Is Fidgety Philip's ground truth also ours? The creation and application of a machine learning algorithm
Autor: | Boris Kuzeljevic, H. Hussaina, Gerhard Kloesch, Yanyun Bu, Heinrich Garn, S. McWilliams, Linus Hung, Karen Spruyt, Osman S. Ipsiroglu, Calvin Kuo, N. Beyzaei, S. Bao, K.S. Maher, E. Tse, Bernhard Kohn, M. Chan, Hendrik F. Machiel Van der Loos |
---|---|
Rok vydání: | 2020 |
Předmět: |
Ground truth
Receiver operating characteristic Computer science Movement Sitting Akathisia medicine.disease Motion (physics) 030227 psychiatry Machine Learning 03 medical and health sciences Psychiatry and Mental health 0302 clinical medicine Attention Deficit Disorder with Hyperactivity Restless Legs Syndrome Pattern recognition (psychology) medicine Humans Attention deficit hyperactivity disorder Restless legs syndrome medicine.symptom Algorithm Algorithms 030217 neurology & neurosurgery Biological Psychiatry |
Zdroj: | Journal of Psychiatric Research. 131:144-151 |
ISSN: | 0022-3956 |
Popis: | Background Behavioral observations support clinical in-depth phenotyping but phenotyping and pattern recognition are affected by training background. As Attention Deficit Hyperactivity Disorder, Restless Legs syndrome/Willis Ekbom disease and medication induced activation syndromes (including increased irritability and/or akathisia), present with hyperactive-behaviors with hyper-arousability and/or hypermotor-restlessness (H-behaviors), we first developed a non-interpretative, neutral pictogram-guided phenotyping language (PG-PL) for describing body-segment movements during sitting. Methodology & results The PG-PL was applied for annotating 12 1-min sitting-videos (inter-observer agreements >85%->97%) and these manual annotations were used as a ground truth to develop an automated algorithm using OpenPose, which locates skeletal landmarks in 2D video. We evaluated the algorithm's performance against the ground truth by computing the area under the receiver operator curve (>0.79 for the legs, arms, and feet, but 0.65 for the head). While our pixel displacement algorithm performed well for the legs, arms, and feet, it predicted head motion less well, indicating the need for further investigations. Conclusion This first automated analysis algorithm allows to start the discussion about distinct phenotypical characteristics of H-behaviors during structured behavioral observations and may support differential diagnostic considerations via in-depth phenotyping of sitting behaviors and, in consequence, of better treatment concepts. |
Databáze: | OpenAIRE |
Externí odkaz: |