Utility of 3D Facial Analysis As A Biomarker In Rare Diseases Exploration with Hereditary Angioedema

ImportanceDigital Phenotyping (DP) utilizes digital technologies to assess observable phenotypic traits, enhancing our understanding of various disease states. It aims to support equitable interventions through diverse digital data, fostering inclusivity by integrating various digital devices. Central to DP is identifying digital biomarkers (DBMs), which offer real-time health monitoring and personalized insights into disease conditions. Applying machine learning (ML) techniques on non-invasive signals sets the ideal platform for precision medicine application, especially in rare diseases (RDs). People living with rare diseases (PLWRD) often face significant challenges in receiving timely and accurate diagnoses, leading to what is known as a diagnostic odyssey. Digital phenotyping (DP) offers a promising solution by leveraging advanced technology, such as 3D facial photography, to capture unique digital signatures associated with various rare diseases. This innovative approach not only aids in the identification of these conditions but also facilitates the detection of digital biomarkers (DBM). These biomarkers enable healthcare providers to monitor the progression of the disease over time, enhancing patient care and potentially shortening the duration of the diagnostic odyssey. By utilizing DP and DBMs, we can improve both the diagnosis and management of RDs, ultimately leading to better health outcomes for affected participants. ObjectiveTo identify whether DBMs can be identified by DP utilizing 3D facial imaging techniques in outpatient settings in participants with RDs. The primary objective of this study was to determine if specific facial measurements in participants with RD who experience transient episodes of facial swelling (oedema) differ from established ethnically matched norms. The secondary objective was to assess peri-orbital and/or facial swelling as a potential biomarker for identifying flare-ups in hereditary angioedema (HAE). Design, setting, and participantsThis multicentre observational study was conducted in 3 hospitals in Singapore. The eligible participants were male and female RD participants of various age groups. The study duration was 4 years and 8 months. Interventions: Twenty participants of Chinese genetic ancestry were photographed using a 3D camera. Additionally, two participants with hereditary angioedema (HAE) were photographed during acute stages of disease flare-ups. Main outcomes and measuresThe obtained facial scans of participants (that included participants with HAE in non-acute phase) were plotted using Artificial Intelligence-powered software - Cliniface. The growth curves and facial landmarks obtained were compared against the growth curves of normal RD-unaffected individuals of Chinese genetic ancestry. The two participants with HAE were photographed qualitatively over a longer period of time, and their scans were plotted, yielding growth curves. ResultsDistinct facial markers such as periorbital swelling were identified in two qualitatively assessed HAE participants during flare-up stages. This provides an opportunity to explore and validate further if these facial signatures in a disease condition can be assigned as DBM for HAE. Conclusions and relevanceThis study explores the utility of 3D facial analysis as a DBM in rare diseases such as HAE. Applying non-invasive signals coupled with AI may open new vistas for precision medicine in real-world settings. The individual measurements that yielded small p-values demonstrate significant relevance and potential utility. These findings offer preliminary objective evidence that supports existing subjective reports of facial features in the literature. Additionally, while DPs diagnostic capabilities may be limited, it successfully identified DBM, which could facilitate disease monitoring in conditions such as HAE. Author SummaryRare diseases pose a significant challenge to all stakeholders, including clinicians, patients families, care providers, and the healthcare system. Diagnostic delays are integral and impose a massive financial and emotional burden on everyone involved in care delivery, beyond the patients themselves. A universally acceptable, scalable, and replicable non-invasive mechanism to detect distinct biomarkers associated with a rare disease can help identify the diseases signs and symptoms far earlier and ease the burden. An easy-to-deploy approach could be 3D facial imaging of patients with rare diseases, which are associated with distinct or subtle facial changes at different stages of disease progression. A rare disease, such as hereditary angioedema, which is known to exhibit facial swelling in patients during the acute disease state, is a prime example. The facial changes can be identified and assigned as specific disease markers, also known as facial biomarkers. These facial biomarkers can be identified and measured using 3D facial imaging when patients present to the clinic. Subsequently, these initial signs can be correlated clinically to establish a firm diagnosis earlier than traditional approaches.