Machine learning techniques such as logistic regression (LR), support vector machine (SVM) and artificial neural network (ANN) were used to detect fasting blood glucose levels (FBGL) in a mixed population of healthy and diseased individuals in an Indian population. The occurrence of elevated FBGL was estimated in a non-invasive manner from the status of an individual’s salivary electrochemical parameters such as pH, redox potential, conductivity and concentration of sodium, potassium and calcium ions. The samples were obtained from 175 randomly selected volunteers comprising half healthy and half diabetic patients. The models were trained using 70 % of the total data, and tested upon the remaining set. For each algorithm, data points were cross-validated by randomly shuffling them three times prior to implementing the model. The performance of the machine learning technique was reported in terms of four statistically significant parameters—accuracy, precision, sensitivity and F1 score. SVM using RBF kernel showed the best performance for classifying high FBGLs with approximately 85 % accuracy, 84 % precision, 85 % sensitivity and 85 % F1 score. This study has been approved by the ethical committee of All India Institute of Medical Sciences, New Delhi, India with the reference number: IEC/NP-278/01-08-2014, RP-29/2014.Electronic supplementary materialThe online version of this article (doi:10.1186/s40064-016-2339-6) contains supplementary material, which is available to authorized users.
The design of pressurized metered dose inhalers (MDI) used to assess asthma is variable. We have examined the aerosol spray flumes generated by four commercially available MDI products using high speed video photography. For this purpose a moulded jacket was designed which could hold the inhaler in an immovable position during actuation. Fresh inhalers were fitted in the jacket after thorough shaking and three successive actuations 30 s apart were filmed with a high speed video camera (200 frames s-1). The aerosol, ejected at high velocity into calm room air, was seen to have a 'jet' phase followed by a 'cloud' phase as a result of particle dispersion. Filming was continued till the flume could no longer be visualized on the TV monitor. High speed photography was used to record flumes seen on the video monitor, to enable characterization of flume appearance, dimensions and mean velocity.
The MAGhaler (Mundipharma GmbH) is a multidose dry powder inhaler (DPI) containing a novel formulation of drug and lactose compacted by an isostatic pressing technique (GGU GmbH). On actuation, a precise dose is metered from a compacted ring-shaped drug tablet. In this study, the lung deposition of salbutamol from this device has been assessed. Ten healthy non-smoking subjects completed a two-way cross-over study assessing the pulmonary deposition of salbutamol (200 microg) from the MAGhaler at high (60 l/min) and low (30 l/min) peak inhaled flow rates (PIFRs), representing maximal and sub-maximal inspiratory efforts. The formulation was radiolabelled with 99mTc, and lung and oropharyngeal depositions were quantified by gamma scintigraphyThe mean (SD)% ofthe delivered dose deposited in the lungs was 26.4 (4.3)% at 60 l/min and 21.1 (5.1)% at 30 l/min (P < 0.05), corresponding to mean lung depositions of 52.8 and 42.2 microg salbutamol, respectively. The distribution of drug within different lung regions did not vary significantly with inhaled flow rate. The data provided proof of concept for the novel inhaler device and the innovative drug formulation. In comparison with previous deposition data obtained with other DPIs, the lung deposition was relatively high, relatively reproducible (coefficient of variation 16% at 60 l/min) and relatively insensitive to the change in peak inhaled flow rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.