Development and Validation of a Machine Learning Model for Bone Metastasis in Prostate Cancer: Based on Inflammatory and Nutritional Indicators.

OBJECTIVE: To establish a predictive model for prostate cancer bone metastasis utilizing multiple machine learning algorithms. METHODS: Retrospective analysis of the clinical data of prostate cancer initially diagnosed in the Department of Urology of Gansu Provincial People's Hospital from June 2017 to June 2022. Logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) are used to jointly screen the model features. The filtered features are incorporated into algorithms including LR, random forest (RF), extreme gradient boosting (XGBoost), naive Bayes (NB), k-nearest neighbor (KNN), and decision tree (DT), to develop prostate cancer bone metastasis models. RESULTS: A total of 404 patients were finally screened. Gleason score, T stage, N stage, PSA, and ALP were used as features for modeling. The average AUC of the 5-fold cross-validation for each machine learning model in the training set is as follows: LR (AUC=0.9054), RF (AUC=0.9032), NB (AUC=0.8961), KNN (AUC=0.8704), DT (AUC=0.8526), XGBoost (AUC=0.8066). The AUC of each machine learning model in the test set is KNN (AUC=0.9390, 95%CI: 0.8760-1), RF (AUC=0.9290, 95%CI: 0.8718-0.9861), NB (AUC=0.9268, 95%CI: 0.8615-0.9920), LR (AUC=0.9212, 95%CI: 0.8506-0.9917), XGBoost (AUC=0.8292, 95%CI: 0.7442-0.9141), DT (AUC=0.8057, 95%CI: 0.7100-0.9014). A comprehensive evaluation showed that LR performed well in interpretability and clinical applications. CONCLUSION: A bone metastasis model of prostate cancer was established, and it was observed that indicators such as inflammation and nutrition had a weak correlation with bone metastasis.

Multimodal data integration for predicting progression risk in castration-resistant prostate cancer using deep learning: a multicenter retrospective study.

Purpose: Patients with advanced prostate cancer (PCa) often develop castration-resistant PCa (CRPC) with poor prognosis. Prognostic information obtained from multiparametric magnetic resonance imaging (mpMRI) and histopathology specimens can be effectively utilized through artificial intelligence (AI) techniques. The objective of this study is to construct an AI-based CRPC progress prediction model by integrating multimodal data. Methods and materials: Data from 399 patients diagnosed with PCa at three medical centers between January 2018 and January 2021 were collected retrospectively. We delineated regions of interest (ROIs) from 3 MRI sequences viz, T2WI, DWI, and ADC and utilized a cropping tool to extract the largest section of each ROI. We selected representative pathological hematoxylin and eosin (H&E) slides for deep-learning model training. A joint combined model nomogram was constructed. ROC curves and calibration curves were plotted to assess the predictive performance and goodness of fit of the model. We generated decision curve analysis (DCA) curves and Kaplan-Meier (KM) survival curves to evaluate the clinical net benefit of the model and its association with progression-free survival (PFS). Results: The AUC of the machine learning (ML) model was 0.755. The best deep learning (DL) model for radiomics and pathomics was the ResNet-50 model, with an AUC of 0.768 and 0.752, respectively. The nomogram graph showed that DL model contributed the most, and the AUC for the combined model was 0.86. The calibration curves and DCA indicate that the combined model had a good calibration ability and net clinical benefit. The KM curve indicated that the model integrating multimodal data can guide patient prognosis and management strategies. Conclusion: The integration of multimodal data effectively improves the prediction of risk for the progression of PCa to CRPC.

Deep learning algorithm-based multimodal MRI radiomics and pathomics data improve prediction of bone metastases in primary prostate cancer.

