Conectar
To identify and explore variable groups and individual predictors of long sickness absences outside of well-known predictors such as service use and previous sickness absence using machine learning, explainable artificial intelligence methods and a submodel approach.
Retrospective study of prospectively collected registry data on sickness absences and a questionnaire used in health examinations.
Electronic medical record data of one large occupational health service provider in Finland.
11 533 employees of various occupations who, between 2011 and 2019, had at least once completed a health questionnaire that could be linked to service usage data and who had not had their initial health check within 1 year before or 3 months after completing the questionnaire.
To identify predictors of at least one long sickness absence period (≥30 days) during a 2-year follow-up.
The highest area under the receiver operating characteristic curve (AUROC) values among the submodel groups were for the sickness absence and service use submodels (0.68–0.74). The AUROC values for the submodels of sociodemographic factors, health habits or diseases data category ranged from 0.55 to 0.67 and from 0.55 to 0.67 for the submodels of questionnaire data. The AUROC value of the ensemble model that combined all submodels was 0.79 (95% CI 0.788 to 0.794).
The most important factors predicting long sickness absences based on the submodels were reported pain, number of symptoms and diseases, body mass index and short sleep duration. Additionally, several work and mental health-related variables increased the risk of long sickness absence.
Other variables besides service use and sickness absence increase the accuracy in predicting long sickness absence and providing information for planning interventions that could have a beneficial impact on work disability risk.
To (1) analyse managers' experiences with handling patient safety incident reports in an incident reporting software, identifying key challenges; (2) analyse the incident report processes from the managers' perspective; (3) examine managers' perceptions of ways to support and improve health professionals' experiences of report-handling processes; and (4) investigate how, from their point of view, incident reporting software should be developed in the future.
A descriptive qualitative study.
Interviews and focus group discussions on Microsoft Teams from 11/2024 to 3/2025, including 16 participants, analysis with deductive and inductive content analysis.
Of 16 participants, 15 were managers and one was a patient safety expert. Most were nurse managers (n = 9). Four discussion themes were divided into 30 categories. Participants highlighted the need to improve the reporting software's terminology, classification and analysis tools. The use of artificial intelligence was desired but not currently integrated into the software. Participants were unsure of their skills to use all the software features. Clear and transparent handling processes, feedback, managers' behaviour and communication methods were seen as key to improving staff's experience with report processes. A real-time warning system was considered beneficial for various incident types. Specific questions must be answered before further developing such systems.
This study deepened the understanding of reporting software's challenges regarding its handling features. The handling processes of incident reports had multiple shortcomings, which may negatively affect health professionals' experiences in report handling. Real-time warning systems could assist healthcare managers in processing reports.
Organisational-level guidance for incident report processing is needed. Improvements to report processing and reporting software can improve shared learning and understanding of the status of patient safety.
No patient or public contribution.
COnsolidated criteria for REporting Qualitative research Checklist.
FreshRSS 