Early identification of stroke through deep learning with multi-modal human speech and movement data.

JOURNAL/nrgr/04.03/01300535-202501000-00031/figure1/v/2024-05-14T021156Z/r/image-tiff Early identification and treatment of stroke can greatly improve patient outcomes and quality of life. Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale (CPSS) and the Face Arm Speech Test (FAST) are commonly used for stroke screening, accurate administration is dependent on specialized training. In this study, we proposed a novel multimodal deep learning approach, based on the FAST, for assessing suspected stroke patients exhibiting symptoms such as limb weakness, facial paresis, and speech disorders in acute settings. We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements, facial expressions, and speech tests based on the FAST. We compared the constructed deep learning model, which was designed to process multi-modal datasets, with six prior models that achieved good action classification performance, including the I3D, SlowFast, X3D, TPN, TimeSformer, and MViT. We found that the findings of our deep learning model had a higher clinical value compared with the other approaches. Moreover, the multi-modal model outperformed its single-module variants, highlighting the benefit of utilizing multiple types of patient data, such as action videos and speech audio. These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke, thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.

Machine learning-assisted fluorescence visualization for sequential quantitative detection of aluminum and fluoride ions.

The presence of aluminum (Al3+) and fluoride (F-) ions in the environment can be harmful to ecosystems and human health, highlighting the need for accurate and efficient monitoring. In this paper, an innovative approach is presented that leverages the power of machine learning to enhance the accuracy and efficiency of fluorescence-based detection for sequential quantitative analysis of aluminum (Al3+) and fluoride (F-) ions in aqueous solutions. The proposed method involves the synthesis of sulfur-functionalized carbon dots (C-dots) as fluorescence probes, with fluorescence enhancement upon interaction with Al3+ ions, achieving a detection limit of 4.2 nmol/L. Subsequently, in the presence of F- ions, fluorescence is quenched, with a detection limit of 47.6 nmol/L. The fingerprints of fluorescence images are extracted using a cross-platform computer vision library in Python, followed by data preprocessing. Subsequently, the fingerprint data is subjected to cluster analysis using the K-means model from machine learning, and the average Silhouette Coefficient indicates excellent model performance. Finally, a regression analysis based on the principal component analysis method is employed to achieve more precise quantitative analysis of aluminum and fluoride ions. The results demonstrate that the developed model excels in terms of accuracy and sensitivity. This groundbreaking model not only showcases exceptional performance but also addresses the urgent need for effective environmental monitoring and risk assessment, making it a valuable tool for safeguarding our ecosystems and public health.

A dendritic cell-recruiting, antimicrobial blood clot hydrogel for melanoma recurrence prevention and infected wound management.

Surgical resection, the mainstay for melanoma treatment, faces challenges due to high tumor recurrence rates and complex postoperative wound healing. Chronic inflammation from residual disease and the risk of secondary infections impede healing. We introduce an innovative, injectable hydrogel system that integrates a multifaceted therapeutic approach. The hydrogel, crosslinked by calcium ions with sodium alginate, encapsulates a blood clot rich in dendritic cells (DCs) chemoattractants and melanoma cell-derived nanovesicles (NVs), functioning as a potent immunostimulant. This in situ recruitment strategy overcomes the limitations of subcutaneous tumor vaccine injections and more effectively achieves antitumor immunity. Additionally, the hydrogel incorporates Chlorella extracts, enhancing its antimicrobial properties to prevent wound infections and promote healing. One of the key findings of our research is the dual functionality of Chlorella extracts; they not only expedite the healing process of infected wounds but also increase the hydrogel's ability to stimulate an antitumor immune response. Given the patient-specific nature of the blood clot and NVs, our hydrogel system offers customizable solutions for individual postoperative requirements. This personalized approach is highlighted by our study, which demonstrates the synergistic impact of the composite hydrogel on preventing melanoma recurrence and hastening wound healing, potentially transforming postsurgical melanoma management.

Cognitive function in dyslipidemia patients: exploring the impact of statins.

