Development and validation of a prediction model for postoperative pneumonia in patients who received spinal surgery: A retrospective study.

Objectives: To develop and validate a risk prediction model by identifying the preoperative factors associated with an increased risk of pneumonia after spinal surgery. Methods: This study included patients with spinal disease from two hospitals between January 2021 and June 2023. The patients were divided into the training and validation sets, which were categorized as postoperative pneumonia (POP) or non-POP, respectively. This study identified the independent risk variables for POP using a multivariate logistic regression analysis. A nomogram prediction model was developed and validated using risk factors, receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) to assess predictive performance. Results: Following exclusion, 2223 patients from Changzheng Hospital were enrolled in the training set and 357 patients from the No. 905 Hospital of PLA Navy were enrolled in the validation set. Univariate and multivariate logistic regression analyses revealed that operation time, American Society of Anesthesiologists (ASA) grade, smoking, non-wearing of medical masks, lack of preoperative respiratory training, chronic obstructive pulmonary disease (COPD), underlying diseases, and spinal section were risk factors for POP development in patients with spinal diseases. The area under the ROC curve of the training set was 0.950, whereas that of the validation set was 0.879. The model calibration curves demonstrated good agreement, and the DCA indicated a high expected net benefit value. Conclusion: The POP risk prediction model has high accuracy and efficiency in predicting POP in patients with spinal diseases. POP development is influenced by factors such as operation length, ASA grade, smoking, non-wearing of medical masks, lack of preoperative respiratory training, COPD, underlying diseases, and lumbar surgery.

Long non-coding RNA MSL3P1 regulates CUL3 mRNA cytoplasmic transport and stability and promotes lung adenocarcinoma metastasis.

Lung adenocarcinoma (LUAD) is the most prevalent histological type of lung cancer. Previous studies have reported that specific long non-coding RNAs (lncRNAs) are involved in cancer development and progression. The phenotype and mechanism of ENST00000440028, named MSL3P1, a lncRNA which we referring to a cancer-testis gene with potential roles in tumorigenesis and progression, have not been reported. We found that MSL3P1 is overexpressed in LUAD tumor tissues, which is significantly associated with clinical characteristics, metastasis, and poor clinical prognosis. MSL3P1 promotes the metastasis of LUAD in vitro and in vivo. The enhancer reprogramming in LUAD tumor tissue is the major driver of the aberrantly expression of MSL3P1. Mechanistically, due to the competitive binding to CUL3 mRNA with ZFC3H1 protein (a protein involved in targeting polyadenylated RNA to exosomes and promoting the degradation of target mRNA), MSL3P1 can prevent the ZFC3H1-mediated RNA degradation of CUL3 mRNA and transport it to the cytoplasm. This activates the downstream epithelial-to-mesenchymal transition signaling pathway, and promote tumor invasion and metastasis. Implications: This study indicates that lncRNA MSL3P1 regulates CUL3 mRNA stability and promotes the metastasis and holds potential as a prognostic biomarker and therapeutic target in LUAD.

Molecular targets and mechanisms of different aberrant alternative splicing in metastatic liver cancer.

Metastasis remains a major challenge in the successful management of malignant diseases. The liver is a major site of metastatic disease and a leading cause of death from gastrointestinal malignancies such as colon, stomach, and pancreatic cancers, as well as melanoma, breast cancer, and sarcoma. As an important factor that influences the development of metastatic liver cancer, alternative splicing drives the diversity of RNA transcripts and protein subtypes, which may provide potential to broaden the target space. In particular, the dysfunction of splicing factors and abnormal expression of splicing variants are associated with the occurrence, progression, aggressiveness, and drug resistance of cancers caused by the selective splicing of specific genes. This review is the first to provide a detailed summary of the normal splicing process and alterations that occur during metastatic liver cancer. It will cover the role of alternative splicing in the mechanisms of metastatic liver cancer by examining splicing factor changes, abnormal splicing, and the contribution of hypoxia to these changes during metastasis.

Latent profile analysis of depression in US adults with obstructive sleep apnea hypopnea syndrome.

