Uveal melanoma distant metastasis prediction system: A retrospective observational study based on machine learning.

Uveal melanoma (UM) patients face a significant risk of distant metastasis, closely tied to a poor prognosis. Despite this, there is a dearth of research utilizing big data to predict UM distant metastasis. This study leveraged machine learning methods on the Surveillance, Epidemiology, and End Results (SEER) database to forecast the risk probability of distant metastasis. Therefore, the information on UM patients from the SEER database (2000-2020) was split into a 7:3 ratio training set and an internal test set based on distant metastasis presence. Univariate and multivariate logistic regression analyses assessed distant metastasis risk factors. Six machine learning methods constructed a predictive model post-feature variable selection. The model evaluation identified the multilayer perceptron (MLP) as optimal. Shapley additive explanations (SHAP) interpreted the chosen model. A web-based calculator personalized risk probabilities for UM patients. The results show that nine feature variables contributed to the machine learning model. The MLP model demonstrated superior predictive accuracy (Precision = 0.788; ROC AUC = 0.876; PR AUC = 0.788). Grade recode, age, primary site, time from diagnosis to treatment initiation, and total number of malignant tumors were identified as distant metastasis risk factors. Diagnostic method, laterality, rural-urban continuum code, and radiation recode emerged as protective factors. The developed web calculator utilizes the MLP model for personalized risk assessments. In conclusion, the MLP machine learning model emerges as the optimal tool for predicting distant metastasis in UM patients. This model facilitates personalized risk assessments, empowering early and tailored treatment strategies.

The H1/H5 domain contributes to OsTRBF2 phase separation and gene repression during rice development.

Transcription factors (TFs) tightly control plant development by regulating gene expression. The phase separation of TFs plays a vital role in gene regulation. Many plant TFs have the potential to form phase-separated protein condensates; however, little is known about which TFs are regulated by phase separation and how it affects their roles in plant development. Here, we report that the rice (Oryza sativa) single Myb TF TELOMERE REPEAT-BINDING FACTOR 2 (TRBF2) is highly expressed in fast-growing tissues at the seedling stage. TRBF2 is a transcriptional repressor that binds to the transcriptional start site of thousands of genes. Mutation of TRBF2 leads to pleiotropic developmental defects and misexpression of many genes. TRBF2 displays characteristics consistent with phase separation in vivo and forms phase-separated condensates in vitro. The H1/H5 domain of TRBF2 plays a crucial role in phase separation, chromatin targeting and gene repression. Replacing the H1/H5 domain by a phase-separated intrinsically disordered region from Arabidopsis (Arabidopsis thaliana) AtSERRATE partially recovers the function of TRBF2 in gene repression in vitro and in transgenic plants. We also found that TRBF2 is required for trimethylation of histone H3 Lys27 (H3K27me3) deposition at specific genes and genome-wide. Our findings reveal that phase separation of TRBF2 facilitates gene repression in rice development.

Strain to shine: stretching-induced three-dimensional symmetries in nanoparticle-assembled photonic crystals.

Stretching elastic materials containing nanoparticle lattices is common in research and industrial settings, yet our knowledge of the deformation process remains limited. Understanding how such lattices reconfigure is critically important, as changes in microstructure lead to significant alterations in their performance. This understanding has been extremely difficult to achieve due to a lack of fundamental rules governing the rearrangements. Our study elucidates the physical processes and underlying mechanisms of three-dimensional lattice transformations in a polymeric photonic crystal from 0% to over 200% strain during uniaxial stretching. Corroborated by comprehensive experimental characterizations, we present analytical models that precisely predict both the three-dimensional lattice structures and the macroscale deformations throughout the stretching process. These models reveal how the nanoparticle lattice and matrix polymer jointly determine the resultant structures, which breaks the original structural symmetry and profoundly changes the dispersion of photonic bandgaps. Stretching induces shifting of the main pseudogap structure out from the 1st Brillouin zone and the merging of different symmetry points. Evolutions of multiple photonic bandgaps reveal potential optical singularities shifting with strain. This work sets a new benchmark for the reconfiguration of soft material structures and may lay the groundwork for the study of stretchable three-dimensional topological photonic crystals.

