Decoding spontaneous pain from brain cellular calcium signals using deep learning

We developed AI-bRNN (Average training, Individual test-bidirectional Recurrent Neural Network) to decipher spontaneous pain information from brain cellular calcium signals recorded by two-photon imaging in awake, head-fixed mice. The AI-bRNN determines the intensity and time point of spontaneous pain even during the chronic pain period and evaluates the efficacy of analgesics. Furthermore, it could be applied to different cell types and brain areas, and it distinguished between itch and pain, proving its versatility.