Ethical Implications of the Use of Language Analysis Technologies for the Diagnosis and Prediction of Psychiatric Disorders

Investigating Health and Well-Being Challenges Faced by an Aging Workforce in the Construction and Nursing Industries: Computational Linguistic Analysis of Twitter Data

BACKGROUND

Construction and nursing are critical industries. Although both careers involve physically and mentally demanding work, the risks to workers during the COVID-19 pandemic are not well understood. Nurses (both younger and older) are more likely to experience the ill effects of burnout and stress than construction workers, likely due to accelerated work demands and increased pressure on nurses during the COVID-19 pandemic. In this study, we analyzed a large social media data set using advanced natural language processing techniques to explore indicators of the mental status of workers across both industries before and during the COVID-19 pandemic.

OBJECTIVE

This social media analysis aims to fill a knowledge gap by comparing the tweets of younger and older construction workers and nurses to obtain insights into any potential risks to their mental health due to work health and safety issues.

METHODS

We analyzed 1,505,638 tweets published on Twitter (subsequently rebranded as X) by younger and older (aged <45 vs >45 years) construction workers and nurses. The study period spanned 54 months, from January 2018 to June 2022, which equates to approximately 27 months before and 27 months after the World Health Organization declared COVID-19 a global pandemic on March 11, 2020. The tweets were analyzed using big data analytics and computational linguistic analyses.

RESULTS

Text analyses revealed that nurses made greater use of hashtags and keywords (both monograms and bigrams) associated with burnout, health issues, and mental health compared to construction workers. The COVID-19 pandemic had a pronounced effect on nurses' tweets, and this was especially noticeable in younger nurses. Tweets about health and well-being contained more first-person singular pronouns and affect words, and health-related tweets contained more affect words. Sentiment analyses revealed that, overall, nurses had a higher proportion of positive sentiment in their tweets than construction workers. However, this changed markedly during the COVID-19 pandemic. Since early 2020, sentiment switched, and negative sentiment dominated the tweets of nurses. No such crossover was observed in the tweets of construction workers.

CONCLUSIONS

The social media analysis revealed that younger nurses had language use patterns consistent with someone experiencing the ill effects of burnout and stress. Older construction workers had more negative sentiments than younger workers, who were more focused on communicating about social and recreational activities rather than work matters. More broadly, these findings demonstrate the utility of large data sets enabled by social media to understand the well-being of target populations, especially during times of rapid societal change.

ChatGPT is not ready yet for use in providing mental health assessment and interventions

Background

Psychiatry is a specialized field of medicine that focuses on the diagnosis, treatment, and prevention of mental health disorders. With advancements in technology and the rise of artificial intelligence (AI), there has been a growing interest in exploring the potential of AI language models systems, such as Chat Generative Pre-training Transformer (ChatGPT), to assist in the field of psychiatry.

Objective

Our study aimed to evaluates the effectiveness, reliability and safeness of ChatGPT in assisting patients with mental health problems, and to assess its potential as a collaborative tool for mental health professionals through a simulated interaction with three distinct imaginary patients.

Methods

Three imaginary patient scenarios (cases A, B, and C) were created, representing different mental health problems. All three patients present with, and seek to eliminate, the same chief complaint (i.e., difficulty falling asleep and waking up frequently during the night in the last 2°weeks). ChatGPT was engaged as a virtual psychiatric assistant to provide responses and treatment recommendations.

Results

In case A, the recommendations were relatively appropriate (albeit non-specific), and could potentially be beneficial for both users and clinicians. However, as complexity of clinical cases increased (cases B and C), the information and recommendations generated by ChatGPT became inappropriate, even dangerous; and the limitations of the program became more glaring. The main strengths of ChatGPT lie in its ability to provide quick responses to user queries and to simulate empathy. One notable limitation is ChatGPT inability to interact with users to collect further information relevant to the diagnosis and management of a patient's clinical condition. Another serious limitation is ChatGPT inability to use critical thinking and clinical judgment to drive patient's management.

Conclusion

As for July 2023, ChatGPT failed to give the simple medical advice given certain clinical scenarios. This supports that the quality of ChatGPT-generated content is still far from being a guide for users and professionals to provide accurate mental health information. It remains, therefore, premature to conclude on the usefulness and safety of ChatGPT in mental health practice.

Detecting at-risk mental states for psychosis (ARMS) using machine learning ensembles and facial features

AIMS

Our study aimed to develop a machine learning ensemble to distinguish "at-risk mental states for psychosis" (ARMS) subjects from control individuals from the general population based on facial data extracted from video-recordings.

METHODS

58 non-help-seeking medication-naïve ARMS and 70 healthy subjects were screened from a general population sample. At-risk status was assessed with the Structured Interview for Prodromal Syndromes (SIPS), and "Subject's Overview" section was filmed (5-10 min). Several features were extracted, e.g., eye and mouth aspect ratio, Euler angles, coordinates from 51 facial landmarks. This elicited 649 facial features, which were further selected using Gradient Boosting Machines (AdaBoost combined with Random Forests). Data was split in 70/30 for training, and Monte Carlo cross validation was used.

RESULTS

Final model reached 83 % of mean F1-score, and balanced accuracy of 85 %. Mean area under the curve for the receiver operator curve classifier was 93 %. Convergent validity testing showed that two features included in the model were significantly correlated with Avolition (SIPS N2 item) and expression of emotion (SIPS N3 item).

CONCLUSION

Our model capitalized on short video-recordings from individuals recruited from the general population, effectively distinguishing between ARMS and controls. Results are encouraging for large-screening purposes in low-resource settings.