Machine learning-based prediction of suicidality in adolescents during the COVID-19 pandemic (2020-2021): Derivation and validation in two independent nationwide cohorts

Machine Learning-Based Prediction for Incident Hypertension Based on Regular Health Checkup Data: Derivation and Validation in 2 Independent Nationwide Cohorts in South Korea and Japan

BACKGROUND

Worldwide, cardiovascular diseases are the primary cause of death, with hypertension as a key contributor. In 2019, cardiovascular diseases led to 17.9 million deaths, predicted to reach 23 million by 2030.

OBJECTIVE

This study presents a new method to predict hypertension using demographic data, using 6 machine learning models for enhanced reliability and applicability. The goal is to harness artificial intelligence for early and accurate hypertension diagnosis across diverse populations.

METHODS

Data from 2 national cohort studies, National Health Insurance Service-National Sample Cohort (South Korea, n=244,814), conducted between 2002 and 2013 were used to train and test machine learning models designed to anticipate incident hypertension within 5 years of a health checkup involving those aged ≥20 years, and Japanese Medical Data Center cohort (Japan, n=1,296,649) were used for extra validation. An ensemble from 6 diverse machine learning models was used to identify the 5 most salient features contributing to hypertension by presenting a feature importance analysis to confirm the contribution of each future.

RESULTS

The Adaptive Boosting and logistic regression ensemble showed superior balanced accuracy (0.812, sensitivity 0.806, specificity 0.818, and area under the receiver operating characteristic curve 0.901). The 5 key hypertension indicators were age, diastolic blood pressure, BMI, systolic blood pressure, and fasting blood glucose. The Japanese Medical Data Center cohort dataset (extra validation set) corroborated these findings (balanced accuracy 0.741 and area under the receiver operating characteristic curve 0.824). The ensemble model was integrated into a public web portal for predicting hypertension onset based on health checkup data.

CONCLUSIONS

Comparative evaluation of our machine learning models against classical statistical models across 2 distinct studies emphasized the former's enhanced stability, generalizability, and reproducibility in predicting hypertension onset.

Psychosocial alterations during the COVID-19 pandemic and the global burden of anxiety and major depressive disorders in adolescents, 1990-2021: challenges in mental health amid socioeconomic disparities

BACKGROUND

The coronavirus disease 2019 (COVID-19) pandemic, a global health crisis, profoundly impacted all aspects of daily life. Adolescence, a pivotal stage of psychological and social development, is heavily influenced by the psychosocial and socio-cultural context. Hence, it is imperative to thoroughly understand the psychosocial changes adolescents experienced during the pandemic and implement effective management initiatives.

DATA SOURCES

We examined the incidence rates of depressive and anxiety disorders among adolescents aged 10-19 years globally and regionally. We utilized data from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021 to compare pre-pandemic (2018-2019) and pandemic (2020-2021) periods. Our investigation covered 204 countries and territories across the six World Health Organization regions. We conducted a comprehensive literature search using databases including PubMed/MEDLINE, Scopus, and Google Scholar, employing search terms such as "psychosocial", "adolescent", "youth", "risk factors", "COVID-19 pandemic", "prevention", and "intervention".

RESULTS

During the pandemic, the mental health outcomes of adolescents deteriorated, particularly in terms of depressive and anxiety disorders. According to GBD 2021, the incidence rate of anxiety disorders increased from 720.26 [95% uncertainty intervals (UI) = 548.90-929.19] before the COVID-19 pandemic (2018-2019) to 880.87 per 100,000 people (95% UI = 670.43-1132.58) during the COVID-19 pandemic (2020-2021). Similarly, the incidence rate of major depressive disorder increased from 2333.91 (95% UI = 1626.92-3138.55) before the COVID-19 pandemic to 3030.49 per 100,000 people (95% UI = 2096.73-4077.73) during the COVID-19 pandemic. This worsening was notably pronounced in high-income countries (HICs). Rapid environmental changes, including heightened social anxiety, school closures, economic crises, and exacerbated racism, have been shown to adversely affect the mental well-being of adolescents.

CONCLUSIONS

The abrupt shift to remote learning and the absence of in-person social interactions heightened feelings of loneliness, anxiety, sadness, and stress among adolescents. This change magnified existing socioeconomic disparities, posing additional challenges. These complexities profoundly impact adolescents' well-being, especially vulnerable groups like those from HICs, females, and minorities. Acknowledging the underreporting bias in low- to middle-income countries highlights the importance of addressing these mental health alterations in assessments and interventions within these regions as well. Urgent interventions are crucial as the pandemic-induced mental stress may have lasting effects on adolescents' mental health.

