DeepLabCut to Automate Behavioral Analysis of Parkinsonism
There was good absolute agreement between the two scoring methods, using the two-way random effect model, kappa = 0.9, <i>p</i> < 0.0001. It takes 10-15 min to go through each video manually, but the DLC-assisted scoring resulted in 3-4 min per video. These results show that DLC-assisted scoring produced results that could be on par with manual scoring. In addition, this shows a feasible avenue to integrate AI/ML in parkinsonian behavioral studies to reduce the workload for analysis and eventually, fully automating such tasks.
Authors
- Vaibhavi Peshattiwar (ORCID: https://orcid.org/0000-0001-7234-0483)
- Kala Venkiteswaran (ORCID: https://orcid.org/0000-0002-6707-7067)
- Thyagarajan Subramanian (ORCID: https://orcid.org/0000-0001-5930-017X)
- Tatiana White (ORCID: https://orcid.org/0000-0002-0505-138X)
- Khoi Le (ORCID: https://orcid.org/0009-0001-7675-877X)
- Dipesh Pokharel (ORCID: https://orcid.org/0000-0002-3593-3367)
- Caroline Swain (ORCID: https://orcid.org/0009-0001-1758-0553)
- Nabeel Rangoonwala
Institutions
- University of Toledo (US)
Publication Details
- Journal
- AI in neuroscience.
- Published
- 2025-02-20
- DOI
- https://doi.org/10.1089/ains.2024.0008
- Citations
- 2
- Primary Topic
- Human Pose and Action Recognition
- Type
- article
- Field-Weighted Citation Impact
- 2.55