Objective: This study used latent profile analysis to explore the level of depression among US adults with obstructive sleep apnea hypopnea syndrome (OSAHS) symptoms and to identify different latent categories of depression to gain insight into the characteristic differences between these categories. Methods: The data of this study were obtained from the National Health and Nutrition Examination Survey (NHANES) database, and the subjects with OSAHS symptoms were aged 18 years and older. The latent profile analysis (LPA) method was used to fit the latent depression categories in subjects with OSAHS symptoms. The chi-square test, rank sum test, and binary logistic regression were used to analyze the influencing factors of depression subgroups in subjects with OSAHS symptoms. Results: Three latent profiles were identified: low-level (83.7%), moderate-level (14.5%) and high-level (1.8%) depression. The scores of 9 items in the high-level depression group were higher than those in the other two groups. Among them, item 4 "feeling tired or lack of energy" had the highest score in all categories. Conclusion: Depression in subjects with OSAHS symptoms can be divided into low-level, moderate-level and high-level depression. There are significant differences among different levels of depression in gender, marital status, PIR, BMI, smoking, general health condition, sleep duration and OSAHS symptom severity.

Survival nomogram and risk classification system for patients with adrenocortical carcinoma: a study based on the SEER database and external validation in China.

Background: Adrenocortical carcinoma (ACC) is an extremely rare and highly invasive malignant tumor. However, there is currently no reliable method to predict the prognosis of ACC. Our objective is to construct a nomogram and a risk classification system to predict the 1-year, 3-year, and 5-year overall survival (OS) of ACC. Methods: We retrieved clinicopathological data of patients diagnosed with ACC in The Surveillance, Epidemiology, and End Results (SEER) database and divided them into training and validation cohorts with a 7:3 ratio. Simultaneously, we collected an external validation cohort from The First Affiliated Hospital of Naval Medical University (Shanghai, China). Univariate and multivariate Cox analyses were performed to identify relevant risk factors, which were then combined to develop a correlation nomogram. The predictive performance of the nomogram was evaluated using the concordance index (C-index), receiver-operating characteristic curve (ROC), and calibration curves. Decision curve analysis (DCA) was applied to assess the clinical utility of the nomogram. In addition, Kaplan-Meier survival curves were generated to demonstrate the variation in OS between groups. Results: The final nomogram consisted of five factors: age, T, N, M, and history of chemotherapy. Our prognostic model demonstrated significant discriminative ability, with C-index and the area under the receiver operating characteristic (AUC) values exceeding 0.70. Additionally, DCA validated the clinical utility of the nomogram. In the entire cohort, the median OS for patients in the low- and high-risk groups was 70 and 10 months, respectively. Conclusions: A nomogram and a corresponding risk classification system were developed in order to predict the OS of patients diagnosed with ACC. These tools have the potential to provide valuable support for patient counseling and assist in the decision-making process related to treatment options.

Effectiveness and safety of early lens extraction during par plana vitrectomy for proliferative diabetes retinopathy with mild cataract: a randomized clinical trial.

AIM: To evaluate the effectiveness and safety of early lens extraction during pars plana vitrectomy (PPV) for proliferative diabetic retinopathy (PDR) compared to those of PPV with subsequent cataract surgery. METHODS: This multicenter randomized controlled trial was conducted in three Chinese hospitals on patients with PDR, aged >45y, with mild cataracts. The participants were randomly assigned to the combined (PPV combined with simultaneously cataract surgery, i.e., phacovitrectomy) or subsequent (PPV with subsequent cataract surgery 6mo later) group and followed up for 12mo. The primary outcome was the change in best-corrected visual acuity (BCVA) from baseline to 6mo, and the secondary outcomes included complication rates and medical expenses. RESULTS: In total, 129 patients with PDR were recruited and equally randomized (66 and 63 in the combined and subsequent groups respectively). The change in BCVA in the combined group [mean, 36.90 letters; 95% confidence interval (CI), 30.35-43.45] was significantly better (adjusted difference, 16.43; 95%CI, 8.77-24.08; P<0.001) than in the subsequent group (mean, 22.40 letters; 95%CI, 15.55-29.24) 6mo after the PPV, with no significant difference between the two groups at 12mo. The overall surgical risk of two sequential surgeries was significantly higher than that of the combined surgery for neovascular glaucoma (17.65% vs 3.77%, P=0.005). No significant differences were found in the photocoagulation spots, surgical time, and economic expenses between two groups. In the subsequent group, the duration of work incapacity (22.54±9.11d) was significantly longer (P<0.001) than that of the combined group (12.44±6.48d). CONCLUSION: PDR patients aged over 45y with mild cataract can also benefit from early lens extraction during PPV with gratifying effectiveness, safety and convenience, compared to sequential surgeries.

