Fructose induces hepatic steatosis in adolescent mice linked to the disorders of lipid metabolism, bile acid metabolism, and autophagy.

The effects of excessive fructose intake on the development and progression of metabolic disorders have received widespread attention. However, the deleterious effects of fructose on the development of hepatic metabolic disease in adolescents and its potential mechanisms are not fully understood. In this study, we investigated the effects of isocaloric fructose-rich diets on the liver of adolescent mice. The results showed that fructose-rich diets had no effect on the development of obesity in the adolescent mice, but did induce hepatic lipid accumulation. Besides, we found that fructose-rich diets promoted hepatic inflammatory responses and oxidative stress in adolescent mice, which may be associated with activation of the NLRP3 inflammasome and inhibition of the Nrf2 pathway. Furthermore, our results showed that fructose-rich diets caused disturbances in hepatic lipid metabolism and bile acid metabolism, as well as endoplasmic reticulum stress and autophagy dysfunction. Finally, we found that the intestinal barrier function was impaired in the mice fed fructose-rich diets. In conclusion, our study demonstrates that dietary high fructose induces hepatic metabolic disorders in adolescent mice. These findings provide a theoretical foundation for fully understanding the effects of high fructose intake on the development of hepatic metabolic diseases during adolescence.

Umbilical cord blood-derived neutrophils possess higher viability than peripheral blood derived neutrophils.

Neutrophils, a primary type of immune cell, play critical roles in numerous biological processes. Both umbilical cord blood (UCB) and peripheral blood are rich in neutrophils. UCB is more abundant than peripheral blood, with cells generally at a more immature stage. However, comparative data between these two cell sources is lacking. This study aims to elucidate differences between UCB-derived neutrophils (UCBN) and peripheral blood-derived neutrophils (PBN). UCBN and PBN were isolated from fresh human umbilical cord blood and peripheral blood, respectively. Transcriptomic profiling was performed and compared against neutrophil RNA from three different donors. Bioinformatics analysis was employed to compare cell phenotypes. A cytokine cocktail (IFN-ß, IFN-γ, and LPS) was used to activate UCBN and PBN in vitro. A united multi-omic approach, combining transcriptomic and proteomic analysis, was followed by experimental validation through flow cytometry, cell killing assays, and proteome profiler array to verify cell functions. Transcriptomic analysis revealed that the most upregulated genes in freshly isolated umbilical cord blood neutrophils (UCBN) compared to peripheral blood neutrophils (PBN) predominantly involve neutrophil activation and cell-killing functions. Validation through flow cytometry and cell-killing experiments demonstrated that highly viable UCBN exhibited significantly stronger ovarian tumor cell-killing activity in vitro compared to PBN. Both transcriptomic and proteomic analyses indicated that the primary upregulated genes in activated UCBN are chiefly involved in biological processes related to the regulation of cytokine secretion. Integrative multi-omic analysis, including a proteome profiler array, confirmed that UCBN indeed secrete elevated levels of cytokines. In conclusion: UCBN shows higher viability and cellular activity compared with PBN, particularly in tumor cell-killing and cytokine secretion.

Exposure to the environmental pollutant chlorpyrifos induces hepatic toxicity through activation of the JAK/STAT and MAPK pathways.

Chlorpyrifos (CHP) is an inexpensive highly effective organophosphate insecticide used worldwide. The unguided and excessive use of CHP by farmers has led to its significant accumulation in crops as well as contamination of water sources, causing health problems for humans and animals. Therefore, this study evaluated the toxicological effects of exposure to the environmental pollutant CHP at low, medium, and high (2.5, 5, and 10 mg·kg-1 BW) levels on rat liver by examining antioxidant levels, inflammation, and apoptosis based on the no observed adverse effect levels (NOAEL) (1 mg·kg-1 BW) and the CHP dose that does not cause any visual symptoms (5 mg·kg-1 BW). Furthermore, the involvement of the JAK/STAT and MAPK pathways in CHP-induced toxic effects was identified. The relationship between the expression levels of key proteins (p-JAK/JAK, p-STAT/STAT, p-JNK/JNK, p-P38/P38, and p-ERK/ERK) in the pathways and changes in the expression of markers associated with inflammation [inflammatory factors (IL-1ß, IL-6, IL-10, TNF-α), chemokines (GCLC and GCLM), and inflammatory signaling pathways (NF-кB, TLR2, TLR4, NLRP3, ASC, MyD88, IFN-γ, and iNOS)] and apoptosis [Bad, Bax, Bcl-2, Caspase3, Caspase9, and the cleavage substrate of Caspase PARP1] were also determined. The results suggest that CHP exposure disrupts liver function and activates the JAK/STAT and MAPK pathways via oxidative stress, exacerbating inflammation and apoptosis. Meanwhile, the JAK/STAT and MAPK pathways are involved in CHP-induced hepatotoxicity. These findings provide a novel direction for effective prevention and amelioration of health problems caused by CHP abuse in agriculture and households.

