Relationship between night work and health-related quality of life: an analysis based on profiles and cumulative duration of exposure to night work among French workers in the CONSTANCES cohort.

OBJECTIVE: The aim of this study is to estimate the association between night work and health-related quality of life (HRQoL) among French workers. The association between cumulative duration of night work and HRQoL was also investigated. METHODS: Three career-long night work exposure groups were defined at inclusion in the CONSTANCES cohort: permanent night workers, rotating night workers and former night workers. Day workers with no experience of night work were the reference group. HRQoL was assessed using the Short Form Health Survey (SF-12), in particular the physical component summary (PCS) and mental component summary (MCS) scores, with a higher score indicating better HRQoL. Several linear regression models were built to test the association between night work exposure and HRQoL. The relationship between cumulative duration of night work and HRQoL scores was analyzed using generalised additive models. RESULTS: The sample consisted of 10,372 participants. Former night workers had a significantly lower PCS score than day workers (ß [95% CI]: - 1.09 [- 1.73; - 0.45], p = 0.001), whereas permanent night workers had a significantly higher MCS score (ß [95% CI]: 1.19 [0.009; 2.36], p = 0.048). A significant decrease in PCS score from 5 to 20 years of cumulative night work was observed among former night workers. CONCLUSIONS: Former night workers had poorer physical HRQoL in contrast to permanent and rotating night workers who had similar or even better HRQoL than day workers, suggesting the well-known healthy worker survivor effect. Consequently, both current and former night workers require regular and specific follow-up focused on the physical components of their health.

[Development of an artificial intelligence system to improve cancer clinical trial eligibility screening]. / Développement d'une solution d'intelligence artificielle pour améliorer le screening en recherche clinique.

INTRODUCTION: The recruitment step of all clinical trials is time consuming, harsh and generate extra costs. Artificial intelligence tools could improve recruitment in order to shorten inclusion phase. The objective was to assess the performance of an artificial intelligence driven tool (text mining, machine learning, classification…) for the screening and detection of patients, potentially eligible for recruitment in one of the clinical trials open at the "Institut de Cancérologie de Lorraine". METHODS: Computerized clinical data during the first medical consultation among patients managed in an anticancer center over the 2019-2023 period were used to study the performances of an artificial intelligence tool (SAS® Viya). Recall, precision and F1-score were used to determine the artificial intelligence algorithm effectiveness. Time saved on screening was determined by the difference between the time taken using the artificial intelligence-assisted method and that taken using the standard method in clinical trial participant screening. RESULTS: Out of 9876 patients included in the study, the artificial intelligence algorithm obtained the following scores: precision of 96 %, recall of 94 % and a 0.95 F1-score to detect patients with breast cancer (n=2039) and potentially eligible for inclusion in a clinical trial. The screening of 258 potentially eligible patient's files took 20s per file vs. 5min and 6s with standard method. DISCUSSION: This study suggests that artificial intelligence could yield sizable improvements over standard practices in several aspects of the patient screening process, as well as in approaches to feasibility, site selection, and trial selection.