Hepatic cystic echinococcosis (HCE) requires accurate WHO–IWGE CE1–CE5 subtyping to guide treatment, but timely non-invasive classification remains challenging in resource–limited settings. We developed and externally validated a lightweight, interpretable, two-stage multimodal deep–learning framework based on non-contrast CT for automated lesion segmentation and CE1–CE5 classification, and assessed whether model assistance improved physician performance. This multicentre retrospective study included 733 patients from Qinghai University Affiliated Hospital for development and internal validation and 261 patients from two county-level hospitals for external validation. We compared 2D multi–slice, 3D volumetric, and multimodal fusion models integrating 2D, 3D, and radiomics features, using macro-AUC as the primary outcome. The multimodal model achieved the highest observed macro-AUC, with macro-AUC of 0.942 (95% CI: 0.910–0.964) internally and 0.931 (95% CI: 0.898–0.956) externally; subtype–level AUCs were consistent across CE1–CE5, with most errors occurring between adjacent transitional stages. In the reader study, AI-assisted interpretation yielded higher observed macro-AUCs than physician-only interpretation in the tertiary cohort (0.970 vs. 0.905) and the county-hospital cohort (0.963 vs. 0.902). Interpretability analyses localised subtype-relevant regions and quantified patient-specific modality contributions, supporting prospective evaluation as a human-in-the-loop decision-support tool using widely available non–contrast CT.

Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmentation, CNNs lack global context modeling due to local receptive fields, and Transformers, though capable of capturing long-range dependencies, are computationally expensive. Recently, state space models (SSMs), such as Mamba, have gained attention for their ability to model long sequences with linear complexity. In this paper, we propose EAGLE, a U-shaped network composed of a Progressive Visual State Space (PVSS) encoder and a Hybrid Visual State Space (HVSS) decoder that work collaboratively to achieve efficient and accurate segmentation of hepatic echinococcosis (HE) lesions. The proposed Convolutional Vision State Space Block (CVSSB) module is designed to fuse local and global features, while the Haar Wavelet Transformation Block (HWTB) module compresses spatial information into the channel dimension to enable lossless downsampling. Due to the lack of publicly available HE datasets, we collected CT slices from 260 patients at the Affiliated Hospital of Qinghai University. Experimental results show that EAGLE achieves state-of-the-art performance with a Dice Similarity Coefficient (DSC) of 89.76 https://chenjiayan-qhu.github.io/EAGLE/ .

Objective This study developed and validated a stacked ensemble machine learning model to predict the risk of acute kidney injury in patients with acute pancreatitis complicated by sepsis.Design A retrospective study based on patient data from public databases.Participants This study analysed 1295 patients with acute pancreatitis complicated by septicaemia from the US Intensive Care Database.Methods From the MIMIC database, data of patients with acute pancreatitis and sepsis were obtained to construct machine learning models, which were internally and externally validated. The Boruta algorithm was used to select variables. Then, eight machine learning algorithms were used to construct prediction models for acute kidney injury (AKI) occurrence in intensive care unit (ICU) patients. A new stacked ensemble model was developed using the Stacking ensemble method. Model evaluation was performed using area under the receiver operating characteristic curve (AUC), precision-recall (PR) curve, accuracy, recall and F1 score. The Shapley additive explanation (SHAP) method was used to explain the models.Main outcome measures AKI in patients with acute pancreatitis complicated by sepsis.Results The final study included 1295 patients with acute pancreatitis complicated by sepsis, among whom 893 cases (68.9%) developed acute kidney injury. We established eight base models, including Logit, SVM, CatBoost, RF, XGBoost, LightGBM, AdaBoost and MLP, as well as a stacked ensemble model called Multimodel. Among all models, Multimodel had an AUC value of 0.853 (95% CI: 0.792 to 0.896) in the internal validation dataset and 0.802 (95% CI: 0.732 to 0.861) in the external validation dataset. This model demonstrated the best predictive performance in terms of discrimination and clinical application.Conclusion The stack ensemble model developed by us achieved AUC values of 0.853 and 0.802 in internal and external validation cohorts respectively and also demonstrated excellent performance in other metrics. It serves as a reliable tool for predicting AKI in patients with acute pancreatitis complicated by sepsis.

