RESUMO
Objective@#The loudness dependence of the auditory evoked potential (LDAEP) is a reliable indicator that is inversely related to central serotonergic activity, and recent studies have suggested an association between LDAEP and suicidal ideation. This study investigated differences in LDAEP between patients with major depressive disorder and high suicidality and those with major depressive disorder and low suicidality compared to healthy controls. @*Methods@#This study included 67 participants: 23 patients with major depressive disorder with high suicidality (9 males, mean age 29.3 ± 15.7 years, total score of SSI-BECK ≥ 15), 22 patients with major depressive disorder with low suicidality (9 males, mean age 42.2 ± 14.4 years, total score of SSI-BECK ≤ 14), and 22 healthy controls (11 males, mean age 31.6 ± 8.7 years). Participants completed the following assessments: Patient Health Questionnaire-9, Beck Depression Inventory-II, Beck Scale for Suicidal ideation, State Anxiety Scale of the State-Trait Anxiety Inventory, Beck Anxiety Inventory, and LDAEP (measured at electrode Cz). @*Results@#There were no sex-related differences among groups (p = 0.821). The high-suicidality group exhibited significantly higher LDAEP compared to the low-suicidality group (0.82 ± 0.79 vs. 0.26 ± 0.36, p = 0.014). No significant differences were found between the control and high-suicidality (p = 0.281) or the control and low-suicidality groups (p = 0.236). @*Conclusion@#LDAEP was applied to demonstrate the association between serotonergic activity and suicidal ideation and suicide risk in major depression and may be a candidate of biological marker for preventing suicide in this study.
RESUMO
Objective@#The loudness dependence of the auditory evoked potential (LDAEP) is a reliable indicator that is inversely related to central serotonergic activity, and recent studies have suggested an association between LDAEP and suicidal ideation. This study investigated differences in LDAEP between patients with major depressive disorder and high suicidality and those with major depressive disorder and low suicidality compared to healthy controls. @*Methods@#This study included 67 participants: 23 patients with major depressive disorder with high suicidality (9 males, mean age 29.3 ± 15.7 years, total score of SSI-BECK ≥ 15), 22 patients with major depressive disorder with low suicidality (9 males, mean age 42.2 ± 14.4 years, total score of SSI-BECK ≤ 14), and 22 healthy controls (11 males, mean age 31.6 ± 8.7 years). Participants completed the following assessments: Patient Health Questionnaire-9, Beck Depression Inventory-II, Beck Scale for Suicidal ideation, State Anxiety Scale of the State-Trait Anxiety Inventory, Beck Anxiety Inventory, and LDAEP (measured at electrode Cz). @*Results@#There were no sex-related differences among groups (p = 0.821). The high-suicidality group exhibited significantly higher LDAEP compared to the low-suicidality group (0.82 ± 0.79 vs. 0.26 ± 0.36, p = 0.014). No significant differences were found between the control and high-suicidality (p = 0.281) or the control and low-suicidality groups (p = 0.236). @*Conclusion@#LDAEP was applied to demonstrate the association between serotonergic activity and suicidal ideation and suicide risk in major depression and may be a candidate of biological marker for preventing suicide in this study.
RESUMO
Objectives@#ZZThe aim was to find effective vectorization and classification models to predict a psychiatric diagnosis from text-basedmedical records. @*Methods@#ZZElectronic medical records (n = 494) of present illness were collected retrospectively in inpatient admission notes withthree diagnoses of major depressive disorder, type 1 bipolar disorder, and schizophrenia. Data were split into 400 training data and 94 independentvalidation data. Data were vectorized by two different models such as term frequency-inverse document frequency (TF-IDF)and Doc2vec. Machine learning models for classification including stochastic gradient descent, logistic regression, support vectorclassification, and deep learning (DL) were applied to predict three psychiatric diagnoses. Five-fold cross-validation was used to find aneffective model. Metrics such as accuracy, precision, recall, and F1-score were measured for comparison between the models. @*Results@#ZZFive-fold cross-validation in training data showed DL model with Doc2vec was the most effective model to predict the diagnosis(accuracy = 0.87, F1-score = 0.87). However, these metrics have been reduced in independent test data set with final workingDL models (accuracy = 0.79, F1-score = 0.79), while the model of logistic regression and support vector machine with Doc2vec showedslightly better performance (accuracy = 0.80, F1-score = 0.80) than the DL models with Doc2vec and others with TF-IDF. @*Conclusions@#ZZThe current results suggest that the vectorization may have more impact on the performance of classification thanthe machine learning model. However, data set had a number of limitations including small sample size, imbalance among the category,and its generalizability. With this regard, the need for research with multi-sites and large samples is suggested to improve the machinelearning models.
RESUMO
Objectives@#ZZThe aim was to find effective vectorization and classification models to predict a psychiatric diagnosis from text-basedmedical records. @*Methods@#ZZElectronic medical records (n = 494) of present illness were collected retrospectively in inpatient admission notes withthree diagnoses of major depressive disorder, type 1 bipolar disorder, and schizophrenia. Data were split into 400 training data and 94 independentvalidation data. Data were vectorized by two different models such as term frequency-inverse document frequency (TF-IDF)and Doc2vec. Machine learning models for classification including stochastic gradient descent, logistic regression, support vectorclassification, and deep learning (DL) were applied to predict three psychiatric diagnoses. Five-fold cross-validation was used to find aneffective model. Metrics such as accuracy, precision, recall, and F1-score were measured for comparison between the models. @*Results@#ZZFive-fold cross-validation in training data showed DL model with Doc2vec was the most effective model to predict the diagnosis(accuracy = 0.87, F1-score = 0.87). However, these metrics have been reduced in independent test data set with final workingDL models (accuracy = 0.79, F1-score = 0.79), while the model of logistic regression and support vector machine with Doc2vec showedslightly better performance (accuracy = 0.80, F1-score = 0.80) than the DL models with Doc2vec and others with TF-IDF. @*Conclusions@#ZZThe current results suggest that the vectorization may have more impact on the performance of classification thanthe machine learning model. However, data set had a number of limitations including small sample size, imbalance among the category,and its generalizability. With this regard, the need for research with multi-sites and large samples is suggested to improve the machinelearning models.