Natural Language Processing Identifies Under-Documentation of Symptoms in Patients on Hemodialysis.

Link: https://doi.org/10.34067/KID.0000000694
Authors: Dai, Yang; Wen, Huei Hsun; Yang, Joanna; Gupta, Neepa; Rhee, Connie; Horowitz, Carol R; Mohottige, Dinushika; Nadkarni, Girish N; Coca, Steven; Chan, Lili

Abstract: Patients on hemodialysis (HD) have a high burden of emotional and physical symptoms. These symptoms are often under-recognized. NLP can be used to identify patient symptoms from the EHR. However, whether symptom documentation matches patient reported burden is unclear. We conducted a prospective study of patients seen at an ambulatory nephrology practice from September 2020 to April 2021. We collected symptom surveys from patients, nurses, and physicians. We then developed a natural language processing (NLP) algorithm to identify symptoms from the patients’ electronic health records (EHR) and validated the performance of this algorithm using manual chart review and patient surveys as a reference standard. Using patient surveys as the reference standard, we compared symptom identification by 1) physicians, 2) nurses, 3) physicians or nurses, and 4) NLP. We enrolled 97 patients into our study, 63% were female, 49% were Non-Hispanic Black, and 41% were Hispanic. The most common symptoms reported by patients were fatigue (61%), cramping (59%), dry skin (53%), muscle soreness (43%), and itching (41%). Physicians and nurses significantly under-recognized patients’ symptoms (sensitivity 0.51 (95% CI 0.40-0.61) and 0.63 (95% CI 0.52-0.72) respectively). Nurses were better at identifying symptoms when patients reported more severe symptoms. There was no difference in results by patients’ sex or ethnicity. NLP had a sensitivity of 0.92, specificity of 0.95, PPV of 0.75, and NPV of 0.99 with manual EHR review as the reference standard, and a sensitivity of 0.58 (95% CI 0.47-0.68), specificity of 0.73 (95% CI 0.48-0.89), PPV of 0.92 (95% CI 0.82-0.97), and NPV of 0.24 (95% CI 0.14-0.38) compared with patient surveys. While patients on HD report high prevalence of symptoms, symptoms are under-recognized and under-documented. NLP was accurate at identifying symptoms when they were documented. Larger studies in representative populations are needed to assess the generalizability of the results of the study.