Machine learning algorithms to predict major adverse cardiovascular events in patients with diabetes.

BACKGROUND: Major Adverse Cardiovascular Events (MACE) are common complications of type 2 diabetes mellitus (T2DM) that include myocardial infarction (MI), stroke, and heart failure (HF). The objective of the current study was to predict MACE among T2DM patients. METHODS: Type 2 diabetes mellitus patients above 18 years old were recruited for the study from the All of Us Research Program. Eligible participants were those who took sodium-glucose cotransporter 2 inhibitors. Different Machine learning algorithms: including RandomForest (RF), XGBoost, logistic regression (LR), and weighted ensemble model (WEM) were employed. Clinical attributes, electrolytes and biomarkers were explored in predicting MACE. The feature importance was determined using mean decrease accuracy. RESULTS: Overall, 9, 059 subjects were included in the analyses, of which 5197 (57.4%) were females. The XGBoost Model demonstrated a prediction accuracy of 0.80 [0.78-0.82], which is higher as compared to the RF 0.78[0.76-0.80], the LR model 0.65 [0.62-0.67], and the WEM 0.75 [0.73-0.76], respectively. The classification accuracy of the models for stroke was more than 95%, which was higher than prediction accuracy for MI (∼85%), and HF (∼80%). Phosphate, blood urea nitrogen and troponin levels were the major predictors of MACE. CONCLUSION: The ML models had shown acceptable performance in predicting MACE in T2DM patients, except the LR model. Phosphate, blood urea nitrogen, and other electrolytes were important predictors of MACE, which is consistent between the individual components of MACE, such as stroke, MI, and HF. These parameters can be calibrated as prognostic parameters of MACE events in T2DM patients.

A comparative analysis of the chemical composition and compliance level to established standards of concrete reinforcement steel rods rolled in Nigeria.

Nigeria is presently facing the challenges of collapsing buildings and bridges due to substandard materials used as reinforcement products. The increasing use of scraps as feedstock for the production of reinforcing steel bars by steel rolling mill companies has adversely affected the quality of rebars in Nigeria. This research study aimed to appraise the chemical properties of selected brands of steel rebars of Nigeria. Thirty selected brands of rebars were sourced from the six geopolitical zones in Nigeria, and their chemical compositions were analysed for level of compliance with five selected standards (SON, BSI, ASTM, AISI, ISO). The chemical composition test was performed using Optical Light Spectrometric methods. One way analysis of variance (ANOVA) test was performed using SPSS version 20 to examine whether significant differences exist or not in mean chemical composition for the different categories of selected steel rods. Statistical analysis shows a significant difference (P < 0.05) in chemical composition and compliance level between the different types of selected steel rods. The imported steel rods recorded the highest mean (µ = 101.4) in terms of chemical composition and compliance, followed by locally rolled from imported billets (µ = 101.2), TMT steel rods (µ = 101.0), and ordinary steel rods (µ = 100.6). Concerning CEV1 and CEV2, it was observed that all the brands were fully compliant within the maximum permissible ranges given in the local, foreign and international standards except an ordinary steel bar of Brand 16, which has value beyond the specified limits of CEV1. This study also shows that all imported and 77.8% of locally-rolled steel bars are low-carbon steel as specified by the selected standards.

Dataset on physical properties of raw and roasted cashew nuts.

Cashew nut is one of the topmost edible crops in the world. However, one of the challenges of this crop is processing. Designing an equipment for the processing of cashew nut requires the knowledge of its physical properties data. The dataset in this article contained the physical properties of raw and roasted cashew nuts. The physical properties include length, width, thickness, geometric mean diameter, sphericity, true density, bulk density, porosity and mass of cashew nut. Two experiments were performed. In one experiment, raw cashew nut was roasted in groundnut oil. In the second experiment, raw cashew nut was roasted in palm-kernel oil. The physical properties of the nuts were measured before and after roasting in hot oil. The data were subjected to a paired sample t-test analysis to determine the level of significant difference. The data of the cashew nut graded with machine and sorted with hand manually were compared. The data provided in this article will be useful in designing various types of equipment for grading, separating and cleaning cashew nut. It will also be useful in the design of storage structures and processing machines.