Comparing deep neural network and other machine learning algorithms for stroke prediction in a large-scale population-based electronic medical claims database.

Electronic medical claims (EMCs) can be used to accurately predict the occurrence of a variety of diseases, which can contribute to precise medical interventions. While there is a growing interest in the application of machine learning (ML) techniques to address clinical problems, the use of deep-learning in healthcare have just gained attention recently. Deep learning, such as deep neural network (DNN), has achieved impressive results in the areas of speech recognition, computer vision, and natural language processing in recent years. However, deep learning is often difficult to comprehend due to the complexities in its framework. Furthermore, this method has not yet been demonstrated to achieve a better performance comparing to other conventional ML algorithms in disease prediction tasks using EMCs. In this study, we utilize a large population-based EMC database of around 800,000 patients to compare DNN with three other ML approaches for predicting 5-year stroke occurrence. The result shows that DNN and gradient boosting decision tree (GBDT) can result in similarly high prediction accuracies that are better compared to logistic regression (LR) and support vector machine (SVM) approaches. Meanwhile, DNN achieves optimal results by using lesser amounts of patient data when comparing to GBDT method.

Enhancement of bioactivity on medical polymer surface using high power impulse magnetron sputtered titanium dioxide film.

This study utilizes a novel technique, high power impulse magnetron sputtering (HIPIMS), which provides a higher ionization rate and ion bombardment energy than direct current magnetron sputtering (DCMS), to deposit high osteoblast compatible titanium dioxide (TiO2) coatings with anatase (A-TiO2) and rutile (R-TiO2) phases onto the biomedical polyetheretherketone (PEEK) polymer substrates at low temperature. The adhesions of TiO2 coatings that were fabricated using HIPIMS and DCMS were compared. The in vitro biocompatibility of these coatings was confirmed. The results reveal that HIPIMS can be used to prepare crystallinic columnar A-TiO2 and R-TiO2 coatings on PEEK substrate if the ratio of oxygen to argon is properly controlled. According to a tape adhesion test, the HIPIMS-TiO2 coatings had an adhesion grade of 5B even after they were immersed in simulated body fluid (SBF) environments for 28days. Scratch tests proved that HIPIMS-TiO2 coatings undergo cohesive failure. These results demonstrate that the adhesive force between HIPIMS-TiO2 coating/PEEK is stronger than that between DCMS-TiO2 coating/PEEK. After a long period (28days) of immersion in SBF, a bone-like crystallinic hydroxyapatite layer with a corresponding Ca/P stoichiometry was formed on both HIPIMS-TiO2. The osteoblast compatibility of HIPIMS-TiO2 exceeded that of the bare PEEK substrate. It is also noticeable that the R-TiO2 performed better in vitro than the A-TiO2 due to the formation of many negatively charged hydroxyl groups (-OH(-)) groups on R-TiO2 (110) surface. In summary, the HIPIMS-TiO2 coatings satisfied the requirements for osseointegration, suggesting the possibility of using HIPIMS to modify the PEEK surface with TiO2 for spinal implants.

Antimicrobial brass coatings prepared on poly(ethylene terephthalate) textile by high power impulse magnetron sputtering.

The goal of this work is to prepare antimicrobial, corrosion-resistant and low-cost Cu65Zn35 brass film on poly(ethylene terephthalate) (PET) fabric by high-power impulse magnetron sputtering (HIPIMS), which is known to provide high-density plasma, so as to generate a strongly adherent film at a reduced substrate temperature. The results reveal that the brass film grows in a layer-plus-island mode. Independent of their deposition time, the obtained films retain a Cu/Zn elemental composition ratio of 1.86 and exhibit primarily an α copper phase structure. Oxygen plasma pre-treatment for 1min before coating can significantly increase film adhesion such that the brass-coated fabric of Grade 5 or Grade 4-5 can ultimately be obtained under dry and wet rubbing tests, respectively. However, a deposition time of 1min suffices to provide effective antimicrobial properties for both Staphylococcus aureus and Escherichia coli. As a whole, the feasibility of using such advanced HIPIMS coating technique to develop durable antimicrobial textile was demonstrated.

Statin Therapy for Primary Prevention of Atrial Fibrillation: Guided by CHADS2/CHA2DS2VASc Score

Atrial fibrillation (AF) is the most common arrhythmia and is associated with increased cardiovascular morbidity and mortality. The anti-arrhythmic effect of statins on AF prevention appears to be highly significant in most clinical studies. However, some discrepancies do exist among different clinical studies. Different clinical settings and types of stains used may explain these differences between trials. The CHADS2 and CHA2DS2VASc scoring systems have been used for stroke risk stratification in AF patients. The recent study suggested that these scores can also be used to guide statin therapy for AF prevention. Patients with higher scores had a higher risk of developing AF and gained more benefits from statins therapy than those with lower scores. This review article focused on the ability of these scores to predict AF prevention by statins.