Aims:Bleeding from gastroesophageal varices(GEV)is a medical emergency associated with high mortality.We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography(2D-SWE)of the...Aims:Bleeding from gastroesophageal varices(GEV)is a medical emergency associated with high mortality.We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography(2D-SWE)of the liver and spleen to precisely assess the risk of GEV and high-risk GEV(HRV).Methods:This was a multicenter,prospective study conducted from October 2020 to September 2022 across 12 hospitals in China.Patients with compensated advanced chronic liver disease(cACLD)were enrolled,with informed consent obtained.A total of 1136 liver stiffness measurement(LSM)images and 1042 spleen stiffness measurement(SSM)images generated by 2D SWE.Weleveraged deep learning methods to uncover associations between image features and patient risk;in this manner,we constructed models to predict GEV and HRV.Results:A multimodality deep learning risk prediction(DLRP)model was constructed to assess GEV and HRV based on LSM and SSM images and clinical information.Validation analysis revealed that the area under the curve(AUC)values of DLRP were 0.91 for GEV(95%confidence interval[CI],0.90-0.93,p<0.05)and 0.88 for HRV(95%CI,0.86-0.89,p<0.01),which were significantly and robustly better than those of canonical risk indicators,including the values of LSM(0.63 and 0.68 for GEV and HRV)andSSM(0.75for both GEV andHRV).Moreover,the DLRP model outperformed the model using individual parameters.In HRV prediction,the 2D-SWE SSM images(0.75)were more informative than LSM(0.68,p<0.01).Conclusion:Our DLRP model shows excellent performance in predicting GEV and HRV,outperforming the canonical risk indicators LSM and SSM.Additionally,the 2D-SWE SSM images provided more information and thus better accuracy in HRV prediction than the LSM images.展开更多
Background and Aims:This study aimed to determine the performance of the non-invasive score using noncontrastenhanced MRI(CHESS-DIS score)for detecting portal hy-pertension in cirrhosis.Methods:In this international m...Background and Aims:This study aimed to determine the performance of the non-invasive score using noncontrastenhanced MRI(CHESS-DIS score)for detecting portal hy-pertension in cirrhosis.Methods:In this international multicenter,diagnostic study(ClinicalTrials.gov,NCT03766880),patients with cirrhosis who had hepatic venous pressure gradient(HVPG)measurement and noncontrast-enhanced MRI were prospectively recruited from four university hospitals in China(n=4)and Turkey(n=1)between December 2018 and April 2019.A cohort of patients was retrospectively recruited from a university hospital in Italy between March 2015 and November 2017.After segmentation of the liver on fat-suppressed T1-weighted MRI maps,CHESS-DIS score was calculated automatically by an in-house developed code based on the quantification of liver surface nodularity.Results:A total of 149 patients were included,of which 124 were from four Chinese hospitals(training cohort)and 25 were from two international hospitals(validation cohort).A positive correlation between CHESS-DIS score and HVPG was found with the correlation coefficients of 0.36(p<0.0001)and 0.55(p<0.01)for the training and validation cohorts,respectively.The area under the receiver operating characteristic curve of CHESS-DIS score in detection of clinically significant portal hypertension(CSPH)was 0.81 and 0.9 in the training and validation cohorts,respectively.The intra-class correlation coefficients for assessing the inter-and intra-observer agreement were 0.846 and 0.841,respectively.Conclusions:A non-invasive score using noncontrast-enhanced MRI was developed and proved to be significantly correlated with invasive HVPG.Besides,this score could be used to detect CSPH in patients with cirrhosis.展开更多
Aims:The renewing Baveno VII consensus proposed criteria for the diagnosis of clinically significant portal hypertension(CSPH)in patients with compensated advanced chronic liver disease(cACLD).The performance of a com...Aims:The renewing Baveno VII consensus proposed criteria for the diagnosis of clinically significant portal hypertension(CSPH)in patients with compensated advanced chronic liver disease(cACLD).The performance of a combined model of spleen stiffness measurement(SSM)by spleen-dedicated 100 Hz(SSM@100 Hz)or conventional 50 Hz(SSM@50 Hz)and Baveno VII criteria to rule-in or rule-out CSPH had not been well validated.This study aims to compare the performance of the combined model with Baveno VIIcriteria alone to rule-in and rule-out CSPH in cACLD.Methods:This international multicenter study included cACLD patients who underwent paired liver stiffness measurement(LSM),SSM@100 Hz or SSM@50 