AI-assisted facial phenotyping supports rare genetic disorder prioritization by retrieving visually similar diagnosed cases from facial image reference databases such as the GestaltMatcher Database (GMDB). Existing GestaltMatcher-based retrieval frameworks compare each test image with individual gallery images in a facial phenotype embedding space. However, this pointwise formulation does not fully exploit available evidence, because patients may have multiple images and disorders may be represented by multiple diagnosed gallery patients. We propose an inference-time multi-level evidence aggregation framework that improves facial phenotype retrieval without modifying the underlying GestaltMatcher-Arc encoder. The framework combines embedding-level patient aggregation of multiple images from the same individual, patient-weighted disorder centroids, and hybrid individual-centroid scoring to integrate test-patient observations, disorder-level gallery evidence, and local nearest-neighbor evidence. We evaluated the approach on GMDB v1.1.4 across disorders represented during training (GMDB-Freq), unseen disorders (GMDB-Rare), and multi-image patient subsets, using a unified gallery containing both GMDB-Freq and GMDB-Rare disorders. Multi-level evidence aggregation improved mean per-disorder top-$N$ retrieval accuracy across all evaluation subsets. Top-1 accuracy increased from 38.52% to 48.82% on GMDB-Freq and from 19.38% to 23.79% on GMDB-Rare. On multi-image subsets, top-1 accuracy increased from 46.12% to 60.94% on GMDB-Multi-Freq and from 18.54% to 26.71% on GMDB-Multi-Rare. These findings show that inference-time aggregation can improve next-generation facial phenotype retrieval without retraining the encoder, supporting a shift from isolated single-image matching toward multi-level aggregation of patient and disorder evidence for rare-disorder prioritization.
Alexander Hustinx, Carolin Kaffiné, Behnam Javanmardi et al.· 0 citations
Variants in BRSK2, encoding brain specific kinase-2, have recently been associated with an autosomal dominant neurodevelopmental disorder (NDD). We have assembled 52 cases with heterozygous BRSK2 variants and variable neurodevelopmental phenotypes with frequent neuropsychiatric and behavioral symptoms. The variant spectrum included 15 different truncating variants, seven (potential) splice variants, three structural variants, and 12 different missense variants. Of the missense variants, seven were in the kinase domain, and the others in the UBA and the KA1 domain or outside domains. Variants occurred de novo in 19 cases and were inherited in 18. We utilized Drosophila melanogaster as a model and assessed viability and performed climbing and bang sensitivity assays upon knockdown of the fly orthologue sff or upon overexpression of wildtype or mutant human BRSK2. Pan-neuronal knockdown of sff resulted in impaired locomotor behavior and seizure susceptibility. Ubiquitous or pan-neuronal overexpression of human wildtype BRSK2 in Drosophila resulted in lethality or locomotor impairment, respectively, indicating toxicity. Overexpressing mutant BRSK2 did not or incompletely affect viability and locomotor behavior for six of seven tested kinase domain missense variants and one KA1 domain variant, indicating a (partial) loss-of-function effect. Interestingly, overexpressing BRSK2 with the remaining missense variant from the kinase domain and the two most C-terminal missense variants resulted in possible gain of function. Our findings further delineate the clinical and molecular spectrum of BRSK2-associated NDD and provide further insights into the role of BRSK2/sff in nervous system function and dysfunction.
Palak Singhal, Tzung-Chien Hsieh, Nadja Ehmke et al.· European Journal of Human Ge...· 0 citations
Results demonstrate that hierarchical modeling of 3D facial geometry enables interpretable, ontology-linked phenotype classification, though performance on rare leaf terms remains limited.
F. Hellmann, Alexander Hustinx, Benjamin D. Solomon et al.· 0 citations