The CoO-doped carbon nanotubes enhance electronic performance and effectively activate persulfate for the degradation of sulfafurazole.

In recent studies, carbon nanotube (CNTs) materials and their composites have demonstrated remarkable catalytic activity in the activation of persulfate (PS), facilitating the efficient degradation of organic pollutants. In this study, a novel Co loaded carbon nanotubes (CoO@CNT) catalyst was prepared to promote PDS activation for the degradation of sulfafurazole (SIZ). Experimental results, the CNT as a carrier effectively reduces the leaching of cobalt ions and improves the electron transport capacity，whereas the introduced Co effectively activates the PDS, promoting the generation of highly reactive radicals to degrade SIZ. Under optimized conditions (a catalyst dose of 0.2 g/L, a PDS dose of 1 g/L and an initial pH = 9.0), the obtained CoO@CNT demonstrated favorable Fenton-like performance, reaching a degradation efficiency of 95.55% within 30 min. Furthermore, density functional theory (DFT) calculations demonstrate that the introduction of cobalt (Co) accelerates electron transfer, promoting the decomposition of PDS while facilitating the Co2+/Co3+ redox cycling. We further employed the environmental chemistry and risk assessment system (ECOSAR) to evaluate the ecological toxicity of intermediate products, revealing a significant reduction in ecological toxicity associated with this degradation process, thereby confirming its environmental harmlessness. Through batch experiments and studies, we gained a comprehensive understanding of the mechanism and influencing factors of CoO@CNT in the role of SIZ degradation, and provided robust support for evaluating the ecological toxicity of degradation products. This study provides a significant strategy for the development of efficient catalysts incorporating Co for the environmentally friendly degradation of organic pollutants.

Detection of Medication Mentions and Medication Change Events in Clinical Notes Using Transformer-Based Models.

In this paper, we address the related tasks of medication extraction, event classification, and context classification from clinical text. The data for the tasks were obtained from the National Natural Language Processing (NLP) Clinical Challenges (n2c2) Track 1. We developed a named entity recognition (NER) model based on BioClinicalBERT and applied a dictionary-based fuzzy matching mechanism to identify the medication mentions in clinical notes. We developed a unified model architecture for event classification and context classification. The model used two pre-trained models-BioClinicalBERT and RoBERTa to predict the class, separately. Additionally, we applied an ensemble mechanism to combine the predictions of BioClinicalBERT and RoBERTa. For event classification, our best model achieved 0.926 micro-averaged F1-score, 5% higher than the baseline model. The shared task released the data in different stages during the evaluation phase. Our system consistently ranked among the top 10 for Releases 1 and 2.

Data Augmentation with Nearest Neighbor Classifier for Few-Shot Named Entity Recognition.

Few-shot learning (FSL) is a category of machine learning models that are designed with the intent of solving problems that have small amounts of labeled data available for training. FSL research progress in natural language processing (NLP), particularly within the medical domain, has been notably slow, primarily due to greater difficulties posed by domain-specific characteristics and data sparsity problems. We explored the use of novel methods for text representation and encoding combined with distance-based measures for improving FSL entity detection. In this paper, we propose a data augmentation method to incorporate semantic information from medical texts into the learning process and combine it with a nearest-neighbor classification strategy for predicting entities. Experiments performed on five biomedical text datasets demonstrate that our proposed approach often outperforms other approaches.