Background: Evidence regarding the relationship between the use of statins and cognitive outcomes presents varying findings. This study aims to analyze the relationship between sustained statin use and cognitive performance in dyslipidemia patients. Methods: This study presents findings from the Beijing Ageing Brain Rejuvenation Initiative (BABRI) study, in which a cohort of community-dwelling dyslipidemia patients (Entire sample, N = 1,062, aged 50-86) was recruited. Participants were divided into two groups based on their sustained use statins (Statins group, N = 677) or not use any lipid-lowering agents (Untreated group, N = 385). Furthermore, the entire sample was stratified by age into the middle-aged sample (N = 451) and the older people sample (N = 611), following a similar categorization based on statin application. ANCOVA was used to evaluate the relationship between sustained statin use and cognitive function. Results: Overall, in the total sample, the statins group demonstrated better cognition in overall cognition, memory, visuospatial ability, attention, executive function, and language domains compared to the untreated group. Moreover, the statins group only showed better performance in attention among the middle-aged sample. In the older people sample, statins group exhibited superior cognitive performance across various cognitive domains compared to untreated group. Conclusion: Among dyslipidemia patients in Beijing community, sustained statin users exhibited superior cognitive function across all domains compared to untreated individuals, with particularly noticeable improvements among those aged 65 and above. These findings underscore the protective effect of statins on cognitive function in dyslipidemia patients, highlighting significant benefits for the older people population.

Protein tyrosine phosphatase non-receptor II: A possible biomarker of poor prognosis and mediator of immune evasion in hepatocellular carcinoma.

BACKGROUND: The incidence of primary liver cancer is increasing year by year. In 2022 alone, more than 900000 people were diagnosed with liver cancer worldwide, with hepatocellular carcinoma (HCC) accounting for 75%-85% of cases. HCC is the most common primary liver cancer. China has the highest incidence and mortality rate of HCC in the world, and it is one of the malignant tumors that seriously threaten the health of Chinese people. The onset of liver cancer is occult, the early cases lack typical clinical symptoms, and most of the patients are already in the middle and late stage when diagnosed. Therefore, it is very important to find new markers for the early detection and diagnosis of liver cancer, improve the therapeutic effect, and improve the prognosis of patients. Protein tyrosine phosphatase non-receptor 2 (PTPN2) has been shown to be associated with colorectal cancer, triple-negative breast cancer, non-small cell lung cancer, and prostate cancer, but its biological role and function in tumors remain to be further studied. AIM: To combine the results of relevant data obtained from The Cancer Genome Atlas (TCGA) to provide the first in-depth analysis of the biological role of PTPN2 in HCC. METHODS: The expression of PTPN2 in HCC was first analyzed based on the TCGA database, and the findings were then verified by immunohistochemical staining, quantitative real-time polymerase chain reaction (qRT-PCR), and immunoblotting. The value of PTPN2 in predicting the survival of patients with HCC was assessed by analyzing the relationship between PTPN2 expression in HCC tissues and clinicopathological features. Finally, the potential of PTPN2 affecting immune escape of liver cancer was evaluated by tumor immune dysfunction and exclusion and immunohistochemical staining. RESULTS: The results of immunohistochemical staining, qRT-PCR, and immunoblotting in combination with TCGA database analysis showed that PTPN2 was highly expressed and associated with a poor prognosis in HCC patients. Kyoto Encyclopedia of Genes and Genomes enrichment analysis showed that PTPN2 was associated with various pathways, including cancer-related pathways, the Notch signaling pathway, and the MAPK signaling pathway. Gene Set Enrichment Analysis showed that PTPN2 was highly expressed in various immune-related pathways, such as the epithelial mesenchymal transition process. A risk model score based on PTPN2 showed that immune escape was significantly enhanced in the high-risk group compared with the low-risk group. CONCLUSION: This study investigated PTPN2 from multiple biological perspectives, revealing that PTPN2 can function as a biomarker of poor prognosis and mediate immune evasion in HCC.

Urolithin A alleviates cell senescence by inhibiting ferroptosis and enhances corneal epithelial wound healing.