[Clinical Analysis of PEG-rhG-CSF in Mobilization of Autologous Hematopoietic Stem Cells in Hematological Tumors].

OBJECTIVE: To investigate the efficiency and optimal time of stem cell apheresis mobilized by pegylated recombinant human granulocyte colony stimulating factor (PEG-rhG-CSF) in autologous stem cell transplantation (ASCT) for hematological malignancies without monitoring pre-collection CD34+ cells. METHODS: Forty-six patients underwent stem cell mobilization were retrospectively analyzed between August 2017 and January 2022 at the First Affiliated Hospital of Fujian Medical University. 27 patients using high dose chemotherapy combined with PEG-rhG-CSF mobilization were enrolled in the PEG-rhG-CSF group, and other 19 patients mobilized with recombinant human granulocyte colony stimulating factor (G-CSF) were enrolled in G-CSF group. The mobilization and collection effects of the patients in two groups were compared. RESULTS: A total of 46 patients underwent 86 apheresis procedures, the median amount of mononuclear cell (MNC) in the PEG-rhG-CSF group and G-CSF group was 6.54（3.85-12.61）×108/kg and 6.15（1.13-11.58）×108/kg, respectively (P >0.05), the total CD34+ cells of the grafts were 11.44(1.33-65.02)×106/kg and 4.95(0.30-24.02)×106/kg (P < 0.05), with harvest timing of 14(10-20) days and 14(4-22) days, respectively (P >0.05). In the PEG-rhG-CSF group, there was a significant difference between the number of CD34+ cells collected when white blood cells (WBC) ≥10×109/L and WBC<10×109 /L, 19.04(2.85-65.02)×106/kg and 6.22(0.81-34.86)×106/kg, respectively (P < 0.05). CONCLUSION: Stem cells mobilization with PEG-rhG-CSF was highly efficient with a median mobilization time of 14 days. In the absence of peripheral blood CD34 monitoring, peripheral blood WBC≥10×109/L can be considered as a threshold for a single stem cell apheresis to collect sufficient stem cells.

Phytochemical Profile and Bioactivity of Bound Polyphenols Released from Rosa roxburghii Fruit Pomace Dietary Fiber by Solid-State Fermentation with Aspergillus niger.

This study aimed to investigate the phytochemical profile, bioactivity, and release mechanism of bound polyphenols (BPs) released from Rosa roxburghii fruit pomace insoluble dietary fiber (RPDF) through solid-state fermentation (SSF) with Aspergillus niger. The results indicated that the amount of BPs released from RPDF through SSF was 17.22 mg GAE/g DW, which was significantly higher than that achieved through alkaline hydrolysis extraction (5.33 mg GAE/g DW). The BPs released through SSF exhibited superior antioxidant and α-glucosidase inhibitory activities compared to that released through alkaline hydrolysis. Chemical composition analysis revealed that SSF released several main compounds, including ellagic acid, epigallocatechin, p-hydroxybenzoic acid, quercetin, and 3,4-dihydroxyphenylpropionic acid. Mechanism analysis indicated that the disruption of tight structure, chemical bonds, and hemicellulose was crucial for the release of BPs from RPDF. This study provides valuable information on the potential application of SSF for the efficient release of BPs from RPDF, contributing to the utilization of RPDF as a functional food ingredient.

[Corrigendum] miR­27a promotes proliferation, migration, and invasion of colorectal cancer by targeting FAM172A and acts as a diagnostic and prognostic biomarker.

Following the publication of this article, an interested reader drew to the authors' attention that the western blots in Fig. 4B on p. 3560 and Fig. 6B on p. 3562 shared remarkably similar data (including both the GAPDH and the FAM172A blots in Fig. 4B), such that these data were likely to have been derived from the same original source. Upon asking the authors to provide an explanation, the authors realized that these errors inadvertently arose during the process of assembling these figures. Due to a mislabelling of the files, representative blots for FAM172A and GAPDH were chosen incorrectly for Fig. 4B. The authors had retained their original data, however, and were also able to present to the Editorial Office for our perusal the uncropped versions of their western blots, which resolved any other potential issues of anomalies associated with the data. The revised version of Fig. 4, now showing alternative data for Fig. 4B, is shown on the next page (note that, in the repeated experiment, relative to the original version of this figure the miR­27a, miR27a­inhibitor and negative control experiments were run on different lanes of the gel). Also note that the errors made in terms of assembling the data in Fig. 4 did not greatly affect either the results or the conclusions reported in this paper, and all the authors agree to the publication of this corrigendum. The authors regret that these errors went unnoticed prior to the publication of their article, are grateful to the Editor of Oncology Reports for granting them this opportunity to publish a corrigendum, and apologize to the readership for any inconvenience caused. [Oncology Reports 37: 3554­3564, 2017; DOI: 10.3892/or.2017.5592].

