0000000000417316
AUTHOR
Antonio Artés-rodríguez
Smartphone-based ecological momentary assessment (EMA) in psychiatric patients and student controls: A real-world feasibility study
Abstract Background Smartphone-based ecological momentary assessment (EMA) is a promising methodology for mental health research. The objective of this study is to determine the feasibility of smartphone-based active and passive EMA in psychiatric outpatients and student controls. Methods Two smartphone applications —MEmind and eB2— were developed for behavioral active and passive monitoring. The applications were tested in psychiatric patients with a history of suicidal thoughts and/or behaviors (STB), psychiatric patients without a history of STB, and student controls. Main outcome was feasibility, measured as response to recruitment, retention, and EMA compliance. Secondary outcomes were…
Multi-dimensional Function Approximation and Regression Estimation
In this communication, we generalize the Support Vector Machines (SVM) for regression estimation and function approximation to multi-dimensional problems. We propose a multi-dimensional Support Vector Regressor (MSVR) that uses a cost function with a hyperspherical insensitive zone, capable of obtaining better predictions than using an SVM independently for each dimension. The resolution of the MSVR is achieved by an iterative procedure over the Karush-Kuhn-Tucker conditions. The proposed algorithm is illustrated by computers experiments.
Therapeutic Drug Monitoring of Kidney Transplant Recipients Using Profiled Support Vector Machines
This paper proposes a twofold approach for therapeutic drug monitoring (TDM) of kidney recipients using support vector machines (SVMs), for both predicting and detecting Cyclosporine A (CyA) blood concentrations. The final goal is to build useful, robust, and ultimately understandable models for individualizing the dosage of CyA. We compare SVMs with several neural network models, such as the multilayer perceptron (MLP), the Elman recurrent network, finite/infinite impulse response networks, and neural network ARMAX approaches. In addition, we present a profile-dependent SVM (PD-SVM), which incorporates a priori knowledge in both tasks. Models are compared numerically, statistically, and in…