BACKGROUND:Differentiating whether hepatic cystic echinococcosis (HCE) lesions exhibit biological activity is essential for developing effective treatment plans. This study evaluates the performance of a Transformer-based fusion model in assessing HCE lesion activity. METHODS:This study analyzed CT images and clinical variables from 700 HCE patients across three hospitals from 2018 to 2023. Univariate and multivariate logistic regression analyses were conducted for the selection of clinical variables to construct a clinical model. Radiomics features were extracted from CT images using Pyradiomics to develop a radiomics model. Additionally, a 2D deep learning model and a 3D deep learning model were trained using the CT images. The fusion model was constructed using feature-level fusion, decision-level fusion, and a Transformer network architecture, allowing for the analysis of the discriminative ability and correlation among radiomics features, 2D deep learning features, and 3D deep learning features, while comparing the classification performance of the three multimodal fusion models. RESULTS:In comparison to radiomics and 2D deep learning features, the 3D deep learning features exhibited superior discriminative ability in identifying the biological activity of HCE lesions. The Transformer-based fusion model demonstrated the highest performance in both the internal validation set and the external validation set, achieving AUC values of 0.997 (0.992-1.000) and 0.944 (0.911-0.977), respectively, thereby outperforming both the feature-level and decision-level fusion models, and enabling precise differentiation of HCE lesion biological activity. CONCLUSION:The Transformer multimodal fusion model integrates clinical features, radiomics features, and both 2D and 3D deep learning features, facilitating accurate differentiation of the biological activity of HCE lesions and exhibiting significant potential for clinical application.

This study aims to predict the mortality rate among septic patients with early-onset hypoalbuminemia in the intensive care unit (ICU) using machine learning algorithms. Utilizing patient data from the MIMIC-IV and eICU databases, we divided MIMIC-IV samples into training and internal validation sets, with eICU samples serving as an external validation set. We developed the predictive model using various feature selection techniques and machine learning algorithms, and evaluated its performance using metrics such as AUC, accuracy, precision, recall, and F1 score. The SHAP method was used for model interpretability. The CatBoost model, developed using recursive feature elimination, outperformed other algorithms, demonstrating robust generalization with AUC values of 0.845, 0.746, and 0.827 across the respective datasets. This pioneering study presents a machine learning model with high accuracy and robust extrapolation capabilities for predicting mortality rates in septic patients with early-onset hypoalbuminemia in the ICU, providing valuable decision support for clinicians.

Objective Critically ill patients with liver cirrhosis generally have a poor prognosis due to complications such as multiple organ failure. This study aims to develop a machine learning-based prediction model to forecast short-term mortality in critically ill cirrhotic patients in the intensive care unit (ICU), thereby assisting clinical decision-making for intervention and treatment. Methods Machine learning models were developed using clinical data from critically ill cirrhotic patients in the MIMIC database, with multicenter validation performed using data from the eICU database and Qinghai University Affiliated Hospital(QUAH). Various machine learning models, including a Stacking ensemble model, were employed, with the SHAP method used to enhance model interpretability. Results The Stacking ensemble model demonstrated superior predictive performance through internal and external validation, with AUC and AP values surpassing those of individual algorithms. The AUC values were 0.845 in the internal validation set, 0.819 in the eICU external validation, and 0.761 in the QUAH validation set. Additionally, the SHAP method highlighted key prognostic variables such as INR, bilirubin, and urine output. The model was ultimately deployed as a web-based calculator for bedside decision-making. Conclusion The machine learning model effectively predicts short-term mortality risk in critically ill cirrhotic patients in the ICU, showing strong predictive performance and generalizability. The model's robust interpretability and its deployment as a web-based calculator suggest its potential as a valuable tool for assessing the prognosis of cirrhotic patients.

Hepatic echinococcosis (HE) is a prevalent disease in economically underdeveloped pastoral areas, where adequate medical resources are usually lacking. Existing methods often ignore multi-scale feature fusion or focus only on feature fusion between adjacent levels, which may lead to insufficient feature fusion. To address these issues, we propose HES-UNet, an efficient and accurate model for HE lesion segmentation. This model combines convolutional layers and attention modules to capture local and global features. During downsampling, the multi-directional downsampling block (MDB) is employed to integrate high-frequency and low-frequency features, effectively extracting image details. The multi-scale aggregation block (MAB) aggregates multi-scale feature information. In contrast, the multi-scale upsampling Block (MUB) learns highly abstract features and supplies this information to the skip connection module to fuse multi-scale features. Due to the distinct regional characteristics of HE, there is currently no publicly available high-quality dataset for training our model. We collected CT slice data from 268 patients at a certain hospital to train and evaluate the model. The experimental results show that HES-UNet achieves state-of-the-art performance on our dataset, achieving an overall Dice Similarity Coefficient (DSC) of 89.21 1.09 https://chenjiayan-qhu.github.io/HES-UNet-page.

