Feature replacement methods enable reliable home video analysis for machine learning detection of autism.

Journal: Scientific reports
Published Date: Dec 4, 2020

Abstract

Autism Spectrum Disorder is a neuropsychiatric condition affecting 53 million children worldwide and for which early diagnosis is critical to the outcome of behavior therapies. Machine learning applied to features manually extracted from readily accessible videos (e.g., from smartphones) has the potential to scale this diagnostic process. However, nearly unavoidable variability in video quality can lead to missing features that degrade algorithm performance. To manage this uncertainty, we evaluated the impact of missing values and feature imputation methods on two previously published autism detection classifiers, trained on standard-of-care instrument scoresheets and tested on ratings of 140 children videos from YouTube. We compare the baseline method of listwise deletion to classic univariate and multivariate techniques. We also introduce a feature replacement method that, based on a score, selects a feature from an expanded dataset to fill-in the missing value. The replacement feature selected can be identical for all records (general) or automatically adjusted to the record considered (dynamic). Our results show that general and dynamic feature replacement methods achieve a higher performance than classic univariate and multivariate methods, supporting the hypothesis that algorithmic management can maintain the fidelity of video-based diagnostics in the face of missing values and variable video quality.

Authors

  • Emilie Leblanc
    Department of Pediatrics, Stanford University, Palo Alto, CA, 94305, USA.
  • Peter Washington
    Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USA.
  • Maya Varma
    Department of Computer Science, Stanford University, Stanford, California.
  • Kaitlyn Dunlap
    Division of Systems Medicine, Department of Pediatrics, Stanford University, Palo Alto, CA, United States.
  • Yordan Penev
    Department of Pediatrics, Stanford University, Palo Alto, CA, 94305, USA.
  • Aaron Kline
    Department of Pediatrics (Systems Medicine), Stanford University, Stanford, California; Department of Biomedical Data Science, Stanford University, Stanford, California.
  • Dennis P Wall
    Department of Pediatrics (Systems Medicine), Stanford University, Stanford, California; Department of Biomedical Data Science, Stanford University, Stanford, California; Department of Psychiatry and Behavioral Sciences (by courtesy), Stanford University, Stanford, California. Electronic address: dpwall@stanford.edu.

Keywords

External Resources

Popular Topics
Recent Journals