Disparities in Health Coverage Across Gender and Marital Status among Discharged Psychiatric Patients

Comparisons of deep learning and machine learning while using text mining methods to identify suicide attempts of patients with mood disorders

BACKGROUND

Suicide attempt is one of the most severe consequences for patients with mood disorders. This study aimed to perform deep learning and machine learning while using text mining to identify patients with suicide attempts and to compare their effectiveness.

METHODS

A total of 13,100 patients with mood disorders were selected. Two traditional text mining methods, logistic regression and Support vector machine (SVM), and one deep learning model (Convolutional neural network, CNN) were adopted to perform overall analysis and gender-specific subgroup analysis of patients to identify suicide attempts. The classification effectiveness of these models was evaluated by accuracy, F1-value, precision, recall, and the area under Receiver operator characteristic curve (ROC).

RESULTS

CNN's results were greater than the other two for all indicators except recall which was slightly smaller than SVM in male subgroup analysis. The accuracy values of the CNN were 98.4 %, 98.2 %, and 98.5 % in the overall analysis and the subgroup analysis for males and females, respectively. The results of McNemar's test showed that CNN and SVM models' predictions were statistically different from the logistic regression model's predictions in the overall analysis and the subgroup analysis for females (P < 0.050).

LIMITATIONS

A fixed number of features were selected based on document frequency to train models; this was a single-site study.

CONCLUSIONS

CNN model was a better way to detect suicide attempts in patients with mood disorders prior to hospital admission, saving time and resources in recognizing high-risk patients and preventing suicide.

National Prevalence Rates of Suicidal Ideation and Suicide Attempts Among Adults With and Without Depression

ABSTRACT

Using the 2018 National Survey on Drug Use and Health, this study examined the US national prevalence rates of suicidal ideation (SI) and suicide attempts (SA) among four demographic adult groups (race-sex, age, education, and marital status) with and without major depressive episode (MDE). The highest prevalence rates of SI for those with and without MDE occurred among adults 18 to 25 years, with some college education, White females and males, and unmarried and never been married. Among the same demographic groups, proportions of SA were also the highest for those with MDE. A Pearson chi-square test confirmed significant associations between MDE and SI and between MDE and SA. The model fit results showed that the four variables were significant predictors of SI and SA (p < 0.05). Serious mental health needs are unmet, especially among adults with depression. Population-based clinical interventions are needed to reduce rates of depression, SI, and SA.