Precision telemedicine through crowdsourced machine learning: testing variability of crowd workers for video-based autism feature recognition - Université de Lille
Article Dans Une Revue Journal of Personalized Medicine Année : 2020

Precision telemedicine through crowdsourced machine learning: testing variability of crowd workers for video-based autism feature recognition

Kaitlyn Dunlap
  • Fonction : Auteur
Yordan Penev
  • Fonction : Auteur
Aaron Kline
  • Fonction : Auteur
Kelley Paskov
  • Fonction : Auteur
Min Woo Sun
  • Fonction : Auteur
Brianna Chrisman
  • Fonction : Auteur
Nathaniel Stockham
  • Fonction : Auteur
Maya Varma
  • Fonction : Auteur
Catalin Voss
  • Fonction : Auteur
Nick Haber
  • Fonction : Auteur
Dennis P. Wall
  • Fonction : Auteur

Résumé

Mobilized telemedicine is becoming a key, and even necessary, facet of both precision health and precision medicine. In this study, we evaluate the capability and potential of a crowd of virtual workers-defined as vetted members of popular crowdsourcing platforms-to aid in the task of diagnosing autism. We evaluate workers when crowdsourcing the task of providing categorical ordinal behavioral ratings to unstructured public YouTube videos of children with autism and neurotypical controls. To evaluate emerging patterns that are consistent across independent crowds, we target workers from distinct geographic loci on two crowdsourcing platforms: an international group of workers on Amazon Mechanical Turk (MTurk) (N = 15) and Microworkers from Bangladesh (N = 56), Kenya (N = 23), and the Philippines (N = 25). We feed worker responses as input to a validated diagnostic machine learning classifier trained on clinician-filled electronic health records. We find that regardless of crowd platform or targeted country, workers vary in the average confidence of the correct diagnosis predicted by the classifier. The best worker responses produce a mean probability of the correct class above 80% and over one standard deviation above 50%, accuracy and variability on par with experts according to prior studies. There is a weak correlation between mean time spent on task and mean performance (r = 0.358, p = 0.005). These results demonstrate that while the crowd can produce accurate diagnoses, there are intrinsic differences in crowdworker ability to rate behavioral features. We propose a novel strategy for recruitment of crowdsourced workers to ensure high quality diagnostic evaluations of autism, and potentially many other pediatric behavioral health conditions. Our approach represents a viable step in the direction of crowd-based approaches for more scalable and affordable precision medicine.
Fichier principal
Vignette du fichier
jpm-10-00086-v3.pdf (2.01 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03967249 , version 1 (01-02-2023)

Licence

Identifiants

Citer

Peter Washington, Emilie Leblanc, Kaitlyn Dunlap, Yordan Penev, Aaron Kline, et al.. Precision telemedicine through crowdsourced machine learning: testing variability of crowd workers for video-based autism feature recognition. Journal of Personalized Medicine, 2020, Journal of Personalized Medicine, 10 (3), pp.86. ⟨10.3390/jpm10030086⟩. ⟨hal-03967249⟩

Collections

UNIV-LILLE
29 Consultations
5 Téléchargements

Altmetric

Partager

More