Automatic origin prediction of liver metastases via hierarchical artificial-intelligence system trained on multiphasic CT data: a retrospective, multicentre study.

Background: Currently, the diagnostic testing for the primary origin of liver metastases (LMs) can be laborious, complicating clinical decision-making. Directly classifying the primary origin of LMs at computed tomography (CT) images has proven to be challenging, despite its potential to streamline the entire diagnostic workflow. Methods: We developed ALMSS, an artificial intelligence (AI)-based LMs screening system, to provide automated liver contrast-enhanced CT analysis for distinguishing LMs from hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC), as well as subtyping primary origin of LMs as six organ systems. We processed a CECT dataset between January 1, 2013 and June 30, 2022 (n = 3105: 840 HCC, 354 ICC, and 1911 LMs) for training and internally testing ALMSS, and two additional cohorts (n = 622) for external validation of its diagnostic performance. The performance of radiologists with and without the assistance of ALMSS in diagnosing and subtyping LMs was assessed. Findings: ALMSS achieved average area under the curve (AUC) of 0.917 (95% confidence interval [CI]: 0.899-0.931) and 0.923 (95% [CI]: 0.905-0.937) for differentiating LMs, HCC and ICC on both the internal testing set and external testing set, outperformed that of two radiologists. Moreover, ALMSS yielded average AUC of 0.815 (95% [CI]: 0.794-0.836) and 0.818 (95% [CI]: 0.790-0.842) for predicting six primary origins on both two testing sets. Interestingly, ALMSS assigned origin diagnoses for LMs with pathological phenotypes beyond the training categories with average AUC of 0.761 (95% [CI]: 0.657-0.842), which verify the model's diagnostic expandability. Interpretation: Our study established an AI-based diagnostic system that effectively identifies and characterizes LMs directly from multiphasic CT images. Funding: National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Medical Image Processing.

Distinguishing infectivity in patients with pulmonary tuberculosis using deep learning.

Introduction: This study aimed to develop and assess a deep-learning model based on CT images for distinguishing infectivity in patients with pulmonary tuberculosis (PTB). Methods: We labeled all 925 patients from four centers with weak and strong infectivity based on multiple sputum smears within a month for our deep-learning model named TBINet's training. We compared TBINet's performance in identifying infectious patients to that of the conventional 3D ResNet model. For model explainability, we used gradient-weighted class activation mapping (Grad-CAM) technology to identify the site of lesion activation in the CT images. Results: The TBINet model demonstrated superior performance with an area under the curve (AUC) of 0.819 and 0.753 on the validation and external test sets, respectively, compared to existing deep learning methods. Furthermore, using Grad-CAM, we observed that CT images with higher levels of consolidation, voids, upper lobe involvement, and enlarged lymph nodes were more likely to come from patients with highly infectious forms of PTB. Conclusion: Our study proves the feasibility of using CT images to identify the infectivity of PTB patients based on the deep learning method.

Weil's Disease in an HIV-Infected Patient: A Case Report and Literature Review.

Weil's disease, an icterohemorrhagic infection, is the most severe and fatal form of leptospirosis and is characterized by jaundice, renal dysfunction, and hemorrhagic predisposition. Weil's disease with HIV infection has rarely been reported. A 68-year-old male with HIV infection presented to our hospital with fever and dyspnea that progressed to severe hemoptysis and systemic multiple organ failure, necessitating a tracheal intubation ventilator. A diagnosis of Weil's disease was made after Leptospira interrogans was identified via metagenomic next-generation sequencing (mNGS) in bronchoalveolar lavage fluid (BALF). After immediately receiving supportive therapy and targeted antimicrobial agents, the patient achieved complete recovery upon discharge. The co-infection of HIV infection and leptospirosis resulting in systemic multi-organ failure is rare, but awareness should be raised of the differential diagnosis. mNGS can help identify pathogens and facilitate the use of targeted and efficacious antimicrobial therapy in unusual clinical environments.

The role of dietary fiber on preventing gestational diabetes mellitus in an at-risk group of high triglyceride-glucose index women: a randomized controlled trial.

BACKGROUND: Pregnant women with a high triglyceride-glucose (TyG) index during early pregnancy may increase the risk of gestational diabetes mellitus (GDM), and dietary fiber could play an important role in glucose and lipid metabolism. However, no trials have tested the effects of dietary fiber on preventing GDM in women with a high TyG index. This study aims to investigate whether GDM can be prevented by dietary fiber supplementation in women with a TyG index ≥8.5 during early pregnancy (<20 weeks). METHODS: A randomized clinical trial was performed among 295 women with a TyG index ≥8.5 before 20 weeks of gestation, divided into a fiber group (24 g dietary fiber powder/day) or a control group (usual care). The intervention was conducted from 20 to 24+6 gestational weeks, and both groups received guidance on exercise and diet. The primary outcomes were the incidence of GDM diagnosed by a 75 g oral glucose tolerance test at 25-28 gestational weeks, and levels of maternal blood glucose, lipids. Secondary outcomes include gestational hypertension, postpartum hemorrhage, preterm birth, and other maternal and neonatal complications. RESULTS: GDM occurred at 11.2% (10 of 89) in the fiber group, which was significantly lower than 23.7 (44 of 186) in the control group (P = 0.015). The mean gestational weeks increased dramatically in the fiber group compared with the control group (39.07 ± 1.08 vs. 38.58 ± 1.44 weeks, P = 0.006). The incidence of preterm birth was 2.3% (2 of 86) of women randomized to the fiber group compared with 9.4% (17 of 181) in the control group (P = 0.032). The concentrations of 2 h postprandial blood glucose showed statistically higher in the control group compared with the intervention group (6.69 ± 1.65 vs. 6.45 ± 1.25 mmol/L, P = 0.026). There were no other significant differences between groups in lipid profile values, or other secondary outcomes. CONCLUSION: An intervention with dietary fiber supplementation during pregnancy may prevent GDM and preterm birth in women with a TyG index ≥8.5 before 20 weeks of gestation.