Artificial intelligence for the detection of glaucoma with SD-OCT images: a systematic review and Meta-analysis.

AIM: To quantify the performance of artificial intelligence (AI) in detecting glaucoma with spectral-domain optical coherence tomography (SD-OCT) images. METHODS: Electronic databases including PubMed, Embase, Scopus, ScienceDirect, ProQuest and Cochrane Library were searched before May 31, 2023 which adopted AI for glaucoma detection with SD-OCT images. All pieces of the literature were screened and extracted by two investigators. Meta-analysis, Meta-regression, subgroup, and publication of bias were conducted by Stata16.0. The risk of bias assessment was performed in Revman5.4 using the QUADAS-2 tool. RESULTS: Twenty studies and 51 models were selected for systematic review and Meta-analysis. The pooled sensitivity and specificity were 0.91 (95%CI: 0.86-0.94, I2=94.67%), 0.90 (95%CI: 0.87-0.92, I2=89.24%). The pooled positive likelihood ratio (PLR) and negative likelihood ratio (NLR) were 8.79 (95%CI: 6.93-11.15, I2=89.31%) and 0.11 (95%CI: 0.07-0.16, I2=95.25%). The pooled diagnostic odds ratio (DOR) and area under curve (AUC) were 83.58 (95%CI: 47.15-148.15, I2=100%) and 0.95 (95%CI: 0.93-0.97). There was no threshold effect (Spearman correlation coefficient=0.22, P>0.05). CONCLUSION: There is a high accuracy for the detection of glaucoma with AI with SD-OCT images. The application of AI-based algorithms allows together with "doctor+artificial intelligence" to improve the diagnosis of glaucoma.

Interleukin-21 receptor signaling promotes metabolic dysfunction-associated steatohepatitis-driven hepatocellular carcinoma by inducing immunosuppressive IgA+ B cells.

BACKGROUND: Dysregulation of immune surveillance is tightly linked to the development of metabolic dysfunction-associated steatohepatitis (MASH)-driven hepatocellular carcinoma (HCC); however, its underlying mechanisms remain unclear. Herein, we aimed to determine the role of interleukin-21 receptor (IL-21R) in MASH-driven HCC. METHODS: The clinical significance of IL-21R was assessed in human HCC specimens using immunohistochemistry staining. Furthermore, the expression of IL-21R in mice was assessed in the STAM model. Thereafter, two different MASH-driven HCC mouse models were applied between IL-21R-deficient mice and wild type controls to explore the role of IL-21R in MASH-driven HCC. To further elucidate the potential mechanisms by which IL-21R affected MASH-driven HCC, whole transcriptome sequencing, flow cytometry and adoptive lymphocyte transfer were performed. Finally, flow cytometry, enzyme-linked immunosorbent assay, immunofluorescent staining, chromatin immunoprecipitation assay and western blotting were conducted to explore the mechanism by which IL-21R induced IgA+ B cells. RESULTS: HCC patients with high IL-21R expression exhibited poor relapse-free survival, advanced TNM stage and severe steatosis. Additionally, IL-21R was demonstrated to be upregulated in mouse liver tumors. Particularly, ablation of IL-21R impeded MASH-driven hepatocarcinogenesis with dramatically reduction of lipid accumulation. Moreover, cytotoxic CD8+ T lymphocyte activation was enhanced in the absence of IL-21R due to the reduction of immunosuppressive IgA+ B cells. Mechanistically, the IL-21R-STAT1-c-Jun/c-Fos regulatory axis was activated in MASH-driven HCC and thus promoted the transcription of Igha, resulting in the induction of IgA+ B cells. CONCLUSIONS: IL-21R plays a cancer-promoting role by inducing IgA+ B cells in MASH-driven hepatocarcinogenesis. Targeting IL-21R signaling represents a potential therapeutic strategy for cancer therapy.

