Machine learning reveals prominent spontaneous behavioral changes and treatment efficacy in humanized and transgenic Alzheimer's disease models
Stephanie R. Miller, Kevin Luxem, Kelli Lauderdale, Pranav Nambiar, Patrick Honma, Katie K. Ly, Shreya C. Bangera, Mary Bullock, Jia Shin, N. Kaliss, Yuechen Qiu, Catherine W. Cai, Kevin Shen, K Dakota Mallen, Zhaoqi Yan, Andrew S. Mendiola, Takashi Saito, Takaomi C. Saido, Alexander R. Pico, Reuben Thomas, Erik D. Roberson, Katerina Akassoglou, Pavol Bauer, Stefan Remy, Jorge J. Palop
Abstract
mice largely prevented spontaneous behavioral alterations, indicating a key role for neuroinflammation. Thus, AD-related spontaneous behavioral alterations are prominent in knockin and transgenic models and sensitive to therapeutic interventions. VAME outcomes had higher specificity and sensitivity than conventional behavioral outcomes. We conclude that spontaneous behavior effectively captures age- and sex-dependent disease manifestations and treatment efficacy in AD models.