RESUMEN
AIMS: The main aim of this study was to assess the prevalence of suicidal ideation and previous suicide attempts among Iranian patients diagnosed with Type-1 diabetes (T1D) and Type-2 diabetes (T2D). Additionally, the study sought to estimate the network structure of depressive symptoms and cognitive functions. METHODS: 1073 patients participated in the current study. We used Patient Health Questionnaire-9 (PHQ-9), Ask Suicide-Screening Questionnaire, diabetes-related factors, and a battery of cognitive functions tasks to estimate network structures. Also, suicidal ideations and suicide attempts prevalence have been estimated. Statistical analyses were performed using R-studio software, including mixed-graphical models (MGMs) for undirected effects and Directed Acyclic Graphs (DAGs) for directed effects. RESULTS: The prevalence of suicidal ideation was 29.97% in T1D and 26.81% in T2D (p < 0.05). The history of suicide attempts was higher in T1D (10.78%) compared to T2D (8.36%) (p < 0.01). In the MRF networks for T1D, suicidal ideation was directly linked to 'feeling guilt (PHQ.6)', 'Suicide (PHQ.9)', HbA1c, and FBS, while the Inhibition node was directly related to suicidal ideation. The DAGs suggested connections between 'depression', HbA1c, and 'inhibition' with suicidal ideation, along with a link between the current family history of suicide attempts and the patient's history of suicide attempts. For T2D, the MRF networks indicated direct links between suicidal ideation and 'anhedonia (PHQ.1)', 'suicide (PHQ.9)', age, being female, and BMI, with inhibition also being directly related to suicidal ideation. The DAGs revealed connections between 'depression', age, and 'inhibition' with suicidal ideation, as well as links between being female or single/divorced and the patient's history of suicide attempts. CONCLUSION: The findings suggest that suicide ideation is highly prevalent in patients with diabetes, and these symptoms should be carefully monitored in these patients.
Asunto(s)
Cognición , Depresión , Diabetes Mellitus Tipo 1 , Diabetes Mellitus Tipo 2 , Ideación Suicida , Intento de Suicidio , Humanos , Irán/epidemiología , Femenino , Masculino , Persona de Mediana Edad , Adulto , Diabetes Mellitus Tipo 2/psicología , Diabetes Mellitus Tipo 2/epidemiología , Depresión/epidemiología , Depresión/psicología , Diabetes Mellitus Tipo 1/psicología , Diabetes Mellitus Tipo 1/epidemiología , Intento de Suicidio/estadística & datos numéricos , Intento de Suicidio/psicología , Prevalencia , Anciano , Adulto Joven , Estudios Epidemiológicos , Estudios TransversalesRESUMEN
The diagnosis and treatment of cancer is one of the most challenging aspects of the medical profession, despite advances in disease diagnosis. MicroRNAs are small noncoding RNA molecules involved in regulating gene expression and are associated with several cancer types. Therefore, the analysis of microRNA data has become one of the most important areas of cancer research in recent years. This paper presents an improved method for cancer-type classification based on microRNA expression data using a hybrid radial basis function (RBF) and particle swarm optimization (PSO) algorithm. Two datasets containing microRNA information were used, and preprocessing and normalization operations were performed on the raw data. Feature selection was carried out by using the PSO algorithm, which can identify the most relevant and informative features in the data along with helping to prioritize them. Using a PSO algorithm for feature selection is an effective approach to microRNA analysis. This enhances the accuracy and reliability of cancer-type classifications based on microRNA expression data. In the proposed method, we, respectively, achieved an accuracy of 0.95% and 0.91% on both datasets, with an average of 0.93%, using an improved RBF neural network classifier. These results demonstrate that the proposed method outperforms previous works. RESEARCH HIGHLIGHTS: To enhance the accuracy of cancer-type classifications based on microRNA expression data. We present a minimal feature selection method using particle swarm optimization to reduce computational load & radial basis function to improve accuracy.