Recent advances in organic waste pyrolysis and gasification in a CO2 environment to value-added products.

The persistent combustion of fossil fuels has resulted in a widespread greenhouse effect attributable to the continual elevation of carbon dioxide (CO2) levels in the atmosphere. Recent research indicates that utilizing CO2 as a pyrolysis gasification medium diminishes CO2 emissions and concurrently augments the value of the resultant pyrolysis gasification products. This paper reviews recent advancements in the pyrolysis gasification of organic solid wastes under a CO2 atmosphere. Meanwhile, the mechanisms of CO2 influence in the pyrolysis and gasification processes were also discussed. In comparison to noble gases, CO2 exhibits reactivity with char at≥710 °C, resulting in additional mass loss of the sample. In addition, CO2 was able to increase the specific surface area and stability of biochar and reduce biooil toxicity by lowering the content of cyclic compounds in the biooil, while CO2 was able to react with GPRs with some volatile products (e.g., light hydrocarbons) to increase biogas yield. Finally, CO2 also prevents catalyst deactivation by reducing secondary coke formation. We also recommend directing future attention toward utilizing unpurified CO2 in pyrolysis and gasification. This review aims to expand the utilization of CO2 and advocate for applying pyrolysis gasification products.

Case report: Synchronous tumors of the female reproductive tract in systemic lupus erythematosus: report of two cases and review of the literature.

Background: Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that affects multiple systems. Patients with SLE are prone to a variety of malignancies, especially neoplasms of the female reproductive tract. Synchronous tumors, considered to involve multiple sites, are rare in the female reproductive tract. There are hardly any reports of SLE with synchronous reproductive tract tumors. Case presentation: We report the occurrence of two to three reproductive tract tumors in two women with SLE. A 52-year-old woman was diagnosed with vulvar cancer and cervical cancer. Another woman, aged 67, was diagnosed with concurrent vulvar cancer, vaginal cancer, and cervical cancer and also presented with a suspected lung cancer. Conclusion: The presence of synchronous tumors of the reproductive tract in patients with SLE is uncommon and can be easily disregarded. It is crucial to highlight that SLE patients with multiple primary malignancies exhibit notable late-stage presentation at the time of diagnosis, inadequate disease-free survival, poor overall survival, rapid progression rates, and mortality. Consequently, greater awareness must be raised regarding synchronous reproductive tract tumors in patients with SLE. Regular comprehensive cancer screening and management should be implemented for individuals diagnosed with SLE.

Zea mays cultivation, biochar, and arbuscular mycorrhizal fungal inoculation influenced lead immobilization.

Plant cultivation can influence the immobilization of heavy metals in soil. However, the roles of soil amendments and microorganisms in crop-based phytoremediation require further exploration. In this study, we evaluated the impact of Zea mays L. cultivation, biochar application, and arbuscular mycorrhizal fungi (AMF) inoculation on soil lead (Pb) immobilization. Our results indicated that biochar addition resulted in a significant, 42.00%, reduction in AMF colonization. Plant cultivation, AMF inoculation, and biochar addition all contributed to enhanced Pb immobilization, as evidenced by decreased levels of diethylenetriaminepentaacetic acid- and CaCl2-extractable Pb in the soil. Furthermore, soil subjected to plant cultivation with AMF and biochar displayed reduced concentrations of bioavailable Pb. Biochar addition altered the distribution of Pb fractions in the soil, transforming the acid-soluble form into the relatively inert reducible and oxidizable forms. Additionally, biochar, AMF, and their combined use promoted maize growth parameters, including height, stem diameter, shoot and root biomass, and phosphorus uptake, while simultaneously reducing the shoot Pb concentration. These findings suggest a synergistic effect in Pb phytostabilization. In summary, despite the adverse impact of biochar on mycorrhizal growth, cultivating maize with the concurrent use of biochar and AMF emerges as a recommended and effective strategy for Pb phytoremediation.IMPORTANCEHeavy metal contamination in soil is a pressing environmental issue, and phytoremediation has emerged as a sustainable approach for mitigating this problem. This study sheds light on the potential of maize cultivation, biochar application, and arbuscular mycorrhizal fungi (AMF) inoculation to enhance the immobilization of Pb in contaminated soil. The findings demonstrate that the combined use of biochar and AMF during maize cultivation can significantly improve Pb immobilization and simultaneously enhance maize growth, offering a promising strategy for sustainable and effective Pb phytoremediation practices. This research contributes valuable insights into the field of phytoremediation and its potential to address heavy metal pollution in agricultural soils.

