Artificial intelligence(AI)is revolutionizing medical imaging,particularly in chronic liver diseases assessment.AI technologies,including machine learning and deep learning,are increasingly integrated with multiparame...Artificial intelligence(AI)is revolutionizing medical imaging,particularly in chronic liver diseases assessment.AI technologies,including machine learning and deep learning,are increasingly integrated with multiparametric ultrasound(US)techniques to provide more accurate,objective,and non-invasive evaluations of liver fibrosis and steatosis.Analyzing large datasets from US images,AI enhances diagnostic precision,enabling better quantification of liver stiffness and fat content,which are essential for diagnosing and staging liver fibrosis and steatosis.Combining advanced US modalities,such as elastography and doppler imaging with AI,has demonstrated improved sensitivity in identifying different stages of liver disease and distinguishing various degrees of steatotic liver.These advancements also contribute to greater reproducibility and reduced operator dependency,addressing some of the limitations of traditional methods.The clinical implications of AI in liver disease are vast,ranging from early detection to predicting disease progression and evaluating treatment response.Despite these promising developments,challenges such as the need for large-scale datasets,algorithm transparency,and clinical validation remain.The aim of this review is to explore the current applications and future potential of AI in liver fibrosis and steatosis assessment using multiparametric US,highlighting the technological advances and clinical relevance of this emerging field.展开更多
BACKGROUND Gallstones and gallbladder wall thickening(GBWT)are frequent findings in patients with cirrhosis,reflecting the critical interplay between hepatobiliary dysfunction and portal hypertension.AIM To assess the...BACKGROUND Gallstones and gallbladder wall thickening(GBWT)are frequent findings in patients with cirrhosis,reflecting the critical interplay between hepatobiliary dysfunction and portal hypertension.AIM To assess the prevalence of gallstones and asymptomatic GBWT in patients with cirrhosis.METHODS Hospitalized patients with cirrhosis who had undergone abdominal imaging studies during hospitalization were retrospectively analyzed.RESULTS A total of 128 patients were included.The patients had a mean age of 64±12.2 years,were predominantly male(73.4%),and most had decompensated liver cirrhosis(DeCi)(78.1%).Alcohol-associated liver disease(47.7%)and metabolic dysfunction-associated steatohepatitis(16.4%)are the leading causes of cirrhosis.Most patients were classified as Child-Pugh stage B(53.1%),followed by stage C(32%),and stage A(14.8%).A significant percentage of patients had cholelithiasis(39.8%),and DeCi patients were more likely to have gallstones(45%)than compensated patients(21.4%)(P=0.024).Furthermore,a significant number of patients had asymptomatic GBWT(32.8%),and almost half(42.9%)did not have concurrent cholelithiasis.Patients with DeCi were significantly more likely to have GBWT(39%)than those with compensated disease(10.7%)(P=0.005).There