Efficient degradation of ciprofloxacin in wastewater by CuFe2O4/CuS photocatalyst activated peroxynomosulfate.

In this study, CuFe2O4/CuS composite photocatalysts were successfully synthesized for the activation of peroxynomosulfate to remove ciprofloxacin from wastewater. The structural composition and morphology of the materials were analyzed by XRD, SEM, TEM, and Raman spectroscopy. The electrochemical properties of the samples were tested by an electrochemical workstation. The band gap of the samples was calculated by DFT and compared with the experimental values. The effects of different catalysts, oxidant PMS concentrations, and coexisting ions on the experiments were investigated. The reusability and stability of the photocatalysts were also investigated. The mechanism of the photocatalytic degradation process was proposed based on the free radical trapping experiment. The results show that the p-p heterojunction formed between the two contact surfaces of the CuFe2O4 nanoparticle and CuS promoted the charge transfer between the interfaces and inhibited the recombination of electrons and holes. CuFe2O4-5/CuS photocatalyst has the best catalytic activity, and the removal rate of ciprofloxacin is 93.7%. The intermediates in the degradation process were tested by liquid chromatography-mass spectrometry (LC-MS), and the molecular structure characteristics of ciprofloxacin were analyzed by combining with DFT calculations. The possible degradation pathways of pollutants were proposed. This study reveals the great potential of the photocatalyst CuFe2O4/CuS in the activation of PMS for the degradation of ciprofloxacin wastewater.

MnFe2O4/polyaniline/diatomite composite with multiple loss mechanisms towards broadband absorption.

The research and development of absorbing materials with high absorbing capacity, wide effective absorption bandwidth, and lightweight has always been interesting. In this research, a facile hydrothermal method was used to prepare MnFe2O4, and the grain size of MnFe2O4 decreased with increasing hydrothermal temperature. When the size of MnFe2O4 nanoparticles is less than 10 nm, its quantum size effect and surface effect make its electromagnetic microwave absorption performance greatly optimized. When the thickness of MnFe2O4-110 °C is 2.57 mm, the minimum reflection loss (RLmin) is -35.28 dB. Based on this, light porous diatomite and a three-dimensional polyaniline network are introduced. Diatomite is used as the base material to effectively reduce the agglomeration of MnFe2O4 quantum dots. The relatively high surface area introduced by a three-dimensional network of polyaniline promotes the orientation, interfacial polarization, multiple relaxation, and impedance matching, thereby generating further dielectric loss. Additionally, the magnetic properties of manganese ferrite and the strong electrical conductivity of polyaniline play an appropriate complementary role in electromagnetic wave absorption. The RLmin of MnFe2O4/PANI/diatomite is -56.70 dB at 11.12 GHz with an absorber layer thickness of 2.57 mm. The effective frequency bandwidth (RL < -10 dB) ranges from 9.21 to 18.00 GHz. The absorption mechanism indicates that the high absorption intensity is the result of the synergistic effect of impedance matching, conduction losses, polarization losses, and magnetic losses.

Prognostic differences in sepsis caused by gram-negative bacteria and gram-positive bacteria: a systematic review and meta-analysis.

