Objectives The relationship between the A240T polymorphism in the angiotensin-converting enzyme ( ACE) gene and cancer risk remains controversial. Therefore, we conducted a meta-analysis of relevant studies from the published literature. Methods We comprehensively searched available databases to identify eligible studies on the relationship of ACE A240T polymorphism with cancer risk. We calculated pooled odds ratios (OR) with 95% confidence intervals (CI) and then evaluated heterogeneity and publication bias. Results Eight case-control studies were identified from five articles. Results showed that the ACE A240T polymorphism was related to cancer risk (AT vs AA: OR 2.14, 95% CI: 1.51–3.04; TT vs AA: OR 1.07, 95% CI: 0.90–1.27; recessive model: OR 0.48, 95% CI: 0.31–0.77; dominant model: OR 2.13, 95% CI: 1.54–2.97). The same conclusion was made for subgroup analysis by race or cancer type. In the subgroup analysis by quality score assessment, the ACE A240T polymorphism contributed to cancer risk in high-quality studies but not in low-quality studies. Conclusion The A240T polymorphism in the ACE gene might be related to the risk of cancer. Nevertheless, large-scale studies should be performed to obtain convincing evidence on the roles of ACE A240T polymorphism on cancer risk.

Objectives A sample with a blood clot may produce an inaccurate outcome in coagulation testing, which may mislead clinicians into making improper clinical decisions. Currently, there is no efficient method to automatically detect clots. This study demonstrates the feasibility of utilizing machine learning (ML) to identify clotted specimens. Methods The results of coagulation testing with 192 clotted samples and 2,889 no-clot-detected (NCD) samples were retrospectively retrieved from a laboratory information system to form the training dataset and testing dataset. Standard and momentum backpropagation neural networks (BPNNs) were trained and validated using the training dataset with a five-fold cross-validation method. The predictive performances of the models were then assessed based on the testing dataset. Results Our results demonstrated that there were intrinsic distinctions between the clotted and NCD specimens regarding differences in the testing results and the separation of the groups (clotted and NCD) in the t-SNE analysis. The standard and momentum BPNNs could identify the sample status (clotted and NCD) with areas under the ROC curves of 0.966 (95% CI, 0.958–0.974) and 0.971 (95% CI, 0.9641–0.9784), respectively. Conclusions Here, we have described the application of ML algorithms in identifying the sample status based on the results of coagulation testing. This approach provides a proof-of-concept application of ML algorithms to evaluate the sample quality, and it has the potential to facilitate clinical laboratory automation.