A Gallbladder Cancer Survival Prediction Model Based on Multimodal Fusion Analysis.

BACKGROUND: 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. AIMS: 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). METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.

Risk factors and socio-economic burden in pancreatic ductal adenocarcinoma operation: a machine learning based analysis.

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.

Dexmedetomidine use during orthotopic liver transplantation surgery on early allograft dysfunction: A randomized controlled trial.

BACKGROUND: Previous studies have shown a protective effect of dexmedetomidine use in kidney transplantation. In contrast, it is not known whether intraoperative administration of dexmedetomidine can reduce early allograft dysfunction incidence following liver transplantation. OBJECTIVE: To investigate the effect of dexmedetomidine use during surgery on early allograft dysfunction following orthotopic liver transplantation (OLT). STUDY DESIGN: This is a single-center, double-blinded, placebo-controlled randomized clinical trial. 330 adult patients undergoing orthotopic liver transplantation were enrolled from Jan 14th, 2019 to May 22nd, 2022. Patients received dexmedetomidine or normal saline during surgery. 1 year follow-ups were recorded. METHODS: Patients were randomized to two groups receiving either dexmedetomidine or normal saline intraoperatively. For patients in the dexmedetomidine group, a loading dose (1 µg/kg over 10 min) of dexmedetomidine was given after induction of anesthesia followed by a continuous infusion (0.5 µg/kg /h) until the end of surgery. For patients in the normal saline group, an equal volume loading dose of 0.9% saline was given after the induction of anesthesia followed by an equal volume continuous infusion until the end of surgery. The primary outcome was early allograft dysfunction. Secondary outcomes included primary graft non-function, acute kidney injury and acute lung injury/ acute respiratory distress syndrome. RESULTS: Of 330 patients included in the intention-to-treat analysis, 165 were in the dexmedetomidine group (mean [SD] age, 49 [10] years; 117 [70.9%] men), and 165 were in the normal saline group (mean SD age, 49 [9] years; 118 [74%] men). 39 (24.4%) patients in the dexmedetomidine group and 31 (19.4%) in normal saline group developed early allograft dysfunction and the difference was statistically insignificant (P=0.28). Secondary outcomes including primary graft non-function and acute kidney injury was similar between the two groups. CONCLUSION: Intraoperative administration of dexmedetomidine did not reduce early allograft dysfunction rate after orthotopic liver transplantation.

LncRNA FTX ameliorates neuropathic pain by targeting miR-320a in a rat model of chronic constriction injury.

INTRODUCTION: Long non-coding RNAs (lncRNAs) participate in the process of neuropathic pain (NP). Herein, the goal of this research was to examine the roles of lncRNA five prime to XIST (FTX) in influencing chronic constriction injury (CCI)-induced NP. MATERIAL AND METHODS: We have established a rat CCI model to simulate NP in vivo. Reverse transcription-quantitative PCR (RT-qPCR) was used to detect mRNA levels of FTX, microRNA (miR)-320a, and runt-related transcription factor 2 (RUNX2) in the spinal cord. This was followed by subsequent regulation of FTX or miR-320a levels in vivo by intrathecal injection of overexpression FTX or miR-320a mimic lentivirus. The behaviour of rat NP the paw withdrawal threshold (PWT) and paw withdrawal latency (PWL). Enzyme-linked immunosorbent assay (ELISA) was used to assess the secretion of pro-inflammatory and anti-inflammatory factors in the spinal cord tissue. A correlation between FTX and miR-320a, and RUNX2 was validated by luciferase reporter. RESULTS: FTX levels were reduced in CCI rats ( p < 0.05), and miR-320a was a direct target of FTX. Overexpression of FTX typically reduced PWL and PWT as well as neuroinflammation thus alleviating NP ( p < 0.05). However, increasing miR-320a reversed the alleviation of FTX on NP, increased PWL and PWT, and promoted neuroinflammation ( p < 0.05). Additionally, RUNX2, which is a miR-320a target gene, was significantly repressed in CCI rats and its expression was increased by FTX, however, this increase was attenuated by elevated miR-320a ( p < 0.05). CONCLUSIONS: In the CCI-induced NP rat model, FTX attenuates NP and neuroinflammation by regulating the miR-320a/RUNX2 axis. This provides a new vision for NP treatment.

