Artificial intelligence for the diagnosis of clinically significant prostate cancer based on multimodal data: a multicenter study.

BACKGROUND: The introduction of multiparameter MRI and novel biomarkers has greatly improved the prediction of clinically significant prostate cancer (csPCa). However, decision-making regarding prostate biopsy and prebiopsy examinations is still difficult. We aimed to establish a quick and economic tool to improve the detection of csPCa based on routinely performed clinical examinations through an automated machine learning platform (AutoML). METHODS: This study included a multicenter retrospective cohort and two prospective cohorts with 4747 cases from 9 hospitals across China. The multimodal data, including demographics, clinical characteristics, laboratory tests, and ultrasound reports, of consecutive participants were retrieved using extract-transform-load tools. AutoML was applied to explore potential data processing patterns and the most suitable algorithm to build the Prostate Cancer Artificial Intelligence Diagnostic System (PCAIDS). The diagnostic performance was determined by the receiver operating characteristic curve (ROC) for discriminating csPCa from insignificant prostate cancer (PCa) and benign disease. The clinical utility was evaluated by decision curve analysis (DCA) and waterfall plots. RESULTS: The random forest algorithm was applied in the feature selection, and the AutoML algorithm was applied for model establishment. The area under the curve (AUC) value in identifying csPCa was 0.853 in the training cohort, 0.820 in the validation cohort, 0.807 in the Changhai prospective cohort, and 0.850 in the Zhongda prospective cohort. DCA showed that the PCAIDS was superior to PSA or fPSA/tPSA for diagnosing csPCa with a higher net benefit for all threshold probabilities in all cohorts. Setting a fixed sensitivity of 95%, a total of 32.2%, 17.6%, and 26.3% of unnecessary biopsies could be avoided with less than 5% of csPCa missed in the validation cohort, Changhai and Zhongda prospective cohorts, respectively. CONCLUSIONS: The PCAIDS was an effective tool to inform decision-making regarding the need for prostate biopsy and prebiopsy examinations such as mpMRI. Further prospective and international studies are warranted to validate the findings of this study. TRIAL REGISTRATION: Chinese Clinical Trial Registry ChiCTR2100048428. Registered on 06 July 2021.

The epiphany derived from T-cell-inflamed profiles: Pan-cancer characterization of CD8A as a biomarker spanning clinical relevance, cancer prognosis, immunosuppressive environment, and treatment responses.

CD8A encodes the CD8 alpha chain of αßT cells, which has been proposed as a quantifiable indicator for the assessment of CD8+ cytotoxic T lymphocytes (CTLs) recruitment or activity and a robust biomarker for anti-PD-1/PD-L1 therapy responses. Nonetheless, the lack of research into the role of CD8A in tumor microenvironment predisposes to limitations in its clinical utilization. In the presented study, multiple computational tools were used to investigate the roles of CD8A in the pan-cancer study, revealing its essential associations with tumor immune infiltration, immunosuppressive environment formation, cancer progression, and therapy responses. Based on the pan-cancer cohorts of the Cancer Genome Atlas (TCGA) database, our results demonstrated the distinctive CD8A expression patterns in cancer tissues and its close associations with the prognosis and disease stage of cancer. We then found that CD8A was correlated with six major immune cell types, and immunosuppressive cells in multiple cancer types. Besides, epigenetic modifications of CD8A were related to CTL levels and T cell dysfunctional states, thereby affecting survival outcomes of specific cancer types. After that, we explored the co-occurrence patterns of CD8A mutation, thus identifying RMND5A, RNF103-CHMP3, CHMP3, CD8B, MRPL35, MAT2A, RGPD1, RGPD2, REEP1, and ANAPC1P1 genes, which co-occurred mutations with CD8A, and are concomitantly implicated in the regulation of cancer-related pathways. Finally, we tested CD8A as a therapeutic biomarker for multiple antitumor agents' or compounds' responsiveness on various cancer cell lines and cancer cohorts. Our findings denoted the underlying mechanics of CD8A in reflecting the T-cell-inflamed profiles, which has potential as a biomarker in cancer diagnosis, prognosis, and therapeutic responses.

