Browsing by Subject "Lupus Erythematosus, Cutaneous"
Now showing 1 - 4 of 4
- Results Per Page
- Sort Options
Item Assessing Disease Severity in Cutaneous Lupus Patients Using Natural Language Processing(2024-01-30) Wang, Laura; Nezafati, Kuroush; Rong, Ruichen; Park, Andrew; Zhu, Jane; Xiao, Guanghua; Xie, Yang; Yang, Donghan M.; Chong, Benjamin F.BACKGROUND: Cutaneous lupus erythematous (CLE) is an autoimmune skin disorder that manifests as inflammatory cutaneous lesions commonly in photosensitive areas. It is often chronic in nature, with exacerbations that can lead to hyperpigmentation and scarring. One tool used to measure disease activity and damage in CLE patients is the Cutaneous Lupus Erythematosus Disease Area and Severity Index (CLASI) score. There has been little work done previously using natural language processing (NLP) in dermatology to assess disease severity, though there is promising potential for its use given the role of narrative data in dermatology. OBJECTIVE: We aim to develop a NLP model that interprets physical examination (PE) documentation in CLE patients and computes disease severity scores in the form of CLASI activity and damage scores. METHODS: Dataset was derived from 50 patients enrolled in the UTSW CLE registry. 89 clinical exams of 24 patients were used in a training set, used to train the NLP model. 35 clinical exams of 26 patients were selected for a validation set, used to test the model's accuracy in prediction. An entity dictionary was defined that provided rules for labeling vocabulary pertinent to CLASI scores within the PE note. This was used to label the relationships between entities in the training and validation sets. The BERT (Bidirectional Encoder Representations from Transformers) model was trained to predict all entities and relationships in the notes, based on which the CLASI scores were calculated. After training, the model was applied to the validation set. In evaluation, scores generated from the model were compared to the ground-truth CLASI scores based on human annotation. RESULTS: The model-predicted scores had a correlation of 0.79 and 0.86 with the ground truth on the activity and damage scores, respectively, in the training set, and a 0.61 and 0.79 correlation in the validation set. The model had 0.84 and above for accuracy, recall, precision and F1 within the sub-goal of determining the category of score severity (high or low), for both training and validation sets. CONCLUSIONS: Using PE notes as the input, a BERT-based NLP model can be trained to predict CLASI scores in CLE patients. If successfully implemented, this algorithm can significantly increase the volume of real-world data available for CLE research by efficiently processing PE notes in the EHR. Future steps are to increase the size and representation of the training set to improve accuracy and external validity of BERT's predictions.Item [News](1983-10-17) Rutherford, SusanItem A Retrospective Cohort Study of Subacute Cutaneous Lupus Patients With and Without Systemic Lupus(2012-08-15) Taylor, April; Chong, Benjamin F.OBJECTIVE: To compare subacute cutaneous lupus erythematosus (SCLE) patients with systemic lupus erythematosus (SLE) (+SCLE/+SLE) versus SCLE patients without SLE (+SCLE/-SLE) over a period of five years. DESIGN: Retrospective cohort study. SETTING: Outpatient dermatology and rheumatology clinics at an academic medical center. PATIENTS: Forty-seven SCLE patients presenting between February 1989 and January 2012 were screened with nineteen meeting inclusion/exclusion criteria. PREDICTIVE VARIABLE: Anti-nuclear antibodies (ANA). RESULTS: Of the nineteen patients included, thirteen (68.4%) had SCLE only (+SCLE/-SLE) for the majority of the study period and six (31.6%) had both SCLE and SLE (+SCLE/+SLE). At baseline, +SCLE/+SLE patients were more likely to have a history of discoid lesions, oral ulcers, lupus non-specific findings, and require multiple medications. Over the five year study period, +SCLE/+SLE patients were also more likely to have ANA, immunologic disease (including anti-double-stranded DNA), renal disease, proteinuria, decreased complement, and to complain of arthralgias. Anti-Ro antibodies alone were more common in +SCLE/-SLE patients. CONCLUSIONS: Various cutaneous manifestations of lupus are present early in the course of SCLE, but laboratory values in +SCLE/+SLE become more distinct over time. Thus, the aforementioned variables should be tested for evidence of disease involvement and to ensure adequate treatment among +SCLE/+SLE patients. In contrast, +SCLE/-SLE patients may be tested for the development of anti-Ro antibodies but need not be monitored for the other laboratory abnormalities, given their rarity among patients with SCLE only. Larger prospective studies comparing disease course in SCLE patients with and without SLE are needed to verify these findings.Item The spectrum of lupus erythematosus(1990-02-15) Sontheimer, Richard D.