PURPOSE: Bone metastasis is a significant contributor to morbidity and mortality in advanced prostate cancer, and early diagnosis is challenging due to its insidious onset. The use of machine learning to obtain prognostic information from pathological images has been highlighted. However, there is a limited understanding of the potential of early prediction of bone metastasis through the feature combination method from various sources. This study presents a method of integrating multimodal data to enhance the feasibility of early diagnosis of bone metastasis in prostate cancer. METHODS AND MATERIALS: Overall, 211 patients diagnosed with prostate cancer (PCa) at Gansu Provincial Hospital between January 2017 and February 2023 were included in this study. The patients were randomized (8:2) into a training group (n = 169) and a validation group (n = 42). The region of interest (ROI) were segmented from the three magnetic resonance imaging (MRI) sequences (T2WI, DWI, and ADC), and pathological features were extracted from tissue sections (hematoxylin and eosin [H&E] staining, 10 × 20). A deep learning (DL) model using ResNet 50 was employed to extract deep transfer learning (DTL) features. The least absolute shrinkage and selection operator (LASSO) regression method was utilized for feature selection, feature construction, and reducing feature dimensions. Different machine learning classifiers were used to build predictive models. The performance of the models was evaluated using receiver operating characteristic curves. The net clinical benefit was assessed using decision curve analysis (DCA). The goodness of fit was evaluated using calibration curves. A joint model nomogram was eventually developed by combining clinically independent risk factors. RESULTS: The best prediction models based on DTL and pathomics features showed area under the curve (AUC) values of 0.89 (95% confidence interval [CI], 0.799-0.989) and 0.85 (95% CI, 0.714-0.989), respectively. The AUC for the best prediction model based on radiomics features and combining radiomics features, DTL features, and pathomics features were 0.86 (95% CI, 0.735-0.979) and 0.93 (95% CI, 0.854-1.000), respectively. Based on DCA and calibration curves, the model demonstrated good net clinical benefit and fit. CONCLUSION: Multimodal radiomics and pathomics serve as valuable predictors of the risk of bone metastases in patients with primary PCa.

A prognostic signature based on seven T-cell-related cell clustering genes in bladder urothelial carcinoma.

Bladder urothelial carcinoma (BLCA) is one of the most common cancer-related deaths in the world, along with high mortality. Due to the difficult detection of early symptoms, the treatment for this disease is still dissatisfactory. Thus, the current research hotspot is beginning to focus on the immune microenvironment in this disease, aiming to provide guidance for diagnosis and treatment. In this study, the single-cell RNA sequencing data downloaded from the gene expression omnibus database was used to classify the immune cells of BLCA. And the final seven T-cell-related cell clustering genes associated with BLCA prognosis (HSPA2, A2M, JUN, PDGFRB, GBP2, LGALS1, and GAS6) were screened out, and then used for constructing the prognostic model against BLCA based on the Cox and LASSO regression analysis. Satisfactorily, the model could efficiently evaluate the overall survival of BLCA and had the potential to be applied for the clinic treatment. Moreover, we also revealed that the difference in immune infiltration levels and gene mutation might account for the diverse prognosis in BLCA patients. In a word, our findings provided a novel insight for designing efficient immunotherapies for BLCA.

COVID-19 Vaccine in Renal Transplant Recipients: A Bibliometric-Based Analysis of Trends.

BACKGROUND: The global community has been affected by COVID-19, which emerged in December 2019. Since then, many studies have been conducted on kidney transplant recipients (KTRs) and COVID-19. This study aimed to perform a bibliometric and visual analysis of the published relationship between KTRs and COVID-19. OBJECTIVE: To discuss the current status, hot spots, and development trend of research on KTRs vaccination with the COVID-19 vaccine and to provide a reference for researchers in related fields. METHODS: Visual analysis of countries/regions, institutions, authors, references cited, and keywords for 2020 to 2023 via Microsoft Office Excel 2019 and CiteSpace (6.1.R6) based on the Web of Science core database. RESULTS: A total of 366 publications were included after screening, with a rapid increase in the global literature studying the COVID-19 vaccine of KTRs. The US has the highest number of publications, indicating that it is the leading country in this field of research. Charite University of Medicine Berlin and Schrezenmeier E are the most published institutions and authors, respectively. "Antibody Response After a Third Dose of the messenger RNA-1273 SARS-CoV-2 Vaccine in Kidney Transplant Recipients With Minimal Serologic Response to 2 Doses" is the most central co-cited reference; The keywords "kidney transplant recipient," "covid 19 vaccine," and "mortality" have become hot topics of research. The keywords "humoral response" and "bnt162b2" are the latest research frontiers for detecting bursts. CONCLUSIONS: This paper analyzed the current status and trends of vaccination studies in KTRs through bibliometric analysis. Several studies support the vaccination of KTRs with the COVID-19 vaccine. However, the evidence for improving vaccine efficacy by adjustment of immunosuppression is still limited, and future studies on vaccination will remain a hot topic in this field.

Multiparametric MRI radiomics in prostate cancer for predicting Ki-67 expression and Gleason score: a multicenter retrospective study.