Abstract Background Echinococcosis is one of the most common parasitic diseases among humans and animals worldwide, with the most prominent in the northwest region of China. According to different types of infected larvae, it can be divided into cystic echinococcosis and alveolar echinococcosis. Both types of infected organs are most common in the liver. Here we report a 49 years old female patient with hepatic cystic echinococcosis who was initially misdiagnosed as hepatic cystic echinococcosis (CE1) due to her imaging findings being very similar to those of cystic echinococcosis. After further examination and literature review, we were ultimately diagnosed with hepatic alveolar echinococcosis (P4), which was confirmed by surgery and postoperative pathology. In the article, we use MRI and MRCP as recommendations for distinguishing the two, which can efficiently help us distinguish them and avoid misdiagnosis. Presentation: We report a 49 year old female patient residing in an area with a high incidence of hydatid disease. She was admitted with the chief complaint of "persistent swelling and pain in the upper right abdomen for more than half a month". Prior to admission, the abdominal CT result diagnosed her with hepatic cystic echinococcosis CE1 type, which was a huge liver mass of 13.5cm * 13cm * 14cm. After admission, a comprehensive MRI and MRCP imaging examination was performed, and the results were different from CT. The diagnosis was P4 stage cystic cystic echinococcosis in the right lobe of the liver. Through literature review and general practice discussions, we ultimately diagnosed with P4 type of cystic cystic echinococcosis in the right lobe of the liver, and actively prepared for surgery. Due to the large size of the patient's liver lesion, the risk of surgery was assessed to be high. We first performed percutaneous liver puncture under ultrasound to drain the cystic fluid of the lesion. After the lesion collapsed, we finally performed a right hemihepatectomy. The surgery went smoothly and the patient recovered well, and was discharged as scheduled. After intraoperative and postoperative pathological diagnosis, it was confirmed that our diagnosis and treatment were correct and misdiagnosis was avoided. Conclusion when faced with difficult to distinguish AE and CE, MRI and MRCP may be the best choices to solve the problem, as they can effectively avoid misdiagnosis.

Acute pancreatitis, a potentially lethal ailment that sees a surge in mortality rates when sepsis onset occurs, is quite prevalent. Given its severity, early intervention and tailored treatment become pivotal--underscored by the urgent need to anticipate mortality in patients plagued by acute pancreatitis complicated by sepsis. This highlights the crucial demand for the development of a cogent, interpretable mortality prediction model. The objective of this study is to establish and validate a machine learning predictive model for determining the risk of in-hospital mortality in patients with acute pancreatitis (AP) complicated by sepsis. AP is a prevalent and potentially fatal inflammatory condition of the pancreas. When sepsis complicates AP, the likelihood of multiple organ dysfunction syndrome (MODS) increases, resulting in a very poor prognosis. This study utilized patient cohorts from the MIMIC-III, MIMIC-IV, and eICU databases to conduct a regression analysis for both model development and validation. Feature selection was performed using the LASSO method and feature importance based on SHAP values, resulting in the establishment of 11 different machine learning predictive models. A stacked ensemble learning predictive model was developed using the Stacking ensemble algorithm. Model performance was evaluated using various metrics, including areas under the receiver operating characteristic (ROC) curves (AUC), PR curves, accuracy, recall, and F1 scores. The models were explained using the Kernel-SHAP algorithm and LIME algorithm. An ensemble learning predictive model named AQlearner was developed based on feature variables screened via SHAP importance. The AUC value of AQlearner not only exceeded that of other individual models but also was higher than any machine learning predictive model established on variables screened out via LASSO, with an AUC reaching up to 0.873. Other performance indicators also showed excellent results. In the external validation cohort, the model's performance remained outstanding and was eventually selected. The Kernel-SHAP algorithm and LIME algorithm were used to interpret the machine learning models, and the results showed that this approach is feasible. This study aimed to construct a machine-learning prediction model to evaluate the risk of in-hospital mortality in patients with acute pancreatitis complicated by sepsis. In clinical practice, feature selection based on the SHAP algorithm outperforms that based on Lasso. Furthermore, our ensemble learning predictive model exhibits superior performance compared to traditional single machine learning predictive models. The interpretability of machine learning models can be enhanced through the Kernel-SHAP algorithm and LIME algorithm. This SHAP feature importance-based model is highly suitable for clinical practice, as it can assist physicians in comprehending the underlying causes of predicted death and evaluating the in-hospital outcomes of critically ill patients.

