We investigate the collective behavior of a globalized society under the influence of endogenous mass media trends. The mass media trend is a global field corresponding to the statistical mode of the states of the agents in the system. The interaction dynamics is based on Axelrod's rules for the dissemination of culture. We find situations where the largest minority group, possessing a cultural state different from that of the predominant trend transmitted by the mass media, can grow to almost half of the size of the population. We show that this phenomenon occurs when a critical number of long-range connections are present in the underlying network of interactions. We have numerically characterized four phases on the space of parameters of the system: an ordered phase; a semi-ordered phase where almost half of the population consists of the largest minority in a state different from that of the mass media; a disordered phase; and a chimera-like phase where one large domain coexists with many very small domains.

Obstructive sleep apnea (OSA) is a common respiratory condition characterized by respiratory tract obstruction and breathing disorder. Early detection and treatment of OSA can significantly reduce morbidity and mortality. OSA is often diagnosed with overnight polysomnography (PSG) monitoring; however, continuous PSG monitoring is unfeasible as it is costly and uncomfortable for patients. To circumvent these issues, we propose a detection method of OSA events, named DRIVEN, using only two signals that can be easily measured at home: abdominal movement and pulse oximetry. On test data, DRIVEN achieves an accuracy and F1-score of 88%, a reasonable trade-off between the models performance and patient comfort. We use data from three sleep studies from the National Sleep Research Resource (NSRR), the largest public repository, consisting of 10,878 recordings. DRIVEN is based on a combination of deep convolutional neural networks and a light-gradient-boost machine for classification. Since DRIVEN is simple and computationally efficient, we expect that it can be implemented for automatic detection of OSA in unsupervised long-term home monitoring systems, reducing costs to healthcare systems and improving patient care.

Atrial Fibrillation (AF) is the most common cardiac rhythm disorder. Advance knowledge of an imminent switch from sinus rhythm (SR) to AF could prompt patients to take preventive actions to avoid AF, like taking oral antiarrhythmic drugs. The question is whether there is information, even if subtle, in the minutes prior to AF to indicate an imminent switch from SR. This paper shows that, for the vast majority of patients, the answer is affirmative. On test data, our algorithm can predict the onset of AF on average 31 minutes before it appears, with an accuracy of 83\% and an F1-score of 85\%. The predictions were based on deep learning and data from 350 patients, plus an external validation of 48 patients. Overall, the proposed method has low computational complexity and can be embedded in common wearable devices for continuous heart monitoring and early warning of AF onset.