Recent technological advances have changed how people interact, run businesses, learn, and use their free time. The advantages and facilities provided by electronic devices have played a major role. On the other hand, extensive use of such technology also has adverse effects on several aspects of human life (e.g., the development of societal sedentary lifestyles and new addictions). Smartphone dependency is new addiction that primarily affects the young population. The consequences may negatively impact mental and physical health (e.g., lack of attention or local pain). Health professionals rely on self-reported subjective information to assess the dependency level, requiring specialists' opinions to diagnose such a dependency. This study proposes a data-driven prediction model for smartphone dependency based on machine learning techniques using an analytical retrospective case–control approach. Different classification methods were applied, including classical and modern machine learning models. Students from a private university in Cali—Colombia (n = 1228) were tested for (i) smartphone dependency, (ii) musculoskeletal symptoms, and (iii) the Risk Factors Questionnaire. Random forest, logistic regression, and support vector machine-based classifiers exhibited the highest prediction accuracy, 76–77%, for smartphone dependency, estimated through the stratified-k-fold cross-validation technique. Results showed that self-reported information provides insight into predicting smartphone dependency correctly. Such an approach opens doors for future research aiming to include objective measures to increase accuracy and help to reduce the negative consequences of this new addiction form.

Particle filters are general methods for the solution of state estimation problems, which can be applied to nonlinear models with non-Gaussian uncertainties. In this paper, an algorithm of the particle filter is used for the simultaneous estimation of model parameters and state variables in a bioheat transfer problem associated with the radio frequency (RF) hyperthermia treatment of cancer. Results obtained with simulated measurements indicate an excellent agreement between the estimated and the exact quantities, even for cases with large uncertainties in the measurements, as well as in the evolution and measurement models.

Purpose: The purpose of this paper is to focus on applications related to the hyperthermia treatment of cancer, with heating imposed either by a laser in the near-infrared range or by radiofrequency waves. The particle filter algorithms are compared in terms of computational time and solution accuracy. Design/methodology/approach: The authors extend the analyses performed in their previous works to compare three different algorithms of the particle filter, as applied to the hyperthermia treatment of cancer. The particle filters examined here are the sampling importance resampling (SIR) algorithm, the auxiliary sampling importance resampling (ASIR) algorithm and Liu & West’s algorithm. Findings: Liu & West’s algorithm resulted in the largest computational times. On the other hand, this filter was shown to be capable of dealing with very large uncertainties. In fact, besides the uncertainties in the model parameters, Gaussian noises, similar to those used for the SIR and ASIR filters, were added to the evolution models for the application of Liu & West’s filter. For the three filters, the estimated temperatures were in excellent agreement with the exact ones. Practical implications: This work may help medical doctors in the future to prescribe treatment protocols and also opens the possibility of devising control strategies for the hyperthermia treatment of cancer. Originality/value: The natural solution to couple the uncertain results from numerical simulations with the measurements that contain uncertainties, aiming at the better prediction of the temperature field of the tissues inside the body, is to formulate the problem in terms of state estimation, as performed in this work.

Background: One of the challenges faced during the hyperthermia treatment of cancer is to monitor the temperature distribution in the region of interest. The main objective of this work was to accurately estimate the transient temperature distribution in the heated region, by using a stochastic heat transfer model and temperature measurements. Methods: Experiments involved the laser heating of a cylindrical phantom, partially loaded with iron oxide nanoparticles. The nanoparticles were manufactured and characterized in this work. The solution of the state estimation problem was obtained with an algorithm of the Particle Filter method, which allowed for simultaneous estimation of state variables and model parameters. Measurements of one single sensor were used for the estimation procedure, which is highly desirable for practical applications in order to avoid patient discomfort. Results: Despite the large uncertainties assumed for the model parameters and for the coupled radiation–conduction model, discrepancies between estimated temperatures and internal measurements were smaller than 0.7 °C. In addition, the estimated fluence rate distribution was physically meaningful. Maximum discrepancies between the prior means and the estimated means were of 2% for thermal conductivity and heat transfer coefficient, 4% for the volumetric heat capacity and 3% for the irradiance. Conclusions: This article demonstrated that the Particle Filter method can be used to accurately predict the temperatures in regions where measurements are not available. The present technique has potential applications in hyperthermia treatments as an observer for active control strategies, as well as to plan personalized heating protocols.

In this article, the temperature of biological tissues is estimated during hyperthermia therapy, while accounting for uncertainties in the bioheat transfer problem and in the available measurements. A state estimation problem is solved with the Steady-State Kalman Filter. The Pennes bioheat transfer model and the PRF-Shift Magnetic Resonance Thermometry are used as evolution and observation models, respectively. Instead of using the direct inversion of the measured data as with the PRF-Shift Magnetic Resonance Thermometry, the state-estimation framework allows for enhancing the spatial resolution of the estimated temperature variation and reducing the related uncertainties. Since the time consuming steps of the Steady-State Kalman Filter can be performed offline, the recursive solution of the state estimation problem is performed with computational times smaller than the simulated physical times. Synthetic measurements are used for the state estimation problem in a region of the human forearm, for radiofrequency and laser-diode heat sources of the hyperthermia therapy.