BACKGROUND:Hepatic echinococcosis is a severe endemic disease in some underdeveloped rural areas worldwide. Qualified physicians are in short supply in such areas, resulting in low rates of accurate diagnosis of this condition. In this study, we aimed to develop and evaluate an artificial intelligence (AI) system for automated detection and subtyping of hepatic echinococcosis using plain CT images with the goal of providing interpretable assistance to radiologists and clinicians. METHODS:We developed EDAM, an echinococcosis diagnostic AI system, to provide accurate and generalisable CT analysis for distinguishing hepatic echinococcosis from hepatic cysts and normal controls (no liver lesions), as well as subtyping hepatic echinococcosis as alveolar or cystic echinococcosis. EDAM includes a slice-level prediction model for lesion classification and segmentation and a patient-level diagnostic model for patient classification. We collected a plain CT database (n=700: 395 cystic echinococcosis, 122 alveolar echinococcosis, 130 hepatic cysts, and 53 normal controls) for developing EDAM, and two additional independent cohorts (n=156) for external validation of its performance and generalisation ability. We compared the performance of EDAM with 52 experienced radiologists in diagnosing and subtyping hepatic echinococcosis. FINDINGS:EDAM showed reliable performance in patient-level diagnosis on both the internal testing data (overall area under the receiver operating characteristic curve [AUC]: 0·974 [95% CI 0·936-0·994]; accuracy: 0·952 [0·939-0·965] for cystic echinococcosis, 0·981 [0·973-0·989] for alveolar echinococcosis; sensitivity: 0·966 [0·951-0·979] for cystic echinococcosis, 0·944 [0·908-0·970] for alveolar echinococcosis) and the external testing set (overall AUC: 0·953 [95% CI 0·840-0·973]; accuracy: 0·929 [0·915-0·947] for cystic echinococcosis, 0·936 [0·919-0·950] for alveolar echinococcosis; sensitivity: 0·913 [0·879-0·944] for cystic echinococcosis, 0·868 [0·841-0·897] for alveolar echinococcosis). The sensitivity of EDAM was robust across images from different CT manufacturers. EDAM outperformed most of the enrolled radiologists in detecting both alveolar echinococcosis and cystic echinococcosis. INTERPRETATION:EDAM is a clinically applicable AI system that can provide patient-level diagnoses with interpretable results. The accuracy and generalisation ability of EDAM demonstrates its potential for clinical use, especially in underdeveloped areas. FUNDING:Project of Qinghai Provincial Department of Science and Technology of China, National Natural Science Foundation of China, and Tsinghua-Fuzhou Institute of Data Technology Project. TRANSLATION:For the Chinese translation of the abstract see Supplementary Materials section.

Hepatic alveolar echinococcosis (HAE) is a zoonotic parasitic disease caused by the larvae of Echinococcus multilocularis. Because of its characteristics of diffuse infiltration and growth similar to tumors, the disability rate and mortality rate are high among patients. Although surgery (including hepatectomy, liver transplantation, and autologous liver transplantation) is the first choice for the treatment of hepatic alveolar echinococcosis in clinic, drug treatment still plays an important and irreplaceable role in patients with end-stage echinococcosis, including patients with multiple organ metastasis, patients with inferior vena cava invasion, or patients with surgical contraindications, etc. However, Albendazole is the only recommended clinical drug which could exhibit a parasitostatic rather than a parasitocidal effect. Novel drugs are needed but few investment was made in the field because the rarity of the cases. Drug repurposing might be a solution. In this review, FDA-approved drugs that have a potential curative effect on hepatic alveolar echinococcosis in animal models are summarized. Further, nano drug delivery systems boosting the therapeutic effect on hepatic alveolar echinococcosis are also reviewed. Taken together, these might contribute to the development of novel strategy for advanced hepatic alveolar echinococcosis.