Purpose: To analyze the therapeutic effect and mechanism of Urolithin A (UA) on delayed corneal epithelial wound healing. Methods: The C57BL/6 mice were continuously exposed to hyperosmotic stress (HS) for 7 days followed by the removal of central corneal epithelium to establish a delayed corneal epithelial wound healing model in vivo. In vitro, the human corneal epithelial cell line (HCE-T) was also incubated under HS. UA was administered in vivo and in vitro to study its effects on corneal epithelial cells. Senescence-associated ß-galactosidase (SA-ß-gal) staining was performed to detect the level of cell senescence. Transcriptome sequencing (RNA-seq) was conducted to elucidate the molecular mechanism underlying the effect of UA on corneal epithelial repair. Additionally, the expression of senescence-related and ferroptosis-related genes and the levels of lipid peroxides (LPO) and malondialdehyde (MDA) were measured. Results: Hyperosmotic stress (HS) significantly increased the proportion of SA-ß-gal staining positive cells in corneal epithelial cells and upregulated the expression of p16 and p21 (p < 0.0001). Topical application of UA decreased the accumulation of senescent cells in corneal epithelial wounds and promoted epithelial wound healing. The results of RNA-seq of HS-induced corneal epithelial cells showed that the ferroptosis pathway was significantly dysregulated. Further investigation revealed that UA decreased the level of oxidative stress in HCE-T cells, including the levels of LPO and MDA (p < 0.05). Inhibition of ferroptosis significantly prevented cellular senescence in HS-induced HCE-T cells. Conclusion: In this study, UA promoted HS-induced delayed epithelial wound healing by reducing the senescence of corneal epithelial cells through the inhibition of ferroptosis.

Efficacy Analysis of Temporary Spinal Cord Stimulation in the Treatment of Refractory Postherpetic Neuralgia.

BACKGROUND: Spinal cord stimulation can be considered in PHN patients if conservative treatment is not effective. However, the long-term pain outcomes of temporary (7-14 days) spinal cord stimulation (tSCS) in refractory PHN patients with a course of more than 3 months have not been  documented. OBJECTIVES: To investigate the efficacy of tSCS as a treatment for refractory PHN. STUDY DESIGN: Retrospective study. SETTING: Pain Department in a university hospital. METHODS: A total of 52 patients with refractory PHN were treated with tSCS between March 2018 and February 2021. Their medical records were collected, and the patients were divided into 3 groups according to the course of their disease into the medium-term group, long-term group and ultra-long-term group. The changes in the numeric rating scale (NRS) scores, Pittsburgh sleep quality index (PSQI) responses, pain relief rate, postoperative efficiency and patients' use of analgesics were recorded before the operation, 3 days, 10 days, one month, 3 months, 6 months and 12 months after the operation. RESULTS: The average NRS scores, the maximum NRS scores and the PSQI scores at 3 days, 10 days, one month, 3 months, 6 months and 12 months after the operation were significantly lower than those before the operation (P < 0.05). The average NRS scores and the maximum NRS scores of all groups increased significantly from one month to 6 months compared to those at 10 days after the tSCS treatment, and they decreased significantly at 12 months compared with 6 months post-operation. The average NRS scores of the medium-term and long-term group were significantly lower than that of the ultra-long-term group at 1-3 months after the operation, and the maximum NRS scores at one month, 3 months and 12 months after the operation were also significantly lower in the medium-term and long-term group compared to the ultra-long-term group. The average PSQI scores at 1-12 months after the operation were not significantly higher than that at 10 days after the operation, but it decreased significantly at 12 months compared with 6 months after the operation. Among the 3 groups, the PSQI scores of the medium-term and long-term group were significantly lower than those of the ultra-long-term group at 6 months after the operation. The postoperative pain relief rate ranged from 41.51%-59.81%, and the total effective rate was 42.31%-69.23%, and there was no significant difference among the 3 groups. Some patients still needed analgesics at 12 months after the operation, but the number of patients who were taking medications post-operation was significantly lower than that before the operation. LIMITATIONS: This is a single-center retrospective study with the inability to completely control for variables. Additionally, the number of cases is small and the follow-up duration is short. CONCLUSION: tSCS can be used as a safe and effective method to relieve refractory PHN, and the curative effect is substantially higher in patients with a disease course of 3-12 months compared to that in patients with a course of more than 12 months.

In Situ Construction of SnS2@SnO2 Heterostructure for Photo-Assisted Electrocatalysis of Oxygen Evolution Reaction.

