Browse
Submit Data
Databases
API
Help

Dataset Information

19 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Diagnostically relevant facial gestalt information from ordinary photos.

ABSTRACT: Craniofacial characteristics are highly informative for clinical geneticists when diagnosing genetic diseases. As a first step towards the high-throughput diagnosis of ultra-rare developmental diseases we introduce an automatic approach that implements recent developments in computer vision. This algorithm extracts phenotypic information from ordinary non-clinical photographs and, using machine learning, models human facial dysmorphisms in a multidimensional 'Clinical Face Phenotype Space'. The space locates patients in the context of known syndromes and thereby facilitates the generation of diagnostic hypotheses. Consequently, the approach will aid clinicians by greatly narrowing (by 27.6-fold) the search space of potential diagnoses for patients with suspected developmental disorders. Furthermore, this Clinical Face Phenotype Space allows the clustering of patients by phenotype even when no known syndrome diagnosis exists, thereby aiding disease identification. We demonstrate that this approach provides a novel method for inferring causative genetic variants from clinical sequencing data through functional genetic pathway comparisons.DOI: http://dx.doi.org/10.7554/eLife.02020.001.

SUBMITTER: Ferry Q

PROVIDER: S-EPMC4067075 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Introducing polymer conductance in diagnostically relevant transduction.

Project description:In this work we demonstrate that an impedance derived capacitance method is able to cleanly resolve the resonant conductance characteristics of an electrode-confined polymer film. In decorating the film with receptors, this conductance is thereafter modulated by the capturing of specific targets, demonstrated herein with C-reactive protein. This entirely reagentless and single step marker quantification is relevant to the drive of moving assays to a scaleable format requiring minimal user intervention.

| S-EPMC7581358 | biostudies-literature

Forgotten features of head zones and their relation to diagnostically relevant acupuncture points.

Project description:In the 1890s Sir Henry Head discovered certain areas of the skin that develop tenderness (allodynia) in the course of visceral disease. These areas were later termed "Head zones". In addition, he also emphasized the existence of specific points within these zones, that he called "maximum points", a finding that seems to be almost forgotten today. We hypothesized that two important groups of acupuncture points, the diagnostically relevant Mu and Shu points, spatially and functionally coincide with these maximum points to a large extent. A comparison of Head's papers with the Huang Di Neijing (Yellow Thearch's Inner Classic) and the Zhen Jiu Jia Yi Jing (Systematic Classic of Acupuncture and Moxibustion), two of the oldest still extant Chinese sources on acupuncture, revealed astonishing parallels between the two concepts regarding both point locations and functional aspects. These findings suggest that the Chinese discovery of viscerocutaneous reflexes preceded the discovery in the West by more than 2000 years. Furthermore, the fact that Chinese medicine uses Mu and Shu points not only diagnostically but also therapeutically may give us new insights into the underlying mechanisms of acupuncture.

| S-EPMC3135114 | biostudies-literature

Using photos of basic facial expressions as a new approach to measuring implicit attitudes.

Project description:BackgroundMeasuring implicit attitudes is difficult due to social desirability (SD). A new method, the Emotion Based Approach (EBA), can solve this by using emotions from a display of faces as response categories. We applied this on an EBA Spirituality tool (EBA-SPT) and an Actual Situation tool (EBA-AST). Our aim was to assess the structure, reliability and validity of the tools and to compare two EBA assessment approaches, i.e., an explicit one (only assessing final replies to items) and an implicit one (assessing also the selection process).MethodsWe obtained data on a sample of Czech adults (n = 522, age 30.3±12.58; 27.0% men) via an online survey; cortisol was assessed in 46 participants. We assessed the structure and psychometric properties (internal consistency and test-retest reliability; convergent, discriminant, and criterion validity) of the EBA, and examined the differences between explicit vs. implicit EBA approaches.ResultsWe found an acceptable-good internal consistency reliability of the EBA tools, acceptable discriminant validity between them and low (neutral expression) to good (joy) test-retest reliability for concrete emotions assessed by the tools. An implicit EBA approach showed stronger correlations between emotions and weaker convergent validity, but higher criterion validity, than an explicit approach and standard questionnaires.ConclusionCompared to standard questionnaires, EBA is a more reliable approach for measuring attitudes, with an implicit approach that reflects the selection process yielding the best results.

| S-EPMC8118344 | biostudies-literature

Photos provide information on age, but not kinship, of Andean bear.

Project description:Using photos of captive Andean bears of known age and pedigree, and photos of wild Andean bear cubs <6 months old, we evaluated the degree to which visual information may be used to estimate bears' ages and assess their kinship. We demonstrate that the ages of Andean bear cubs ≤6 months old may be estimated from their size relative to their mothers with an average error of <0.01 ± 13.2 days (SD; n = 14), and that ages of adults ≥10 years old may be estimated from the proportion of their nose that is pink with an average error of <0.01 ± 3.5 years (n = 41). We also show that similarity among the bears' natural markings, as perceived by humans, is not associated with pedigree kinship among the bears (R (2) < 0.001, N = 1,043, p = 0.499). Thus, researchers may use photos of wild Andean bears to estimate the ages of young cubs and older adults, but not to infer their kinship. Given that camera trap photos are one of the most readily available sources of information on large cryptic mammals, we suggest that similar methods be tested for use in other poorly understood species.

| S-EPMC4512767 | biostudies-literature

A BERT model generates diagnostically relevant semantic embeddings from pathology synopses with active learning.

