Search

Background: Many complex factors contribute to suicide in older adults. The suicidal ideation that precedes suicide is an especially direct predictor of suicide. This study aimed to identify the effects between variables affecting suicidal ideation among older adults using the International Classification of Functioning, Disability and Health (ICF) model and understand the causal relationships to systematize complex factors. Methods: This study used data from 9920 community-dwelling older adults who completed a national survey in 2020 to classify predictors of suicidal ideation (e.g., depression, subjective health status, sociodemographic factors, health factors, social support, instrumental activities of daily living (IADL), and social participation) by using the ICF model. To determine the causal relationship between variables, this study examined significance based on the critical ratio (C.R.) and squared multiple correlation (SMC) by using a path model. Results: Gender, education level, economic level, age, IADL, relationship satisfaction with a child, depression, and the number of chronic diseases significantly affected suicidal ideation, while age, employment status, participation in social groups, formal and informal support, satisfaction with a friend/neighbor relationship, and subjective health status did not significantly influence it. Moreover, depression mediated the relationship between each of these variables and suicidal ideation. Conclusions: It was found that depression was the most direct and mediating factor in suicidal ideation among many factors affecting the suicidal ideation of community-dwelling older adults. Additional studies should be conducted to develop community-level strategies based on these factors and understand causal relationships.

Classification problems due to data imbalance occur in many fields and have long been studied in the machine learning field. Many real-world datasets suffer from the issue of class imbalance, which occurs when the sizes of classes are not uniform; thus, data belonging to the minority class are likely to be misclassified. It is particularly important to overcome this issue when dealing with medical data because class imbalance inevitably arises due to incidence rates within medical datasets. This study adjusted the imbalance ratio (IR) within the National Biobank of Korea dataset “Epidemiologic data of Parkinson’s disease dementia patients” to values of 6.8 (raw data), 9, and 19 and compared four traditional oversampling methods with techniques using the conditional generative adversarial network (CGAN) and conditional tabular generative adversarial network (CTGAN). The results showed that when the classes were balanced with CGAN and CTGAN, they showed a better classification performance than the more traditional oversampling techniques based on the AUC and F1-score. We were able to expand the application scope of GAN, widely used in unstructured data, to structured data. We also offer a better solution for the imbalanced data problem and suggest future research directions.

COVID-19 has further aggravated problems by compelling people to stay indoors and limit social interactions, leading to a worsening of the depression situation. This study aimed to construct a TabNet model combined with SHapley Additive exPlanations (SHAP) to predict depression in South Korean society during the COVID-19 pandemic. We used a tabular dataset extracted from the Seoul Welfare Survey with a total of 3027 samples. The TabNet model was trained on this dataset, and its performance was compared to that of several other machine learning models, including Random Forest, eXtreme Gradient Boosting, Light Gradient Boosting, and CatBoost. According to the results, the TabNet model achieved an Area under the receiver operating characteristic curve value (AUC) of 0.9957 on the training set and an AUC of 0.9937 on the test set. Additionally, the study investigated the TabNet model’s local interpretability using SHapley Additive exPlanations (SHAP) to provide post hoc global and local explanations for the proposed model. By combining the TabNet model with SHAP, our proposed model might offer a valuable tool for professionals in social fields, and psychologists without expert knowledge in the field of data analysis can easily comprehend the decision-making process of this AI model.

The Eastern Cooperative Oncology Group (ECOG) performance status is a widely used method for evaluating the functional abilities of cancer patients and predicting their prognosis. It is essential for healthcare providers to frequently assess the ECOG performance status of lung cancer patients to ensure that it accurately reflects their current functional abilities and to modify their treatment plan accordingly. This study aimed to develop and evaluate an AdaBoost classification (ADB-C) model to predict a lung cancer patient’s performance status following treatment. According to the results, the ADB-C model has the highest “Area under the receiver operating characteristic curve” (ROC AUC) score at 0.7890 which outperformed other benchmark models including Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forest, XGBoost, and TabNet. In order to achieve model prediction explainability, we combined the ADB-C model with a LIME-based explainable model. This explainable ADB-C model may assist medical professionals in exploring effective cancer treatments that would not negatively impact the post-treatment performance status of a patient.