Artificial intelligence CT radiomics to predict early recurrence of intrahepatic cholangiocarcinoma: a multicenter study.

OBJECTIVES: In this multicenter study, we sought to develop and validate a preoperative model for predicting early recurrence (ER) risk after curative resection of intrahepatic cholangiocarcinoma (ICC) through artificial intelligence (AI)-based CT radiomics approach. MATERIALS AND METHODS: A total of 311 patients (Derivation: 160; Internal and two external validations: 36, 74 and 61) from 8 medical centers who underwent curative resection were collected retrospectively. In derivation cohort, radiomics and clinical-radiomics models for ER prediction were constructed by LightGBM (a machine learning algorithm). A clinical model was also developed for comparison. Model performance was validated in internal and two external cohorts by ROC. In addition, we investigated the interpretability of the LightGBM model. RESULTS: The combined clinical-radiomics model that included 15 radiomic features and 3 clinical features (CA19-9 > 1000 U/ml, vascular invasion and tumor margin), resulting in the area under the curves (AUCs) of 0.974 (95% CI 0.946-1.000) in the derivation cohort, and 0.871-0.882 (95% CI 0.672-0.962) in the internal and external validation cohorts, respectively, which are higher than the AJCC 8th TNM staging system (AUCs: 0.686-0.717, p all < 0.05). Especially, the sensitivity of this machine learning model could reach 94.6% on average for all the cohorts. CONCLUSIONS: This AI-driven combined radiomics model may provide as a useful tool to preoperatively predict ER and improve therapeutic management of ICC patients.

Effects of Dietary Fiber on the Risk of Gestational Diabetes Mellitus in Advanced Maternal Age Women: Study Protocol for a Randomized Controlled Trial.

SCOPE: To investigate whether dietary fiber supplementation may reduce the risk of gestational diabetes mellitus (GDM) in advanced maternal age Chinese women (≥35 years). Secondary outcomes include glucose metabolism, diet change, weight gain, and maternal and neonatal outcomes. METHODS AND RESULTS: In a randomized controlled trial, a dietary fiber group (19.56 g day-1 ) or control group (standard prenatal care) was conducted from 20 to 24+6 gestational weeks in advanced maternal age women. Dietary intakes were assessed using a validated 39-item Food Frequency Questionnaire (FFQ). GDM was diagnosed by a 75 g oral glucose tolerance test (OGTT) at 25-28 weeks. After intervention, the incidence of GDM was not significantly different between groups (21.6% vs 12.9%, p = 0.165). The mean increased in carbohydrate intake in the dietary fiber group is significantly lower than in the control group (-0.94 ± 92.12 g vs 32.27 ± 91.81 g, p = 0.032). In addition, the glucose tolerance, weight gain between 20 and 25 weeks, and preterm birth in the intervention group have improved compared to the control group. CONCLUSION: Supplementation with dietary fiber during pregnancy among advanced maternal age Chinese women do not lower the incidence of GDM, but improve glucose metabolism, gestational weight gain, and preterm birth.

Association between Nonalcoholic Fatty Liver Disease and Bone Mineral Density in HIV-Infected Patients Receiving Long-term TDF-Based Antiretroviral Therapy.

BACKGROUND: Tenofovir (TDF) has a detrimental effect on bone mineral density (BMD), while nonalcoholic fatty liver disease (NAFLD) is associated with a lower BMD. OBJECTIVE: To help understand the mutual effects of NAFLD and TDF on BMD, this study was designed to explore the potential association between NAFLD and BMD in HIV-infected patients receiving long-term TDF-based antiretroviral therapy (ART). METHODS: A total of 89 HIV-infected patients who received TDF-based ART for more than three years were enrolled in this cross-sectional study. We measured BMD using an ultrasonic bone density apparatus, and liver ultrasonography was performed to determine the severity of the fatty liver. The association of NAFLD with BMD was examined using multiple logistic regression analyses. RESULTS: Patients with NAFLD showed a worse BMD status than those without NAFLD. The incidence rates of osteopenia (42.86% versus 25.93%) and osteoporosis (17.14% versus 3.70%) were significantly higher in HIV-infected patients with NAFLD than in those without NAFLD. After multivariate adjustment, the odds ratio (OR) for patients with NAFLD exhibiting a worse BMD status compared with those without NAFLD was 4.49 (95% confidence interval [CI] 1.42, 14.15). CONCLUSION: Based on our results, NAFLD was significantly associated with a worse BMD status, including osteopenia and osteoporosis, in HIV patients after receiving long-term TDF-based ART. Furthermore, we may want to avoid using TDF for ART in HIV-infected patients with NAFLD.