Fig. 2: Broad applicability of AI-bRNN to various pain models with different chronicities.
From: Development of a spontaneous pain indicator based on brain cellular calcium using deep learning
Estimated pain values of the a capsaicin-, b CFA-, and c oxaliplatin-injected animals. The estimated pain values are based on the Ca2+ activity of the neurons in S1. Saline (s.c.) group (n = 28 sessions from 14 mice); capsaicin (0.01%, 10 μl, s.c.) group (n = 9 mice); CFA (10 μl, s.c.) group (n = 6 mice); oxaliplatin (6 mg/kg, i.p.) group at 3 d (n = 9 mice); oxaliplatin group at 10 d (n = 7) d Classification performance in the capsaicin-, CFA- and oxaliplatin-induced pain conditions. e Estimated pain values of the animals subjected to PSL or sham surgery. Sham group (n = 6 mice); PSL group at 3 d (n = 20 mice); PSL group at 10 d (n = 24 mice); PSL + GB/VX (GB 100 mg/kg, VX 50 mg/kg, i.p.) group (n = 8 mice) f Heatmap plots showing changes in estimated pain values over time with 2-min time resolution. g The classification performance for PSL pain conditions based on the S1 neuronal signals. Scatter plots indicate individual data. Bars indicate the mean ± SEM; N.S., nonsignificant; ***P < 0.001, *P < 0.05 compared to baseline (Mann–Whitney U test).
