A Machine Learning Model Based on Genetic and Traditional Cardiovascular Risk Factors to Predict Premature Coronary Artery Disease.

BACKGROUND: Premature coronary artery disease (PCAD) has a poor prognosis and a high mortality and disability rate. Accurate prediction of the risk of PCAD is very important for the prevention and early diagnosis of this disease. Machine learning (ML) has been proven a reliable method used for disease diagnosis and for building risk prediction models based on complex factors. The aim of the present study was to develop an accurate prediction model of PCAD risk that allows early intervention. METHODS: We performed retrospective analysis of single nucleotide polymorphisms (SNPs) and traditional cardiovascular risk factors (TCRFs) for 131 PCAD patients and 187 controls. The data was used to construct classifiers for the prediction of PCAD risk with the machine learning (ML) algorithms LogisticRegression (LRC), RandomForestClassifier (RFC) and GradientBoostingClassifier (GBC) in scikit-learn. Three quarters of the participants were randomly grouped into a training dataset and the rest into a test dataset. The performance of classifiers was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity and concordance index. R packages were used to construct nomograms. RESULTS: Three optimized feature combinations (FCs) were identified: RS-DT-FC1 (rs2259816, rs1378577, rs10757274, rs4961, smoking, hyperlipidemia, glucose, triglycerides), RS-DT-FC2 (rs1378577, rs10757274, smoking, diabetes, hyperlipidemia, glucose, triglycerides) and RS-DT-FC3 (rs1169313, rs5082, rs9340799, rs10757274, rs1152002, smoking, hyperlipidemia, high-density lipoprotein cholesterol). These were able to build the classifiers with an AUC >0.90 and sensitivity >0.90. The nomograms built with RS-DT-FC1, RS-DT-FC2 and RS-DT-FC3 had a concordance index of 0.94, 0.94 and 0.90, respectively, when validated with the test dataset, and 0.79, 0.82 and 0.79 when validated with the training dataset. Manual prediction of the test data with the three nomograms resulted in an AUC of 0.89, 0.92 and 0.83, respectively, and a sensitivity of 0.92, 0.96 and 0.86, respectively. CONCLUSIONS: The selection of suitable features determines the performance of ML models. RS-DT-FC2 may be a suitable FC for building a high-performance prediction model of PCAD with good sensitivity and accuracy. The nomograms allow practical scoring and interpretation of each predictor and may be useful for clinicians in determining the risk of PCAD.

Surface Modification of Stöber Silica Nanoparticles with Controlled Moiety Densities Determines Their Cytotoxicity Profiles in Macrophages.

Physicochemical properties of nanomaterials play important roles in determining their toxicological profiles during nano-biointeraction. Among them, surface modification is one of the most effective manners to tune the cytotoxicity induced by nanomaterials. However, currently, there is no consistency in surface modification including moiety types and quantities considering the conflicting toxicological profiles of particles across different studies. In this study, in order to systematically investigate how the moiety density affects cytotoxicity of NPs, we chose three different types of functional groups, that is, -NH2, -COOH, and -PEG, and further controlled their densities on modified Stöber silica nanoparticles (NPs). We demonstrated that densities of functional groups could significantly affect the cytotoxicities of Stöber silica NPs. Regardless of the types of functional groups, high grafting densities could ameliorate the cytotoxicities induced by Stöber silica NPs in macrophages, for example, J774A.1 and N9 cells. When equal amounts of functional groups were present, the cell viability increased in the order of -COOH < -NH2 < -PEG. Furthermore, it was shown that surface modification could significantly affect the quantities of the surface silanol, which is the determining factor that affects their cytotoxicity. These results show that it is critical to control the surface moiety both quantitatively and qualitatively, which can tune the interaction outcomes at the nano-bio interface. The results found in this article provide useful guidance to adjust nanomaterial cytotoxicity for safer biomedical applications.

Assessment of neurotoxicity induced by different-sized Stöber silica nanoparticles: induction of pyroptosis in microglia.

With the wide application of Stöber silica nanoparticles and their ability to access the brain, it is crucial to evaluate their neurotoxicity. In this study, we used three in vitro model cells, i.e., N9, bEnd.3 and HT22 cells, representing microglia, microendothelial cells and neurons, respectively, to assess the neurotoxicity of Stöber silica nanoparticles with different sizes. We found that Stöber silica nanoparticles almost had no effect on the viability of bEnd.3 and HT22 cells. In contrast, they induced size-dependent toxicity in N9 cells, which represent the residential macrophages of the central nervous system. Further mechanistic study demonstrated that the toxicity in N9 cells was related to their surface silanol display. In addition, we demonstrated that Stöber silica nanoparticles induced the production of mitochondrial ROS, release of IL-1ß, cleavage of GSDMD, and occurrence of pyroptosis in N9 cells. Features of pyroptosis were also observed in primary microglia and macrophage J774A.1. In conclusion, these findings were helpful for the safety consideration of Stöber silica nanoparticles considering their wide applications in our daily life.

The neurotoxicity induced by engineered nanomaterials.

Engineered nanomaterials (ENMs) have been widely used in various fields due to their novel physicochemical properties. However, the use of ENMs has led to an increased exposure in humans, and the safety of ENMs has attracted much attention. It is universally acknowledged that ENMs could enter the human body via different routes, eg, inhalation, skin contact, and intravenous injection. Studies have proven that ENMs can cross or bypass the blood-brain barrier and then access the central nervous system and cause neurotoxicity. Until now, diverse in vivo and in vitro models have been developed to evaluate the neurotoxicity of ENMs, and oxidative stress, inflammation, DNA damage, and cell death have been identified as being involved. However, due to various physicochemical properties of ENMs and diverse study models in existing studies, it remains challenging to establish the structure-activity relationship of nanomaterials in neurotoxicity. In this paper, we aimed to review current studies on ENM-induced neurotoxicity, with an emphasis on the molecular and cellular mechanisms involved. We hope to provide a rational material design strategy for ENMs when they are applied in biomedical or other engineering applications.