Background Hypoxia is a risk factor for non-alcoholic fatty liver diseases, leading to permanent imbalance of liver lipid homeostasis and steatohepatitis. However, a detailed understanding of the metabolic genes and pathways involved remains elusive. Methods In vivo experiments were designed to analyze body weight and lipid metabolism changes of rats under hypoxia. After this, we combined microarray analysis and gene overexpression experiments to validate the core mechanisms involved in the response to hypoxia. Results The hypobaric hypoxia treated rats exhibited significantly increased serum triglycerides (TG) ( p < 0.05), despite no significant changes in serum alanine aminotransferase (ALT) and blood glucose (BG) were observed. In addition, serum high-density lipoprotein cholesterol (HDL-C) greatly increased after 3 days and then returned to normal level at 30 days. Interestingly, serum low-density lipoprotein cholesterol (LDL-C) showed an opposite pattern. Transcriptome analysis, qRT-PCR, ICC revealed that the genes PPARA, ANGPTL4, CPT-I, ACC and LPL play a crucial role in response to hypobaric hypoxia. IPA pathway analysis further confirmed that PPARA-mediated regulation of ANGPTL4 participated in TG clearance and lipoprotein metabolism. Finally, the PPARA-ANGPTL4 pathway was validated in rats and HL 7702 cells treated with Fenofibrate, a PPARA specific agonist. Conclusions Our study showed this pathway plays an important role on lipid metabolism caused by hypobaric hypoxia and the potential target genes associated with oxygen-dependent lipid homeostasis in the liver.

Abstract Background: Acute hypoxia consistently results in altitude sickness and can be fatal. Until present, no studies focusing on global proteomic changes induced by acute hypoxia have been reported. Here, we combined animal experiments and tandem mass tag (TMT)-based proteomic analysis to identify metabolic changes as a result of acute hypoxia. Methods: We first generated a rat model under acute hypoxia conditions, and combined animal experiments and TMT-based proteomics to identify metabolic changes under acute hypoxia. Then we used qPCR analyses to validate the key regulators, and present a schematic model of acute reactions occurring in the livers of rats subjected to acute hypoxia challenge. Results: We identified a large number of acute hypoxic responsive proteins in diverse biological pathways, which helped unveil the different mechanisms involved in hypoxia responses in rats. These pathways included those of peroxisome, peroxisome proliferator-activated receptor (PPAR) signaling, lipid metabolism, glycolysis/gluconeogenesis, and amino acid metabolism. According to data obtained from proteomic analysis, rats were able to maintain normal physical activity as a response to acute hypoxia by activating their catabolic capacity in order to get more energy (e.g., lipolysis and amino acid catabolism), and decreasing biosynthesis to reduce energy consumption (e.g., biosynthesis of amino acids and lipids). Conclusions: We identified a large number of acute hypoxia-responsive proteins associated with diverse biological pathways, and showed rats quickly respond to acute hypoxia by activating lipid biosynthesis to increase lipid storage, and reducing lipolysis to reduce energy consumption. The observed hypoxia-related changes in the liver proteome of rats provide a deeper understanding on the mammalian response to hypoxia.

Echinococcosis is a human-animal parasitic disease caused by Echinococcosis tapeworm larvae in humans. From a global perspective, it is mainly prevalent in the mid-high latitudes of the Northern Hemisphere, and it is a widespread infectious disease. Its form, host and release areas are slightly different. In clinical practice, Echinococcus granulosus (hepatic cystic echinococcosis) is the most common. Its growth mode is swelling growth and its metastasis is more common in implanted metastasis; However, hepatic alveolar echinococcosis (HAE) is rare. It has been reported that HAE can metastasize through the blood or lymph nodes, and its invasive growth pattern is known as "carcinoma". At this time, it may be accompanied by invasion of the portal vein and inferior vena cava(IVC)or metastasis to distant organs outside the liver (such as lung, brain, lymph nodes). Most patients are in the middle or late stages, making treatment complicated. World Health Organization guidelines recommend radical resection of HAE; However, there is no consensus on lymph node dissection. To date, there have been no reports of cases of HAE accompanied by inferior vena cava-para-abdominal aortic suspected lymph node metastasis and infection. This article reports a clinical case of a complex HAE treated by the surgical method of "middle liver resection + abdominal enlarged lymph node resection + inferior vena cava repair", and histological examination was performed to illustrate the differences in microscopic pathology of alveolar echinococcosis invading the liver and lymph nodes at different magnifications. This article reviews the relevant literature on HAE and derives the latest treatment methods for HAE to provide a reference for future clinical cases of similar alveolar echinococcosis and maximize the benefits of patients.