was no statistical correlation between cirrhosis etiology and cholelithiasis or Tsankof A et al.Gallstones and GBWT in patients with cirrhosis WJCC https://www.wjgnet.com 2 January 6,2026 Volume 14 Issue 1 GBWT.CONCLUSION This study underlines the high prevalence of radiologic gallbladder findings in patients with cirrhosis while simultaneously serving as a reminder to clinicians to refrain from accrediting these findings to a diagnosis of acute cholecystitis in the absence of symptoms.展开更多
目的探讨Fried衰弱表型(FFP)、肝脏衰弱指数(LFI)和简易体能状况量表(SPPB)对肝硬化患者2年全因死亡率及失代偿事件的预测价值。方法选取2020年12月—2021年12月首都医科大学附属北京友谊医院收治的277例肝硬化住院患者,采用FFP、LFI和S...目的探讨Fried衰弱表型(FFP)、肝脏衰弱指数(LFI)和简易体能状况量表(SPPB)对肝硬化患者2年全因死亡率及失代偿事件的预测价值。方法选取2020年12月—2021年12月首都医科大学附属北京友谊医院收治的277例肝硬化住院患者,采用FFP、LFI和SPPB评估患者衰弱状态,分为衰弱组和非衰弱组,比较3种工具的一致性及其对预后的独立预测效能。主要终点事件为2年全因死亡率和复合终点事件(死亡+失代偿),采用Cox回归、受试者操作特征曲线(ROC曲线)、净重新分类指数(NRI)和综合判别改善指数(IDI)分析3种工具的预测价值。符合正态分布的计量资料两组间比较采用成组t检验;不符合正态分布的计量资料两组间比较采用Mann-Whitney U检验;计数资料组间比较采用χ^(2)检验或Fisher精确检验。不同衰弱工具间一致性比较采用Cohen’s Kappa检验。绘制Kaplan-Meier生存曲线,生存分析采用Log-rank检验。结果FFP、LFI和SPPB评估的衰弱患病率分别为37.2%、22.4%和20.2%,FFP与LFI、SPPB一致性中等(κ=0.57,95%CI:0.47~0.67;κ=0.51,95%CI:0.41~0.62),而LFI与SPPB一致性较高(κ=0.87,95%CI:0.80~0.94)。衰弱组全因死亡率及复合终点发生率均显著高于非衰弱组(P值均<0.001)。多因素校正后,FFP、LFI、SPPB预测全因死亡率的风险比(HR)分别为2.42(95%CI:1.51~5.11)、2.21(95%CI:1.11~4.42)和2.21(95%CI:1.14~4.30),预测复合终点的HR分别为2.51(95%CI:1.61~3.91)、2.40(95%CI:1.51~3.80)和2.20(95%CI:1.39~3.47)。FFP对全因死亡率的预测ROC曲线下面积(AUC)(0.79 vs 0.69,P=0.032)及复合终点的预测AUC(0.75 vs 0.68,P=0.044)均显著高于Child-Pugh评分。联合衰弱评估工具与Child-Pugh评分的结合可显著提升预测效能(全因死亡AUC为0.81~0.82,复合终点AUC为0.77~0.78,P值均<0.05)。NRI和IDI分析进一步证实了联合模型在分类上的改进(P值均<0.001)。结论FFP、LFI和SPPB均可独立预测肝硬化患者的不良结局,其中FFP的预测效能最佳,且与Child-Pugh评分联合使用可显著提高预后评估的准确性。展开更多
文摘Artificial intelligence(AI)is revolutionizing medical imaging,particularly in chronic liver diseases assessment.AI technologies,including machine learning and deep learning,are increasingly integrated with multiparametric ultrasound(US)techniques to provide more accurate,objective,and non-invasive evaluations of liver fibrosis and steatosis.Analyzing large datasets from US images,AI enhances diagnostic precision,enabling better quantification of liver stiffness and fat content,which are essential for diagnosing and staging liver fibrosis and steatosis.Combining advanced US modalities,such as elastography and doppler imaging with AI,has demonstrated improved sensitivity in identifying different stages of liver disease and distinguishing various degrees of steatotic liver.These advancements also contribute to greater reproducibility and reduced operator dependency,addressing some of the limitations of traditional methods.The clinical implications of AI in liver disease are vast,ranging from early detection to predicting disease progression and evaluating treatment response.Despite these promising developments,challenges such as the need for large-scale datasets,algorithm transparency,and clinical validation remain.The aim of this review is to explore the current applications and future potential of AI in liver fibrosis and steatosis assessment using multiparametric US,highlighting the technological advances and clinical relevance of this emerging field.