PURPOSE: Prostate cancer (PCa) with high Ki-67 expression and high Gleason Scores (GS) tends to have aggressive clinicopathological characteristics and a dismal prognosis. In order to predict the Ki-67 expression status and the GS in PCa, we sought to construct and verify MRI-based radiomics signatures. METHODS AND MATERIALS: We collected T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) images from 170 PCa patients at three institutions and extracted 321 original radiomic features from each image modality. We used support vector machine (SVM) and least absolute shrinkage and selection operator (LASSO) logistic regression to select the most informative radiomic features and built predictive models using up sampling and feature selection techniques. Using receiver operating characteristic (ROC) analysis, the discriminating power of this feature was determined. Subsequent decision curve analysis (DCA) assessed the clinical utility of the radiomic features. The Kaplan-Meier (KM) test revealed that the radiomics-predicted Ki-67 expression status and GS were prognostic factors for PCa survival. RESULT: The hypothesized radiomics signature, which included 15 and 9 selected radiomics features, respectively, was significantly correlated with pathological Ki-67 and GS outcomes in both the training and validation datasets. Areas under the curve (AUC) for the developed model were 0.813 (95% CI 0.681,0.930) and 0.793 (95% CI 0.621, 0.929) for the training and validation datasets, respectively, demonstrating discrimination and calibration performance. The model's clinical usefulness was verified using DCA. In both the training and validation sets, high Ki-67 expression and high GS predicted by radiomics using SVM models were substantially linked with poor overall survival (OS). CONCLUSIONS: Both Ki-67 expression status and high GS correlate with PCa patient survival outcomes; therefore, the ability of the SVM classifier-based model to estimate Ki-67 expression status and the Lasso classifier-based model to assess high GS may enhance clinical decision-making.

Adipocyte-derived extracellular vesicles: bridging the communications between obesity and tumor microenvironment.

By the year 2035 more than 4 billion people might be affected by obesity and being overweight. Adipocyte-derived Extracellular Vesicles (ADEVs/ADEV-singular) are essential for communication between the tumor microenvironment (TME) and obesity, emerging as a prominent mechanism of tumor progression. Adipose tissue (AT) becomes hypertrophic and hyperplastic in an obese state resulting in insulin resistance in the body. This modifies the energy supply to tumor cells and simultaneously stimulates the production of pro-inflammatory adipokines. In addition, obese AT has a dysregulated cargo content of discharged ADEVs, leading to elevated amounts of pro-inflammatory proteins, fatty acids, and carcinogenic microRNAs. ADEVs are strongly associated with hallmarks of cancer (proliferation and resistance to cell death, angiogenesis, invasion, metastasis, immunological response) and may be useful as biomarkers and antitumor therapy strategy. Given the present developments in obesity and cancer-related research, we conclude by outlining significant challenges and significant advances that must be addressed expeditiously to promote ADEVs research and clinical applications.

Association between multiple sclerosis and cancer risk: An extensive review/meta and Mendelian randomization analyses.

BACKGROUND: Observational investigations examining cancer risk among multiple sclerosis (MS) patients have produced contradictory findings. Herein, we performed an extensive review and meta-analysis to evaluate the correlation and causation between MS and cancer incidence. METHODS: We systematically screened for published articles examining cancer incidences among MS patients within the Cochrane Library, PubMed, and Embase databases. Next, we employed STATA v.16.0 for data analysis. Following meta-analysis, we performed a two-sample Mendelian randomization (MR) analysis to uncover the underlying mechanism behind the MS-mediated regulation of certain cancers. RESULTS: Overall, we selected 18 articles encompassing 14 individual cancers incidences and a total of 368,952 patients for meta-analysis. Based on our analysis, there was reduced pancreatic (ES = 0.68; 95% CI: 0.49-0.93; I 2 = 0%) and ovarian cancer (ES = 0.65; 95% CI: 0.53-0.80; I 2 = 86.7%) co-occurrences among MS patients. Meanwhile, the incidences of breast (ES = 1.10; 95% CI: 1.01-1.21; I 2 = 60.9%) and brain cancers (ES = 1.94; 95% CI: 1.12-3.37; I 2 = 56.1%) were elevated among the same population. However, MR analysis revealed the opposite relation between MS and breast cancer risk (OR = 0.94392; 95% CI: 0.91011-0.97900, P = 0.002). Moreover, it revealed strong incidence of lung cancer (OR = 1.0004; 95% CI: 1.0001-1.0083, P = 0.001) among MS patients, as evidenced by the inverse variance weighting estimator. Lastly, MR found that other forms of cancers were not significantly related to MS. CONCLUSIONS: Using meta-analysis, we demonstrated that MS patients exhibited enhanced pancreatic and ovarian cancer risk, and diminished breast and brain cancer risk. However, using MR analysis, we discovered an inverse relation between MS and breast cancer risk, and additionally saw an uptick in lung cancer co-occurrence among MS patients.