Since the emergence of the Coronavirus disease (COVID-19) pandemic, the disease has affected more than 675 million people worldwide, including more than 6.87 million deaths. To mitigate the effects of this pandemic, many countries established control measures to contain its spread. Their riposte was based on a combination of pharmaceutical (vaccination) and non-pharmaceutical (such as facemask wearing, social distancing, and quarantine) measures. In this way, cross-sectional research was conducted in Algeria from 23 December 2021 to 12 March 2022 to investigate the effectiveness of preventative interventions in lowering COVID-19 infection and severity. More specifically, we investigated the link between mask-wearing and infection on one side, and the relationship between vaccination and the risk of hospitalization on the other. For this purpose, we used binary logistic regression modeling that allows learning the role of mask-wearing and vaccination in a heterogeneous society with respect to compliance with barrier measures. This study determined that wearing a mask is equally important for people of all ages. Further, findings revealed that the risk of infection was 0.79 times lower among those who were using masks (odds ratio (OR) = 0.79; confidence interval (CI) 95% = 0.668–0.936; p-value = 0.006). At the same time, vaccination is a necessary preventive measure as the risk of hospitalization increases with age. Compared with those who did not get vaccinated, those who got vaccinated were 0.429 times less likely to end up in the hospital (OR = 0.429; CI95% = 0.273–0.676; p < 0.0001). The model performance demonstrates significant relationships between the dependent and independent variables, with the absence of over-dispersion in both studied models, such as the Akaike Information Criterion (AIC) scores. These findings emphasize the significance of preventative measures and immunization in the battle against the COVID-19 pandemic.

Survival after out-of-hospital cardiac arrest (OHCA) is contingent on time-sensitive interventions taken by onlookers, emergency call operators, first responders, emergency medical services (EMS) personnel, and hospital healthcare staff. By building integrated cardiac resuscitation systems of care, measurement systems, and techniques for assuring the correct execution of evidence-based treatments by bystanders, EMS professionals, and hospital employees, survival results can be improved. To aid in OHCA prognosis and treatment, we develop a hybrid agnostic explanation TabNet (HAE-TabNet) model to predict OHCA patient survival. According to the results, the HAE-TabNet model has an “Area under the receiver operating characteristic curve value” (ROC AUC) score of 0.9934 (95% confidence interval 0.9933–0.9935), which outperformed other machine learning models in the previous study, such as XGBoost, k-nearest neighbors, random forest, decision trees, and logistic regression. In order to achieve model prediction explainability for a non-expert in the artificial intelligence field, we combined the HAE-TabNet model with a LIME-based explainable model. This HAE-TabNet model may assist medical professionals in the prognosis and treatment of OHCA patients effectively.

This study aimed to test a predictive model for depression in older adults in the community after the COVID-19 pandemic and identify influencing factors using the International Classification of Functioning, Disability, and Health (ICF). The subjects of this study were 9920 older adults in South Korean local communities. The analysis results of path analysis and bootstrapping analysis revealed that subjective health status, instrumental activities of daily living (IADL), number of chronic diseases, social support satisfaction, household economic level, informal support, and participation in social groups were factors directly influencing depression, while formal support, age, gender, education level, employment status, and participation in social groups were factors indirectly affecting it. It will be needed to prepare measures to prevent depression in older adults during an infectious disease pandemic, such as the COVID-19 pandemic, based on the results of this study.

