Development of a machine learning algorithm based on administrative claims data for identification of ED anaphylaxis patient visits.

Background: Epidemiologic studies of anaphylaxis commonly rely on International Classification of Diseases (ICD) codes to identify anaphylaxis cases, which may lead to suboptimal epidemiologic classification. Objective: We sought to develop and assess the accuracy of a machine learning algorithm using ICD codes and other administrative data compared with ICD code-only algorithms to identify emergency department (ED) anaphylaxis visits. Methods: We conducted a retrospective review of ED visits from January 2013 to September 2017. Potential ED anaphylaxis visits were identified using 3 methods: anaphylaxis ICD diagnostic codes (method 1), ICD symptom-based codes with or without a code indicating an allergic trigger (method 2), and ICD codes indicating a potential allergic reaction only (method 3). A machine learning algorithm was developed from administrative data, and test characteristics were compared with ICD code-only algorithms. Results: A total of 699 of 2191 (31.9%) potential ED anaphylaxis visits were classified as anaphylaxis. The sensitivity and specificity of method 1 were 49.1% and 87.5%, respectively. Method 1 used in combination with method 2 resulted in a sensitivity of 53.9% and a specificity of 68.7%. Method 1 used in combination with method 3 resulted in a sensitivity of 98.4% and a specificity of 15.1%. The sensitivity and specificity of the machine learning algorithm were 87.3% and 79.1%, respectively. Conclusions: ICD coding alone demonstrated poor sensitivity in identifying cases of anaphylaxis, with venom-related anaphylaxis missing 96% of cases. The machine learning algorithm resulted in a better balance of sensitivity and specificity and improves upon previous strategies to identify ED anaphylaxis visits.

Subjective health among LGBT persons living with disabilities: A qualitative content analysis.

OBJECTIVE: There exist significant health disparities among both lesbian, gay, bisexual, transexual (LGBT) and disability persons; however, there is a dearth of information regarding the subjective health experiences of LGBT persons living with disabilities (LGBTPWD). As such, the purpose of this study was to understand how LGBTPWD subjectively defined and characterized the meaning of health in their lives. METHOD: Using qualitative content analyses procedures outlined by Elo and Kyngäs (2008), we conducted a secondary data analysis using a larger questionnaire study that was administered via the Internet. Participants were originally asked to answer the following prompt, "Describe what it personally means to you to be healthy?" Open-ended responses from 79 participants were thematically analyzed over several inductive and comparative coding iterations by a 3-person research team. Trustworthiness of data analysis was ensured via researcher triangulation, negative case analyses, and researcher reflexivity. RESULTS: Four dimensions of subjective health emerged during the qualitative analytic process: physical wellness, emotional vitality, functionality, and social engagement. CONCLUSIONS/IMPLICATIONS: There are contextually nuanced characteristics that constitute subjective health for LGBTPWD. These findings could help rehabilitation professionals provide culturally competent interventions. Implications for future research and limitations are provided in the discussion section. (PsycINFO Database Record