Progress in the study of biomarkers for early prediction of systemic inflammatory response syndrome after percutaneous nephrolithotomy.

Urolithiasis is a common and frequent disease in urology. Percutaneous nephrolithotomy (PCNL) is preferred for the treatment of upper urinary tract stones and complicated renal stones >2 cm in diameter, but it has a higher rate of postoperative complications, especially infection, compared with other minimally invasive treatments for urinary stones. Complications associated with infection after percutaneous nephrolithotomy include transient fever, systemic inflammatory response syndrome (SIRS), and sepsis, which is considered one of the most common causes of perioperative death after percutaneous nephrolithotomy. In contrast, SIRS serves as a sentinel for sepsis, so early intervention of SIRS by biomarker identification can reduce the incidence of postoperative sepsis, which in turn reduces the length of stay and hospital costs for patients. In this paper, we summarize traditional inflammatory indicators, novel inflammatory indicators, composite inflammatory indicators and other biomarkers for early identification of systemic inflammatory response syndrome after percutaneous nephrolithotomy.

The functional roles of m6A modification in prostate cancer.

Prostate cancer (PCa) is the most prevalent malignancy of the male genitourinary system, and its etiology suggests that genetics is an essential risk factor for its development and progression, while exogenous factors may have an significant impact on this risk. Initial diagnosis of advanced PCa is relatively frequent, and androgen deprivation therapy (ADT) is the predominant standard of care for PCa and the basis for various novel combination therapy regimens, and is often required throughout the patient's subsequent treatment. Although diagnostic modalities and treatment options are evolving, some patients suffer from complications, including biochemical relapse, metastasis and treatment resistance. Mechanisms of PCa pathogenesis and progression have been the focus of research. N6-methyladenosine (m6A) is an RNA modification involved in cell physiology and tumor metabolism. It has been observed to affect the evolution of diverse cancers through the regulation of gene expression. Genes associated with m6A are prominent in PCa and are involved in multiple aspects of desmoresistant PCa occurrence, progression, PCa bone metastasis (BM), and treatment resistance. Here, we explore the role of m6A modifications in promoting PCa.

Advances in cancer vaccines for immunotherapy of prostate cancer. / å‰åˆ—è ºç™Œå ç–«æ²»ç–—ä¸­ç™Œç—‡ç–«è‹—çš„ç ”ç©¶è¿›å±•.

Prostate cancer is currently one of the most common malignancies that endanger the lives and health of elderly men. In recent years, immunotherapy, which exploits the activation of anti-cancer host immune cells to accomplish tumor-killing effects, has emerged as a new study avenue in the treatment of prostate cancer. As an important component of immunotherapy, cancer vaccines have a unique position in the precision treatment of malignant tumors. Monocyte cell vaccines, dendritic cell vaccines, viral vaccines, peptide vaccines, and DNA/mRNA vaccines are the most often used prostate cancer vaccines. Among them, Sipuleucel-T, as a monocyte cell-based cancer vaccine, is the only FDA-approved therapeutic vaccine for prostate cancer, and has a unique position and role in advancing the development of immunotherapy for prostate cancer. However, due to its own limitations, Sipuleucel-T has not been widely adopted. Meanwhile, owing to the complexity of immunotherapy and the specificity of prostate cancer, the remaining prostate cancer vaccines have not shown good clinical benefit in large randomized phase II and phase III trials, and further in-depth studies are still needed.

Diagnostic value of 18F-PSMA-1007 PET/CT combined with prostate specific antigen derived indicators in gray area prostate cancer. / 18F-PSMA-1007 PET/CTè”åˆå‰åˆ—è ºç‰¹å¼‚æ€§æŠ—åŽŸè¡ç”ŸæŒ‡æ ‡å¯¹ç°åŒºå‰åˆ—è ºç™Œçš„è¯Šæ–­ä»·å€¼.

