ABSTRACT
Introduction: A no-show appointment occurs when a patient does not attend a previously booked appointment. This situation can cause other problems, such as discontinuity of patient treatments as well as a waste of both human and financial resources. One of the latest approaches to address this issue is predicting no-shows using machine learning techniques. This study aims to propose a predictive analytical approach for developing a patient no-show appointment model in Hospital Kuala Lumpur (HKL) using machine learning algorithms. Methods: This study uses outpatient data from the HKL's Patient Management System (SPP) throughout 2019. The final data set has 246,943 appointment records with 13 attributes used for both descriptive and predictive analyses. The predictive analysis was carried out using seven machine learning algorithms, namely, logistic regression (LR), decision tree (DT), k-near neighbours (k-NN), Naïve Bayes (NB), random forest (RF), gradient boosting (GB) and multilayer perceptron (MLP). Results: The descriptive analysis showed that the no-show rate was 28%, and attributes such as the month of the appointment and the gender of the patient seem to influence the possibility of a patient not showing up. Evaluation of the predictive model found that the GB model had the highest accuracy of 78%, F1 score of 0.76 and area under the curve (AUC) value of 0.65. Conclusion: The predictive model could be used to formulate intervention steps to reduce no-shows, improving patient care quality.
ABSTRACT
In the absence of external fields, interfacial tensions between different phases dictate the equilibrium morphology of a multiphase system. Depending on the relative magnitudes of these interfacial tensions, a composite system made up of immiscible fluids in contact with one another can exhibit contrasting behavior: the formation of lenses in one case and complete encapsulation in another. Relatively simple concepts such as the spreading coefficient (SC) have been extensively used by many researchers to make predictions. However, these qualitative methods are limited to determining the nature of the equilibrium states and do not provide enough information to calculate the exact equilibrium geometries. Moreover, due to the assumptions made, their validity is questionable at smaller scales where pressure forces due to curvature of the interfaces become significant or in systems where a compressible gas phase is present. Here we investigate equilibrium configurations of two fluid drops suspended in another fluid, which can be seen as a simple building block of more complicated systems. We use Gibbsian composite-system thermodynamics to derive equilibrium conditions and the equation acting as the free energy (thermodynamic potential) for this system. These equations are then numerically solved for an example system consisting of a dodecane drop and an air bubble surrounded by water, and the relative stability of distinct equilibrium shapes is investigated based on free-energy comparisons. Quantitative effects of system parameters such as interfacial tensions, volumes, and the scale of the system on geometry and stability are further explored. Multiphase systems similar to the ones analyzed here have broad applications in microfluidics, atmospheric physics, soft photonics, froth flotation, oil recovery, and some biological phenomena.
