English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Advances in computer-assisted syndrome recognition by the example of inborn errors of metabolism

Pantel, J. T., Zhao, M., Mensah, M., Hajjir, N., Hsieh, T.-C., Hanani, Y., et al. (2018). Advances in computer-assisted syndrome recognition by the example of inborn errors of metabolism. Journal of Inherited Metabolic Disease, 41(3), 533-539. doi:10.1007/s10545-018-0174-3.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0003-5A24-0 Version Permalink: http://hdl.handle.net/21.11116/0000-0003-5A25-F
Genre: Journal Article
Alternative Title : Journal of Inherited Metabolic Disease

Files

show Files
hide Files
:
Pantel.pdf (Publisher version), 768KB
Name:
Pantel.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
© 2018 The Author(s)

Locators

show

Creators

show
hide
 Creators:
Pantel, Jean Tori, Author
Zhao, Max, Author
Mensah, Martin, Author
Hajjir, Nurulhuda, Author
Hsieh, Tzung-Chien, Author
Hanani, Yair, Author
Fleischer, Nicole, Author
Kamphans, Tom, Author
Mundlos, Stefan1, 2, Author              
Gurovich, Yaron, Author
M. Krawitz, Peter, Author
Affiliations:
1Research Group Development & Disease (Head: Stefan Mundlos), Max Planck Institute for Molecular Genetics, Max Planck Society, ou_1433557              
2Institute of Human Genetics and Medical Genetics, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Significant improvements in automated image analysis have been achieved in recent years and tools are now increasingly being used in computer-assisted syndromology. However, the ability to recognize a syndromic facial gestalt might depend on the syndrome and may also be confounded by severity of phenotype, size of available training sets, ethnicity, age, and sex. Therefore, benchmarking and comparing the performance of deep-learned classification processes is inherently difficult. For a systematic analysis of these influencing factors we chose the lysosomal storage diseases mucolipidosis as well as mucopolysaccharidosis type I and II that are known for their wide and overlapping phenotypic spectra. For a dysmorphic comparison we used Smith-Lemli-Opitz syndrome as another inborn error of metabolism and Nicolaides-Baraitser syndrome as another disorder that is also characterized by coarse facies. A classifier that was trained on these five cohorts, comprising 289 patients in total, achieved a mean accuracy of 62%. We also developed a simulation framework to analyze the effect of potential confounders, such as cohort size, age, sex, or ethnic background on the distinguishability of phenotypes. We found that the true positive rate increases for all analyzed disorders for growing cohorts (n = [10...40]) while ethnicity and sex have no significant influence. The dynamics of the accuracies strongly suggest that the maximum distinguishability is a phenotype-specific value, which has not been reached yet for any of the studied disorders. This should also be a motivation to further intensify data sharing efforts, as computer-assisted syndrome classification can still be improved by enlarging the available training sets.

Details

show
hide
Language(s): eng - English
 Dates: 2018-04-052018-05
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1007/s10545-018-0174-3
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Journal of Inherited Metabolic Disease
  Other : J. Inherit. Metab. Dis.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Lancaster, Eng. : MTP Press.
Pages: - Volume / Issue: 41 (3) Sequence Number: - Start / End Page: 533 - 539 Identifier: ISSN: 0141-8955
CoNE: https://pure.mpg.de/cone/journals/resource/954925471350