Anticipating influential factors on suicide outcomes through machine learning techniques: Insights from a suicide registration program in western Iran

Suicide is a global public health concern, with increasing rates observed in various regions, including Iran. This study focuses on the province of Hamadan, Iran, where suicide rates have been on the rise. The research aims to predict factors influencing suicide outcomes by leveraging machine learning techniques on the Hamadan Suicide Registry Program data collected from 2016 to 2017. The study employs Naïve Bayes and Random Forest algorithms, comparing their performance to logistic regression. Results highlight the superiority of the Random Forest model. Based on the variable importance and multiple logistic regression analyses, the most important determinants of suicide outcomes were identified as suicide method, age, and timing of attempts, income, and motivation. The findings emphasize the cultural context's impact on suicide methods and underscore the importance of tailoring prevention programs to address specific risk factors, especially for older individuals. This study contributes valuable insights for suicide prevention efforts in the region, advocating for context-specific interventions and further research to refine predictive models and develop targeted prevention strategies.

Global public concern of childhood and adolescence suicide: a new perspective and new strategies for suicide prevention in the post-pandemic era

BACKGROUND

Suicide is the second leading cause of death in young people worldwide and is responsible for about 52,000 deaths annually in children and adolescents aged 5-19 years. Familial, social, psychological, and behavioral factors play important roles in suicide risk. As traumatic events such as the COVID-19 pandemic may contribute to suicidal behaviors in young people, there is a need to understand the current status of suicide in adolescents, including its epidemiology, associated factors, the influence of the pandemic, and management initiatives.

DATA SOURCES

We investigated global and regional suicide mortality rates among children and adolescents aged 5-19 years using data from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2019. The suicide mortality rates from 1990 to 2019 were examined in 204 countries and territories across six World Health Organization (WHO) regions. Additionally, we utilized electronic databases, including PubMed/MEDLINE and Scopus, and employed various combinations of terms such as "suicide", "adolescents", "youth", "children", "risk factors", "COVID-19 pandemic", "prevention", and "intervention" to provide a narrative review on suicide within the pediatric population in the post-pandemic era.

RESULTS

Despite the decreasing trend in the global suicide mortality rate from 1990 to 2019, it remains high. The mortality rates from suicide by firearms or any other specified means were both greater in males. Additionally, Southeast Asia had the highest suicide rate among the six WHO regions. The COVID-19 pandemic seems to contribute to suicide risk in young people; thus, there is still a strong need to revisit appropriate management for suicidal children and adolescents during the pandemic.

CONCLUSIONS

The current narrative review integrates up-to-date knowledge on suicide epidemiology and the effects of the COVID-19 pandemic, risk factors, and intervention strategies. Although numerous studies have characterized trends in suicide among young people during the pre-pandemic era, further studies are required to investigate suicide during the pandemic and new strategies for suicide prevention in the post-pandemic era. It is necessary to identify effective prevention strategies targeting young people, particularly those at high risk, and successful treatment for individuals already manifesting suicidal behaviors. Care for suicidal children and adolescents should be improved with parental, school, community, and clinical involvement.

Machine learning-based model to predict delirium in patients with advanced cancer treated with palliative care: a multicenter, patient-based registry cohort

This study aimed to present a new approach to predict to delirium admitted to the acute palliative care unit. To achieve this, this study employed machine learning model to predict delirium in patients in palliative care and identified the significant features that influenced the model. A multicenter, patient-based registry cohort study in South Korea between January 1, 2019, and December 31, 2020. Delirium was identified by reviewing the medical records based on the criteria of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. The study dataset included 165 patients with delirium among 2314 patients with advanced cancer admitted to the acute palliative care unit. Seven machine learning models, including extreme gradient boosting, adaptive boosting, gradient boosting, light gradient boosting, logistic regression, support vector machine, and random forest, were evaluated to predict delirium in patients with advanced cancer admitted to the acute palliative care unit. An ensemble approach was adopted to determine the optimal model. For k-fold cross-validation, the combination of extreme gradient boosting and random forest provided the best performance, achieving the following accuracy metrics: 68.83% sensitivity, 70.85% specificity, 69.84% balanced accuracy, and 74.55% area under the receiver operating characteristic curve. The performance of the isolated testing dataset was also validated, and the machine learning model was successfully deployed on a public website ( http://ai-wm.khu.ac.kr/Delirium/ ) to provide public access to delirium prediction results in patients with advanced cancer. Furthermore, using feature importance analysis, sex was determined to be the top contributor in predicting delirium, followed by a history of delirium, chemotherapy, smoking status, alcohol consumption, and living with family. Based on a large-scale, multicenter, patient-based registry cohort, a machine learning prediction model for delirium in patients with advanced cancer was developed in South Korea. We believe that this model will assist healthcare providers in treating patients with delirium and advanced cancer.

Machine Learning-Based Prediction of Suicidal Thinking in Adolescents by Derivation and Validation in 3 Independent Worldwide Cohorts: Algorithm Development and Validation Study

BACKGROUND

Suicide is the second-leading cause of death among adolescents and is associated with clusters of suicides. Despite numerous studies on this preventable cause of death, the focus has primarily been on single nations and traditional statistical methods.

OBJECTIVE

This study aims to develop a predictive model for adolescent suicidal thinking using multinational data sets and machine learning (ML).

