Forecasting the Suitability of Online Mental Health Information for Effective Self-Care Developing Machine Learning Classifiers Using Natural Language Features

Background: Online mental health information represents important resources for people living with mental health issues. Suitability of mental health information for effective self-care remains understudied, despite the increasing needs for more actionable mental health resources, especially among young people. Objective: We aimed to develop Bayesian machine learning classifiers as data-based decision aids for the assessment of the actionability of credible mental health information for people with mental health issues and diseases. Methods: We collected and classified creditable online health information on mental health issues into generic mental health (GEN) information and patient-specific (PAS) mental health information. GEN and PAS were both patient-oriented health resources developed by health authorities of mental health and public health promotion. GENs were non-classified online health information without indication of targeted readerships; PASs were developed purposefully for specific populations (young, elderly people, pregnant women, and men) as indicated by their website labels. To ensure the generalisability of our model, we chose to develop a sparse Bayesian machine learning classifier using Relevance Vector Machine (RVM). Results: Using optimisation and normalisation techniques, we developed a best-performing classifier through joint optimisation of natural language features and min-max normalisation of feature frequencies. The AUC (0.957), sensitivity (0.900), and specificity (0.953) of the best model were statistically higher (p < 0.05) than other models using parallel optimisation of structural and semantic features with or without feature normalisation. We subsequently evaluated the diagnostic utility of our model in the clinic by comparing its positive (LR+) and negative likelihood ratios (LR−) and 95% confidence intervals (95% C.I.) as we adjusted the probability thresholds with the range of 0.1 and 0.9. We found that the best pair of LR+ (18.031, 95% C.I.: 10.992, 29.577) and LR− (0.100, 95% C.I.: 0.068, 0.148) was found when the probability threshold was set to 0.45 associated with a sensitivity of 0.905 (95%: 0.867, 0.942) and specificity of 0.950 (95% C.I.: 0.925, 0.975). These statistical properties of our model suggested its applicability in the clinic. Conclusion: Our study found that PAS had significant advantage over GEN mental health information regarding information actionability, engagement, and suitability for specific populations with distinct mental health issues. GEN is more suitable for general mental health information acquisition, whereas PAS can effectively engage patients and provide more effective and needed self-care support. The Bayesian machine learning classifier developed provided automatic tools to support decision making in the clinic to identify more actionable resources, effective to support self-care among different populations.

Download Full-text

Health Information and Teenagers in Residential Care: A qualitative Study to Identify Young People's Views

Adoption & Fostering ◽

10.1177/030857590202600404 ◽

2002 ◽

Vol 26 (4) ◽

pp. 19-25 ◽

Cited By ~ 2

Author(s):

Annabelle Bundle

Keyword(s):

Mental Health ◽

Young People ◽

Qualitative Study ◽

Health Information ◽

Personal Health ◽

Health Issues ◽

Health Concerns ◽

Mental Health Issues ◽

Children's Home ◽

Medical Examinations

Annabelle Bundle presents the results of a qualitative study, undertaken in a mixed residential children's home, which aimed to identify what looked after young people see as important in terms of health information. The young people wanted information particularly on mental health issues, keeping fit, substance use and sexual health. Many were reluctant to request appointments for personal matters and did not feel they were encouraged to ask about personal health concerns during medical examinations.

Download Full-text

Human Behavioral Analyzer using Machine Learning Technique

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.f8531.088619 ◽

2019 ◽

Vol 8 (6) ◽

pp. 5150-5154

Keyword(s):

Mental Health ◽

Machine Learning ◽

Health Issues ◽

Machine Learning Technique ◽

Behavioral Traits ◽

Low Level ◽

Mental Health Issues ◽

The World ◽

Learning Technique ◽

The Status

This research paper aims to the variety of people suffering from medium or low level of mental agitation i.e. being stress, depression etc. As countries like India in which more than 65% of the population is under the age of 35 [1] are continuously falling down the rank in the World Happiness Report, In 2018, India ranked on 133rd [2] position, and it can be concluded that the majority of population is facing mental health issues and does not have proper methods to analyze their mental health and take appropriate precautions and also to provide automated solutions to the Industry for hiring a productive group of people those are cool minded and sensible, the purpose of this research is to analyze the mental health of a person using behavioral traits of the person that are entered by the person or chosen from a list of given options throughout the analyses procedure of the application in which surveyed data is tested through Machine Learning to determine the status of mental health of a person and associated stress levels and suggesting the user with appropriate recommendations

