Mat-O-Covid: Validation of a SARS-CoV-2 Job Exposure Matrix (JEM) Using Data from a National Compensation System for Occupational COVID-19

Abstract

Background. We aimed to assess the validity of the Mat-O-Covid Job Exposure Matrix (JEM) on SARS-CoV-2 using compensation data from the French National Health Insurance compensation system for occupational-related COVID-19. Methods. Deidentified compensation data for occupational COVID-19 in France were obtained between August 2020 and August 2021. The case acceptance was considered as the reference. Mat-O-Covid is an expert-based French JEM on workplace exposure to SARS-CoV-2. Bi- and multivariable models were used to study the association between the exposure assessed by Mat-O-Covid and the reference, as well as the area under the curve (AUC), sensitivity, specificity, predictive values, and likelihood ratios. Results. In the 1140 cases included, there was a close association between the Mat-O-Covid index and the reference (p < 0.0001). The overall predictivity was good, with an AUC of 0.78 and an optimal threshold at 13 per thousand. Using Youden’s J statistic resulted in 0.67 sensitivity and 0.87 specificity. Both positive and negative likelihood ratios were significant: 4.9 [2.4−6.4] and 0.4 [0.3−0.4], respectively. Discussion. It was possible to assess Mat-O-Covid’s validity using data from the national compensation system for occupational COVID-19. Though further studies are needed, Mat-O-Covid exposure assessment appears to be accurate enough to be used in research.

Keywords: COVID-19; JEM; SARS-CoV-2; accuracy; compensation; job exposure matrix; occupational; predictivity; public health; validity; work.

Figure 1

Receiver operative characteristic curve. Mat-O-Covid data were compared to the health insurance decisions on compensation. The Youden’s J statistic illustrated the cut point.