Suicide detection in Chile: proposing a predictive model for suicide risk in a clinical sample of patients with mood disorders

Objective: To analyze suicidal behavior and build a predictive model for suicide risk using data mining (DM) analysis. Methods: A study of 707 Chilean mental health patients (with and without suicide risk) was carried out across three healthcare centers in the Metropolitan Region of Santiago, Chile. Three hundred forty-three variables were studied using five questionnaires. DM and machine-learning tools were used via the support vector machine technique. Results: The model selected 22 variables that, depending on the circumstances in which they all occur, define whether a person belongs in a suicide risk zone (accuracy = 0.78, sensitivity = 0.77, and specificity = 0.79). Being in a suicide risk zone means patients are more vulnerable to suicide attempts or are thinking about suicide. The interrelationship between these variables is highly nonlinear, and it is interesting to note the particular ways in which they are configured for each case. The model shows that the variables of a suicide risk zone are related to individual unrest, personal satisfaction, and reasons for living, particularly those related to beliefs in one’s own capacities and coping abilities. Conclusion: These variables can be used to create an assessment tool and enables us to identify individual risk and protective factors. This may also contribute to therapeutic intervention by strengthening feelings of personal well-being and reasons for staying alive. Our results prompted the design of a new clinical tool, which is fast and easy to use and aids in evaluating the trajectory of suicide risk at a given moment.

Variabilidad en la determinación de fracción grasa muscular en resonancia magnética utilizando la técnica de Dixon / Variability in magnetic resonance quantification of muscle fat fraction using Dixon's technique

Abstract. Muscle MRI has emerged as a valuable tool in the diagnosis of neuromuscular-disorders. The Dixon fat-water separation technique allows objective intra-muscular fat quantification. There are few reports concerning measurement standardisation with Dixon technique. The objective of this study was to evaluate the variability in fat quantification using Dixon's technique in a cohort of patients with congenital myopathies, by analysing intra-segment, intra-muscle, and inter-muscle variability of 60 muscles in each patient. Whole body MRI was performed on 31 patients, 23 with congenital myopathies and 8 healthy controls, aged between 10 months and 35 years old, from January 2014 to June 2016. The mean fat-fraction in healthy patients was around 5%, with less than 2% intra-muscle variability. An intra-muscle variability between 3.1-7.8% was estimated in patients with congenital myopathies. It may be concluded that there is high intra- and inter-muscle fat-fraction variability among patients with congenital myopathies, and this is an observation that should be incorporated in the analysis of fat replacement.

Resumen. La resonancia magnética muscular ha emergido como una valiosa herramienta de apoyo diagnóstico en enfermedades neuromusculares. La técnica de Dixon permite objetivar la fracción grasa muscular, pero no existe consenso sobre la estandarización de estas mediciones. El objetivo de este estudio fue evaluar la variabilidad en la determinación de fracción grasa utilizando la técnica de Dixon, estudiando la variabilidad intrasegmentaria, intramuscular e intermuscular en 60 músculos por paciente. Se realizó RM de cuerpo completo a 31 pacientes: 23 con miopatía congénita y 8 controles, entre 10 meses y 35 años de edad, desde enero del 2014 a junio del 2016. En pacientes sanos se estimó una fracción grasa promedio cercana al 5%, con una variabilidad intramuscular inferior al 2%. En pacientes con miopatías congénitas existe una variabilidad entre el 3,1-7,8%. El estudio permite concluir que existe una alta variabilidad intra e intermuscular en pacientes miopáticos, que no se observa en pacientes sanos.