Molecular Mechanism of MicroRNA-200c Regulating Transforming Growth Factor-ß (TGF-ß)/SMAD Family Member 3 (SMAD3) Pathway by Targeting Zinc Finger E-Box Binding Homeobox 1 (ZEB1) in Hypospadias in Rats.

BACKGROUND The aim of this study was to explore effects of microRNA-200c regulating TGF-ß/Smad3 pathway by targeting Zeb1 on the occurrence and development of hypospadias and to evaluate the relationship between microRNA-200c and occurrence of hypospadias. MATERIAL AND METHODS Pregnant rats with a gestational age of 12 days were allocated into 2 groups; one received gavage of DEHP-contained soybean oil (1 ml/day, 8 days; Group A) and the other had gavage of normal soybean oil (1 ml/day, 8 days; Group B). Baby rats with hypospadias from Group A were assigned to the model group (n=20) and healthy baby rats from Group B were assigned to the control group (n=20). Real-time quantitative polymerase chain reaction (qRT-PCR), immunohistochemistry and Western blot analysis were performed to detect microRNA-200c, Zeb1, TGF-ß, and Smad3 mRNA and protein expressions in the model group (n=20) and the control group (n=20). The relationship between microRNA-200c and Zeb1 was detected using a dual-luciferase reporter gene experiment. After the in vitro intervention experiment in fetal rat penises, Western blot was used to detect the expression of Zeb1, TGF-ß, and Smad3. RESULTS In the model group, microRNA-200c was expressed at a low level, and microRNA-200c expression in control group was 2.1 times higher than in the model group (P<0.05). When compared with the control group, mRNA expressions, protein expressions, and positive rates of Zeb1, TGF-ß, and Smad3 were higher in the model group (all P<0.01). Luciferase gene report determined that Zeb1 is a target gene of microRNA-200c. The in vitro intervention experiment in fetal rat penises found that a high concentration of microRNA-200c inhibited hypospadias occurrence by suppressing the expression of Zeb1, TGF-ß, and Smad3. CONCLUSIONS MicroRNA-200c was expressed in hypospadias penis tissues at low levels and was negatively correlated with Zeb1 expression. MicroRNA-200c up-regulated Zeb1 expression to regulate the TGF-ß/Smad3 pathway, which led to the occurrence of hypospadias.

Role of metabolic factors in the association between osteocalcin and testosterone in Chinese men.

OBJECTIVE: Osteocalcin can regulate energy metabolism and increase testosterone production. Although previous studies have shown the positive association between osteocalcin and testosterone, the effect of metabolic factors in the association is unclear. DESIGN AND SETTING: Osteocalcin, testosterone, and metabolic factors were accessed in 2400 men aged 20 to 69 years, who participated in the population-based Fangchenggang Area Male Health and Examination Survey in Guangxi province of China from September 2009 to December 2009. MAIN OUTCOME MEASURES: Metabolic syndrome was defined based on the updated report of National Cholesterol Education Program Adult Treatment Panel III criteria. Serum total osteocalcin, total testosterone (TT), and sex hormone binding globulin (SHBG) were measured, whereas free testosterone (FT) and bioavailable testosterone (BT) were calculated based on Vermeulen's formula. The multivariable linear regression analysis was used. RESULTS: Osteocalcin was positively associated with TT, FT, and BT in the unadjusted model (all P < .001). After adjusting for age, the positive association between osteocalcin and TT remained statistically significant (ß = .17, 95% confidence interval = 0.14-0.20) and was not attenuated in each MetS subgroup including hypertriglyceridemia, hyperglycemia, elevated blood pressure, and low high-density lipoprotein cholesterol, while in the group of central obesity (waist circumstance ≥90 cm), the association appeared significantly stronger (ß = 0.21, 95% confidence interval = 0.12-0.30). After further adjusting for SHBG, osteocalcin was positively associated with TT, FT, and BT in men with central obesity or men with any two MetS components (all P < .05). CONCLUSIONS: Serum total osteocalcin is positively associated with testosterone, which is probably modified by SHBG and central obesity.