Natural Language Processing-Assisted Classification Models to Confirm Monoclonal Gammopathy of Undetermined Significance and Progression in Veterans' Electronic Health Records

The Association of Agent Orange Exposure with the progression of monoclonal gammopathy of undetermined significance to multiple myeloma: a population-based study of Vietnam War Era Veterans

Herbicide and pesticide exposure [e.g., agent orange (AO)] is associated with an increased risk of multiple myeloma (MM) due to the contaminant, 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD). However, it is unclear whether TCDD/AO exposure (AO exposure hereafter) increases the risk of progression of monoclonal gammopathy of undetermined significance (MGUS) to MM. We sought to evaluate the association in a nationwide study of US Veterans. A natural language processing algorithm was used to confirm MGUS and progression to MM. We included Veterans who were diagnosed with MGUS from 10/1/1999 to 12/31/2021 and served during the Vietnam War Era from 1/9/1962 to 5/7/1975. AO exposure was stratified according to three TCDD exposure levels: high (1/9/1962-11/30/1965), medium (12/1/1965-12/31/1970), or low (1/1/1971-5/7/1975). The association between AO exposure and progression was analyzed using multivariable Fine-Gray subdistribution hazard model with death as a competing event. The analytic cohort included 10,847 Veterans with MGUS, of whom 26.3% had AO exposure and 7.4% progressed to MM over a median follow-up of 5.2 years. In multivariable analysis, high exposure was associated with an increased progression rate (multivariable-adjusted hazard ratio 1.48; 95% confidence interval 1.02-2.16), compared to Veterans with no exposure. This information is critical to inform progression risk in patients diagnosed with MGUS and prior AO exposure. It is also applicable to MGUS patients with occupational TCDD exposure from herbicides and pesticides.