Photo-assisted electrocatalysis has arisen as a promising approach for hydrogen generation by incorporating photocatalysts into electrocatalysts. 2D SnS2 is a photocatalyst that absorbs visible light. However, the rapid recombination of photo-generated electron-hole pairs significantly reduces the overall photocatalytic efficiency of SnS2, limiting its practical application. Thus, this study prepares an in situ heterojunction SnS2@SnO2 using a one-step hydrothermal method. The degradation efficiency of methyl orange (MO) using SnS2@SnO2 is measured, achieving a degradation rate of 92.75% within 1 h, which is 1.9 times higher than that of pure SnS2. Additionally, FeNiS/SnS2@SnO2 is synthesized and exhibited significant improvements in the photo-assisted oxygen evolution reaction (OER). It achieves an overpotential of 260 mV and a Tafel slope of 65.1 mV dec-1 at 10 mA cm-2, showing reductions of 11.8% and 31.8%, respectively, compared to FeNiS alone. These enhancements highlight the strong photo-response capability of SnS2@SnO2. Under the internal electric field of SnS2@SnO2, the photogenerated electrons in the conduction band of SnS2 quickly move toward SnO2, facilitating efficient photocatalytic reactions. FeNiS, with a lower Fermi energy level (EF), facilitates electron transfer from SnS2@SnO2 and enhances OER performance by efficiently participating in the reaction. This study paves a new path for 2D photocatalyst materials.

Application of Indocyanine Green Fluorescence Imaging During Laparoscopic Reoperations of the Biliary Tract Enhances Surgical Precision and Efficiency.

BACKGROUND: A history of abdominal surgery is considered a contraindication for laparoscopic procedures. However, the advancements in laparoscopic instruments and techniques have facilitated the performance of increasingly intricate operations, even in patients with prior abdominal surgeries. ICG fluorescence imaging technology offers advantages in terms of convenient operation and clearer intraoperative bile duct imaging, as confirmed by numerous international clinical studies on its feasibility and safety. The application of ICG fluorescence imaging technology in repeat laparoscopic biliary surgery, however, lacks sufficient reports. METHODS: The clinical data of patients who underwent elective reoperation of the biliary tract in our department between January 2020 and June 2022 were retrospectively analyzed. ICG was injected peripherally before the operation, and near-infrared light was used for 3-dimensional imaging of the bile duct during the operation. RESULTS: Altogether, 143 patients were included in this study and divided into the fluorescence and nonfluorescence groups according to the inclusion criteria. Among the 26 patients in the fluorescence group, cholangiography was successfully performed in 24 cases, and the success rate of intraoperative biliary ICG fluorescence imaging was 92.31%. The intraoperative biliary tract identification time was significantly different between the fluorescence and nonfluorescence groups, but no statistical difference was observed in the final operation method, operative time, and intraoperative blood loss between the 2 groups. Although there was no significant difference in the postoperative ventilation rate, incidence of bile leakage, and stone recurrence rate at 6 months postoperatively between the 2 groups (P>0.05), a significant difference in postoperative hospitalization days was observed (P=0.032). CONCLUSION: The application of ICG fluorescence imaging technology in laparoscopic reoperation of the biliary tract is useful for the early identification of the biliary tract during operation, thereby shortening the operative time and reducing the risk of damage to nonoperative areas. This approach also enhances the visualization of the biliary system and avoids secondary injury intraoperatively due to poor identification of the biliary system. This technique is safe for repeat biliary tract surgery and has a good application prospect.

Niraparib Enhances and Synergizes with Ganglioside GD2 to Potentiate its Inhibitory Effect on Bladder Cancer Cells.

PURPOSE: This study aimed to study the inhibitory effect of niraparib alone or in combination with GD2 specific antibody on Bladder Cancer (BCa). METHODS: The migration ability of BCa cells was assessed through a scratch assay. CCK-8 assay was performed to evaluate the viability of BCa cells, and Transwell invasion assays were utilized to examine invasive capacity. The expression levels of E-cadherin and vimentin in BCa cells were measured using QRT-PCR. RESULTS: Western blot showed the EMT level to be the lowest in the niraparib+GD2 group. The transwell invasion assay suggested that the invasion ability of BCa cells was weakened in the niraparib+ GD2 group. CCK8 assay indicated that the proliferation ability of BCa cells was decreased. Scratch test suggested that the migration ability of BCa cells was weakened. PCR result showed that the niraparib + GD2 group had the most significant inhibitory effect on mRNA expression of EMT markers. CONCLUSION: Niraparib combined with a GD2-specific antibody exerted a more prominent inhibitory effect on BCa.