Objectives: This study explores different machine learning models (KNN: k-nearest neighbor, MLP: Multilayer Perceptron, SVM: Support Vector Machine) to identify the optimal model for accurate and rapid mental health detection among the recovered COVID-19 patients. Other techniques are also investigated, such as feature selection (Recursive Feature Elimination (RFE) and Extra Trees (ET) methods) and hyper-parameter tuning, to achieve a system that could effectively and quickly indicate mental health. Method/Analysis: To achieve the objectives, the study employs a dataset collected from recovered COVID-19 patients, encompassing information related to depression, anxiety, and stress. Machine learning models are utilized in the analysis. Additionally, feature selection methods and hyper-parameter tuning techniques are explored to enhance the model’s predictive capabilities. The performance of each model is assessed based on accuracy metrics. Findings: The experimental results show that SVM is the most suitable model for accurately predicting an individual’s mental health among recovered COVID-19 patients (accuracy ≥ 0.984). Furthermore, the ET method is more effective than the RFE method for feature selection in the anxiety and stress datasets. Novelty/Improvement:The study lies in the understanding of predictive modeling for mental health and provides insights into the choice of models and techniques for accurate and early detection. Doi: 10.28991/HEF-2024-05-01-01 Full Text: PDF

Mental health disorders have become a growing public health concern among individuals recovering from COVID-19. Long COVID, a condition where symptoms persist for an extended period, can predict psychological problems among COVID-19 patients. This study aimed to investigate the prevalence of long COVID and mental health status among Thai adults who had recovered from COVID-19, identify the association between the mental health status and long COVID symptoms, and investigate the risk factors associated with the correlation between long COVID and mental health outcomes. A cross-sectional study was conducted among 939 randomly selected participants in Nakhon Si Thammarat province, southern Thailand. The Depression, Anxiety, and Stress Scale-21 was used to investigate mental health symptoms, and a checklist comprised of thirteen common symptoms was used to identify the long COVID among participants. Logistic regression models were used to investigate the risk factors associated with mental health status and long COVID symptoms among participants. Among the 939 participants, 104 (11.1%) had depression, 179 (19.1%) had anxiety, and 42 (4.8%) were stressed. A total of 745 participants (79.3%) reported experiencing at least one symptom of long COVID, with fatigue (72.9%, SE±0.02), cough (66.0%, SE±0.02), and muscle pain (54.1%, SE±0.02) being the most frequently reported symptoms. All long COVID symptoms were significantly associated with mental health status. Shortness of breath, fatigue, and chest tightness were the highest risk factors for mental health status among COVID-19 patients. The final multivariable model indicated that female patients (OR = 1.89), medical history (OR = 1.92), and monthly income lower than 5,000 Thai baht (OR = 2.09) were associated with developing long COVID symptoms and mental health status (all p<0.01). This study provides valuable insights into the potential long-term effects of COVID-19 on mental health and enhances understanding of the mechanisms underlying the condition for predicting the occurrence of mental health issues in Thai COVID-19 patients.

(1) Background: Medical cannabis (MC) is attracting global attention due to its therapeutic potential; however, the preparedness of nursing students in countries where MC remains banned is not well understood. This convergent parallel mixed-methods study aimed to examine the knowledge, attitudes, beliefs and intention to support the future legalization of MC among Vietnamese nursing students, as well as to identify factors associated with this intention. (2) Methods: A cross-sectional survey was conducted among 422 nursing students selected via simple random sampling at Dong Thap Medical College, Vietnam, alongside in-depth interviews with 10 purposefully selected participants. Data were analyzed using descriptive statistics, ordinal logistic regression, and thematic analysis. (3) Results: Nursing students achieved 56.5% of the maximum knowledge score, while attitude and belief scores were 73.5% and 68.1% of the respective maximums. Notably, 56.2% of students remained undecided about supporting the future legalization of MC. Greater knowledge and stronger beliefs regarding the therapeutic benefits and safety of MC were independently associated with higher intention to support future legalization, whereas general attitudes were not statistically significant in the multivariable model. Four core qualitative themes emerged—therapeutic value, safety and ethical concerns, professional readiness, and social, legal, and organizational impacts—providing rich contextual explanations for the quantitative findings. (4) Conclusions: Intention to support the future legalization of MC depends not only on individual knowledge and beliefs but also on confidence in evidence-based practice, professional preparedness, and regulatory oversight. Integrating education on MC into nursing curricula can enhance future workforce readiness and support evidence-based healthcare policy.

(1) Background: Medical cannabis (MC) is attracting attention globally due to its therapeutic potential; however, the preparedness of nursing students in countries where MC remains banned is limited. The convergent parallel mixed-methods study examined the knowledge, attitudes, beliefs, and intention. (2) Methods: A cross-sectional survey was conducted with 422 nursing students selected through simple random sampling at Dong Thap Medical College, Vietnam, and in-depth interviews were conducted with 10 purposefully selected participants. Descriptive statistics, ordinal logistic regression, and thematic analysis were used in the data analysis. (3) Results: Nursing students demonstrated average knowledge and positive attitudes and beliefs toward MC. Over 50% of students were undecided about supporting MC legalization. Deep knowledge and stronger beliefs about therapeutic benefits and safety were independently associated with higher intention to advocate for MC, while attitudes were not statistically significant. Four themes emerging include therapeutic value, safety and ethical concerns, professional readiness, and social, legal, and organizational impacts, providing contextual explanations for the quantitative results. (4) Conclusion: The adoption of MC is dependent not only on knowledge and beliefs but also on confidence in evidence-based practice, professional readiness, and regulatory oversight. Nursing education on MC can enhance future workforce readiness and support evidence-based healthcare policy.