Evaluating Face-Recognition Technology in Syndrome Diagnosis
Research type
Research Study
Full title
Evaluating the Clinical Utility of Face-Recognition Technology in Syndrome Diagnosis
IRAS ID
174839
Contact name
Lynne Webster
Contact email
Sponsor organisation
Manchester University NHS Foundation Trust
Duration of Study in the UK
2 years, 0 months, 6 days
Research summary
Resarch Summary:
Birth defects are relatively common, occurring in 1 in 40 liveborn babies. They can be single, or multiple. They may occur as part of multiple malformation syndromes, often in association with growth disturbance or intellectual disability. Over 7000 rare syndromes have been identified. Thus, though they are rare they are collectively important. Understanding how a multiple malformation syndrome came about, defining what investigations and health surveillance is needed for affected children and identifying whether there is a treatment is very important for parents and professionals caring for affected children and also for genetic counselling of their extended families, since the majority will have a genetic basis. Diagnosis of these rare disorders is therefore important,but as many syndromes are rare this can be extremely difficult and requires specialist knowledge, many investigations and many hospital appointments. This study aims to determine whether using face-recognition software can improve diagnosis of rare syndromes when used in addition to current routine practice.Summary of Results:
Birth defects are relatively common, occurring in 1 in 40 liveborn babies. They can be single, or multiple. They may occur as part of multiple malformation syndromes, often in association with growth disturbance or intellectual disability. Over 7000 rare syndromes have been identified. Thus, though they are rare they are collectively important. Understanding how a multiple malformation syndrome came about, defining what investigations and health surveillance is needed for affected children and identifying whether there is a treatment is very important for parents and professionals caring for affected children and also for genetic counselling of their extended families, since the majority will have a genetic basis. Diagnosis of these rare disorders is therefore important, but as many syndromes are rare this can be extremely difficult and requires specialist knowledge, many investigations and many hospital appointments.Recently, advances in technology have led to the development of software which can analyse facial features in detail and suggest possible diagnoses. There is some published evidence to suggest that tools like this can detect tiny differences in facial features which are specific to particular disorders. This study aims to determine whether using face-recognition software can improve diagnosis of rare syndromes when used in addition to current routine practice.
Study Outcomes
An ad hoc recruitment strategy was set up, to identify eligible individuals with developmental disorders that affect craniofacial development (otherwise known as dysmorphic developmental disorders, DDD) referred to the general paediatric clinics of the Manchester Centre for Genomic Medicine (MCGM) and reviewed by consultants and specialists in training in clinical genetics. This included individuals where a DDD was suspected on clinical grounds, prior to genetic testing and also individuals with molecularly confirmed diagnoses of a DDD. A successful collaboration with the Face2Gene project team was established to ensure that consented patient photographs were included in a safe, password-protected, web-based interface accessible only to MCGM Consultants and Specialty Doctors in Training who were participating in this study.
Using this strategy, 106 participants consented, were recruited and suitable photographs were uploaded on the MCGM interface of the Face2Gene project (https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Furl6570.hra.nhs.uk%2Fls%2Fclick%3Fupn%3DXv3JSvJ-2B3M71ppf7N9agbdNJudfBjvaucqfEPLBM9kER8vQF-2FCe0PjmW5ieKgN-2BFIF8B_E1aO2-2BZlVOSJJV-2FajQqskegTd6IRomHYTi-2Fbt8SH3YLXCixGlBCdM6YidvptCy5siMGaViOBHX2n60Pub78xtgvaodQjzc05KJeB-2FkD6tNbdAlDXQ3UaGtYpkv7PA3aC7ZnqhF-2Fv18p9GG-2BV37TN-2FcCuF4tnL8CLFVg7Aw5LJcGFj9XGkjFfcq5wjf95CgAAgzc1bb-2BeRVtHIbbHSxNHDA-3D-3D&data=04%7C01%7Capprovals%40hra.nhs.uk%7Ca0f554a2e1d9430d060008d9cc710f25%7C8e1f0acad87d4f20939e36243d574267%7C0%7C0%7C637765608219868555%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=gWRXxTidrCfYgb5Pu3l3idKrTiOy3WLL5tL%2BtNxtUsY%3D&reserved=0 Each recruiting doctor also contributed a filled-in data collection proforma detailing their observations before and after inclusion on the MCGM Face2Gene web-based interface. Finally a small subset of recruiting doctors (4) contributed their opinion in an audit about the use of image analysis technology in this setting.
It is important to take into consideration that the last period of the study was impacted by the COVID-19 pandemic and leadership changes as the CI of the project moved to a new position outside of the United Kingdom.
This study has resulted in an extensive cohort of data that is now awaiting analysis for total and conclusive findings regarding the utility of image analysis technologies in the standard setting of a general genetic paediatric clinic based in an NHS Trust. This study has also built foundations for good working relationships between MCGM and international stakeholders in this field and enabled an international dialogue about global clinical collaborations on identifiable patient data. We hope to report on the final results in due course.