BACKGROUND: Bacteria are the main pathogens that cause sepsis. The pathogenic mechanisms of sepsis caused by gram-negative and gram-positive bacteria are completely different, and their prognostic differences in sepsis remain unclear. METHODS: The PubMed, Web of Science, Cochrane Library, and Embase databases were searched for Chinese and English studies (January 2003 to September 2023). Observational studies involving gram-negative (G (-))/gram-positive (G (+)) bacterial infection and the prognosis of sepsis were included. The stability of the results was evaluated by sensitivity analysis. Funnel plots and Egger tests were used to check whether there was publication bias. A meta-regression analysis was conducted on the results with high heterogeneity to identify the source of heterogeneity. A total of 6949 articles were retrieved from the database, and 45 studies involving 5586 subjects were included after screening according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Twenty-seven high-quality studies and 18 moderate-quality studies were identified according to the Newcastle‒Ottawa Scale score. There was no significant difference in the survival rate of sepsis caused by G (-) bacteria and G (+) bacteria (OR 0.95, 95% CI 0.70-1.28). Subgroup analysis according to survival follow-up time showed no significant difference. The serum concentrations of C-reactive protein (CRP) (SMD = 0.39, 95% CI 0.02-0.76), procalcitonin (SMD = 1.95, 95% CI 1.32-2.59) and tumor necrosis factor-alpha (TNF-α) (MD = 0.31, 95% CI 0.25-0.38) in the G (-) bacterial infection group were significantly higher than those in the G (+) bacterial infection group, but there was no significant difference in IL-6 (SMD = 1.33, 95% CI - 0.18-2.84) and WBC count (MD = - 0.15, 95% CI - 0.96-00.66). There were no significant differences between G (-) and G (+) bacteria in D dimer level, activated partial thromboplastin time, thrombin time, international normalized ratio, platelet count, length of stay or length of ICU stay. Sensitivity analysis of the above results indicated that the results were stable. CONCLUSION: The incidence of severe sepsis and the concentrations of inflammatory factors (CRP, PCT, TNF-α) in sepsis caused by G (-) bacteria were higher than those caused by G (+) bacteria. The two groups had no significant difference in survival rate, coagulation function, or hospital stay. The study was registered with PROSPERO (registration number: CRD42023465051).

A comprehensive multimodal dataset for contactless lip reading and acoustic analysis.

Small-scale motion detection using non-invasive remote sensing techniques has recently garnered significant interest in the field of speech recognition. Our dataset paper aims to facilitate the enhancement and restoration of speech information from diverse data sources for speakers. In this paper, we introduce a novel multimodal dataset based on Radio Frequency, visual, text, audio, laser and lip landmark information, also called RVTALL. Specifically, the dataset consists of 7.5 GHz Channel Impulse Response (CIR) data from ultra-wideband (UWB) radars, 77 GHz frequency modulated continuous wave (FMCW) data from millimeter wave (mmWave) radar, visual and audio information, lip landmarks and laser data, offering a unique multimodal approach to speech recognition research. Meanwhile, a depth camera is adopted to record the landmarks of the subject's lip and voice. Approximately 400 minutes of annotated speech profiles are provided, which are collected from 20 participants speaking 5 vowels, 15 words, and 16 sentences. The dataset has been validated and has potential for the investigation of lip reading and multimodal speech recognition.

[Silencing of SMAD family member 3 promotes M2 polarization of macrophages and the expression of SMAD7 in rheumatoid arthritis].

Objective To investigate the effect of SMAD family member 3(SMAD3) silenced by small interfering RNA (siRNA) on macrophage polarization and transforming growth factor ß1 (TGF-ß1)/ SMAD family signaling pathway in rheumatoid arthritis (RA). Methods RA macrophages co-cultured with rheumatoid arthritis fibroblast-like synoviocytes (RA-FLS) were used as a cell model. TGF-ß1 was used to stimulate macrophages, and SMAD3-specific siRNA (si-SMAD3) and negative control siRNA (si-NC) were transfected into human RA macrophages co-cultured in TranswellTM chamber. The expression of SMAD3 mRNA was detected by real-time fluorescence quantitative PCR, and the expression of TGF-ß1, SMAD3 and SMAD7 protein was detected by Western blot analysis. The contents of TGF-ß1 and IL-23 in cell culture supernatant were determined by ELISA. Cell proliferation was detected by CCK-8 assay. TranswellTM chamber was used to measure cell migration. Results Compared with the model group and the si-NC group, the expression of TGF-ß1, SMAD3 mRNA and protein in RA macrophages decreased significantly after silencing SMAD3. In addition, the secretion of IL-23 decreased significantly, and the cell proliferation activity and cell migration were inhibited, with high expression of SMAD7. Conclusion Knockdown of SMAD3 can promote M2 polarization and SMAD7 expression in RA macrophages.

A framework for multi-faceted content analysis of social media chatter regarding non-medical use of prescription medications.

