Search

Acute myocardial infarction (AMI) or heart attack is a significant global health threat and one of the leading causes of death. The evolution of machine learning has greatly revamped the risk stratification and death prediction of AMI. In this study, an integrated feature selection and machine learning approach was used to identify potential biomarkers for early detection and treatment of AMI. First, feature selection was conducted and evaluated before all classification tasks with machine learning. Full classification models (using all 62 features) and reduced classification models (using various feature selection methods ranging from 5 to 30 features) were built and evaluated using six machine learning classification algorithms. The results showed that the reduced models performed generally better (mean AUPRC via random forest (RF) algorithm for recursive feature elimination (RFE) method ranges from 0.8048 to 0.8260, while for random forest importance (RFI) method, it ranges from 0.8301 to 0.8505) than the full models (mean AUPRC via RF: 0.8044). The most notable finding of this study was the identification of a five-feature model that included cardiac troponin I, HDL cholesterol, HbA1c, anion gap, and albumin, which had achieved comparable results (mean AUPRC via RF: 0.8462) as to the models that containing more features. These five features were proven by the previous studies as significant risk factors for AMI or cardiovascular disease and could be used as potential biomarkers to predict the prognosis of AMI patients. From the medical point of view, fewer features for diagnosis or prognosis could reduce the cost and time of a patient as lesser clinical and pathological tests are needed. [ABSTRACT FROM AUTHOR]

A sensitive biosensor capable of detecting trace concentrations of several cancer biomarkers in clinical samples is critical for early detection of cancer because different cancer biomarkers may be expressed at different stages of cancer. Previous multiplex studies using microarrays or color-coded beads had limited multiplex detection in a single well, and difficulty in optimizing and unifying the incubation parameters for all tests made in different wells had posed challenges to small sample size and lengthened assay time. Herein, we proposed a novel approach to achieve multiplex analysis on a single three-dimensional porous calcium alginate bead. Because of the high surface area to volume ratio of the calcium alginate immuno-bead, the sensitivity and linear dynamic range of the as-proposed multiplex analysis method are significantly improved. Based on the direct sandwich immunoassay principle, dual-capturing antibodies were encapsulated into a single 3D porous calcium alginate bead as a proof-of-concept for multiplexity detection of serum-HER2 and serum-CA125 breast cancer biomarkers. High sensitivity was attained, with LODs of 0.004 ng mL−1 for serum HER2, and 0.005 U mL−1 for serum CA125, both of which are below the clinical cutoff values, enabling for early breast cancer diagnosis. Stability tests revealed that the 3D immuno-beads were stable at 4 °C and room temperature (25 °C) for at least 14 days. Most importantly, the results obtained using the developed system were in good agreement with those obtained using standard methods while analyzing real clinical samples. In addition, the analysis required only approximately 30 min, which was much less time than typical ELISA techniques. When endogenous interferences were introduced, no cross-reactivity was observed. We anticipate this approach to be potentially used in the multiplex assays and biosensors. [ABSTRACT FROM AUTHOR]

Human health is threatened by significant emissions of heavy metals into the urban environment due to various activities. Various studies describing health risk analyses on soil and dust have been conducted previously. However, there are limited studies that have been carried out regarding the potential health risk assessment of heavy metals in urban road dust of < 63-μm diameter, via incidental ingestion, dermal contact, and inhalation exposure routes by children and adults in developing countries. Therefore, this study evaluated the health risks of heavy metal exposure via ingestion, dermal contact, and inhalation of urban dust particles in Petaling Jaya, Malaysia. Heavy metals such as lead (Pb), chromium (Cr), zinc (Zn), copper (Cu), and manganese (Mn) were measured using dust samples obtained from industrial, high-traffic, commercial, and residential areas by using inductively coupled plasma mass spectrometry (ICP-MS). The principal component and hierarchical cluster analysis showed the dominance of these metal concentrations at sites associated with anthropogenic activities. This was suggestive of industrial, traffic emissions, atmospheric depositions, and wind as the significant contributors towards urban dust contamination in the study sites. Further exploratory analysis underlined Cr, Pb, Cu, and Zn as the most representative metals in the dust samples. In accommodating the uncertainties associated with health risk calculations and simulating the reasonable maximum exposure of these metals, the related health risks were estimated at the 75th and 95th percentiles. Furthermore, assessing the exposure to carcinogenic and non-carcinogenic metals in the dust revealed that ingestion was the primary route of consumption. Children who ingested dust particles in Petaling Jaya could be more vulnerable to carcinogenic and non-carcinogenic risks, but the exposure for both children and adults showed no potential health effects. Therefore, this study serves as an important premise for a review and reformation of the existing environmental quality standards for human health safety. [ABSTRACT FROM AUTHOR]