Hz,platelet count(PLT),and hepatic venous pressure gradient(HVPG).CSPH was defined as HVPG≥10 mmHg.Patients with SSM@100 Hz were prospectively recruited from China between August 2021 and March 2022,while a globalcohort of patients with SSM@50 Hz from Croatia,Japan,and Singapore was retrospectively included between December 2014 and June2022.The diagnostic performance of different models was assessed using sensitivity,specificity,positive predictive value,and negativepredictive value.Results:A total of 206 patients with cACLD were recruited from seven university centers and 110 patients were included in the finalanalysis(54 from the SSM@100 Hz cohort and 56 from the SSM@50 Hz cohort).The success rate of SSM@100 Hz was significantlyhigher than that of SSM@50 Hz(103/105[98.1%]vs.86/101[85.1%];p<0.001).While the combined model(SSM>50 kPa orLSM≥25 kPa)and Baveno VII criteria(LSM≥25 kPa)had a positive predictive value and specificity>90%to rule-in CSPH,thecombined model correctly ruled-in more cACLD patients with CSPH compared to Baveno VII criteria alone(35/110[31.8%]vs.22/110[20.0%];p<0.001).Furthermore,the combined model(SSM<21 kPa or[LSM≤15 kPa and PLT≥150×10^(9)/L])and Baveno VIIcriteria(LSM≤15 kPa and PLT≥150×10^(9)/L)had a sensitivity and negative predictive value>90%to rule-out CSPH.Compared to theBaveno VII criteria alone,the combined model correctly ruled-out more patients without CSPH,although there was no statisticaldifference(39/110[35.5%]vs.34/110[30.9%];p=0.063).The findings remained broadly similar when subgroup analyses were per-formed in the SSM@100 Hz cohort and the SSM@50 Hz cohort.Notably,the combined model reduced patients in the gray zonecompared to Baveno VII criteria alone(36/110[32.7%]vs.54/110[49.1%];p<0.001).Conclusions:Whether using SSM@100Hz or SSM@50Hz,the combined model of SSM and Baveno VII criteria was superior toBaveno VII criteria alone to rule-in and rule-out CSPH in cACLD patients,which may guide therapeutic decisions by mini-mizing cACLD patients in the gray zone.Trial Registration:ClinicalTrials.gov;No.NCT05251272.展开更多
基金funded by the Key Research and Development Program of Jiangsu Province(No.BE2023767a)The Fundamental Research Fund of Southeast University(No.3290002303A2)+5 种基金Changjiang Scholars Talent Cultivation Project of Zhongda Hospital of Southeast University(No.2023YJXYYRCPY03)Research Personnel Cultivation Programme of Zhongda Hospital Southeast University(No.CZXM-GSP-RC125,CZXM-GSP-RC119)China Postdoctoral Science Foundation(No.2024M750461)National Natural Science Foundation of China(No.82402413)Natural Science Foundation of Jiangsu Province(No.BK20241681)National Natural Science Foundation of China(No.62061160369).
文摘Aims:Bleeding from gastroesophageal varices(GEV)is a medical emergency associated with high mortality.We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography(2D-SWE)of the liver and spleen to precisely assess the risk of GEV and high-risk GEV(HRV).Methods:This was a multicenter,prospective study conducted from October 2020 to September 2022 across 12 hospitals in China.Patients with compensated advanced chronic liver disease(cACLD)were enrolled,with informed consent obtained.A total of 1136 liver stiffness measurement(LSM)images and 1042 spleen stiffness measurement(SSM)images generated by 2D SWE.Weleveraged deep learning methods to uncover associations between image features and patient risk;in this manner,we constructed models to predict GEV and HRV.Results:A multimodality deep learning risk prediction(DLRP)model was constructed to assess GEV and HRV based on LSM and SSM images and clinical information.Validation analysis revealed that the area under the curve(AUC)values of DLRP were 0.91 for GEV(95%confidence interval[CI],0.90-0.93,p<0.05)and 0.88 for HRV(95%CI,0.86-0.89,p<0.01),which were significantly and robustly better than those of canonical risk indicators,including the values of LSM(0.63 and 0.68 for GEV and HRV)andSSM(0.75for both GEV andHRV).Moreover,the DLRP model outperformed the model using individual parameters.In HRV prediction,the 2D-SWE SSM images(0.75)were more informative than LSM(0.68,p<0.01).Conclusion:Our DLRP model shows excellent performance in predicting GEV and HRV,outperforming the canonical risk indicators LSM and SSM.Additionally,the 2D-SWE SSM images provided more information and thus better accuracy in HRV prediction than the LSM images.
基金the National Natural Science Foundation of China(81830053,82001780)Guangzhou Industry-Academia-Research Collaborative Innovation Major Project(201704020015)+2 种基金Natural Science Foundation of Jiangsu Province of China(BK20200361)President Foundation of Nanfang Hospital,Southern Medical University(2017Z012)Distinguished Young Scholars of Gansu Province(20JR10RA713).
