A1 Refereed original research article in a scientific journal
Towards automated detection of psychosocial risk factors with text mining
Authors: Uronen L, Moen H, Teperi S, Martimo KP, Hartiala J, Salantera S
Publisher: OXFORD UNIV PRESS
Publishing place: Oxford
Publication year: 2020
Journal: Occupational Medicine
Journal name in source: OCCUPATIONAL MEDICINE-OXFORD
Journal acronym: OCCUP MED-OXFORD
Volume: 70
Issue: 3
First page : 203
Last page: 206
Number of pages: 4
ISSN: 0962-7480
eISSN: 1471-8405
DOI: https://doi.org/10.1093/occmed/kqaa022
Web address : 10.1093/occmed/kqaa022
Abstract
Background Psychosocial risk factors influence early retirement and absence from work. Health checks by occupational health nurses (OHNs) may prevent deterioration of work ability. Health checks are documented electronically mostly as free text, and therefore the effect of psychological risk factors on working capacity is difficult to detect.Aims To evaluate the potential of text mining for automated early detection of psychosocial risk factors by examining health check free-text documentation, which may indicate medical statements recommending early retirement, prolonged sick leave or rehabilitation. Psychosocial risk factors were extracted from OHN documentation in a nationwide occupational health care registry.Methods Analysis of health check documentation and medical statements regarding pension, sick leave and rehabilitation. Annotations of 13 psychosocial factors based on the Prima-EF standard (PAS 1010) were used with a combination of unsupervised machine learning, a document search engine and manual filtering.Results Health check documentation was analysed for 7078 employees. In 83% of their health checks, psychosocial risk factors were mentioned. All of these occurred more frequently in the group that received medical statements for pension, rehabilitation or sick leave than the group that did not receive medical statement. Documentation of career development and work control indicated future loss of work ability.Conclusions This study showed that it was possible to detect risk factors for sick leave, rehabilitation and pension from free-text documentation of health checks. It is suggested to develop a text mining tool to automate the detection of psychosocial risk factors at an early stage.
Background Psychosocial risk factors influence early retirement and absence from work. Health checks by occupational health nurses (OHNs) may prevent deterioration of work ability. Health checks are documented electronically mostly as free text, and therefore the effect of psychological risk factors on working capacity is difficult to detect.Aims To evaluate the potential of text mining for automated early detection of psychosocial risk factors by examining health check free-text documentation, which may indicate medical statements recommending early retirement, prolonged sick leave or rehabilitation. Psychosocial risk factors were extracted from OHN documentation in a nationwide occupational health care registry.Methods Analysis of health check documentation and medical statements regarding pension, sick leave and rehabilitation. Annotations of 13 psychosocial factors based on the Prima-EF standard (PAS 1010) were used with a combination of unsupervised machine learning, a document search engine and manual filtering.Results Health check documentation was analysed for 7078 employees. In 83% of their health checks, psychosocial risk factors were mentioned. All of these occurred more frequently in the group that received medical statements for pension, rehabilitation or sick leave than the group that did not receive medical statement. Documentation of career development and work control indicated future loss of work ability.Conclusions This study showed that it was possible to detect risk factors for sick leave, rehabilitation and pension from free-text documentation of health checks. It is suggested to develop a text mining tool to automate the detection of psychosocial risk factors at an early stage.
UTU Research Portal