Effects of MTHFR C677T polymorphism on homocysteine and vitamin D in women with polycystic ovary syndrome.

OBJECTIVES: To evaluate the correlation between serum vitamin D, homocysteine and the methylene tetrahydrofolate reductase (MTHFR) C677T polymorphism in women with polycystic ovary syndrome (PCOS). Study design We retrospectively compared the serum homocysteine and vitamin D levels and the MTHFR C677T polymorphism in 104 PCOS patients and 104 controls. Parameters related to PCOS were statistically analysed. RESULTS: Comparative analysis revealed that women with PCOS had significantly greater serum homocysteine levels (P = 0.002) and lower vitamin D concentrations (P = 0.040) than controls. The distribution frequency of the MTHFR C677T genotype did not significantly differ between the PCOS group and the control group. (P > 0.05). In the PCOS group, the serum level of homocysteine in the TT group was significantly greater than that in the CT (P = 0.003) and CC (P = 0.002) groups and the level of vitamin D in the TT group was significantly less than that in the CC (P < 0.001) and CT (P = 0.172) groups. The results were similar when the PCOS and control groups were divided according to whether they had insulin resistance. Vitamin D levels were significantly negatively correlated with homocysteine levels in all PCOS patients (r = -0.281, P = 0.004), similarly, vitamin D levels were negatively correlated with homocysteine levels in the CC, CT and TT of PCOS patients. According to multivariate analysis, vitamin D concentration was an independent risk factor for hyperhomocysteinaemia (adjusted OR 1.372, 95 % CI: 1.100-1.712). CONCLUSIONS: No significant differences were found in the distributions of MTHFR C677T genotypes between the PCOS and control groups but these genotypes affected the patients' serum homocysteine and vitamin D concentrations. Women with the TT genotype have significantly lower vitamin D levels and higher homocysteine levels than women with the CC and CT genotypes. However, because of the limitations of this investigation, large-sample, high-quality prospective studies are needed to further verify these results in the future.

Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma.

Objectives: Combination therapy of lenvatinib and immune checkpoint inhibitors (CLICI) has emerged as a promising approach for managing unresectable hepatocellular carcinoma (HCC). However, the response to such treatment is observed in only a subset of patients, underscoring the pressing need for reliable methods to identify potential responders. Materials & methods: This was a retrospective analysis involving 120 patients with unresectable HCC. They were divided into training (n = 72) and validation (n = 48) cohorts. We developed an interpretable deep learning model using multiphase computed tomography (CT) images to predict whether patients will respond or not to CLICI treatment, based on the Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST v1.1). We evaluated the models' performance and analyzed the impact of each CT phase. Critical regions influencing predictions were identified and visualized through heatmaps. Results: The multiphase model outperformed the best biphase and uniphase models, achieving an area under the curve (AUC) of 0.802 (95% CI = 0.780-0.824). The portal phase images were found to significantly enhance the model's predictive accuracy. Heatmaps identified six critical features influencing treatment response, offering valuable insights to clinicians. Additionally, we have made this model accessible via a web server at http://uhccnet.com/ for ease of use. Conclusions: The integration of multiphase CT images with deep learning-generated heatmaps for predicting treatment response provides a robust and practical tool for guiding CLICI therapy in patients with unresectable HCC.

Preliminary exploration of animal models of congenital choledochal cysts.

