The TRACTOR Project: TRACking and MoniToring Occupational Risks in Agriculture Using French Insurance Health Data (MSA).

OBJECTIVES: A vast data mining project called 'TRACking and moniToring Occupational Risks in agriculture' (TRACTOR) was initiated in 2017 to investigate work-related health events among the entire French agricultural workforce. The goal of this work is to present the TRACTOR project, the challenges faced during its implementation, to discuss its strengths and limitations and to address its potential impact for health surveillance. METHODS: Three routinely collected administrative health databases from the National Health Insurance Fund for Agricultural Workers and Farmers (MSA) were made available for the TRACTOR project. Data management was required to properly clean and prepare the data before linking together all available databases. RESULTS: After removing few missing and aberrant data (4.6% values), all available databases were fully linked together. The TRACTOR project is an exhaustive database of agricultural workforce (active and retired) from 2002 to 2016, with around 10.5 million individuals including seasonal workers and farm managers. From 2012 to 2016, a total of 6 906 290 individuals were recorded. Half of these individuals were active and 46% had at least one health event (e.g. declared chronic disease, reimbursed drug prescription) during this 5-year period. CONCLUSIONS: The assembled MSA databases available in the TRACTOR project are regularly updated and represent a promising and unprecedent dataset for data mining analysis dedicated to the early identification of current and emerging work-related illnesses and hypothesis generation. As a result, this project could help building a prospective integrated health surveillance system for the benefit of agricultural workers.

Medico-administrative data combined with agricultural practices data to retrospectively estimate pesticide use by agricultural workers.

This work is part of a global project aiming to use medico-administrative big data from the whole French agricultural population (~3 millions), collected through their mandatory health insurance system (Mutualité Sociale Agricole), to highlight associations between chronic diseases and agricultural activities. At the request of the French Agency for Food, Environmental and Occupational Health & Safety (ANSES), our objective was to estimate which pesticides were probably used by each agricultural worker, in order to include this information in our analyses and search for association with diseases. We selected five databases to achieve this objective: the Graphical Land Parcel Registration (RPG), the French Agricultural Census, "Cultivation Practice" surveys from the Agriculture ministry, the MATPHYTO crop-exposure matrix and the Compilation of Phytosanitary Indexes from the French Public Health Agency. A geographical grid was designed to use geographical location while maintaining worker anonymity, dividing France into square tracts of variable surface each containing a minimum of 1500 agricultural workers. We developed an automated algorithm to predict each individual potential exposure by crossing her/his occupational activity, the geographical grid and the RPG to deduce cultivation practices and use it as a gateway to estimate pesticides use. This approach allowed drawing, from administrative data, a list of substances potentially used by each agricultural worker throughout France. Results of the algorithm are illustrated at collective level (descriptive statistics for the whole population), as well as at individual level (some workers taken as examples). The generalization of this method in other national contexts is discussed. By linking this information with the health insurance databases, this approach could contribute to the agricultural workers health surveillance.