Bladder cancer has been increasing globally. Urinary cytology is considered a major screening method for bladder cancer, but it has poor sensitivity. This study aimed to utilize clinical laboratory data and machine learning methods to build predictive models of bladder cancer. A total of 1336 patients with cystitis, bladder cancer, kidney cancer, uterus cancer, and prostate cancer were enrolled in this study. Two-step feature selection combined with WEKA and forward selection was performed. Furthermore, five machine learning models, including decision tree, random forest, support vector machine, extreme gradient boosting (XGBoost), and light gradient boosting machine (GBM) were applied. Features, including calcium, alkaline phosphatase (ALP), albumin, urine ketone, urine occult blood, creatinine, alanine aminotransferase (ALT), and diabetes were selected. The lightGBM model obtained an accuracy of 84.8% to 86.9%, a sensitivity 84% to 87.8%, a specificity of 82.9% to 86.7%, and an area under the curve (AUC) of 0.88 to 0.92 in discriminating bladder cancer from cystitis and other cancers. Our study provides a demonstration of utilizing clinical laboratory data to predict bladder cancer.

Altered metabolism is a hallmark of aging. The tricarboxylic acid cycle (TCA cycle) is an essential metabolic pathway and plays an important role in lifespan regulation. Supplementation of α-ketoglutarate, a metabolite converted by isocitrate dehydrogenase alpha-1 (idha-1) in the TCA cycle, increases lifespan in C. elegans. However, whether idha-1 can regulate lifespan in C. elegans remains unknown. Here, we reported that the expression of idha-1 modulates lifespan and oxidative stress tolerance in C. elegans. Transgenic overexpression of idha-1 extends lifespan, increases the levels of NADPH/NADP⁺ ratio, and elevates the tolerance to oxidative stress. Conversely, RNAi knockdown of idha-1 exhibits the opposite effects. In addition, the longevity of eat-2 (ad1116) mutant via dietary restriction (DR) was reduced by idha-1 knockdown, indicating that idha-1 may play a role in DR-mediated longevity. Furthermore, idha-1 mediated lifespan may depend on the target of rapamycin (TOR) signaling. Moreover, the phosphorylation levels of S6 kinase (p-S6K) inversely correlate with idha-1 expression, supporting that the idha-1-mediated lifespan regulation may involve the TOR signaling pathway. Together, our data provide new insights into the understanding of idha-1 new function in lifespan regulation probably via DR and TOR signaling and in oxidative stress tolerance in C. elegans.

Deregulation of redox homeostasis is often associated with an accelerated aging process. Ribose-5-phosphate isomerase A (RPIA) mediates redox homeostasis in the pentose phosphate pathway (PPP). Our previous study demonstrated that Rpi knockdown boosts the healthspan in Drosophila. However, whether the knockdown of rpia-1, the Rpi ortholog in Caenorhabditis elegans, can improve the healthspan in C. elegans remains unknown. Here, we report that spatially and temporally limited knockdown of rpia-1 prolongs lifespan and improves the healthspan in C. elegans, reflecting the evolutionarily conserved phenotypes observed in Drosophila. Ubiquitous and pan-neuronal knockdown of rpia-1 both enhance tolerance to oxidative stress, reduce polyglutamine aggregation, and improve the deteriorated body bending rate caused by polyglutamine aggregation. Additionally, rpia-1 knockdown temporally in the post-developmental stage and spatially in the neuron display enhanced lifespan. Specifically, rpia-1 knockdown in glutamatergic or cholinergic neurons is sufficient to increase lifespan. Importantly, the lifespan extension by rpia-1 knockdown requires the activation of autophagy and AMPK pathways and reduced TOR signaling. Moreover, the RNA-seq data support our experimental findings and reveal potential novel downstream targets. Together, our data disclose the specific spatial and temporal conditions and the molecular mechanisms for rpia-1 knockdown-mediated longevity in C. elegans. These findings may help the understanding and improvement of longevity in humans.

Coronary artery disease (CAD) is one of the most common subtypes of cardiovascular disease. The progression of CAD initiates from the plaque of atherosclerosis and coronary artery stenosis, and eventually turns into acute myocardial infarction (AMI) or stable CAD. Alpha-1-antichymotrypsin (AACT) has been highly associated with cardiac events. In this study, we proposed incorporating clinical data on AACT levels to establish a model for estimating the severity of CAD. Thirty-six healthy controls (HCs) and 162 CAD patients with stenosis rates of 70% were included in this study. Plasma concentration of AACT was determined by enzyme-linked immunosorbent assay (ELISA). The receiver operating characteristic (ROC) curve analysis and associations were conducted. Further, five machine learning models, including decision tree, random forest, support vector machine, XGBoost, and lightGBM were implemented. The lightGBM model obtained a sensitivity of 81.4%, a specificity of 67.3%, and an area under the curve (AUC) of 0.822 for identifying CAD patients with a stenosis rate of 30%. In this study, we provided a demonstration of a monitoring model with clinical data and AACT.

Coronary artery disease (CAD) is a global health issue. Lipid peroxidation produces various by-products that associate with CAD, such as 4-hydroxynonenal (HNE) and malondialdehyde (MDA). The autoantibodies against HNE and MDA-modified peptides may be useful in the diagnosis of CAD. This study included 41 healthy controls (HCs) and 159 CAD patients with stenosis rates of 70%. The plasma level of autoantibodies against four different unmodified and HNE-modified peptides were measured in this study, including CFAH^1211–1230, HPT^78–108, IGKC^2–19, and THRB^328–345. Furthermore, feature ranking, feature selection, and machine learning models have been utilized to exploit the diagnostic performance. Also, we combined autoantibodies against MDA and HNE-modified peptides to improve the models’ performance. The eXtreme Gradient Boosting (XGBoost) model received a sensitivity of 78.6% and a specificity of 90.4%. Our study demonstrated the combination of autoantibodies against oxidative modification may improve the model performance.