Ewbank MP, Cummins R, Tablan V, et al. - Researchers conducted this quality improvement study using a deep learning model applied to a large-scale clinical data set of cognitive behavioral therapy (CBT) session transcripts to generate a quantifiable measure of treatment delivered and to explore the connection between the amount of each aspect of therapy delivered and clinical results. Between June 2012 and March 2018, all data were obtained from patients receiving internet-enabled CBT for the treatment of a mental health disorder in England. In the final analysis, treatment sessions were included from a total of 14,899 patients aged between 18 and 94 years (median age, 34.8 years). An association was found between clinical results in psychotherapy and the content of what therapists said. These results support the concept that CBT methods of change can improve the presenting symptoms of patients. Applying deep learning to large clinical data sets can offer valuable insights into psychotherapy, and help with new treatment development and to standardize clinical practice.