On Monday 21 June 2021, I gave a talk at Leiden University's SAILS Lunch Seminar on Natural Language Processing for Translational Data Science in Mental Healthcare. First, I positioned the research domain of Translational Data Science, in the context of the COVIDA research programme on Dutch NLP for healthcare. Then, I presented our prognostic study on inpatient violence risk assessment by applying natural language processing techniques to clinical notes in patients’ electronic health records (Menger et al, 2019). Finally, I discussed followup work where we try to better understand the performance of the best performing RNN model using LDA as a text representation method among others, which reminded us once more of the lingering issue of data quality in EHRs.