Mechanisms Underlying the Overlooked Chiral Fungicide-Driven Enantioselective Proliferation of Antibiotic Resistance in Earthworm Intestinal Microbiome.

From a "One Health" perspective, the global threat of antibiotic resistance genes (ARGs) is associated with modern agriculture practices including agrochemicals application. Chiral fungicides account for a considerable proportion of wildly used agrochemicals; however, whether and how their enantiomers lead to differential proliferation of antibiotic resistance in agricultural environments remain overlooked. Focused on the soil-earthworm ecosystem, we for the first time deciphered the mechanisms underlying the enantioselective proliferation of antibiotic resistance driven by the enantiomers of a typical chiral fungicide mandipropamid (i.e., R-MDP and S-MDP) utilizing a multiomic approach. Time-series metagenomic analysis revealed that R-MDP led to a significant enhancement of ARGs with potential mobility (particularly the plasmid-borne ARGs) in the earthworm intestinal microbiome. We further demonstrated that R-MDP induced a concentration-dependent facilitation of plasmid-mediated ARG transfer among microbes. In addition, transcriptomic analysis with verification identified the key aspects involved, where R-MDP enhanced cell membrane permeability, transfer ability, biofilm formation and quorum sensing, rebalanced energy production, and decreased cell mobility versus S-MDP. Overall, the findings provide novel insights into the enantioselective disruption of microbiome and resistome in earthworm gut by chiral fungicides and offer significant contributions to the comprehensive risk assessment of chiral agrochemicals in agroecosystems.

Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study.

PURPOSE: This research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management. METHODS: Patients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction. RESULTS: Of the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability. CONCLUSIONS: Our study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians. Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic. CLINICALTRIALS: gov/ct2/show/NCT05867732 .

Enhanced absorption of SO2 from phosphogypsum decomposition by phosphate slurry for phosphoric acid production.

Phosphogypsum (PG) is a major industrial by-product of wet process phosphoric acid production, and untreated PG stockpiled on land will cause severe environmental pollution. Thermal treatment of PG is currently the mainstream treatment method PG can be thermally decomposed to produce CaO, and the decomposition process produces large amounts of SO2. In this paper, phosphate slurry was used to absorb SO2 generated during the PG decomposition to produce phosphoric acid. The effects of operating conditions such as pressure, inlet SO2 concentration, and additive content on the desulfurization efficiency, as well as phosphoric acid yield, were investigated. Under the optimal experimental parameters, the desulfurization efficiency was 100% in the first 3 h, and decreased to 67.42% after 5 h, the maximum phosphate concentration in the solution was 1445.92 mg/L. The Density functional theory (DFT) calculations showed that SO2 and O2 adsorbed on the surface of P2O5 underwent to generate SO3, which can react with H2O to produce H2SO4. Moreover, it was found that Fe3+ could enhance the catalytic oxidation process of SO2 and O2 by decreasing the reaction energy barrier. This study should be helpful for the recycling of phosphorus resources.

RNA-Seq and miRNA-Seq data from Epstein-Barr virus-infected tree shrews reveal a ceRNA network contributing to immune microenvironment regulation.

