Dataset Information

Comparison of predicted psychological distress among workers between artificial intelligence and psychiatrists: a cross-sectional study in Tsukuba Science City, Japan.

ABSTRACT:

Objectives

Psychological distress is a worldwide problem and a serious problem that needs to be addressed in the field of occupational health. This study aimed to use artificial intelligence (AI) to predict psychological distress among workers using sociodemographic, lifestyle and sleep factors, not subjective information such as mood and emotion, and to examine the performance of the AI models through a comparison with psychiatrists.

Design

Cross-sectional study.

Setting

We conducted a survey on psychological distress and living conditions among workers. An AI model for predicting psychological distress was created and then the results were compared in terms of accuracy with predictions made by psychiatrists.

Participants

An AI model of the neural network and six psychiatrists.

Primary outcome

The accuracies of the AI model and psychiatrists for predicting psychological distress.

Methods

In total, data from 7251 workers were analysed to predict moderate and severe psychological distress. An AI model of the neural network was created and accuracy, sensitivity and specificity were calculated. Six psychiatrists used the same data as the AI model to predict psychological distress and conduct a comparison with the AI model.

Results

The accuracies of the AI model and psychiatrists for predicting moderate psychological distress were 65.2% and 64.4%, respectively, showing no significant difference. The accuracies of the AI model and psychiatrists for predicting severe psychological distress were 89.9% and 85.5%, respectively, indicating that the AI model had significantly higher accuracy.

Conclusions

A machine learning model was successfully developed to screen workers with depressed mood. The explanatory variables used for the predictions did not directly ask about mood. Therefore, this newly developed model appears to be able to predict psychological distress among workers easily, regardless of their subjective views.

SUBMITTER: Doki S

PROVIDER: S-EPMC8231007 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundPandemics and natural disasters are immensely stressful events for frontline healthcare workers, as they provide patient care to a population undergoing the impacts of the disaster while experiencing such impacts to their personal lives themselves. With increased stressors to an already demanding job, frontline healthcare workers are at a higher risk of adverse effects to their mental health. The current COVID-19 pandemic has already shown to have had significant impact on the mental health of healthcare workers with increased rates of burnout, anxiety and depression. There is already literature showing the utility of individual programs at improving mental health, however, interventions at the organizational level are not well explored. This scoping review aims to provide an overview and determine the utility of a systematic review of the current body of literature assessing the effectiveness of mental health interventions at the organizational level for healthcare workers during or after a public health emergency.MethodsElectronic databases such as Medline on OVID, CENTRAL, PsycINFO on OVID and Embase on OVID were searched. A targeted search of the grey literature was conducted to identify any non-indexed studies. The population, concept and context approach was used to develop the eligibility criteria. Articles were included if (1) they assessed the impact of interventions to improve wellbeing or reduce the distress on healthcare personnel, first responders or military actively providing medical care; (2) provided quantitative or qualitative data with clearly defined outcomes that focused on established mental health indicators or qualitative descriptions on distress and wellbeing, validated scales and workplace indicators; (3) focused on organizational level interventions that occurred in a public health crisis.ResultsThe literature search resulted in 4007 citations and 115 potentially relevant full-text papers. All except 5 were excluded. There were four review articles and one experimental study. There were no other unpublished reports that warranted inclusion.ConclusionsThere is a distinct lack of research examining organizational interventions addressing mental resilience and well-being in healthcare workers in disaster settings. A systematic review in this area would be low yield. There is a clear need for further research in this area.

Project description:In Cambodia, there has been an increase in entertainment work as a result of the breakdown of the traditional brothel-based sex industry, presenting new challenges to addressing the health issues and needs of people working in the entertainment industry. This study aims to identify factors associated with psychological distress among female entertainment workers (FEWs) in Cambodia.A two-stage cluster sampling method was used to randomly select 657 FEWs from entertainment establishments in Phnom Penh and Siem Reap in April and May 2014 for interviews using a structured questionnaire. Psychological distress was measured using the General Health Questionnaire (GHQ-12), and multivariate logistic regression analysis was conducted.Almost half of FEWs (43.2 %) had a higher level of psychological distress (GHQ-12 > 3), while 19.5 % reported having suicidal thoughts, and 7.3 % reported having attempted to commit suicide in the past 3 months. Controlling for confounding factors, women with a higher level of psychological distress were significantly more likely to rate their overall health (AOR = 1.88, 95 % CI 1.20 to 2.94) and quality of life (AOR = 2.39, 95 % CI 1.47 to 3.87) as poor. They were also significantly more likely to have suicidal ideation (AOR = 2.41, 95 % CI 1.45 to 3.76), rate their HIV risk as higher than the general population (AOR = 0.48, 95 % CI 0.31 to 0.74), have been forced to drink at work (AOR = 1.77, 95 % CI 1.19 to 2.62), have had clients requesting not to use a condom (AOR = 3.48, 95 % CI 1.14 to 10.62), be not able to find condoms when they needed it (AOR = 0.64, 95 % CI 0.45 to 0.93), have had a family member who said hurtful things to them during childhood (AOR = 1.84, 95 % CI 1.24 to 2.75), and have had a parent or guardian who had been physically abused (AOR = 1.93, 95 % CI 1.34 to 2.82).FEWs in Cambodia experience high levels of psychological distress, which likely stems from both past negative experiences and current working conditions. For women that are experiencing psychological distress, intervention programs aimed at improving mental health should specifically address substance use, condom availability and negotiation skills, and suicide risk.

Project description:The coronavirus disease 2019 (COVID-19) pandemic may have a negative impact on mental health of the population, leading to higher suicide rates, in many countries. However, little is known about risk factors associated with worsened mental health during the COVID-19 pandemic. To investigate the factors associated with serious psychological distress (SPD) during the COVID-19 pandemic in Japan. A cross-sectional study using a large-scale internet survey conducted between August 25 and September 30, 2020, in Japan. Demographics (age, gender, marital status, family composition, and caregiving burden), socio-economic status (income level, employment type, educational attainment), the experience of domestic violence (DV), the state of emergency, fear of COVID-19, and stigma related to COVID-19. Prevalence of SPD, defined as Kessler 6 scale score ≥13. Among 25,482 individuals included in this study, 2,556 (10%) met the criteria of SPD. Overall, women (adjusted odds ratio [aOR] 1.59; 95%CI, 1.17-2.16; P=0.003), ages 15-29 (aOR compared with ages 45-59, 2.35; 95%CI, 1.64-3.38; P<0.001), low income (aOR compared with intermediate income, 1.70; 95%CI, 1.16-2.49; P=0.007), providing caregiving to family members (aOR, 5.48; 95%CI, 3.51-8.56; P<0.001), experiencing DV (aOR, 5.72; 95%CI, 3.81-8.59; P<0.001), and fear of COVID-19 (aOR, 1.96; 95%CI, 1.55-2.48; P<0.001) were associated with a higher rate of SPD. Among women aged 15-29 years, who experienced the highest rate of SPD, caregiving, DV, fear of COVID-19, and COVID-19-related stigma were associated with a higher rate of SPD; whereas economic situation (income level and employment type) and social isolation (marital status) were not associated with the prevalence of SPD. Economic situation, caregiving burden, DV, and fear of COVID-19 were independently associated with SPD during the COVID-19 pandemic. Among young women-who have a higher risk of suicide during the COVID-19 pandemic in Japan-similar factors, except economic situation, were associated with a higher rate of SPD. Targeted interventions based on age and gender may be more effective in mitigating the negative impact of the COVID-19 pandemic on the population's mental health.