BACKGROUND:Alveolar echinococcosis (AE) is a serious parasitic disease caused by the larvae of Echinococcus multilocularis. It is the less common but substantially more deadly of the 2 major echinococcosis diseases that can occur globally but are concentrated in central Asia. METHODS:We analyzed parasite circulating cell-free DNA (cfDNA) in 149 plasma samples using a DNA sequencing-based method (105 AE, 16 cystic echinococcosis, 4 liver cancer, 4 gallstones, and 20 healthy volunteers). After identifying the Echinococcus-specific cfDNA (Em-cfDNA) sequences in the samples, we determined whether Em-cfDNA could be used for AE diagnosis and as a potential indicator of the effectiveness of surgical treatment. We also examined potential associations between Em-cfDNA levels and clinical features of AE patients. RESULTS:Our work demonstrates that varying reads of Em-cfDNA were detectable in the plasma of 100% of preoperative AE patients and that all of the non-AE patients and healthy volunteers were negative. Em-cfDNA has good sensitivity and specificity for the diagnosis of AE. We also found that Em-cfDNA levels apparently have reference value for evaluating the therapeutic efficacy of surgery interventions for AE lesions. Finally, our analysis revealed that Em-cfDNA levels can reflect meaningful information about lesion size in preoperative AE patients. CONCLUSIONS:We demonstrate that sequencing-based monitoring of Em-cfDNA can be used in the clinic as a powerful diagnostic indicator for AE. We also note that there is a strong potential for use of this liquid-biopsy method to monitor ongoing disease status in postintervention AE patients.

Hydatidosis is a zoonotic parasitic disease caused byEchinococcus, which is highly prevalent in pastoral areas. In China, this disease is mainly caused byEchinococcus granulosusandEchinococcus multilocularis. Cystic echinococcosis, which is one of the most common types of echinococcosis, is described as swelling and growth of cystic lesions. Alveolar echinococcosis, which is less common, is invasive. Cases of mixed echinococcosis infection accompanied by extrahepatic organ metastasis are extremely rare. Treatment of these cases is complicated and the prognosis is extremely poor. We report a case of hepatic echinococcosis in a 40-year-old Tibetan man who was treated with the hepatic right tricuspidectomy + left hepatic duct jejunostomy (Roux-en-Y) surgical procedure. This procedure provides a reference for treatment of similar cases of echinococcosis. For patients with multiorgan metastasis, chemotherapy is the first choice. This should be followed by possible surgical treatment for life-threatening lesions of alveolar echinococcosis and subsequent chemotherapy. Individualized treatment accompanied by multidisciplinary treatment and damage control surgery could optimally benefit patients with advanced hepatic echinococcosis.

目的 探讨肝囊型包虫病手术患者胆漏发生的危险因素,并建立相应的回归预测模型.方法 回顾性分析2014年6月至2018年12月于青海省福利慈善医院行手术治疗的183例肝囊型包虫病患者临床资料.患者均签署知情同意书,符合医学伦理学规定.其中男67例,女116例;年龄12～78岁,中位年龄41岁.采用Logistic回归筛选出胆漏危险因素,森林图显示多因素Logistic回归的各个指标效应大小,建立肝囊型包虫病手术患者胆漏Logistic回归预测模型.通过Hosmer-Lemeshow检验评价预测模型的拟合度,采用受试者工作特征(ROC)曲线评价模型的预测价值.结果 本组患者胆漏发生率为22.4％(41/183).多因素Logistic回归结果显示,ALP>135 U/L(OR=10.797,95％CI:4.860～23.927,P<0.05)、囊肿直径>10 cm(OR=3.576,95％CI:1.911～6.268,P<0.05)是肝囊型包虫病手术患者胆漏发生的独立危险因素.将这两个因素纳入Logistic回归方程:Logit(P)=-2.580+2.412XALP+1.215X囊肿直径.概率模型为:P=1/[1+Exp(-2.580+2.412XALP+1.215X囊肿直径)].ROC曲线下面积为0.792(95％CI:0.719～0.864,P<0.05),敏感度为0.74,特异度为0.70.结论 ALP、囊肿直径是肝囊型包虫病手术患者胆漏发生的危险因素,根据回归分析建立的预测模型能比较有效地预测肝囊型包虫病手术患者胆漏的发生.