Epstein-Barr virus (EBV) infection in humans is ubiquitous and associated with various diseases. Remodeling of the immune microenvironment is the primary cause of EBV infection and pathogenesis; however, the underlying mechanism has not been fully elucidated. In this study, we used whole-transcriptome RNA-Seq to detect mRNAs, long non-coding RNAs (lncRNA), and microRNA (miRNA) profiles in the control group, 3 days, and 28 days after EBV infection, based on the tree shrew model that we reported previously. First, we estimated the proportion of 22 cell types in each sample using CIBERSORT software and identified 18 high-confidence DElncRNAs related to immune microenvironment regulation after EBV infection. Functional enrichment analysis of these differentially expressed lncRNAs primarily focused on the autophagy, endocytosis, and ferroptosis signalling pathways. Moreover, EBV infection affects miRNA expression patterns, and many miRNAs are silenced. Finally, three competing endogenous RNA regulatory networks were built using lncRNAs that significantly correlated with immune cell types, miRNAs that responded to EBV infection, and potentially targeted the mRNA of the miRNAs. Among them, MRPL42-AS-5 might act as an hsa-miR-296-5p "sponge" and compete with target mRNAs, thus increasing mRNA expression level, which could induce immune cell infiltration through the cellular senescence signalling pathway against EBV infection. Overall, we conducted a complete transcriptomic analysis of EBV infection in vivo for the first time and provided a novel perspective for further investigation of EBV-host interactions.

Prediction Model of Ocular Metastases in Gastric Adenocarcinoma: Machine Learning-Based Development and Interpretation Study.

Background: Although gastric adenocarcinoma (GA) related ocular metastasis (OM) is rare, its occurrence indicates a more severe disease. We aimed to utilize machine learning (ML) to analyze the risk factors of GA-related OM and predict its risks. Methods: This is a retrospective cohort study. The clinical data of 3532 GA patients were collected and randomly classified into training and validation sets in a ratio of 7:3. Those with or without OM were classified into OM and non-OM (NOM) groups. Univariate and multivariate logistic regression analyses and least absolute shrinkage and selection operator were conducted. We integrated the variables identified through feature importance ranking and further refined the selection process using forward sequential feature selection based on random forest (RF) algorithm before incorporating them into the ML model. We applied six ML algorithms to construct the predictive GA model. The area under the receiver operating characteristic (ROC) curve indicated the model's predictive ability. Also, we established a network risk calculator based on the best performance model. We used Shapley additive interpretation (SHAP) to identify risk factors and to confirm the interpretability of the black box model. We have de-identified all patient details. Results: The ML model, consisting of 13 variables, achieved an optimal predictive performance using the gradient boosting machine (GBM) model, with an impressive area under the curve (AUC) of 0.997 in the test set. Utilizing the SHAP method, we identified crucial factors for OM in GA patients, including LDL, CA724, CEA, AFP, CA125, Hb, CA153, and Ca2+. Additionally, we validated the model's reliability through an analysis of two patient cases and developed a functional online web prediction calculator based on the GBM model. Conclusion: We used the ML method to establish a risk prediction model for GA-related OM and showed that GBM performed best among the six ML models. The model may identify patients with GA-related OM to provide early and timely treatment.

Detecting EGFR gene amplification using a fluorescence in situ hybridization platform based on digital microfluidics.

Signal transduction mediated by epidermal growth factor receptor (EGFR) gene affects the proliferation, invasion, metastasis, and angiogenesis of tumor cells. In particular, non-small cell lung cancer (NSCLC) patients with increased in copy number of EGFR gene are often sensitive to tyrosine kinase inhibitors. Despite being the standard for detecting EGFR amplification in the clinic, fluorescence in situ hybridization (FISH) traditionally involves repetitive and complex benchtop procedures that are not only time consuming but also require well-trained personnel. To address these limitations, we develop a digital microfluidics-based FISH platform (DMF-FISH) that automatically implements FISH operations. This system mainly consists of a DMF chip for reagent operation, a heating array for temperature control and a signal processing system. With the capability of automatic droplet handling and efficient temperature control, DMF-FISH performs cell digestion, gradient elution, hybridization and DAPI staining without manual intervention. In addition to operational feasibility, DMF-FISH yields comparable performance with the benchtop FISH protocol but reducing the consumption of DNA probe by 87 % when tested with cell lines and clinical samples. These results highlight unique advantages of the fully automated DMF-FISH system and thus suggest its great potential for clinical diagnosis and personalized therapy of NSCLC.

