A deep learning based method for intelligent detection of seafarers' mental health condition

Zhu, Zhen; Wang, Renda; Zhu, Wei

doi:10.1038/s41598-022-11207-7

Cited by 7 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…92 A recent attempt might be emerging. Zhen et al 93 have developed a mental health test scale for seafarers (SMHT) measuring 13 mental health dimensions, including life on-board-related. The scale presents good initial reliability and validity.…”

Section: Discussionmentioning

confidence: 99%

A Systematic Review of Assessment Methods for Seafarers’ Mental Health and Well-Being During the COVID-19 Pandemic

Carrera-Arce,

Baumler,

Hollander

2023

INQUIRY

View full text Add to dashboard Cite

Seafarers spend more time at sea than on land, which makes them a hard-to-reach community. Since their mental health and well-being is usually addressed from a land-based perspective, dedicated and validated methods incorporating maritime specificities are lacking. During the COVID-19 pandemic, research into seafarers’ mental health and well-being flourished. However, a systematic review of the literature to assess the type and appropriateness of assessment methods pertaining to the mental health and well-being of seafarers has yet to be undertaken. This study reviews 5 databases (ERIC, Scopus, PubMed, Google Scholar and EBSCO) to assess the methods used to examine seafarers’ mental health and well-being during the pandemic. Peer-reviewed literature alongside grey literature that applied quantitative or qualitative instruments to measure seafarers’ mental health and/or well-being, published in English between March 2020 and February 2023, was eligible for the review. Studies from all geographic regions and regardless of nationality, rank and ship type of the subjects were explored. Database searches produced 272 records. Five additional records were identified via other methods. We identified 27 studies suitable for review, including 24 published in peer-reviewed scientific journals and 3 reports and surveys produced by the industry or welfare organizations. Assessment methods used to measure seafarers’ mental health and well-being vary significantly in the literature. The frequent use of ad hoc questionnaires limits the possibility to replicate and compare the studies due to various inconsistencies. Furthermore, several validation and reliability measures needed more solidity when applied to the seafaring population. Such inadequate measuring and a mix of assessment methods impacted the comparison of results and might inflate the risks of underreporting or overstating mental complaints.

show abstract

Section: Discussionmentioning

confidence: 99%

A Systematic Review of Assessment Methods for Seafarers’ Mental Health and Well-Being During the COVID-19 Pandemic

Carrera-Arce,

Baumler,

Hollander

2023

INQUIRY

View full text Add to dashboard Cite

show abstract

“…Three studies mentioned ML based predictive analytics to enhance medical decision-making and help medical professionals to identify patterns and trends that can be used to predict a seafarers health status [25], [27], [28]. These studies were used to identify seafarers who are at risk of developing mental health issues such as depression, anxiety, and loneliness.…”

Section: Enhancing Medical Decision-making Through MLmentioning

confidence: 99%

Exploring the integration of artificial intelligence (AI) and augmented reality (AR) in maritime medicine: A narrative literature review (Preprint)

Battineni,

Chintalapudi,

Ricci

et al. 2023

Preprint

View full text Add to dashboard Cite

UNSTRUCTURED This narrative literature review explores the integration of artificial intelligence (AI) and augmented reality (AR) in the field of maritime medicine. A comprehensive search was conducted in academic databases using relevant search terms, resulting in the identification of 257 records. After screening for relevance and quality, a final review was conducted on 17 papers. The review highlights the potential applications and benefits of AI and AR in enhancing medical practices and safety measures for seafarers. The integration of AI and AR technologies in maritime medicine shows promise in providing real-time medical assistance, remote consultations, augmented training, and improved diagnostic capabilities. Additionally, AI-driven predictive models can aid in early detection of health issues and support proactive health management onboard ships. Challenges related to data privacy, connectivity at sea, and the need for regulatory frameworks are also discussed. The data analysis reported in this review contributes to a better understanding of the current state and future potential of AI and AR in maritime medicine and provide insights into opportunities for further research and implementation in the maritime industry.

show abstract

“…A dual testing technique [20] was developed to achieve a seafarers' mental health status. In this model, the Seafarers' mental health Test scale (SMHT) and fuzzy factor analysis was used to test the data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…It is the proportion of exact detection of MHD over the total samples or labels tested. It is computed as 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 = 𝑇𝑟𝑢𝑒 𝑃𝑜𝑠𝑖𝑡𝑖𝑣𝑒 (𝑇𝑃)+𝑇𝑟𝑢𝑒 𝑁𝑒𝑔𝑎𝑡𝑖𝑣𝑒 (𝑇𝑁) 𝑇𝑃+𝑇𝑁+𝐹𝑎𝑙𝑠𝑒 𝑃𝑜𝑠𝑖𝑡𝑖𝑣𝑒 (𝐹𝑃)+𝐹𝑎𝑙𝑠𝑒 𝑁𝑒𝑔𝑎𝑡𝑖𝑣𝑒 (𝐹𝑁) (20) TP measures an outcome where the CSI-ISDNN exactly classifies the MHD as MHD. FP measures an outcome where the CSI-ISDNN inexactly classifies the MHD labels as non-MHD.FN measures an outcome where the CSI-ISDNN inexactly classifies the non-MHD labels as MHD.…”

Section: Accuracymentioning

confidence: 99%

A Self-Stabilizing and Parameter-Optimized Deep Learning Model for Predicting Mental Health Disorder

2022

IJIES

View full text Add to dashboard Cite

A mental health disorder (MHD) is a behavioural or mental pattern that causes significant distress or impairment of personal functioning. Daily distress faced in social, work, or family activities are associated with MHD which severely affects the person's life style leading to increase of death cases. So, it is very important to detect the MHD at earlier stage itself. Many machine learning (ML) techniques have been suggested to detect MHD based on patient data. But, the ML methods cannot process the large samples efficiently. So, the deep learning (DL) algorithms have been developed for the detection of MHD efficiently. But still, fixed network parameters used in DL methods cannot always perform well for large scale datasets. Also, irrelevant feature in the datasets degrades the performances of DL models. Moreover, stabilization will be another issue of the DL methods. To resolve the above mentioned problems, a chicken swarm intelligence improved self stabilized deep neural network (CSI-ISDNN) is proposed in this article to detect and diagnose the MHD more efficiently. The proposed method employs CSI on training dataset where CS will select the best optimal features and parameters for ISDNN. The fitness value of the CS is then calculated and analysed to find optimised prediction results of ISDNN for MHD with the goal of reducing prediction error. The stabilization of ISDNN is standardized by introducing some additional parameters along with original network parameters. The trained CSI-ISDNN model is used to predict test datasets. Finally, the experimental results exhibit that the CSI-ISDNN model achieves an accuracy of 97.4% on the OSMI mental health database. The accuracy of CSI-ISDNN is superior by 10.18%, 6.21%, 2.63%, and 0.0093% compared to classic model like IGCBA-BPNN, CNN-RNN, CNN-Bi-LSTM, and CSI-MLP respectively.

show abstract

A deep learning based method for intelligent detection of seafarers' mental health condition

Cited by 7 publications

References 40 publications

A Systematic Review of Assessment Methods for Seafarers’ Mental Health and Well-Being During the COVID-19 Pandemic

A Systematic Review of Assessment Methods for Seafarers’ Mental Health and Well-Being During the COVID-19 Pandemic

Exploring the integration of artificial intelligence (AI) and augmented reality (AR) in maritime medicine: A narrative literature review (Preprint)

A Self-Stabilizing and Parameter-Optimized Deep Learning Model for Predicting Mental Health Disorder

Contact Info

Product

Resources

About