Search

Background Acute Hepatic Porphyria is a group of four rare genetic but treatable diseases that often go undiagnosed due to its non-specific symptoms, under-recognition of the condition by clinicians, and the lack of access to specialists and appropriate testing. This case-control study investigates the phenotypic and demographic patterns in Acute Hepatic Porphyria (AHP) patients at a tertiary care center (University of California Los Angeles) to update recommendations for recognition and diagnosis of this disease in our community. Method A retrospective chart analysis was conducted on 45 patients who were evaluated for AHP, Electronic Medical Record (EMR) data was collected and analyzed to investigate clinical differences and correlations. Results 27 patients tested positive for AHP through urinary metabolites and confirmatory genetic testing and 18 patients tested negative; of those, 16 patients received a definite alternative diagnosis. Hashimoto's, T1DM (Type 1 Diabetes Mellitus), Fibromyalgia and cannabinoid use with cyclic vomiting syndrome were negatively correlated with AHP, while psychiatric disorders and OBGYN disorders were positively correlated with AHP. The highest rate of diagnosis resulted from a combination of genetic and biochemical testing. Testing outside of an acute attack was not associated with a positive diagnosis. Conclusions Patients with a history of OBGYN disorders and psychiatric disorders may be at increased risk of having AHP, yet there is a lack of involvement of these specialties in the diagnosis and care of AHP, in addition to a lack of studies investigating AHP in non-white populations potentially leading to reduced recognition of AHP.

Background: Acute hepatic porphyria (AHP) is a group of rare but treatable conditions associated with diagnostic delays of 15 years on average. The advent of electronic health records (EHR) data and machine learning (ML) may improve the timely recognition of rare diseases like AHP. However, prediction models can be difficult to train given the limited case numbers, unstructured EHR data, and selection biases intrinsic to healthcare delivery. We sought to train and characterize models for identifying patients with AHP., Methods: This diagnostic study used structured and notes-based EHR data from 2 centers at the University of California, UCSF (2012-2022) and UCLA (2019-2022). The data were split into 2 cohorts (referral and diagnosis) and used to develop models that predict (1) who will be referred for testing of acute porphyria, among those who presented with abdominal pain (a cardinal symptom of AHP), and (2) who will test positive, among those referred. The referral cohort consisted of 747 patients referred for testing and 99 849 contemporaneous patients who were not. The diagnosis cohort consisted of 72 confirmed AHP cases and 347 patients who tested negative. The case cohort was 81% female and 6-75 years old at the time of diagnosis. Candidate models used a range of architectures. Feature selection was semi-automated and incorporated publicly available data from knowledge graphs. Our primary outcome was the F-score on an outcome-stratified test set., Results: The best center-specific referral models achieved an F-score of 86%-91%. The best diagnosis model achieved an F-score of 92%. To further test our model, we contacted 372 current patients who lack an AHP diagnosis but were predicted by our models as potentially having it (≥10% probability of referral, ≥50% of testing positive). However, we were only able to recruit 10 of these patients for biochemical testing, all of whom were negative. Nonetheless, post hoc evaluations suggested that these models could identify 71% of cases earlier than their diagnosis date, saving 1.2 years., Conclusions: ML can reduce diagnostic delays in AHP and other rare diseases. Robust recruitment strategies and multicenter coordination will be needed to validate these models before they can be deployed., (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)