ABSTRACT
INTRODUCTION: Video-based automatic motion analysis has been employed to identify infant motor development delays. To overcome the limitations of lab-recorded images and training datasets, this study aimed to develop an artificial intelligence (AI) model using videos taken by mobile phone to assess infants' motor skills. METHODS: A total of 270 videos of 41 high-risk infants were taken by parents using a mobile device. Based on the Pull to Sit (PTS) levels from the Hammersmith Motor Evaluation, we set motor skills assessments. The videos included 84 level 0, 106 level 1, and 80 level 3 recordings. We used whole-body pose estimation and three-dimensional transformation with a fuzzy-based approach to develop an AI model. The model was trained with two types of vectors: whole-body skeleton and key points with domain knowledge. RESULTS: The average accuracies of the whole-body skeleton and key point models for level 0 were 77.667% and 88.062%, respectively. The Area Under the ROC curve (AUC) of the whole-body skeleton and key point models for level 3 were 96.049% and 94.333% respectively. CONCLUSIONS: An AI model with minimal environmental restrictions can provide a family-centered developmental delay screen and enable the remote monitoring of infants requiring intervention.
ABSTRACT
The formation of misfolded protein aggregates, in particular inclusion bodies, has been widely considered as the major hindrance of good yield in refolding processes. To enhance the performance of protein refolding, extensive efforts were directed toward seeking out methods or means to reduce the aggregate production during the refolding process. Since simultaneous refolding and separation can be feasibly achieved within the packing matrices, size-exclusion chromatography (SEC) has been regarded as an efficient buffer exchange method to enhance protein refolding performance As of now, the effect of the process or operating parameters has yet to be thoroughly investigated. The present work is aimed at understanding how aggregate formation, as well as renaturation yield, varied with the diameter or length of sample loop in size-exclusion chromatography refolding process. Our results showed that not much difference was found in the patterns of aggregate formation for the contraction and the control cases. However, the formation of an additional peak was observed in the expansion cases. In addition, the amount of aggregates was not dependent on the sample loop diameter or length, but instead, influenced by injection volume and protein concentration. It was further concluded that a sample with large volume and low concentration was preferable for refolding process. We believe that the outcome from this work may shed light on the development of a more effective strategy for refolding processes.
