Computational analysis of non-adherence and non-attendance using the text of narrative physician notes in the electronic medical record

Abstract

Non-adherence to physician recommendations is common and is thought to lead to poor clinical outcomes. However, no techniques exist for a large-scale assessment of this phenomenon. We evaluated a computational approach that quantifies patient non-adherence from an analysis of the text of physician notes. Index of non-adherence (INA) was computed based on the number of non-adherence word tags detected in physician notes. INA was evaluated by comparing the results to a manual patient record review at the individual sentence and patient level. The relationship between INA and frequency of Emergency Department visits was determined. The positive predictive value of identification of individual non-adherence word tags was 93.3%. The Pearson correlation coefficient between the INA and the number of documented instances of non-adherence identified by manual review was 0.62. The frequency of ED visits was more than twice as high for patients with INA in the highest quartile (least adherent) than for patients with INA in the lowest (most adherent) quartile (p < 0.0001). We have described the design and evaluation of a novel approach that allows quantification of patient non-adherence with physician recommendations through an analysis of physician notes. This approach has been validated at several levels and demonstrated to correlate with clinical outcomes.

Keywords:

• Non-adherence
• non-compliance
• narrative notes
• electronic medical record

Acknowledgements

We would like to thank Dr. Shawn Murphy, Jeanne Guerin and Vivian Gainer of Research Patient Data Registry for their invaluable help in obtaining the data. We would like to acknowledge Dr. Maria Shubina at the Brigham and Women's Hospital Center for Clinical Investigation Biostatistics Core for her advice on statistical evaluation. We would also like to express our gratitude to Partners Research Computing and Hewlett-Packard staff, including Dennis Gurgul, Lance Davidow, and Werner Hahn for their unwavering IT support. This research was supported in part by the NLM Training Grant T15-LM-07092-11 (AT), NHLBI training grant T32-HL007609, NLM grant 1U54LM008748 (ISK), and Diabetes Trust Foundation (AT).