Automated Recognition of Visual Acuity Measurements in Ophthalmology Clinical Notes Using Deep Learning.

Purpose: Visual acuity (VA) is a critical component of the eye examination but is often only documented in electronic health records (EHRs) as unstructured free-text notes, making it challenging to use in research. This study aimed to improve on existing rule-based algorithms by developing and evaluating deep learning models to perform named entity recognition of different types of VA measurements and their lateralities from free-text ophthalmology notes: VA for each of the right and left eyes, with and without glasses correction, and with and without pinhole. Design: Cross-sectional study. Subjects: A total of 319 756 clinical notes with documented VA measurements from approximately 90 000 patients were included. Methods: The notes were split into train, validation, and test sets. Bidirectional Encoder Representations from Transformers (BERT) models were fine-tuned to identify VA measurements from the progress notes and included BERT models pretrained on biomedical literature (BioBERT), critical care EHR notes (ClinicalBERT), both (BlueBERT), and a lighter version of BERT with 40% fewer parameters (DistilBERT). A baseline rule-based algorithm was created to recognize the same VA entities to compare against BERT models. Main Outcome Measures: Model performance was evaluated on a held-out test set using microaveraged precision, recall, and F1 score for all entities. Results: On the human-annotated subset, BlueBERT achieved the best microaveraged F1 score (F1 = 0.92), followed by ClinicalBERT (F1 = 0.91), DistilBERT (F1 = 0.90), BioBERT (F1 = 0.84), and the baseline model (F1 = 0.83). Common errors included labeling VA in sections outside of the examination portion of the note, difficulties labeling current VA alongside a series of past VAs, and missing nonnumeric VAs. Conclusions: This study demonstrates that deep learning models are capable of identifying VA measurements from free-text ophthalmology notes with high precision and recall, achieving significant performance improvements over a rule-based algorithm. The ability to recognize VA from free-text notes would enable a more detailed characterization of ophthalmology patient cohorts and enhance the development of models to predict ophthalmology outcomes. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Leveraging weak supervision to perform named entity recognition in electronic health records progress notes to identify the ophthalmology exam.

OBJECTIVE: To develop deep learning models to recognize ophthalmic examination components from clinical notes in electronic health records (EHR) using a weak supervision approach. METHODS: A corpus of 39,099 ophthalmology notes weakly labeled for 24 examination entities was assembled from the EHR of one academic center. Four pre-trained transformer-based language models (DistilBert, BioBert, BlueBert, and ClinicalBert) were fine-tuned to this named entity recognition task and compared to a baseline regular expression model. Models were evaluated on the weakly labeled test dataset, a human-labeled sample of that set, and a human-labeled independent dataset. RESULTS: On the weakly labeled test set, all transformer-based models had recall > 0.93, with precision varying from 0.815 to 0.843. The baseline model had lower recall (0.769) and precision (0.682). On the human-annotated sample, the baseline model had high recall (0.962, 95 % CI 0.955-0.067) with variable precision across entities (0.081-0.999). Bert models had recall ranging from 0.771 to 0.831, and precision >=0.973. On the independent dataset, precision was 0.926 and recall 0.458 for BlueBert. The baseline model had better recall (0.708, 95 % CI 0.674-0.738) but worse precision (0.399, 95 % CI -0.352-0.451). CONCLUSION: We developed the first deep learning system to recognize eye examination components from clinical notes, leveraging a novel opportunity for weak supervision. Transformer-based models had high precision on human-annotated labels, whereas the baseline model had poor precision but higher recall. This system may be used to improve cohort and feature identification using free-text notes.Our weakly supervised approach may help amass large datasets of domain-specific entities from EHRs in many fields.

Intralesional bleomycin for treatment of a recalcitrant wart in an immunocompromised patient: A safe, effective, and underutilized therapy.

Injectable bleomycin is infrequently used for recalcitrant warts despite its efficacy, acceptable safety profile, and high patient satisfaction compared with other treatment modalities. We present an immunocompromised patient with a large recalcitrant wart successfully treated with intralesional bleomycin to provide greater clinical exposure, training, and practice with intralesional bleomycin.

Multicultural Streaming in Group Psychotherapy Supervision: Orientation to and Preparation for Culturally Humble Practice.

How do psychotherapy supervisors most effectively integrate issues and concerns about multiculturalism and social justice (MSJ) into the supervisory experience? Concrete examples of how to best address this integration are needed, and this article provides one such example. The authors propose multicultural streaming as one approach to orient supervisees about, and prepare them for, incorporation of MSJ matters into group supervision and to foster their evolving sense of culturally humble practice. This article defines multicultural streaming, presents a plan for its implementation at the group's outset, and identifies implementation guideposts for consideration. A set of cultural humility guidelines adapted for group supervision is also proposed for group facilitation. This perspective is presented with the hope of generating further discussion about integrating MSJ issues into the group supervisory experience.

Diagnostic yield of stool culture and predictive factors for positive culture in patients with diarrheal illness.

We aimed to investigate the diagnostic yield of stool cultures and identify predictive factors for positive cultures in patients with diarrheal illness.A total of 13,327 patients who underwent stool cultures due to diarrheal illness were reviewed. Stool cultures were performed for enteric pathogens, including Salmonella, Shigella, Vibrio, Klebsiella oxytoca, and Yersinia. The culture-positive group was compared with the culture-negative group who were randomly selected from culture negative patients.A total of 196 patients (1.47%) were diagnosed with positive stool culture. In 196 culture positive patients, Salmonella spp. (75.0%) was detected most commonly, followed by Vibrio (19.4%). Univariate analyses showed fever (>37.8°C), vomiting, duration and frequency of diarrhea, and high C-reactive protein (CRP) were significantly associated with positive stool culture. Multivariate analysis showed fever (odds ratio [OR], 2.33; 95% confidence interval [CI], 1.25-4.35; P = .008), ≥5/day of diarrhea (OR, 3.52; 95% CI, 1.93-6.44; P < .001) and >50 mg/L of CRP (OR, 2.27; 95% CI, 1.18-4.36; P = .014) were independent predictors for positive stool culture. OR in patients with all 3 factors was 6.55 (95% CI, 2.56-16.75; P < .001). Vomiting (OR, 0.32; 95% CI, 0.17-0.57; P < .001) was a negative predictive factor.Diagnostic yield of stool culture in patients with diarrheal illness is very low. Fever, frequency of diarrhea, and high CRP are predictors for positive stool cultures. These findings may lead to more discerning and cost-effective utilization of stool culture by clinicians.