文摘BACKGROUND Gallstones and gallbladder wall thickening(GBWT)are frequent findings in patients with cirrhosis,reflecting the critical interplay between hepatobiliary dysfunction and portal hypertension.AIM To assess the prevalence of gallstones and asymptomatic GBWT in patients with cirrhosis.METHODS Hospitalized patients with cirrhosis who had undergone abdominal imaging studies during hospitalization were retrospectively analyzed.RESULTS A total of 128 patients were included.The patients had a mean age of 64±12.2 years,were predominantly male(73.4%),and most had decompensated liver cirrhosis(DeCi)(78.1%).Alcohol-associated liver disease(47.7%)and metabolic dysfunction-associated steatohepatitis(16.4%)are the leading causes of cirrhosis.Most patients were classified as Child-Pugh stage B(53.1%),followed by stage C(32%),and stage A(14.8%).A significant percentage of patients had cholelithiasis(39.8%),and DeCi patients were more likely to have gallstones(45%)than compensated patients(21.4%)(P=0.024).Furthermore,a significant number of patients had asymptomatic GBWT(32.8%),and almost half(42.9%)did not have concurrent cholelithiasis.Patients with DeCi were significantly more likely to have GBWT(39%)than those with compensated disease(10.7%)(P=0.005).There was no statistical correlation between cirrhosis etiology and cholelithiasis or Tsankof A et al.Gallstones and GBWT in patients with cirrhosis WJCC https://www.wjgnet.com 2 January 6,2026 Volume 14 Issue 1 GBWT.CONCLUSION This study underlines the high prevalence of radiologic gallbladder findings in patients with cirrhosis while simultaneously serving as a reminder to clinicians to refrain from accrediting these findings to a diagnosis of acute cholecystitis in the absence of symptoms.
文摘目的探讨Fried衰弱表型(FFP)、肝脏衰弱指数(LFI)和简易体能状况量表(SPPB)对肝硬化患者2年全因死亡率及失代偿事件的预测价值。方法选取2020年12月—2021年12月首都医科大学附属北京友谊医院收治的277例肝硬化住院患者,采用FFP、LFI和SPPB评估患者衰弱状态,分为衰弱组和非衰弱组,比较3种工具的一致性及其对预后的独立预测效能。主要终点事件为2年全因死亡率和复合终点事件(死亡+失代偿),采用Cox回归、受试者操作特征曲线(ROC曲线)、净重新分类指数(NRI)和综合判别改善指数(IDI)分析3种工具的预测价值。符合正态分布的计量资料两组间比较采用成组t检验;不符合正态分布的计量资料两组间比较采用Mann-Whitney U检验;计数资料组间比较采用χ^(2)检验或Fisher精确检验。不同衰弱工具间一致性比较采用Cohen’s Kappa检验。绘制Kaplan-Meier生存曲线,生存分析采用Log-rank检验。结果FFP、LFI和SPPB评估的衰弱患病率分别为37.2%、22.4%和20.2%,FFP与LFI、SPPB一致性中等(κ=0.57,95%CI:0.47~0.67;κ=0.51,95%CI:0.41~0.62),而LFI与SPPB一致性较高(κ=0.87,95%CI:0.80~0.94)。衰弱组全因死亡率及复合终点发生率均显著高于非衰弱组(P值均<0.001)。多因素校正后,FFP、LFI、SPPB预测全因死亡率的风险比(HR)分别为2.42(95%CI:1.51~5.11)、2.21(95%CI:1.11~4.42)和2.21(95%CI:1.14~4.30),预测复合终点的HR分别为2.51(95%CI:1.61~3.91)、2.40(95%CI:1.51~3.80)和2.20(95%CI:1.39~3.47)。FFP对全因死亡率的预测ROC曲线下面积(AUC)(0.79 vs 0.69,P=0.032)及复合终点的预测AUC(0.75 vs 0.68,P=0.044)均显著高于Child-Pugh评分。联合衰弱评估工具与Child-Pugh评分的结合可显著提升预测效能(全因死亡AUC为0.81~0.82,复合终点AUC为0.77~0.78,P值均<0.05)。NRI和IDI分析进一步证实了联合模型在分类上的改进(P值均<0.001)。结论FFP、LFI和SPPB均可独立预测肝硬化患者的不良结局,其中FFP的预测效能最佳,且与Child-Pugh评分联合使用可显著提高预后评估的准确性。
