiltrating leukocytes, is a mediator of scald burn-induced acute lung injury that involves enhancement of inflammation and proteolysis of membrane skeleton proteins. Its late effects warrant further study.