Download Full-text

Social networking service, patient-generated health data, and population health informatics: patterns and implications for using digital technologies to support mental health

10.1101/2021.06.11.21258777 ◽

2021 ◽

Author(s):

Jiancheng Ye ◽

Zidan Wang ◽

Jiarui Hai

Keyword(s):

Mental Health ◽

Health Status ◽

Social Networking ◽

Health Information ◽

Service Use ◽

Digital Technologies ◽

Health Data ◽

Health Issues ◽

Social Networking Service ◽

Mental Health Issues

Objective: To describe and compare characteristics of the population with and without mental health issues (depression or anxiety disorder), including physical health, sleep, and alcohol use. We also examined the patterns of social networking service use, patient-generated health data on the digital platforms, and health information sharing attitudes and activities. Methods: We drew data from the National Cancer Institute's 2019 Health Information National Trends Survey (HINTS). Participants were divided into two groups by mental health status. Then, we described and compared the characteristics of social determinants of health, health status, sleeping and drinking behaviors, and patterns of social networking service use and health information data sharing between the two groups. Multivariable logistic regression models were applied to assess the predictors of mental health. All analyses were weighted to provide nationally representative estimates. Results: Participants with mental health issues are significantly more likely to be younger, White, female, have a lower income, have a history of chronic diseases, less capable of taking care of their own health; regarding behavioral health, they sleep less than six hours on average, have worse sleep quality, consume more alcohol; meanwhile, they are more likely to visit and share health information on social networking sites, write online diary blogs, participate online forum or support groups, watch health-related videos. Discussion and Conclusion: This study illustrates that individuals with mental health issues have inequitable social determinants of health, poor physical health, and behavioral health. However, they are more likely to use social network platforms and services, share their health information, and have active engagements with patient-generated health data (PGHD). Leveraging these digital technologies and services could be beneficial to develop tailored and effective strategies for self-monitoring and self-management, thus supporting mental health.

Download Full-text

Predicting Mental Health Illness using Machine Learning Algorithms

Journal of Physics Conference Series ◽

10.1088/1742-6596/2161/1/012021 ◽

2022 ◽

Vol 2161 (1) ◽

pp. 012021

Author(s):

Konda Vaishnavi ◽

U Nikhitha Kamath ◽

B Ashwath Rao ◽

N V Subba Reddy

Keyword(s):

Mental Health ◽

Machine Learning ◽

Well Being ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Childhood And Adolescence ◽

Health Issues ◽

Mental Health Issues ◽

Learning Techniques ◽

Tree Classifier

Abstract Early detection of mental health issues allows specialists to treat them more effectively and it improves patient’s quality of life. Mental health is about one’s psychological, emotional, and social well-being. It affects the way how one thinks, feels, and acts. Mental health is very important at every stage of life, from childhood and adolescence through adulthood. This study identified five machine learning techniques and assessed their accuracy in identifying mental health issues using several accuracy criteria. The five machine learning techniques are Logistic Regression, K-NN Classifier, Decision Tree Classifier, Random Forest, and Stacking. We have compared these techniques and implemented them and also obtained the most accurate one in Stacking technique based with an accuracy of prediction 81.75%.

Download Full-text

Who and How: Exploring the Preferred Senders and Channels of Mental Health Information for Wisconsin Farmers

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph16203836 ◽

2019 ◽

Vol 16 (20) ◽

pp. 3836

Author(s):

Josie M. Rudolphi ◽

Richard Berg ◽

Barbara Marlenga

Keyword(s):

Mental Health ◽

Health Information ◽

Health Resources ◽

Medical Providers ◽

Resource Dispersion ◽

Mental Health Information ◽

Safety And Health ◽

Public Health Organizations ◽

Agricultural Safety ◽

Self Administered Questionnaire

Unfavorable economic and environmental conditions have fueled the development of mental health resources and services for farmers. However, it is unclear who farmers want mental health information from (senders) and how they want mental health information delivered (channels). A self-administered questionnaire was used to determine the preferred senders of mental health information and the preferred channels of mental health information. Farmers were most receptive to receiving mental health information from medical providers, spouses/family members, and friends. Among the channels of information, respondents were interested in receiving mental health information from farm newspapers/magazines and one-on-one in person. Our findings have pragmatic implications for agricultural safety and health and public health organizations working to disseminate mental health information to farmers. Receptiveness to specific senders and channels of information among farmers should inform resource dispersion and future intervention.

Download Full-text