Machine learning models of clinically relevant biomarkers for the prediction of stable obstructive coronary artery disease.

Background: In patients with suspected obstructive coronary artery disease (CAD), evaluation using a pre-test probability model is the key element for diagnosis; however, its accuracy is controversial. This study aimed to develop machine learning (ML) models using clinically relevant biomarkers to predict the presence of stable obstructive CAD and to compare ML models with an established pre-test probability of CAD models. Methods: Eight machine learning models for prediction of obstructive CAD were trained on a cohort of 1,312 patients [randomly split into the training (80%) and internal validation sets (20%)]. Twelve clinical and blood biomarker features assessed on admission were used to inform the models. We compared the best-performing ML model and established the pre-test probability of CAD (updated Diamond-Forrester and CAD consortium) models. Results: The CatBoost algorithm model showed the best performance (area under the receiver operating characteristics, AUROC, 0.796, and 95% confidence interval, CI, 0.740-0.853; Matthews correlation coefficient, MCC, 0.448) compared to the seven other algorithms. The CatBoost algorithm model improved risk prediction compared with the CAD consortium clinical model (AUROC 0.727; 95% CI 0.664-0.789; MCC 0.313). The accuracy of the ML model was 74.6%. Age, sex, hypertension, high-sensitivity cardiac troponin T, hemoglobin A1c, triglyceride, and high-density lipoprotein cholesterol levels contributed most to obstructive CAD prediction. Conclusion: The ML models using clinically relevant biomarkers provided high accuracy for stable obstructive CAD prediction. In real-world practice, employing such an approach could improve discrimination of patients with suspected obstructive CAD and help select appropriate non-invasive testing for ischemia.

Preparation, characterization, and application of TiO2-patterned polyimide film as a photocatalyst for oxidation of organic contaminants.

Photocatalytically active TiO2-patterned polyimide (PI) films (PI-TiO2) were fabricated using thermal transfer patterning (TTP). When subjected to hot pressing, the TiO2 nanoparticles electrosprayed on steel mesh templates were successfully transferred and formed checker plate patterns on PI film. FE-SEM studies confirmed that pressing at 350°C and 100MPa was optimum for obtaining patterns with uniform TiO2 coverage. When the quantity of TiO2 on the template increased, the amount of it immobilized on PI film also increased from 0.3245 to 1.2378mg per 25cm2. XPS studies confirmed the presence TiO2 on the patterns, and indicated the formation of carboxylic acid and amide groups on the PI surface during TTP. When tested under UVA irradiation, PI-TiO2 with 1.2378mg/25cm2 TiO2 loading exhibited the highest photocatalytic performance for methylene blue (10µM) degradation, with a rate constant of 0.0225min-1 and stable photocatalytic efficacy for 25 cycles of reuse. The PI-TiO2 was also successfully used to degrade amoxicillin, atrazine, and 4-chlorophenol. During photocatalysis, the toxicity of 4-chlorophenol against Vibrio fischeri and the antibiotic activity of amoxicillin against Escherichia coli were decreased. Overall, TTP was found to be a potentially scalable method for fabricating robust immobilized TiO2 photocatalyst.

Complete atrioventricular block secondary to bortezomib use in multiple myeloma.

Bortezomib is an inhibitor of 26S proteasome, which is an effective treatment for multiple myeloma. The common adverse effects of bortezomib are asthenic conditions, gastrointestinal disturbances, and peripheral neuropathy. Here we describe a patient with dyspnea and general weakness because of complete atrioventricular block while receiving bortezomib. We immediately stopped bortezomib, and after inserting a permanent VDD pacemaker, the patients' symptoms disappeared.