BACKGROUND: Various animal models have been used to explore the pathogenesis of choledochal cysts (CCs), but with little convincing results. Current surgical techniques can achieve satisfactory outcomes for treatment of CCs. Consequently, recent studies have focused more on clinical issues rather than basic research. Therefore, we need appropriate animal models to further basic research. AIM: To establish an appropriate animal model that may contribute to the investigation of the pathogenesis of CCs. METHODS: Eighty-four specific pathogen-free female Sprague-Dawley rats were randomly allocated to a surgical group, sham surgical group, or control group. A rat model of CC was established by partial ligation of the bile duct. The reliability of the model was confirmed by measurements of serum biochemical indices, morphology of common bile ducts of the rats as well as molecular biology experiments in rat and human tissues. RESULTS: Dilation classified as mild (diameter, ≥ 1 mm to < 3 mm), moderate (≥ 3 mm to < 10 mm), and severe (≥ 10 mm) was observed in 17, 17, and 2 rats in the surgical group, respectively, while no dilation was observed in the control and sham surgical groups. Serum levels of alanine aminotransferase, aspartate aminotransferase, total bilirubin, direct bilirubin, and total bile acids were significantly elevated in the surgical group as compared to the control group 7 d after surgery, while direct bilirubin, total bilirubin, and gamma-glutamyltransferase were further increased 14 d after surgery. Most of the biochemical indices gradually decreased to normal ranges 28 d after surgery. The protein expression trend of signal transducer and activator of transcription 3 in rat model was consistent with the human CC tissues. CONCLUSION: The model of partial ligation of the bile duct of juvenile rats could morphologically simulate the cystic or fusiform CC, which may contribute to investigating the pathogenesis of CC.

CGRP Released by Corneal Sensory Nerve Maintains Tear Secretion of the Lacrimal Gland.

Purpose: This study aims to elucidate the calcitonin gene-related peptide (CGRP) mediation and primary mechanism of corneal sensory nerves on tear production of the lacrimal gland. Methods: Mouse corneal denervation models were constructed through surgical axotomy, pharmacologic treatment with capsaicin or resiniferatoxin, and Trpv1-Cre/DTR mice with diphtheria toxin injection. The capsaicin-treated mice received subconjunctival injection of CGRP or substance P, while the normal C57BL/6J mice were administered with CGRP receptor antagonist BIBN-4096. Furthermore, double immunostaining of c-FOS+ and choline acetyltransferase was used to evaluate the activation of the superior salivatory nucleus (SSN). Mouse lacrimal glands were collected for transcriptomic sequencing and subsequent RNA and protein expression analysis. Results: The corneal denervated mice exhibited a significant reduction in corneal sensitivity and tear secretion. In capsaicin-treated mice, tear secretion decreased to 2.5 ± 0.5 mm compared to 6.3 ± 0.9 mm in control mice (P < 0.0001). However, exogenous administration of CGRP in capsaicin-treated mice increased tear secretion from 2.6 ± 0.5 mm to 4.5 ± 0.5 mm (P = 0.0009), while BIBN-4096 treatment reduced tear secretion to 3.4 ± 0.5 mm when compared to 7.3 ± 0.7 mm in control mice (P = 0.0022). Furthermore, c-FOS+ cell number in the SSN increased by twofold (P = 0.0168) after CGRP administration compared with capsaicin-treated mice. In addition, the expressions of CCNA2, Ki67, PCNA, and CDK1 in acinar cells of the lacrimal gland were impaired by corneal denervation and alleviated by CGRP administration. Conclusions: CGRP released by corneal sensory nerves mediates tear secretion of the lacrimal gland, providing a new strategy for improving tear secretion in patients with neurotrophic keratitis.

Application of γ-aminobutyric acid improves the postharvest marketability of strawberry by maintaining fruit quality and enhancing antioxidant system.

The capability of 5, 10, 15 mM γ-aminobutyric acid (GABA) to improve the postharvest quality and antioxidant system of strawberry was evaluated in this study. The application of GABA had no effect on fruit skin color and firmness. The weight loss in fruits treated with 10 mM GABA was significantly lower than the control. GABA treatments resulted in higher levels of total soluble sugar, titratable acid, SOD and CAT activities with 10 mM being the most significant effect. Specifically, 10 mM GABA significantly induced the accumulation of fructose, oxalic acid, and succinic acid. Besides, GABA application increased the content of total anthocyanins and total flavonoids, and DPPH radical scavenging activity in fruits. The GABA-treated fruits especially at 5 mM and 10 mM displayed less ROS and MDA. These data suggested that application of 10 mM GABA might be a promising strategy to improve the postharvest marketability of strawberry.

