The consumption of sugar substitute non-nutritive sweeteners (NNS) has dramatically increased in recent years. Despite being advertised as a healthy alternative, NNS have been linked to adverse effects on the body, such as neurodegenerative diseases (NDs). In NDs, neural stem cell function is impaired, which inhibits neuron regeneration. The purpose of this study was to determine if the NNS acesulfame potassium (Ace-K) and neotame affect planaria neuron regeneration rates. Since human neurons may regenerate, planaria, organisms with extensive regenerative capabilities due to stem cells called neoblasts, were used as the model organism. The heads of planaria exposed to either a control or non-toxic concentrations of NNS were amputated. The posterior regions of the planaria were observed every 24 hours to see the following regeneration stages: (1) wound healing, (2) blastema development, (3) growth, and (4) differentiation. The authors hypothesized that exposure to the NNS would slow planaria regeneration rates. The time it took for the planaria in the Ace-K group and the neotame group to reach the second, third, and fourth regeneration stage was significantly greater than that of the control. The results of this study indicated that exposure to the NNS significantly slowed regeneration rates in planaria. This suggests that the NNS may adversely impact neoblast proliferation rates in planaria, implying that it could impair neural stem cell proliferation in humans, which plays a role in NDs. This study may provide insight into the connection between NNS, human neuron regeneration, and NDs.

The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.