Development and validation of an MRI-radiomics nomogram for the prognosis of pancreatic ductal adenocarcinoma.

Objective: To develop and validate an MRI-radiomics nomogram for the prognosis of pancreatic ductal adenocarcinoma (PDAC). Background: "Radiomics" enables the investigation of huge amounts of radiological features in parallel by extracting high-throughput imaging data. MRI provides better tissue contrast with no ionizing radiation for PDAC. Methods: There were 78 PDAC patients enrolled in this study. In total, there were 386 radiomics features extracted from MRI scan, which were screened by the least absolute shrinkage and selection operator algorithm to develop a risk score. Cox multivariate regression analysis was applied to develop the radiomics-based nomogram. The performance was assessed by discrimination and calibration. Results: The radiomics-based risk-score was significantly associated with PDAC overall survival (OS) (P < 0.05). With respect to survival prediction, integrating the risk score, clinical data and TNM information into the nomogram exhibited better performance than the TNM staging system, radiomics model and clinical model. In addition, the nomogram showed fine discrimination and calibration. Conclusions: The radiomics nomogram incorporating the radiomics data, clinical data and TNM information exhibited precise survival prediction for PDAC, which may help accelerate personalized precision treatment. Clinical trial registration: clinicaltrials.gov, identifier NCT05313854.

Machine Learning-Based Screening of Risk Factors and Prediction of Deep Vein Thrombosis and Pulmonary Embolism After Hip Arthroplasty.

Prophylactic anticoagulation is a standard strategy for patients undergoing total hip arthroplasty (THA) to prevent deep venous thromboembolism (DVT) and pulmonary embolism (PE). Nevertheless, some patients still experience these complications during their hospital stay. Current risk assessment methods like the Caprini and Geneva scores are not specifically designed for THA and may not accurately predict DVT or PE postoperatively. This study used machine learning techniques to establish models for early diagnosis of DVT and PE in patients undergoing THA. Data were collected from 1481 patients who received perioperative prophylactic anticoagulation. Model establishment and parameter tuning were performed using a training set and evaluated using a test set. Among the models, extreme gradient boosting (XGBoost) performed the best, with an area under the receiver operating characteristic curve (AUC) of 0.982, sensitivity of 0.913, and specificity of 0.998. The main features used in the XGBoost model were direct and indirect bilirubin, partial activation prothrombin time, prealbumin, creatinine, D-dimer, and C-reactive protein. Shapley Additive Explanations analysis was conducted to further analyze these features. This study presents a model for early diagnosis DVT or PE after THA and demonstrates bilirubin could be a potential predictor in the assessment of DVT or PE. Compared to traditional risk assessment, XGBoost has a high sensitivity and specificity to predict DVT and PE in the clinical setting. Furthermore, the results of this study were converted into a web calculator that can be used in clinical practice.

The longitudinal change of circulating tumor cell during chemotherapy and its correlation with disease features, treatment response and survival profile of advanced gallbladder carcinoma.

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<0.001) were lower in disease-control patients compared with those in non-disease-control patients. Importantly, pre-treatment CTC count ≥2 (versus <2) was only correlated with worse progression-free survival (PFS) (P=0.014) but not overall survival (OS) (P=0.057); while pre-treatment CTC count ≥5 (versus <5), post-treatment CTC count ≥2 (versus <2), post-treatment CTC count ≥5 (versus <5), CTC count up (versus equal/down) were all correlated with poor PFS and OS (all P<0.050). In conclusion, higher CTC count during chemotherapy correlates with worse treatment response, PFS and OS in advanced GBC patients, which implies that CTC measurement may optimize the prognostication and individualized treatment in these patients.

1H NMR metabolic signature of cerebrospinal fluid following repetitive lower-limb remote ischemia preconditioning.

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.