LINC01977 promotes colorectal cancer growth and metastasis by enhancing aerobic glycolysis via the ERK/c-Myc axis.

Background: How colorectal cancer (CRC) gain the ability to growth and metastasis remains largely unknown. Findings from preceding studies have revealed the participation of long non-coding RNAs (lncRNAs) in CRC progression. However, the role of LINC01977 in CRC remains unexplored. This study aims to explore the function and underlying mechanism of LINC01977 in CRC. Methods: The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) datasets were used to analyze the expression of LINC01977 in CRC and its correlation with CRC prognosis. In our research, we explored the influence of LINC01977 on CRC progression such as cell proliferation, migration, invasion, and aerobic glycolysis, and identified its fundamental molecular mechanism using in vitro CRC cell lines and in vivo mouse xenograft models. Results: LINC01977 exhibited significantly elevated expression in CRC tissues and cell lines, and its level was significantly correlated with malignant clinicopathological characteristics and negative prognosis. Furthermore, both in vivo and in vitro tests revealed LINC01977's role in facilitating CRC cell proliferation and metastasis. LINC01977's significant part in CRC aerobic glycolysis was also discovered. With an aim to uncover the underlying mechanism, we investigated LINC01977's effect on c-Myc, a key gene in glycolysis. The results showed that LINC01977 regulated c-Myc stability via extracellular signal-regulated kinase (ERK)-mediated phosphorylation, and LINC01977-mediated c-Myc activated the level of vital glycolysis-related genes such as HK2, PGK1, LDHA, and GLUT1. Rescue experiments further confirmed that LINC01977 promoted CRC proliferation, metastasis, and aerobic glycolysis via c-Myc. Conclusions: This study is the first to report that LINC01977 facilitates CRC proliferation, metastasis, and aerobic glycolysis through c-Myc, suggesting its potential as a therapeutic target for CRC treatment.

Seven new triterpenoids from the roots of Adenophora tetraphylla (Thub.) Fisch.

Seven new triterpenoids, named Adeterpenoids A-G (1-7) and eight known compounds (8-15), were isolated from 70% ethanol extract of the roots of Adenophora tetraphylla (Thub.) Fisch. The compounds from it were separated by column chromatography techniques such as silica gel, ODS, and preparative liquid chromatography. Their structures were clarified based on extensive spectral analysis (1D, 2D-NMR, HR-ESI-MS, IR, UV, and CD) and comparison with the literature. At the same time, all compounds were evaluated for their cytotoxic activity against the LN229 (human glioma cell line). The results showed that compounds 2, 5, 6, 13, and 14 had a significant inhibitory effect on LN229 cells.

Comparison of the effect between traditional conservation and nasointestinal tube placement in adhesive small bowel obstruction: A matched case-control study.

Adhesive small bowel obstruction (ASBO) causes a major burden in emergency medicine. Owing to in situ decompression, nasointestinal tube (NIT) placement has been increasingly used in clinical practice compared with traditional conservation (TC); however, the indications remain controversial. This study was designed to explore the indications for each treatment in ASBOs and then suggest the optimal strategy. After propensity score matching, 128 pairs were included (the NIT and TC groups). The occurrence of severe adverse events (SAEs), peri-treatment clinical parameters, and radiological features were compared between the successful and failed treatment groups. According to different stages of the entire treatment, the independent risk factors for adverse effects for ASBO were analysed in phase I and phase II. In phase I, normal red blood cells (RBC) levels (p = 0.011) and a balanced sodium ion level (p = 0.016) positively affected the outcomes of TC treatment. In phase II, for the TC group, the successful treatment rate reached 79.5% for patients with ASBOs whose normal RBC levels (p = 0.006) or decreasing white blood cells (WBC) levels (p = 0.014) after treatment. For the NIT group, the treatment success rate was 68.1% for patients whose electrolyte imbalance could be reversed or whose neutrophil count/lymphocyte ratio (NLR) levels was lower than 4.3 (p = 0.018). TC treatment is highly recommended for patients with normal RBC counts and sodium levels pretreatment. After dynamic monitoring of the treatment process, for both the TC and NIT groups, once ASBOs had elevated inflammatory biomarkers or irreversible electrolyte disturbances, surgical interference was preferred.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

BACKGROUND AND AIMS: Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. METHODS: Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). RESULTS: The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). CONCLUSIONS: Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.