From gestalt to gene: early predictive dysmorphic features of PMM2-CDG

Abstract

IntroductionPhosphomannomutase-2 deficiency (PMM2-CDG) is associated with a recognisable facial pattern. There are no early severity predictors for this disorder and no phenotype–genotype correlation. We performed a detailed dysmorphology evaluation to describe facial gestalt and its changes over time, to train digital recognition facial analysis tools and to identify early severity predictors.MethodsPaediatric PMM2-CDG patients were evaluated and compared with controls. A computer-assisted recognition tool was trained. Through the evaluation of dysmorphic features (DFs), a simple categorisation was created and correlated with clinical and neurological scores, and neuroimaging.ResultsDysmorphology analysis of 31 patients (4–19 years of age) identified eight major DFs (strabismus, upslanted eyes, long fingers, lipodystrophy, wide mouth, inverted nipples, long philtrum and joint laxity) with predictive value using receiver operating characteristic (ROC) curveanalysis (p<0.001). Dysmorphology categorisation using lipodystrophy and inverted nipples was employed to divide patients into three groups that are correlated with global clinical and neurological scores, and neuroimaging (p=0.005, 0.003 and 0.002, respectively). After Face2Gene training, PMM2-CDG patients were correctly identified at different ages.ConclusionsPMM2-CDG patients’ DFs are consistent and inform about clinical severity when no clear phenotype–genotype correlation is known. We propose a classification of DFs into major and minor with diagnostic risk implications. At present, Face2Gene is useful to suggest PMM2-CDG. Regarding the prognostic value of DFs, we elaborated a simple severity dysmorphology categorisation with predictive value, and we identified five major DFs associated with clinical severity. Both dysmorphology and digital analysis may help physicians to diagnose PMM2-CDG sooner.

AZATAX: Acetazolamide safety and efficacy in cerebellar syndrome in PMM2 congenital disorder of glycosylation (PMM2‐CDG)

“…7 In a practical way, positive responses were already achieved at 6 weeks (V 6 ) in most responder patients, meaning that a 6-week trial may be enough to test whether a patient would benefit from the treatment. 19 Interestingly, clinical improvement was also evident in other scales, such as the NPCRS and the PATA rate, yielding consistency from our results at different clinical levels. 19 Interestingly, clinical improvement was also evident in other scales, such as the NPCRS and the PATA rate, yielding consistency from our results at different clinical levels.…”

“…Furthermore, initial clinical features were identified as positive predictors for response; on the one hand were patients with higher ICARS, higher NPCRS, and greater atrophy at the beginning, which denoted that severely affected patients tend to improve more; on the other hand were patients suffering from epilepsy or those showing lipodystrophy, which is a marker of severity in PMM2-CDG. 19 Interestingly, clinical improvement was also evident in other scales, such as the NPCRS and the PATA rate, yielding consistency from our results at different clinical levels.…”

Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

“…In all cases, PMM2-CDG appeared in the top 10 syndrome matches offered by the tool. A recognizable facial pattern in PMM2-CDG patients was identified and three different age groups (0-5, 6-11, and 12-18) of PMM2-CDG patients were also differentially discriminated [90].…”

“…One of the major pitfalls in CDG is accurate and timely diagnosis [90]. Face2Gene was used to analyze facial photos of a cohort of 31 PMM2-CDG patients.…”

A comprehensive overview of biometric fusion

“…Recent work in differential privacy in the context of a single biometric modality [205,206] could potentially be extended to multibiometric templates. However, guaranteeing privacy may not be an easy task especially due to the advent of powerful deep learning techniques that can be leveraged for gleaning ancillary information about a subject that was previously not thought to be possible [207]. Another related challenge has to do with the retention of recognition accuracy whist imparting security and privacy.…”