Scientific publications relating to study:
Hsieh TC, Mensah MA, Pantel JT, Aguilar D, Bar O, Bayat A, Becerra-Solano L, Bentzen HB, Biskup S, Borisov O, Braaten O, Ciaccio C, Coutelier M, Cremer K, Danyel M, Daschkey S, Eden HD, Devriendt K, Wilson S, Douzgou S, Đukić D, Ehmke N, Fauth C, Fischer-Zirnsak B, Fleischer N, Gabriel H, Graul-Neumann L, Gripp KW, Gurovich Y, Gusina A, Haddad N, Hajjir N, Hanani Y, Hertzberg J, Hoertnagel K, Howell J, Ivanovski I, Kaindl A, Kamphans T, Kamphausen S, Karimov C, Kathom H, Keryan A, Knaus A, Köhler S, Kornak U, Lavrov A, Leitheiser M, Lyon GJ, Mangold E, Reina PM, Carrascal AM, Mitter D, Herrador LM, Nadav G, Nöthen M, Orrico A, Ott CE, Park K, Peterlin B, Pölsler L, Raas-Rothschild A, Randolph L, Revencu N, Fagerberg CR, Robinson PN, Rosnev S, Rudnik S, Rudolf G, Schatz U, Schossig A, Schubach M, Shanoon O, Sheridan E, Smirin-Yosef P, Spielmann M, Suk EK, Sznajer Y, Thiel CT, Thiel G, Verloes A, Vrecar I, Wahl D, Weber I, Winter K, Wiśniewska M, Wollnik B, Yeung MW, Zhao M, Zhu N, Zschocke J, Mundlos S, Horn D, Krawitz PM. PEDIA: prioritization of exome data by image analysis. Genet Med. 2019;21:2807-2814.
doi: 10.1038/s41436-019-0566-2, https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Furl6570.hra.nhs.uk%2Fls%2Fclick%3Fupn%3DXv3JSvJ-2B3M71ppf7N9agbbeFIxM0b2IFzcIKNwoej7Idf-2FrwmKuvZN0J3PVqpbVhG5IWUqA2iCYKwbxtEsS58g-3D-3Do63J_E1aO2-2BZlVOSJJV-2FajQqskegTd6IRomHYTi-2Fbt8SH3YLXCixGlBCdM6YidvptCy5sW2svnRyBESdi6Fq85r5bKO6R8mQznNq6lP36cgrocd894EqBBGHo1tJlm1sh4DTCC7RDcwo-2BfYuC2ytM9ts8PZJC12-2BxJN8v426M4ph8tetPq-2BPG20bLJNl3v38jEE358b6SlsGrB1ZHAsZMg4B4JA-3D-3D&data=04%7C01%7Capprovals%40hra.nhs.uk%7Ca0f554a2e1d9430d060008d9cc710f25%7C8e1f0acad87d4f20939e36243d574267%7C0%7C0%7C637765608219868555%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=dFMauf6ai3htgYgldcl144IWkzMZQgppQUZdKC4wlVI%3D&reserved=0
Nellåker C, Alkuraya FS, Baynam G, Bernier RA, Bernier FPJ, Boulanger V, Brudno M, Brunner HG, Clayton-Smith J, Cogné B, Dawkins HJS, deVries BBA, Douzgou S, Dudding-Byth T, Eichler EE, Ferlaino M, Fieggen K, Firth HV, FitzPatrick DR, Gration D, Groza T, Haendel M, Hallowell N, Hamosh A, Hehir-Kwa J, Hitz MP, Hughes M, Kini U, Kleefstra T, Kooy RF, Krawitz P, Küry S, Lees M, Lyon GJ, Lyonnet S, Marcadier JL, Meyn S, Moslerová V, Politei JM, Poulton CC, Raymond FL, Reijnders MRF, Robinson PN, Romano C, Rose CM, Sainsbury DCG, Schofield L, Sutton VR, Turnovec M, Van Dijck A, Van Esch H, Wilkie AOM; Minerva Consortium. Enabling Global Clinical Collaborations on Identifiable Patient Data: The Minerva Initiative. Front Genet. 2019;10:611.
doi:10.3389/fgene.2019.00611, https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Furl6570.hra.nhs.uk%2Fls%2Fclick%3Fupn%3DXv3JSvJ-2B3M71ppf7N9agbTz8cxsQF9Zcn5jbmwy3NZeOuX87ZC2uz5AC-2FyZmBL8mT0Xv6MRG2I-2F1x8oVglCefmqIwfHK2wcDY-2BfnOk-2BDYa4-3Dbpr9_E1aO2-2BZlVOSJJV-2FajQqskegTd6IRomHYTi-2Fbt8SH3YLXCixGlBCdM6YidvptCy5ssdvZW2vxHlIFEmgBhwEtXpCXKJZOWlik8eygGeuXuHHQvkeMoa5Ofl-2Fh1RBioro66uZcqRM2vnhhKhQVRYCBmPmW356R4yO4gfNkWrPRi9hCTMjOMg3j8hO8j7CwDSzynCPPIASlE-2FOAPVLa50XdJw-3D-3D&data=04%7C01%7Capprovals%40hra.nhs.uk%7Ca0f554a2e1d9430d060008d9cc710f25%7C8e1f0acad87d4f20939e36243d574267%7C0%7C0%7C637765608219868555%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=NyIzOGJcRrIU3e%2Bf4EKevq1JlOKluq8mZyz6wCxMBos%3D&reserved=0REC name
Wales REC 4
REC reference
17/WA/0394
Date of REC Opinion
8 Dec 2017
REC opinion
Favourable Opinion