Purpose Biliary leakage caused by cystobiliary communication (CBC) is a common clinical concern. This study sought to identify predictors of CBC in hepatic cystic echinococcosis (HCE) patients undergoing hydatid liver cyst surgery and establish nomograms to predict CBC. Methods A predictive model was established in a training cohort of 310 HCE patients diagnosed between January 2013 and May 2017. Upon revision of the records of clinical parameters and imaging features of these patients, the lasso regression model was used to optimize feature selection for the CBC risk model. Combined with feature selection, a CBC nomogram was developed with multivariable logistic regression. C-index and calibration plots were used to analyze and evaluate the discrimination and calibration. The net benefit and predictive accuracy of the nomogram were performed via decision curve analysis (DCA) and receiver operating characteristic (ROC) curve. An independent validation cohort of 132 patients recruited from June 2017 to May 2019 was used to evaluate the practicability of the nomogram. Results Predictors contained four features, namely alkaline phosphatase (ALP), glutamyl transpeptidase (GGT), cyst size and cyst location. The C-index of the nomogram is 0.791 (95% CI, 0.736-0.845), while the C-index verified by bootstrap is 0.746, indicating high prediction accuracy. The area under the curve (AUC) of the CBC in training was 0.766. ROC curve analysis demonstrated high sensitivity and specificity. Decision curve analysis confirmed the CBC nomogram was clinically useful when the intervention was determined at the non-adherence possibility threshold of 8%. Conclusion The nomogram developed using the ALP, GGT, cyst size and cyst location could be used to facilitate the CBC risk prediction in HCE patients.

Background: Echinococcosis is a chronic consumptive liver disease. Little research has been carried out on the nutritional status of infected patients, though liver diseases are often associated with malnutrition. Our study investigated four different nutrition screening tools, to assess nutritional risks of hospitalized patients with echinococcosis. Methods: Nutritional Risk Screening 2002 (NRS 2002), Short Form of Mini Nutritional Assessment (MNA-SF), Malnutrition Universal Screening Tool (MUST), and the Nutrition Risk Index (NRI) were used to assess 164 patients with alveolar echinococcosis (AE) and 232 with cystic echinococcosis (CE). Results were then compared with European Society for Clinical Nutrition and Metabolism (ESPEN) criteria for malnutrition diagnosis. Results: According to ESPEN standards for malnutrition diagnosis, 29.2% of CE patients and 31.1% of AE patients were malnourished. The malnutrition risk rates for CE and AE patients were as follows: NRS 2002 – 40.3% and 30.7%; MUST – 51.5% and 50.9%; MNA-SF – 46.8% and 44.1%; and NRI – 51.1% and 67.4%. In patients with CE, MNA-SF and NRS 2002 results correlated well with ESPEN results (k = 0.515, 0.496). Area-under-the-curve (AUC) values of MNA-SF and NRS 2002 were 0.803 and 0.776, respectively. For patients with AE, NRS 2002 and MNA-SF results correlated well with ESPEN (k = 0.555, 0.493). AUC values of NRS 2002 and MNA-SF were 0.776 and 0.792, respectively. Conclusion: This study is the first to analyze hospitalized echinococcosis patients based on these nutritional screening tools. Our results suggest that NRS 2002 and MNA-SF are suitable tools for nutritional screening of inpatients with echinococcosis.

肝囊性病变分为寄生性和非寄生性.寄生性病变主要指肝囊性包虫病,非寄生性病变可再分为良性、交界性和恶性病变.目前对肝囊性占位性病变的规范治疗尚不健全,查阅了国内外相关文献资料,结合文献对肝囊性相关疾病的病因、临床表现、诊断及治疗相关问题进行综述,以提高对本病的认识.