Search

BACKGROUND Each year, approximately 800,000 people die by suicide worldwide, accounting for 1–2 in every 100 deaths. It is always a tragic event with a huge impact on family, friends, the community and health professionals. Unfortunately, suicide prevention and the development of risk assessment tools have been hindered by the complexity of the underlying mechanisms and the dynamic nature of a person’s motivation and intent. Many of those who die by suicide had contact with health services in the preceding year but identifying those most at risk remains a challenge. OBJECTIVE To explore the feasibility of using artificial neural networks with routinely collected electronic health records to support the identification of those at high risk of suicide when in contact with health services. METHODS Using the Secure Anonymised Information Linkage Databank UK, we extracted the data of those who died by suicide between 2001 and 2015 and paired controls. Looking at primary (general practice) and secondary (hospital admissions) electronic health records, we built a binary feature vector coding the presence of risk factors at different times prior to death. Risk factors included: general practice contact and hospital admission; diagnosis of mental health issues; injury and poisoning; substance misuse; maltreatment; sleep disorders; and the prescription of opiates and psychotropics. Basic artificial neural networks were trained to differentiate between the suicide cases and paired controls. We interpreted the output score as the estimated suicide risk. System performance was assessed with 10x10-fold repeated cross-validation, and its behavior was studied by representing the distribution of estimated risk across the cases and controls, and the distribution of factors across estimated risks. RESULTS We extracted a total of 2604 suicide cases and 20 paired controls per case. Our best system attained a mean error rate of 26.78% (SD 1.46; 64.57% of sensitivity and 81.86% of specificity). While the distribution of controls was concentrated around estimated risks < 0.5, cases were almost uniformly distributed between 0 and 1. Prescription of psychotropics, depression and anxiety, and self-harm increased the estimated risk by ~0.4. At least 95% of those presenting these factors were identified as suicide cases. CONCLUSIONS Despite the simplicity of the implemented system, the proposed methodology obtained an accuracy like other published methods based on specialized questionnaire generated data. Most of the errors came from the heterogeneity of patterns shown by suicide cases, some of which were identical to those of the paired controls. Prescription of psychotropics, depression and anxiety, and self-harm were strongly linked with higher estimated risk scores, followed by hospital admission and long-term drug and alcohol misuse. Other risk factors like sleep disorders and maltreatment had more complex effects.

The creation of an automated system based on digital image processing of photographs of their wings to identify the genus and species of a bee (Apidae: Meliponini) is proposed. A fast and efficient system of taxonomic classification of stingless bees would be a very valuable contribution, as well as a reference for the study of stingless bees. The fore and hind right wings of workers were placed in an inert medium. The bee samples were collected directly from their nests and from the entomological collection of the Tropical Bee Research Center (CINAT).

The nature of the interaction of water molecules with the surface of a set of experimentally well-studied alkane−amidethiols adsorbed on a gold(111) surface and its effect on the water contact angle have been studied by carrying out a systematic determination of the topology of electrostatic potential using ab initio density functional theory methods for periodic systems. The obtained results have shown that the water contact angle decreases systematically as the number of minima by surface cell unit and the electrostatic potential magnitude at these minima, and consequently the adsorption strength, increases. Thus, this electrostatic potential magnitude can be used as a measure of the efficiency and ability of a chemical group for wetting of a surface by water.

Binding between water and models of poly(ethylene oxide), (CH2−CH2−O)n, n = 2−40, has been studied using the topographic features of the electrostatic potential, V(r), and standard density functional theory methods. It was found that, in general, the contour around the minima of the oxygen atoms overlap forming a negative-valued spiral coiled around a positive-valued helix. The positive zone defines a helical groove in the O−C−C−O units where minima lone pairs critical points are located. Topological analysis of the water molecule has also suggested that the attractive electrostatic effect between the positive water O−H zone and the negative PEO lone pairs plays an important role in the hydrogen bonding of the PEO−water system. Thus, the V(r) topology predicts a coil of water molecules around the PEO chain forming hydrogen bonding with two sites of ether oxygens. This coil is formed in such a way that more water molecules accumulate on the cavities surrounding the poly(ethylene oxide)'s oxygen atoms where...

In this work, the topology of the electrostatic potential using density functional theory for periodic systems was used to study the nature of the interaction of water with laponite surfaces; an uncharged sheet model was also used. The topological analysis predicts that for uncharged surfaces the adsorption mode is such that the water molecules are adsorbed almost parallel to the surface. For laponite surfaces, where there is a net charge, the adsorption mode involves electrostatic repulsion between the negative lone pairs on the water molecules and the ones on the surface oxygen atoms. As a consequence, the water molecules bind to the surface in a perpendicular and tilted approach, minimizing the repulsive interactions. The advantage of using the topology of the electrostatic potential as an efficient method to describe the electrostatic interactions between adsorbates and surfaces is also discussed.

Javier Vasquez-Morera1, Jose L. Vasquez-Nunez2 and Carlos Manuel Travieso-Gonzalez3 1University of Costa Rica, Computer Science Deparment, San Jose, 2University of Costa Rica, Sede del Atlantico, Cartago, 3University of Las Palmas de Gran Canaria, Signals and Communications Department, Institute for Technological Development and Innovation in Communications, Campus University of Tafira, Las Palmas de Gran Canaria, 1,2Costa Rica 3Spain

Juan Jose Fuertes Cebrian1, Carlos Manuel Travieso Gonzalez2 and Valery Naranjo Ornedo1 1Instituto Interuniversitario de Investigacion en Bioingenieria y Tecnologia Orientada al Ser Humano, Universitat Politecnica de Valencia, I3BH/Labhuman 2Instituto Universitario para el Desarrollo Tecnologico y la Innovacion en las Comunicaciones (IDETIC), Departamento de Senales y Comunicaciones, Universidad de Las Palmas de Gran Canaria Spain