OBJECTIVES: The incidence of prostate cancer is increasing every year, and precision diagnosis and treatment can help reduce unnecessary prostate punctures for prostate cancer patients in the gray area. This study aims to investigate the diagnostic value of 18F-prostate specific membrane antigen (PSMA) imaging combined with prostate specific antigen (PSA)-derived indicators for gray zone prostate cancer. METHODS: A total of 107 patients who underwent 18F-PSMA PET/CT imaging for suspicious prostate cancer with tPSA of 4 to 10 µg/L (PSA gray zone) in a hospital were retrospectively included, and were divided into a prostate cancer group and a non-prostate cancer group based on pathological findings. Patients underwent PSA testing, 18F-PSMA, and abdominal ultrasound, and age, tPSA, fPSA, f/tPSA, prostate volume, PSA density (PSAD), maximum standardized uptake value (SUVmax), and molecular imaging prostate specific membrane antigen (miPSMA) score were compared between the 2 groups. Multivariate logistic regression was used to analyze the influencing factors the diagnosis of gray zone prostate cancer. Receiver operating characteristic (ROC) curves were constructed to evaluate the efficacy of PSAD and SUVmax alone and in combination in diagnosing gray zone prostate cancer. RESULTS: The volume of the prostate cancer group [42.00(34.00, 58.00) cm3 vs 49.00(41.27, 60.41) cm3] was smaller than that of the non-prostate cancer group (Z=-2.376, P=0.017), and the PSAD [(0.18±0.06) µg/(L·cm3) vs 0.15±0.05 µg/(L·cm3)] and SUVmax [18.63(8.03, 28.57) vs 9.33(5.90, 13.52)] were higher than those in the non-prostate cancer group (both P<0.05). The percentage of miPSMA score ≥2 in the prostate cancer group was higher than that in the non-prostate cancer group (χ2=40.987, P<0.001). PSAD (OR=22.154, 95% CI 1.430 to 873.751, P=0.042) and SUVmax (OR=1.301, 95% CI 1.034 to 1.678, P=0.009) were independent influential factors for the diagnosis of prostate cancer in the gray zone. The optimal cut-off values of PSAD and SUVmax were 0.22 µg/(L·cm3) and 8.02, respectively, and the AUCs for the diagnosis of prostate cancer in the gray zone alone and in combination were 0.628 (95% CI 0.530 to 0.720, P<0.05) and 0.806 (95% CI 0.718 to 0.876, P<0.05), 0.847 (95% CI 0.765 to 0.910, P<0.05), with sensitivities of 41.03%, 76.92%, and 74.36% and specificities of 79.41%, 89.71%, and 92.65%, respectively. CONCLUSIONS: PSAD and SUVmax are increased in patients with gray zone prostate cancer, and the combination of PSAD and SUVmax is of high value in diagnosing gray zone prostate cancer.

Inflammation and tumor microenvironment. / 炎症与肿瘤微环境.

There is a connection between inflammation and cancer. Inflammation is one of the hallmarks of cancer, affecting tumor progression, transition to a malignant phenotype, and the efficacy of tumor chemotherapy. The tumor microenvironment impacts the biological characteristics of tumors through various specific factors and signaling mechanisms. The interaction between inflammation and the tumor microenvironment involves inflammation affecting the tumor microenvironment by inducing immune suppression, while acute inflammation promotes tumor suppression by producing anti-tumor immune responses. This review elaborates on how inflammation affects the tumor microenvironment and thus affects the progression and treatment of tumors, starting from the components of the tumor microenvironment, inflammasomes, cytokines, non-coding RNAs, and other aspects. Inflammatory factors play an important role in regulating inflammatory responses and immune reactions, and they also affect the development of tumors through various pathways in the tumor microenvironment. In addition, non-coding RNAs play an important role in the tumor microenvironment, regulating tumors and inflammation. They are involved in regulating the occurrence, development of tumors, the process of inflammation, as well as regulating inflammation-induced cancer or tumor-related inflammation, and the interaction between the tumor microenvironment, inflammatory factors, and immune cells. Therefore, gaining a deeper understanding of the interaction between inflammation and the tumor microenvironment and its connection to the occurrence and development of cancer can provide a theoretical basis for combating tumors and finding new therapeutic strategies.