Search

Gallbladder cancer is the sixth most common malignant gastrointestinal tumor. Radical surgery is currently the only effective treatment, but patient prognosis is poor, with a 5-year survival rate of only 5-10%. Establishing an effective survival prediction model for gallbladder cancer patients is crucial for disease status assessment, early intervention, and individualized treatment approaches. The existing gallbladder cancer survival prediction model uses clinical data-radiotherapy and chemotherapy, pathology, and surgical scope-but fails to utilize laboratory examination and imaging data, limiting its prediction accuracy and preventing sufficient treatment plan guidance.The aim of this work is to propose an accurate survival prediction model, based on the deep learning 3D-DenseNet network, integrated with multimodal medical data (enhanced CT imaging, laboratory test results, and data regarding systemic treatments).Data were collected from 195 gallbladder cancer patients at two large tertiary hospitals in Shanghai. The 3D-DenseNet network extracted deep imaging features and constructed prognostic factors, from which a multimodal survival prediction model was established, based on the Cox regression model and incorporating patients' laboratory test and systemic treatment data.The model had a C-index of 0.787 in predicting patients' survival rate. Moreover, the area under the curve (AUC) of predicting patients' 1-, 3-, and 5-year survival rates reached 0.827, 0.865, and 0.926, respectively.Compared with the monomodal model based on deep imaging features and the tumor-node-metastasis (TNM) staging system-widely used in clinical practice-our model's prediction accuracy was greatly improved, aiding the prognostic assessment of gallbladder cancer patients.

Background Surgical resection is the major way to cure pancreatic ductal adenocarcinoma (PDAC). However, this operation is complex, and the peri-operative risk is high, making patients more likely to be admitted to the intensive care unit (ICU). Therefore, establishing a risk model that predicts admission to ICU is meaningful in preventing patients from post-operation deterioration and potentially reducing socio-economic burden. Methods We retrospectively collected 120 clinical features from 1242 PDAC patients, including demographic data, pre-operative and intra-operative blood tests, in-hospital duration, and ICU status. Machine learning pipelines, including Supporting Vector Machine (SVM), Logistic Regression, and Lasso Regression, were employed to choose an optimal model in predicting ICU admission. Ordinary least-squares regression (OLS) and Lasso Regression were adopted in the correlation analysis of post-operative bleeding, total in-hospital duration, and discharge costs. Results SVM model achieved higher performance than the other two models, resulted in an AU-ROC of 0.80. The features, such as age, duration of operation, monocyte count, and intra-operative partial arterial pressure of oxygen (PaO2), are risk factors in the ICU admission. The protective factors include RBC count, analgesic pump dexmedetomidine (DEX), and intra-operative maintenance of DEX. Basophil percentage, duration of the operation, and total infusion volume were risk variables for staying in ICU. The bilirubin, CA125, and pre-operative albumin were associated with the post-operative bleeding volume. The operation duration was the most important factor for discharge costs, while pre-lymphocyte percentage and the absolute count are responsible for less cost. Conclusions We observed that several new indicators such as DEX, monocyte count, basophil percentage, and intra-operative PaO2 showed a good predictive effect on the possibility of admission to ICU and duration of stay in ICU. This work provided an essential reference for indication in advance to PDAC operation.

The current study aimed to investigate the relation of circulating tumor cell (CTC) with clinicopathological features. In addition, its longitudinal change during chemotherapy and its correlation with prognosis in advanced gallbladder carcinoma (GBC) patients were explored. Totally 45 unresectable, locally advanced or metastatic GBC patients who underwent chemotherapy were enrolled in this prospective study. The CTC in 7.5 ml blood was detected at pre-treatment and 3 months post-treatment. CTC was almost detectable in all advanced GBC patients before treatment, whose count was positively correlated with metastatic disease (vs. local advanced disease) (P=0.002), number of organs with metastases (P=0.006), and CA199 level (P=0.002). After treatment, CTC count declined from 4.0 (range: 0.0-83.0) at pre-treatment to 2.0 (range: 0.0-36.0) at post-treatment (P=0.003). Interestingly, pre-treatment CTC count (P=0.270) was of no difference, while post-treatment CTC count was lower (P=0.038) in objective-response patients compared to that in non-objective-response patients; meanwhile, both pre-treatment CTC count (P=0.017) and post-treatment CTC count (P

Additional file 1 : Supplementary figure 1. The top features of the predictive model for post-operative admission to ICU.

Background Objective The cerebral ischemia/reperfusion greatly influences brain metabolism. Remote ischemia preconditioning (RIPC) is reported to confer neuroprotective effects against cerebral ischemia in animal models and human. This study aims to investigate the metabolomic profiles of cerebrospinal fluid (CSF) in patients treated with repetitive lower limb RIPC and provides an insight into possible mechanism underlying RIPC-induced neuroprotection. Method Fifty healthy patients undergoing minor surgery under spinal anesthesia were randomly allocated to 2 groups: control group (Group C, n = 25) and RIPC treatment group (Group T,n = 25). Repetitive limb RIPC were performed 3 sessions, consisting of three 5-min cycles per session from the day before surgery to the morning on the surgery day. The CSF samples were collected from 48 patients before intrathecal injection of local anesthetic. A proton nuclear magnetic resonance (1H NMR)-based metabonomics approach was used to obtain the CSF metabolic profiles of the samples (n = 24 each). The acquired data were processed with MestReNova and followed by statistical analysis with SIMCA-P. Results The model obtained with the orthogonal partial least-squares discriminant analysis (OPLS-DA) identified difference of metabolite profiles between two groups. The validation of the discriminant analysis showed that the accuracy of the OPLS-DA model was 81.3%. Sixteen metabolites including glucose, amino-acids and organic acids et al. were identified as the most influential CSF biomarkers for the discrimination between two groups, which are involved in pathways of energy metabolism and amino-acids metabolism. Conclusion 1H NMR spectra combined with pattern recognition analysis offers a new and promising platform to investigate metabolic signatures in patients treated with RIPC. Our results suggest repetitive RIPC mainly changes energy metabolism and amino-acid metabolism in brain, which provides a potential mechanistic understanding of RIPC-induced tolerance to cerebral ischemia.