Background: Substance use, including the non-medical use of prescription medications, is a global health problem resulting in hundreds of thousands of overdose deaths and other health problems. Social media has emerged as a potent source of information for studying substance use-related behaviours and their consequences. Mining large-scale social media data on the topic requires the development of natural language processing (NLP) and machine learning frameworks customized for this problem. Our objective in this research is to develop a framework for conducting a content analysis of Twitter chatter about the non-medical use of a set of prescription medications. Methods: We collected Twitter data for four medications-fentanyl and morphine (opioids), alprazolam (benzodiazepine), and Adderall® (stimulant), and identified posts that indicated non-medical use using an automatic machine learning classifier. In our NLP framework, we applied supervised named entity recognition (NER) to identify other substances mentioned, symptoms, and adverse events. We applied unsupervised topic modelling to identify latent topics associated with the chatter for each medication. Results: The quantitative analysis demonstrated the performance of the proposed NER approach in identifying substance-related entities from data with a high degree of accuracy compared to the baseline methods. The performance evaluation of the topic modelling was also notable. The qualitative analysis revealed knowledge about the use, non-medical use, and side effects of these medications in individuals and communities. Conclusions: NLP-based analyses of Twitter chatter associated with prescription medications belonging to different categories provide multi-faceted insights about their use and consequences. Our developed framework can be applied to chatter about other substances. Further research can validate the predictive value of this information on the prevention, assessment, and management of these disorders.

MUC16 stimulates neutrophils to an inflammatory and immunosuppressive phenotype in ovarian cancer.

BACKGROUND: MUC16 (CA125) is a commonly used tumor marker for ovarian cancer screening and reported to be an immunosuppressive factor by acting on the sialic acid-binding immunoglobulin-like lectin-9 (Siglec-9) on the surface of natural killer cells (NK cells), B cells, and monocytes. However, the role of MUC16 on neutrophils in the tumor microenvironment remains to be further explored. METHODS: The correlation between the proportion and count of peripheral blood cells, serum inflammatory-related factors and serum MUC16 (CA125) level in patients was constructed based on clinical samples. RNAseq data was obtained from TCGA and sequencing of ovarian cancer tissues, followed by TIMER immune cell infiltration and correlation analysis. Ovarian cancer organoid was constructed to stimulate neutrophils with immunophenotype identification by qPCR and flow cytometry. MUC16 protein stimulation to neutrophils validated the role of MUC16 under the analysis of RNA sequencing and inhibition of NK cytotoxicity in vitro. RESULTS: The serum MUC16 level was positively correlated with the proportion and count of peripheral blood neutrophils, neutrophil-to-lymphocyte ratio (NLR) and inflammatory factors IL-6, IL-8, IL-10 and IL-2R. Siglec-9, the receptor of MUC16, was expressed on neutrophils and was positively correlated to neutrophil infiltration in ovarian cancer. After the stimulation of ovarian cancer organoids and MUC16 respectively, the proportions of CD11b+, CD66b+, and ICAM-1+ neutrophils were significantly increased, while the proportion of CXCR4+ neutrophils was slightly decreased, with increasing of of inflammatory factors MMP9, IL-8, OSM, IL-1ß, TNF-α, CXCL3, and ROS. RNA-sequencing analysis revealed that inflammatory response, TNFA signaling pathway, and IL6-related pathway were upregulated in MUC16-stimulated neutrophils, accompanied by high expression of immunosuppression-related factors HHLA2, IL-6, TNFRSF9, ADORA2A, CD274 (PD-L1), and IDO1. NK cytotoxicity was decreased when treated by supernanant of MUC16-stimulated neutrophils in vitro. CONCLUSION: MUC16 acted on neutrophils by Siglec-9 leading to an inflammatory and immunosuppressive phenotype in ovarian cancer.

Few-shot learning for medical text: A review of advances, trends, and opportunities.