The efficacy of rituximab plus belimumab or telitacicept in refractory lupus nephritis.

OBJECTIVE: Lupus nephritis is a severe and common complication of systemic lupus erythematosus (SLE). The pathogenesis of lupus nephritis is characterized by B-cell activation and autoantibody formation. Rituximab and belimumab, as well as telitacicept, target B cells through different mechanisms, potentially exerting a synergistic effect in the treatment of lupus nephritis. This study aims to investigate the efficacy and safety of treatment with rituximab followed by belimumab or telitacicept in the management of refractory lupus nephritis. METHODS: We conducted a single-center, open-label, retrospective study, including 25 patients with refractory lupus nephritis. All patients received combination therapy with rituximab in individualized dosages to achieve peripheral B-cell depletion, and then followed by belimumab or telitacicept. The follow-up period was at least 12 months, and the primary end point was renal remission rate at the last follow-up. RESULTS: During a median follow-up of 19 (13, 29) months, 20 of 25 (80%) patients achieved objective remission (OR), including 19 (76%) patients achieved complete renal response (CRR). After rituximab (712 ± 416mg in average), 18 patients received belimumab and seven patients received telitacicept. In the rituximab plus telitacicept group, all patients achieved CRR; while in the rituximab plus belimumab group, 12 (66.7%) patients achieved CRR and 13 (72.2%) patients achieved OR. The mean SLEDAI-2K score decreased from 15 ± 6 to 6 ± 6, representing an average reduction of 60%. At the last follow-up, 18/25 (72%) had prednisone ≤ 5 mg/d or even discontinued prednisone use. Adverse effects were mainly immunoglobulin deficiency, respiratory tract infection, urinary tract infections, and rash. No death occurred. CONCLUSIONS: Rituximab followed by belimumab or telitacicept may be effective in inducing remission in refractory lupus nephritis, with tolerable adverse effects.

Treatment Outcomes in COVID-19 Patients with Brucellosis: Case Series in Heilongjiang and Systematic Review of Literature.

Objective: Clinical characteristics and outcome in COVID-19 with brucellosis patients has not been well demonstrated, we tried to analyze clinical outcome in local and literature COVID-19 cases with brucellosis before and after recovery. Methods: We retrospectively collected hospitalization data of comorbid patients and prospectively followed up after discharge in Heilongjiang Infectious Disease Hospital from January 15, 2020 to April 29, 2022. Demographics, epidemiological, clinical symptoms, radiological and laboratory data, treatment medicines and outcomes, and follow up were analyzed, and findings of a systematic review were demonstrated. Results: A total of four COVID-19 with brucellosis patients were included. One patient had active brucellosis before covid and 3 patients had nonactive brucellosis before brucellosis. The median age was 54.5 years, and all were males (100.0%). Two cases (50.0%) were moderate, and one was mild and asymptomatic, respectively. Three cases (75.0%) had at least one comorbidity (brucellosis excluded). All 4 patients were found in COVID-19 nucleic acid screening. Case C and D had only headache and fever on admission, respectively. Four cases were treated with Traditional Chinese medicine, western medicines for three cases, no adverse reaction occurred during hospitalization. All patients were cured and discharged. Moreover, one case (25.0%) had still active brucellosis without re-positive COVID-19, and other three cases (75.0%) have no symptoms of discomfort except one case fell fatigue and anxious during the follow-up period after recovery. Conducting the literature review, two similar cases have been reported in two case reports, and were both recovered, whereas, no data of follow up after recovery. Conclusion: These cases indicate that COVID-19 patients with brucellosis had favorable outcome before and after recovery. More clinical studies should be conducted to confirm our findings.