文摘Background and Aims:This study aimed to determine the performance of the non-invasive score using noncontrastenhanced MRI(CHESS-DIS score)for detecting portal hy-pertension in cirrhosis.Methods:In this international multicenter,diagnostic study(ClinicalTrials.gov,NCT03766880),patients with cirrhosis who had hepatic venous pressure gradient(HVPG)measurement and noncontrast-enhanced MRI were prospectively recruited from four university hospitals in China(n=4)and Turkey(n=1)between December 2018 and April 2019.A cohort of patients was retrospectively recruited from a university hospital in Italy between March 2015 and November 2017.After segmentation of the liver on fat-suppressed T1-weighted MRI maps,CHESS-DIS score was calculated automatically by an in-house developed code based on the quantification of liver surface nodularity.Results:A total of 149 patients were included,of which 124 were from four Chinese hospitals(training cohort)and 25 were from two international hospitals(validation cohort).A positive correlation between CHESS-DIS score and HVPG was found with the correlation coefficients of 0.36(p<0.0001)and 0.55(p<0.01)for the training and validation cohorts,respectively.The area under the receiver operating characteristic curve of CHESS-DIS score in detection of clinically significant portal hypertension(CSPH)was 0.81 and 0.9 in the training and validation cohorts,respectively.The intra-class correlation coefficients for assessing the inter-and intra-observer agreement were 0.846 and 0.841,respectively.Conclusions:A non-invasive score using noncontrast-enhanced MRI was developed and proved to be significantly correlated with invasive HVPG.Besides,this score could be used to detect CSPH in patients with cirrhosis.
基金funded by the Noncommunicable Chronic Diseases-National Science and Technology Major Project(2023ZD0508800)The Key Research and Development Program of Jiangsu Province(BE2023767a)+3 种基金the Fundamental Research Fund of Southeast University(3290002303A2)Changjiang Scholars Talent Cultivation Project of Zhongda Hospital of Southeast University(2023YJXYYRCPY03),Research Personnel Cultivation Programme of Zhongda Hospital Southeast University(CZXM-GSP-RC125,CZXM-GSP-RC119)China Postdoctoral Science Foundation(2024M750461),National Natural Science Foundation of China(82402413)Natural Science Foundation of Jiangsu Province(BK20241681).
文摘Aims:The renewing Baveno VII consensus proposed criteria for the diagnosis of clinically significant portal hypertension(CSPH)in patients with compensated advanced chronic liver disease(cACLD).The performance of a combined model of spleen stiffness measurement(SSM)by spleen-dedicated 100 Hz(SSM@100 Hz)or conventional 50 Hz(SSM@50 Hz)and Baveno VII criteria to rule-in or rule-out CSPH had not been well validated.This study aims to compare the performance of the combined model with Baveno VIIcriteria alone to rule-in and rule-out CSPH in cACLD.Methods:This international multicenter study included cACLD patients who underwent paired liver stiffness measurement(LSM),SSM@100 Hz or SSM@50 Hz,platelet count(PLT),and hepatic venous pressure gradient(HVPG).CSPH was defined as HVPG≥10 mmHg.Patients with SSM@100 Hz were prospectively recruited from China between August 2021 and March 2022,while a globalcohort of patients with SSM@50 Hz from Croatia,Japan,and Singapore was retrospectively included between December 2014 and June2022.The diagnostic performance of different models was assessed using sensitivity,specificity,positive predictive value,and negativepredictive value.Results:A total of 206 patients with cACLD were recruited from seven university centers and 110 patients were included in the finalanalysis(54 from the SSM@100 Hz cohort and 56 from the SSM@50 Hz cohort).The success rate of SSM@100 Hz was significantlyhigher than that of SSM@50 Hz(103/105[98.1%]vs.86/101[85.1%];p<0.001).While the combined model(SSM>50 kPa orLSM≥25 kPa)and Baveno VII criteria(LSM≥25 kPa)had a positive predictive value and specificity>90%to rule-in CSPH,thecombined model correctly ruled-in more cACLD patients with CSPH compared to Baveno VII criteria alone(35/110[31.8%]vs.22/110[20.0%];p<0.001).Furthermore,the combined model(SSM<21 kPa or[LSM≤15 kPa and PLT≥150×10^(9)/L])and Baveno VIIcriteria(LSM≤15 kPa and PLT≥150×10^(9)/L)had a sensitivity and negative predictive value>90%to rule-out CSPH.Compared to theBaveno VII criteria alone,the combined model correctly ruled-out more patients without CSPH,although there was no statisticaldifference(39/110[35.5%]vs.34/110[30.9%];p=0.063).The findings remained broadly similar when subgroup analyses were per-formed in the SSM@100 Hz cohort and the SSM@50 Hz cohort.Notably,the combined model reduced patients in the gray zonecompared to Baveno VII criteria alone(36/110[32.7%]vs.54/110[49.1%];p<0.001).Conclusions:Whether using SSM@100Hz or SSM@50Hz,the combined model of SSM and Baveno VII criteria was superior toBaveno VII criteria alone to rule-in and rule-out CSPH in cACLD patients,which may guide therapeutic decisions by mini-mizing cACLD patients in the gray zone.Trial Registration:ClinicalTrials.gov;No.NCT05251272.
