EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantitative facial phenotyping and age-associated differences in Sickle cell disease using interpretable machine learning

Quantitative Gesichtsphänotypisierung und altersassoziierte Unterschiede bei Sichelzellkrankheit mithilfe interpretierbarer maschineller Lernverfahren

D'Andre Spencer iD, Xinyang Liu, Kizito Mosema-Be-Amoti, Gisèle Kandosi, Matthew S Bramble, Faisal Al Munajjed, Esther Likuba, Daniel Okitundu Luwa E-Andjafono, Laure Tshibambe, Brian Colwell, Kristen Howell, Nicole O'Brien und 7 weitere

PLOS Digital Health · 12.11.2026 · 5 (11) · e0001813

DOI: 10.1371/journal.pdig.0001813 ↗

Auf einen Blick

Bei 154 Personen mit Sichelzellkrankheit und 154 Kontrollen wurden Smartphone-Gesichtsaufnahmen ausgewertet. Das Modell unterschied die Gruppen mit AUROC 0,843 und Genauigkeit 0,795.

Fragestellung

Lassen sich subtile Gesichtsmerkmale bei Sichelzellkrankheit mit maschinellem Lernen quantitativ erfassen und zur Unterscheidung von Fällen und Kontrollen nutzen?

Methode

Querschnittsanalyse von 308 frontalen Smartphone-Fotos; 154 Personen mit elektrophoresebestätigter Sichelzellkrankheit und 154 alters- und geschlechtsgematchte Kontrollen; lineare SVM mit rekursiver Merkmalselimination und Leave-one-out-Validierung.

Ergebnisse

Acht geometrische und 6 texturbasierte diskriminative Merkmale unterschieden die Kohorten signifikant. Sechs geometrische Merkmale trugen am konsistentesten zur internen Diskrimination bei. Unterschiede waren in den jüngsten Altersgruppen geringer.

Einschränkungen

Externe, longitudinale und klinisch charakterisierte Studien sind erforderlich.

Schlussfolgerung der Autor:innen

Die Ergebnisse liefern vorläufige Evidenz, dass Sichelzellkrankheit mit quantifizierbaren morphometrischen Mustern verbunden ist.

Kernaussagen

  • 308 frontale Smartphone-Fotos aus Kinshasa wurden analysiert.
  • AUROC 0,843; Genauigkeit 0,795.
  • Externe und longitudinale Studien sind laut Autor:innen nötig.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 12.11.2026. Verfasst von D'Andre Spencer und 18 weiteren Autor:innen. Beteiligte Einrichtung: Center for Precision Medicine and Genomics Research, Children's Research Institute, Children's National Hospital, Washington, District of Columbia, U…. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sickle cell disease (SCD) is a common inherited genetic disorder and contributor to global childhood mortality and morbidity, particularly in Sub-Saharan Africa. Craniofacial and skeletal changes have been described in SCD, but the subtle soft-tissue facial patterns and their variation have not been quantitatively characterized using machine-learning methods. We analyzed 308 front-facing smartphone photographs from 154 participants with electrophoresis-confirmed SCD and 154 age- and sex-matched controls aged from 5 months to 19 years recruited in Kinshasa, Democratic Republic of the Congo. Predefined geometric and texture-based facial descriptors were extracted from standardized images using manually annotated landmarks. An interpretable linear support vector machine with recursive feature elimination was evaluated using leave-one-out cross-validation, with features ranked according to their relevance for distinguishing participants with SCD from controls. Cross-sectional age- and sex- stratified analyses evaluated variation in selected features The facial analysis algorithm identified eight geometric and six texture discriminative features that were significantly different between the cohorts. A combination of six geometric features contributed most consistently to internal discrimination: distance between medial and lateral canthi, angle at nasal ala, distance from nasion to philtrum, distance from medial canthi to the columella, distance from columella to the lower lip, and distance between nasal alae. The model achieved an AUROC of 0.843 [95% CI: 0.798,0.887], and an accuracy of 0.795 [95% CI: 0.750,0.840]. Between-group difference was limited in the youngest age groups and were more pronounced in several older age groups. These findings demonstrate preliminary evidence that SCD is associated with quantifiable morphometric patterns. External, longitudinal, and clinically characterized studies are needed to determine whether these features may serve as reproducible digital biomarkers within a broader supportive disease-assessment framework.

Autor:innen und Institutionen

  • Center for Precision Medicine and Genomics Research, Children's Research Institute, Children's National Hospital, Washington, District of Columbia, United States of America.
  • Institute for Clinical and Translational Science, University of California, Irvine, California, United States of America.
  • Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, District of Columbia, United States of America.
  • Institut National de Recherche Biomédicale (INRB), Kinshasa, Democratic Republic of the Congo.
  • Biamba Marie Mutombo Hospital, Kinshasa, Democratic Republic of the Congo.
  • Department of Neurology, University of Kinshasa, Kinshasa, Democratic Republic of the Congo.

ORCID-Profile: D'Andre Spencer, Dieudonne Mumba Ngoyi, Marius George Linguraru

Zitieren

APA

Spencer, D., Liu, X., Mosema-Be-Amoti, K., Kandosi, G., Bramble, M. S., Al Munajjed, F., Likuba, E., E-Andjafono, D. O. L., Tshibambe, L., Colwell, B., Howell, K., O'Brien, N., Moxon, C., Anwar, S. M., Porras, A. R., Ngoyi, D. M., Vilain, E., Tshala-Katumbay, D., & Linguraru, M. G. (2026). Quantitative facial phenotyping and age-associated differences in Sickle cell disease using interpretable machine learning. PLOS Digital Health, 5(11), e0001813. https://doi.org/10.1371/journal.pdig.0001813

Vancouver

Spencer D, Liu X, Mosema-Be-Amoti K, Kandosi G, Bramble MS, Al Munajjed F, et al. Quantitative facial phenotyping and age-associated differences in Sickle cell disease using interpretable machine learning. PLOS Digital Health. 2026;5(11):e0001813. doi:10.1371/journal.pdig.0001813

BibTeX
@article{Spencer2026,
  author = {Spencer, D'Andre and Liu, Xinyang and Mosema-Be-Amoti, Kizito and Kandosi, Gisèle and Bramble, Matthew S and Al Munajjed, Faisal and Likuba, Esther and E-Andjafono, Daniel Okitundu Luwa and Tshibambe, Laure and Colwell, Brian and Howell, Kristen and O'Brien, Nicole and Moxon, Christopher and Anwar, Syed Muhammad and Porras, Antonio R and Ngoyi, Dieudonne Mumba and Vilain, Eric and Tshala-Katumbay, Desire and Linguraru, Marius George},
  title = {Quantitative facial phenotyping and age-associated differences in Sickle cell disease using interpretable machine learning},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {11},
  pages = {e0001813},
  doi = {10.1371/journal.pdig.0001813}
}
Kostenlos starten →