When the prediction scoring variables were expanded to 25 variables the screening algorithm approached 100% sensitivity/specificity. The 25 variable algorithm run on general population EHR data identified 26 patients as increased risk for HAE at the medical centers.
Rationale: Hereditary angioedema (HAE) is a genetic condition characterized by dysregulation of the complement pathway leading to intermittent and recurrent episodes of angioedema. The goal of this project was to determine if an automated prediction scoring system can identify patients at increased risk for Hereditary Angioedema (HAE). Methods: A prediction scoring system for HAE was created and validated using known cases of HAE from the medical literature as well as positive and negative controls from HAE-focused centers. Using key features of medical and family history, a series of logistic regression models for the five known genetic causes of HAE were created. Top variables populated the digital suspicion scoring system and were run against de-identified electronic health record (EHR) data. Patients were categorized as increased, possible, or no increased risk of HAE at two diverse sites. Results: Prediction scoring using the strongest 13 variables on the “real world” EHR positive control data identified all but one C1-inhibitor deficiency case and one non-C1-inhibitor deficiency case without false positives. The two missed cases had no documented family history of HAE in their EHR. When the prediction scoring variables were expanded to 25 variables the screening algorithm approached 100% sensitivity/specificity. The 25 variable algorithm run on general population EHR data identified 26 patients as increased risk for HAE at the medical centers. Conclusions: These results suggest that development, validation, and implementation of automated prediction scoring systems can be useful to aid providers in identifying patients with rare genetic conditions.
| Poster Number: | 124 |
| Event: | 2022 - AAAAI Annual Meeting |
| Publication: | The Journal of Allergy and Clinical Immunology |
| Author(s): | Marissa Shams, MD, Dawn A. Laney, MS , Dave A. Jacob, BS , Jingjing Yang, PhD, Jessica Dronen, MS , Amanda Logue, MD , Ami Rosen, MS , Marc Riedl, MD |
| Affiliation(s): | Emory University, Emory University School of Medicine, ThinkGenetic Foundation, ThinkGenetic, Inc, Ochsner Lafayette General, University of California, San Diego |
| DOI: | 10.1016/j.jaci.2021.12.170 |
| Link: | https://www.jacionline.org/article/S0091-6749(21)01993-X/fulltext |
| Poster: | Array |
| Citations: | Laney, Dawn & Shams, Marissa & Jacob, Dave & Yang, JingJing & Dronen, Jessica & Logue, Amanda & Rosen, Ami & Riedl, Marc. (2022). Implementation of an automated prediction scoring system to identify patients at possible increased risk for Hereditary Angioedema. Journal of Allergy and Clinical Immunology. 149. AB42. 10.1016/j.jaci.2021.12.170. |