Project description:BackgroundPathology synopses consist of semi-structured or unstructured text summarizing visual information by observing human tissue. Experts write and interpret these synopses with high domain-specific knowledge to extract tissue semantics and formulate a diagnosis in the context of ancillary testing and clinical information. The limited number of specialists available to interpret pathology synopses restricts the utility of the inherent information. Deep learning offers a tool for information extraction and automatic feature generation from complex datasets.MethodsUsing an active learning approach, we developed a set of semantic labels for bone marrow aspirate pathology synopses. We then trained a transformer-based deep-learning model to map these synopses to one or more semantic labels, and extracted learned embeddings (i.e., meaningful attributes) from the model's hidden layer.ResultsHere we demonstrate that with a small amount of training data, a transformer-based natural language model can extract embeddings from pathology synopses that capture diagnostically relevant information. On average, these embeddings can be used to generate semantic labels mapping patients to probable diagnostic groups with a micro-average F1 score of 0.779 Â ± 0.025.ConclusionsWe provide a generalizable deep learning model and approach to unlock the semantic information inherent in pathology synopses toward improved diagnostics, biodiscovery and AI-assisted computational pathology.

| S-EPMC9053264 | biostudies-literature

Variants in ZFX Cause an X-linked Neurodevelopmental Disorder with Recurrent Facial Gestalt

Project description:Pathogenic variants in multiple X-linked genes have been implicated in syndromic and non- syndromic intellectual disability disorders. The gene ZFX on Xp22.11 encodes a transcription factor that has been linked to diverse processes including oncogenesis and development, but germline variants have not previously been reported in association with disease. Here, we present clinical and molecular characterization of 18 patients with germline ZFX variants. Exome or genome sequencing revealed 11 variants in 18 subjects (14 males and 4 females) from 16 unrelated families. Four missense variants were identified in 11 subjects, with seven frameshift variants in the remaining individuals. Clinical findings included developmental delay/intellectual disability, behavioral abnormalities, hypotonia, and congenital anomalies. Overlapping and recurrent facial features were identified in all subjects, including thickening and medial broadening of eyebrows, variations in the shape of the face, external eye abnormalities, smooth and/or long philtrum and ear abnormalities. Hyperparathyroidism was found in 4 families with missense variants and enrichment of different types of tumors was also observed. In molecular studies, variants in the DNA-binding domain demonstrated differential expression of target genes relative to wild-type ZFX in cultured cells, suggesting a gain or loss of transcriptional activity. Additionally, a zebrafish model of ZFX loss displayed an altered behavioral phenotype, supporting the pathogenicity of predicted loss- of-function frameshift variants. Our clinical and experimental data support that variants in ZFX cause a novel X-linked intellectual disability syndrome characterized by a recurrent facial gestalt, neurocognitive and behavioral abnormalities, and an increased risk for congenital anomalies and hyperparathyroidism.

2023-11-30 | GSE218688 | GEO

Variants in ZFX Cause an X-linked Neurodevelopmental Disorder with Recurrent Facial Gestalt

Project description:This SuperSeries is composed of the SubSeries listed below.

2023-11-30 | GSE218691 | GEO

Variants in ZFX Cause an X-linked Neurodevelopmental Disorder with Recurrent Facial Gestalt

2023-11-30 | GSE218689 | GEO

Foreground Detection Analysis of Ultrasound Image Sequences Identifies Markers of Motor Neurone Disease across Diagnostically Relevant Skeletal Muscles.

Project description:Diagnosis of motor neurone disease (MND) includes detection of small, involuntary muscle excitations, termed fasciculations. There is need to improve diagnosis and monitoring of MND through provision of objective markers of change. Fasciculations are visible in ultrasound image sequences. However, few approaches that objectively measure their occurrence have been proposed; their performance has been evaluated in only a few muscles; and their agreement with the clinical gold standard for fasciculation detection, intramuscular electromyography, has not been tested. We present a new application of adaptive foreground detection using a Gaussian mixture model (GMM), evaluating its accuracy across five skeletal muscles in healthy and MND-affected participants. The GMM provided good to excellent accuracy with the electromyography ground truth (80.17%-92.01%) and was robust to different ultrasound probe orientations. The GMM provides objective measurement of fasciculations in each of the body segments necessary for MND diagnosis and hence could provide a new, clinically relevant disease marker.

| S-EPMC6481588 | biostudies-literature

How intelligence interviewees mentally identify relevant information

Project description:This research explored how intelligence interviewees mentally identify the relevant information at their disposal. We theorized that interviewees estimate the interviewer's objectives based on how they frame any attempt to solicit information. Then interviewees organize the information they possess into item designations that pragmatically correspond to the perceived interviewer-objective. The more an interviewer specifies what they want to know, the more the interviewee will mentally designate information items corresponding with that objective. To examine the theory, we conducted two identical experiments wherein participants assumed the role of an informant with one of two dispositions. They were to be cooperative or resistant when undergoing an interview. The interviewer posed specific or ambiguous questions. In Study 1 (N = 210), interviewees identified applicable information items based on their interviewer's questions. And interviewees answered their interviewer's questions in Study 2 (N = 199). We aimed to demonstrate that question type influences mental designations and disposition affects disclosures. Disposition had a stronger influence on interviewees' disclosure than when reasoning about what the interviewer wants to know. But contrary to our expectations, mental designation preferences indicated that interviewees generally assume interviewers want to know complete details, irrespective of question specificity. We suggest avenues for future research.

| S-EPMC10427824 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data