METHODS

We used data from the Korea Youth Risk Behavior Web-based Survey with 566,875 adolescents aged between 13 and 18 years and conducted external validation using the Youth Risk Behavior Survey with 103,874 adolescents and Norway's University National General Survey with 19,574 adolescents. Several tree-based ML models were developed, and feature importance and Shapley additive explanations values were analyzed to identify risk factors for adolescent suicidal thinking.

RESULTS

When trained on the Korea Youth Risk Behavior Web-based Survey data from South Korea with a 95% CI, the XGBoost model reported an area under the receiver operating characteristic (AUROC) curve of 90.06% (95% CI 89.97-90.16), displaying superior performance compared to other models. For external validation using the Youth Risk Behavior Survey data from the United States and the University National General Survey from Norway, the XGBoost model achieved AUROCs of 83.09% and 81.27%, respectively. Across all data sets, XGBoost consistently outperformed the other models with the highest AUROC score, and was selected as the optimal model. In terms of predictors of suicidal thinking, feelings of sadness and despair were the most influential, accounting for 57.4% of the impact, followed by stress status at 19.8%. This was followed by age (5.7%), household income (4%), academic achievement (3.4%), sex (2.1%), and others, which contributed less than 2% each.

CONCLUSIONS

This study used ML by integrating diverse data sets from 3 countries to address adolescent suicide. The findings highlight the important role of emotional health indicators in predicting suicidal thinking among adolescents. Specifically, sadness and despair were identified as the most significant predictors, followed by stressful conditions and age. These findings emphasize the critical need for early diagnosis and prevention of mental health issues during adolescence.

Machine Learning-Based Prediction of Suicidality in Adolescents With Allergic Rhinitis: Derivation and Validation in 2 Independent Nationwide Cohorts

BACKGROUND

Given the additional risk of suicide-related behaviors in adolescents with allergic rhinitis (AR), it is important to use the growing field of machine learning (ML) to evaluate this risk.

OBJECTIVE

This study aims to evaluate the validity and usefulness of an ML model for predicting suicide risk in patients with AR.

METHODS

We used data from 2 independent survey studies, Korea Youth Risk Behavior Web-based Survey (KYRBS; n=299,468) for the original data set and Korea National Health and Nutrition Examination Survey (KNHANES; n=833) for the external validation data set, to predict suicide risks of AR in adolescents aged 13 to 18 years, with 3.45% (10,341/299,468) and 1.4% (12/833) of the patients attempting suicide in the KYRBS and KNHANES studies, respectively. The outcome of interest was the suicide attempt risks. We selected various ML-based models with hyperparameter tuning in the discovery and performed an area under the receiver operating characteristic curve (AUROC) analysis in the train, test, and external validation data.

RESULTS

The study data set included 299,468 (KYRBS; original data set) and 833 (KNHANES; external validation data set) patients with AR recruited between 2005 and 2022. The best-performing ML model was the random forest model with a mean AUROC of 84.12% (95% CI 83.98%-84.27%) in the original data set. Applying this result to the external validation data set revealed the best performance among the models, with an AUROC of 89.87% (sensitivity 83.33%, specificity 82.58%, accuracy 82.59%, and balanced accuracy 82.96%). While looking at feature importance, the 5 most important features in predicting suicide attempts in adolescent patients with AR are depression, stress status, academic achievement, age, and alcohol consumption.

CONCLUSIONS

This study emphasizes the potential of ML models in predicting suicide risks in patients with AR, encouraging further application of these models in other conditions to enhance adolescent health and decrease suicide rates.

National trends in depression and suicide attempts and COVID-19 pandemic-related factors, 1998-2021: A nationwide study in South Korea

BACKGROUND

Despite the significant psychiatric effects of the COVID-19 pandemic, there's limited data on the prevalence and risk factors of depression and suicide attempts among South Korean adults.

METHODS

A nationwide cross-sectional study using the Korea National Health and Nutrition Examination Survey (KNHANES) data from 1998 to 2021 was conducted. Changes in prevalence and risk factors for depression and suicide attempts were assessed using weighted odds ratios or weighted beta coefficients.

RESULTS

During the observation period (1998-2021), the prevalence of depression increased in the overall population; however, no significant surge was found regarding the COVID-19 pandemic, from 2.78% (95% CI, 2.41-3.15) in 1998-2005-4.96% (4.32-5.61) in 2020 and 5.06% (4.43-5.69) in 2021. However, immediately after the onset of the pandemic, younger ages, male sex, urban residence, higher education, and high economic status became significant vulnerable factors compared to pre-pandemic periods. The prevalence of suicide attempts remained stable, and there was no notable surge specifically related to the COVID-19 pandemic, from 0.23% (95% CI, 0.18-0.28) in 1998-2005-0.45% (0.25-0.66) in 2020 and 0.42% (0.24-0.60) in 2021. Furthermore, no distinct vulnerable factors associated with suicide attempts have been identified.

CONCLUSION

Through this nationwide serial cross-sectional survey study, we emphasized the need for understanding the differential impacts of global crises, such as COVID-19, across varied population subgroups, thereby highlighting the importance of specific and targeted mental health support strategies.