No abstract

No abstract

IntroductionTo self-monitor asthma symptoms, existing methods (e.g. peak flow metre, smart spirometer) require special equipment and are not always used by the patients. Voice recording has the potential to generate surrogate measures of lung function and this study aims to apply machine learning approaches to predict lung function and severity of abnormal lung function from recorded voice for asthma patients.MethodsA threshold-based mechanism was designed to separate speech and breathing from 323 recordings. Features extracted from these were combined with biological factors to predict lung function. Three predictive models were developed using Random Forest (RF), Support Vector Machine (SVM), and linear regression algorithms: (a) regression models to predict lung function, (b) multi-class classification models to predict severity of lung function abnormality, and (c) binary classification models to predict lung function abnormality. Training and test samples were separated (70%:30%, using balanced portioning), features were normalised, 10-fold cross-validation was used and model performances were evaluated on the test samples.ResultsThe RF-based regression model performed better with the lowest root mean square error of 10·86. To predict severity of lung function impairment, the SVM-based model performed best in multi-class classification (accuracy = 73.20%), whereas the RF-based model performed best in binary classification models for predicting abnormal lung function (accuracy = 85%).ConclusionOur machine learning approaches can predict lung function, from recorded voice files, better than published approaches. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

Firms increasingly put financial pressure on their suppliers, also called squeezing. Suppliers react and adapt to financial squeeze as autonomous agents, causing complex ripple effects across the extended supply chain network. To capture intertwined and highly interactive effects among suppliers, we use agent‐based models. We explore the impact of financial squeeze on supply chain network structure and operational outcomes. Results suggest that financial squeeze affects the stability of the supply chain network and the effect varies depending on the location of the suppliers. Firms located at the bottom of the supply chain network suffer most from financial squeeze, and the magnitude of the effect increases as one goes further upstream. In addition, as existing suppliers exit the network and new suppliers enter, three network archetypes (Empty Nest, TransitUp, and StableDown) emerge. We identify the condition and operational consequences associated with these three archetypes. Our findings are informative to managers at buyer firms about the impacts of squeezing strategy on their extended supply chain partners, who often times are out of their immediate purview.