An automated ICU agitation monitoring system for video streaming using deep learning classification.

OBJECTIVE: To address the challenge of assessing sedation status in critically ill patients in the intensive care unit (ICU), we aimed to develop a non-contact automatic classifier of agitation using artificial intelligence and deep learning. METHODS: We collected the video recordings of ICU patients and cut them into 30-second (30-s) and 2-second (2-s) segments. All of the segments were annotated with the status of agitation as "Attention" and "Non-attention". After transforming the video segments into movement quantification, we constructed the models of agitation classifiers with Threshold, Random Forest, and LSTM and evaluated their performances. RESULTS: The video recording segmentation yielded 427 30-s and 6405 2-s segments from 61 patients for model construction. The LSTM model achieved remarkable accuracy (ACC 0.92, AUC 0.91), outperforming other methods. CONCLUSION: Our study proposes an advanced monitoring system combining LSTM and image processing to ensure mild patient sedation in ICU care. LSTM proves to be the optimal choice for accurate monitoring. Future efforts should prioritize expanding data collection and enhancing system integration for practical application.

Securinine enhances SMN2 exon 7 inclusion in spinal muscular atrophy cells.

Spinal muscular atrophy (SMA) is an autosomal recessive disease characterized by the degeneration of motor neurons in the spinal cord, leading to muscular atrophy. SMA is caused by deletions or mutations in the survival motor neuron gene (SMN1) on chromosome 5q13. A second copy of the SMN gene (SMN2) also exists on chromosome 5, and both genes can produce functional protein. However, due to alternative splicing of the exon 7, the majority of SMN protein produced by SMN2 is truncated and unable to compensate for the loss of SMN1. Increasing full-length SMN protein production by promoting the exon 7 inclusion in SMN2 mRNA or increasing SMN2 gene transcription could be a therapeutic approach for SMA. In this study, we screened for the compounds that enhance SMN2 exon 7 inclusion by using SMN2 minigene-luciferase reporter system. We found that securinine can increase luciferase activity, indicating that securinine promoted SMN2 exon 7 inclusion. In addition, securinine increased full-length SMN2 mRNA and SMN protein expression in SMA patient-derived lymphoid cell lines. To investigate the mechanism of securinine effect on SMN2 splicing, we compared the protein levels of relevant splicing factors between securinine-treated and untreated cells. We found that securinine downregulated hnRNP A1 and Sam68 and upregulated Tra2-ß1 expression. However, securinine, unlike HDAC inhibitors, did not enhance tra2-ß1 gene transcription, indicating a post-transcriptional mechanism for Tra2-ß1 upregulation. Furthermore, we treated SMA-like mice with securinine by i.p. injection and found that securinine treatment increased SMN2 exon 7 inclusion and SMN protein expression in the brain and spinal cord. According to our results, securinine might have the potential to become a therapeutic drug for SMA disease.

Synthesis and evaluation of 4-(2-hydroxypropyl)piperazin-1-yl) derivatives as Hsp90 inhibitors.

We previously reported 4-(3-((6-bromonaphthalen-2-yl)oxy)-2-hydroxypropyl)-N,N-dimethylpiperazine-1-sulfonamide (1) as a novel heat shock protein 90 inhibitor with moderate activity. In our ongoing efforts for the discovery of Hsp90 modulators we undertake structural investigations on 1. Series of the titled compound were designed, synthesized and evaluated. We have found that compounds with a hydroxyl group at C-4 of the aryl ring on the piperazine moiety possess Hsp90 inhibition properties. Compound 6f with improved activity could be further developed and optimized as Hsp90 inhibitor.