Depression symptoms are comparable to Parkinson’s disease symptoms, including attention deficit, fatigue, and sleep disruption, as well as symptoms of dementia such as apathy. As a result, it is difficult for Parkinson’s disease caregivers to diagnose depression early. We examined a LIME-based stacking ensemble model to predict the depression of patients with Parkinson’s disease. This study used the epidemiologic data of Parkinson’s disease dementia patients (EPD) from the Korea Disease Control and Prevention Agency’s National Biobank, which included 526 patients’ information. We used Logistic Regression (LR) as the meta-model, and five base models, including LightGBM (LGBM), K-nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), and AdaBoost. After cleansing the data, the stacking ensemble model was trained using 261 participants’ data and 10 variables. According to the research, the best combination of the stacking ensemble model is ET + LGBM + RF + LR, a harmonious model. In order to achieve model prediction explainability, we also combined the stacking ensemble model with a LIME-based explainable model. This explainable stacking ensemble model can help identify the patients and start treatment on them early in a way that medical professionals can comprehend.

The impact of the COVID-19 epidemic on the mental health of elderly individuals is causing considerable worry. We examined a deep neural network (DNN) model to predict the depression of the elderly population during the pandemic period based on social factors related to stress, health status, daily changes, and physical distancing. This study used vast data from the 2020 Community Health Survey of the Republic of Korea, which included 97,230 people over the age of 60. After cleansing the data, the DNN model was trained using 36,258 participants’ data and 22 variables. We also integrated the DNN model with a LIME-based explainable model to achieve model prediction explainability. According to the research, the model could reach a prediction accuracy of 89.92%. Furthermore, the F1-score (0.92), precision (93.55%), and recall (97.32%) findings showed the effectiveness of the proposed approach. The COVID-19 pandemic considerably impacts the likelihood of depression in later life in the elderly community. This explainable DNN model can help identify patients to start treatment on them early.

To understand the changes in the lives of adults living in local communities due to the COVID-19 pandemic, it is necessary to identify subjective life satisfaction and to understand key factors affecting life satisfaction. This study identified the effect on life satisfaction of COVID-19 using epidemiological data representing adults in South Korean communities and developed a model for predicting the factors adversely affecting life satisfaction by applying a Bayesian nomogram. The subjects of this study were 227,808 adults who were 19 years old or older. Life satisfaction was measured in units of 10 points from 0 to 100: a score of 30 or less corresponding to −1 standard deviations was reclassified as dissatisfied, and a score of 40 or more was reclassified as satisfied. The nomogram developed in this study showed that “females who were between 30 and 39 years old, living in urban areas, with fewer meetings and sleeping hours, concerned about infection for themselves and the weak in the family due to the COVID-19 pandemic, concerned about death, with a mean household monthly income of KRW 3–5 million, who were non-smokers, with poor subjective health, and an education level of college graduation or above” would have a 66% chance of life dissatisfaction due to the COVID-19 pandemic. The results of this study suggest that the government needs not only to provide economic support but also to support education on infectious diseases and customized psychological counseling programs for those at high risk of life dissatisfaction after the COVID-19 pandemic.

People living in local communities have become more worried about infection due to the extended pandemic situation and the global resurgence of COVID-19. In this study, the author (1) selected features to be included in the nomogram using AdaBoost, which had an advantage in increasing the classification accuracy of single learners and (2) developed a nomogram for predicting high-risk groups of coronavirus anxiety while considering both prediction performance and interpretability based on this. Among 210,606 adults (95,287 males and 115,319 females) in South Korea, 39,768 people (18.9%) experienced anxiety due to COVID-19. The AdaBoost model confirmed that education level, awareness of neighbors/colleagues’ COVID-19 response, age, gender, and subjective stress were five key variables with high weight in predicting anxiety induced by COVID-19 for adults living in South Korean communities. The developed logistic regression nomogram predicted that the risk of anxiety due to COVID-19 would be 63% for a female older adult who felt a lot of subjective stress, did not attend a middle school, was 70.6 years old, and thought that neighbors and colleagues responded to COVID-19 appropriately (classification accuracy = 0.812, precision = 0.761, recall = 0.812, AUC = 0.688, and F-1 score = 0.740). Prospective or retrospective cohort studies are required to causally identify the characteristics of anxiety disorders targeting high-risk COVID-19 anxiety groups identified in this study.