Pulmonary artery aneurysm protruding into the bronchus as an endobronchial mass: A case report.

BACKGROUND: Pulmonary artery (PA) aneurysms are usually diagnosed radiographically and present as small or large lesions resembling inflammation or a neoplasm on chest radiography. It has rarely been reported as an endobronchial mass. CASE SUMMARY: We report the case of a 64-year-old man who presented with recurrent hemoptysis. Bronchoscopy revealed a tumorous protrusion blocking the right middle lobe bronchus, which was confirmed to be a PA aneurysm using endobronchial ultrasound bronchoscopy and computed tomography angiography. CONCLUSION: Although endobronchial PA aneurysms are rare, bronchoscopists need to add this lesion to the list of endobronchial masses for which a biopsy is to be assiduously avoided.

Application of near-infrared fluorescence imaging in theranostics of gastrointestinal tumors.

Gastrointestinal cancers have become an important cause of cancer-related death in humans. Improving the early diagnosis rate of gastrointestinal tumors and improving the effect of surgical treatment can significantly improve the survival rate of patients. The conventional diagnostic method is high-definition white-light endoscopy, which often leads to missed diagnosis. For surgical treatment, intraoperative tumor localization and post-operative anastomotic state evaluation play important roles in the effect of surgical treatment. As a new imaging method, near-infrared fluorescence imaging (NIRFI) has its unique advantages in the diagnosis and auxiliary surgical treatment of gastrointestinal tumors due to its high sensitivity and the ability to image deep tissues. In this review, we focus on the latest advances of NIRFI technology applied in early diagnosis of gastrointestinal tumors, identification of tumor margins, identification of lymph nodes, and assessment of anastomotic leakage. In addition, we summarize the advances of NIRFI systems such as macro imaging and micro imaging systems, and also clearly describe the application process of NIRFI from system to clinical application, and look into the prospect of NIRFI applied in the theranostics of gastrointestinal tumors.

Prediction model of ocular metastasis from primary liver cancer: Machine learning-based development and interpretation study.

BACKGROUND: Ocular metastasis (OM) is a rare metastatic site of primary liver cancer (PLC). The purpose of this study was to establish a clinical predictive model of OM in PLC patients based on machine learning (ML). METHODS: We retrospectively collected the clinical data of 1540 PLC patients and divided it into a training set and an internal test set in a 7:3 proportion. PLC patients were divided into OM and non-ocular metastasis (NOM) groups, and univariate logistic regression analysis was performed between the two groups. The variables with univariate logistic analysis p < 0.05 were selected for the ML model. We constructed six ML models, which were internally verified by 10-fold cross-validation. The prediction performance of each ML model was evaluated by receiver operating characteristic curves (ROCs). We also constructed a web calculator based on the optimal performance ML model to personalize the risk probability for OM. RESULTS: Six variables were selected for the ML model. The extreme gradient boost (XGB) ML model achieved the optimal differential diagnosis ability, with an area under the curve (AUC) = 0.993, accuracy = 0.992, sensitivity = 0.998, and specificity = 0.984. Based on these results, an online web calculator was constructed by using the XGB ML model to help clinicians diagnose and treat the risk probability of OM in PLC patients. Finally, the Shapley additive explanations (SHAP) library was used to obtain the six most important risk factors for OM in PLC patients: CA125, ALP, AFP, TG, CA199, and CEA. CONCLUSION: We used the XGB model to establish a risk prediction model of OM in PLC patients. The predictive model can help identify PLC patients with a high risk of OM, provide early and personalized diagnosis and treatment, reduce the poor prognosis of OM patients, and improve the quality of life of PLC patients.