Published, peer-reviewed, and open to everyone.

Acute Hepatic Porphyria (AHP) is a group of four rare genetic but treatable diseases that often go undiagnosed due to non-specific symptoms, under-recognition by clinicians, and lack of access to specialists and appropriate testing. Reviewing 45 patients evaluated for AHP at UCLA, this study finds significant underdiagnosis in non-White and male patients, shows that combining biochemical and genetic testing outperforms either alone, and recommends broader diagnostic awareness in specialties like psychiatry and obstetrics/gynecology that serve high-risk populations.

This document details an impromptu community gathering following the cancelation of an ARPA-H proposer's day for the Rare Disease AI/ML for Precision Integrated Diagnostics (RAPID) program. The discussion became a powerful example of how shared commitment to improving patient outcomes can transcend institutional boundaries and administrative hurdles. This white paper synthesizes perspectives from healthcare providers, academic researchers, industry experts, registry providers, and people with lived experience to identify critical bottlenecks that must be addressed to accelerate progress in the rare disease field.

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.

Using electronic health records (EHR) data from two centers we developed models to predict: 1) who will be referred for AHP testing, and 2) who will test positive. The best models achieved 89-93% accuracy on the test set. These models appeared capable of recognizing 71% of the cases earlier than their true diagnosis date, reducing diagnostic delays by an average of 1.2 years.