It is essential to understand the voice characteristics in the normal aging process to accurately distinguish presbyphonia from neurological voice disorders. This study developed the best ensemble-based machine learning classifier that could distinguish hypokinetic dysarthria from presbyphonia using classification and regression tree (CART), random forest, gradient boosting algorithm (GBM), and XGBoost and compared the prediction performance of models. The subjects of this study were 76 elderly patients diagnosed with hypokinetic dysarthria and 174 patients with presbyopia. This study developed prediction models for distinguishing hypokinetic dysarthria from presbyphonia by using CART, GBM, XGBoost, and random forest and compared the accuracy, sensitivity, and specificity of the development models to identify the prediction performance of them. The results of this study showed that random forest had the best prediction performance when it was tested with the test dataset (accuracy = 0.83, sensitivity = 0.90, and specificity = 0.80, and area under the curve (AUC) = 0.85). The main predictors for detecting hypokinetic dysarthria were Cepstral peak prominence (CPP), jitter, shimmer, L/H ratio, L/H ratio_SD, CPP max (dB), CPP min (dB), and CPPF0 in the order of magnitude. Among them, CPP was the most important predictor for identifying hypokinetic dysarthria.

The rapid eye movement sleep behavior disorder (RBD) of Parkinson’s disease (PD) patients can be improved with medications such as donepezil as long as it is diagnosed with a thorough medical examination, since identifying a high-risk group of RBD is a critical issue to treat PD. This study develops a model for predicting the high-risk groups of RBD using random forest (RF) and provides baseline information for selecting subjects for polysomnography. Subjects consisted of 350 PD patients (Parkinson’s disease with normal cognition (PD-NC) = 48; Parkinson’s disease with mild cognitive impairment (PD-MCI) = 199; Parkinson’s disease dementia (PDD) = 103) aged 60 years and older. This study compares the prediction performance of RF, discriminant analysis, classification and regression tree (CART), radial basis function (RBF) neural network, and logistic regression model to select a final model with the best model performance and presents the variable importance of the final model’s variable. As a result of analysis, the sensitivity of RF (79%) was superior to other models (discriminant analysis = 14%, CART = 32%, RBF neural network = 25%, and logistic regression = 51%). It was confirmed that age, the motor score of Untitled Parkinson’s Disease Rating (UPDRS), the total score of UPDRS, the age when a subject was diagnosed with PD first time, the Korean Mini Mental State Examination, and Korean Instrumental Activities of Daily Living, were major variables with high weight for predicting RBD. Among them, age was the most important factor. The model for predicting Parkinson’s disease RBD developed in this study will contribute to the screening of patients who should receive a video-polysomnography.

It is necessary to identify how to improve the swallowing-related quality of life, as well as the swallowing function, in order to evaluate the effect of treatments on swallowing disorders. This study aimed to prove the effects of a compound swallowing intervention (Mendelsohn maneuver + neuromuscular electrical stimulation (NMES)) on the swallowing function and the quality of life by applying the compound swallowing intervention to patients with sub-acute swallowing disorders due to cerebral infarction for eight weeks. This study analyzed 43 subjects who were diagnosed with swallowing disorders due to cerebral infarction. The experiment consisted of the Mendelsohn maneuver treatment group (n = 15), the NMES treatment group (n = 13), the compound intervention group (Mendelsohn maneuver + NMES; n = 15). The results of ANCOVA showed that the changes in Functional Dysphagia Scale (FDS) scores and Swallowing−Quality of Life (SWAL−QOL) score were different among groups. The compound intervention group had the highest FDS scores and SWAL−QOL score followed by Mendelsohn, and the NMES group had the lowest. The result of this study suggests that NMES can be more effective when it is combined with a traditional swallowing rehabilitation therapy rather than a single intervention method.