BACKGROUND: Few-shot learning (FSL) is a class of machine learning methods that require small numbers of labeled instances for training. With many medical topics having limited annotated text-based data in practical settings, FSL-based natural language processing (NLP) holds substantial promise. We aimed to conduct a review to explore the current state of FSL methods for medical NLP. METHODS: We searched for articles published between January 2016 and October 2022 using PubMed/Medline, Embase, ACL Anthology, and IEEE Xplore Digital Library. We also searched the preprint servers (e.g., arXiv, medRxiv, and bioRxiv) via Google Scholar to identify the latest relevant methods. We included all articles that involved FSL and any form of medical text. We abstracted articles based on the data source, target task, training set size, primary method(s)/approach(es), and evaluation metric(s). RESULTS: Fifty-one articles met our inclusion criteria-all published after 2018, and most since 2020 (42/51; 82%). Concept extraction/named entity recognition was the most frequently addressed task (21/51; 41%), followed by text classification (16/51; 31%). Thirty-two (61%) articles reconstructed existing datasets to fit few-shot scenarios, and MIMIC-III was the most frequently used dataset (10/51; 20%). 77% of the articles attempted to incorporate prior knowledge to augment the small datasets available for training. Common methods included FSL with attention mechanisms (20/51; 39%), prototypical networks (11/51; 22%), meta-learning (7/51; 14%), and prompt-based learning methods, the latter being particularly popular since 2021. Benchmarking experiments demonstrated relative underperformance of FSL methods on biomedical NLP tasks. CONCLUSION: Despite the potential for FSL in biomedical NLP, progress has been limited. This may be attributed to the rarity of specialized data, lack of standardized evaluation criteria, and the underperformance of FSL methods on biomedical topics. The creation of publicly-available specialized datasets for biomedical FSL may aid method development by facilitating comparative analyses.

Origins of Barents-Kara sea-ice interannual variability modulated by the Atlantic pathway of El Niño-Southern Oscillation.

Winter Arctic sea-ice concentration (SIC) decline plays an important role in Arctic amplification which, in turn, influences Arctic ecosystems, midlatitude weather and climate. SIC over the Barents-Kara Seas (BKS) shows large interannual variations, whose origin is still unclear. Here we find that interannual variations in winter BKS SIC have significantly strengthened in recent decades likely due to increased amplitudes of the El Niño-Southern Oscillation (ENSO) in a warming climate. La Niña leads to enhanced Atlantic Hadley cell and a positive phase North Atlantic Oscillation-like anomaly pattern, together with concurring Ural blocking, that transports Atlantic ocean heat and atmospheric moisture toward the BKS and promotes sea-ice melting via intensified surface warming. The reverse is seen during El Niño which leads to weakened Atlantic poleward transport and an increase in the BKS SIC. Thus, interannual variability of the BKS SIC partly originates from ENSO via the Atlantic pathway.

Contactless WiFi Sensing and Monitoring for Future Healthcare - Emerging Trends, Challenges, and Opportunities.

WiFi sensing has received recent and significant interest from academia, industry, healthcare professionals, and other caregivers (including family members) as a potential mechanism to monitor our aging population at a distance without deploying devices on users' bodies. In particular, these methods have the potential to detect critical events such as falls, sleep disturbances, wandering behavior, respiratory disorders, and abnormal cardiac activity experienced by vulnerable people. The interest in such WiFi-based sensing systems arises from practical advantages including its ease of operation indoors as well as ready compliance from monitored individuals. Unlike other sensing methods, such as wearables, camera-based imaging, and acoustic-based solutions, WiFi technology is easy to implement and unobtrusive. This paper reviews the current state-of-the-art research on collecting and analyzing channel state information extracted using ubiquitous WiFi signals, describing a range of healthcare applications and identifying a series of open research challenges, including untapped areas of research and related trends. This work aims to provide an overarching view in understanding the technology and discusses its use-cases from a perspective that considers hardware, advanced signal processing, and data acquisition.

Chitosan oligosaccharide alleviates and removes the toxicological effects of organophosphorus pesticide chlorpyrifos residues.

The abuse of chlorpyrifos (CHP), a commonly used organophosphorus pesticide, has caused many environmental pollution problems, especially its toxicological effects on non-target organisms. First, CHP enriched on the surface of plants enters ecosystem circulation along the food chain. Second, direct inflow of CHP into the water environment under the action of rainwater runoff inevitably causes toxicity to non-target organisms. Therefore, we used rats as a model to establish a CHP exposure toxicity model and studied the effects of CHP in rats. In addition, to alleviate and remove the injuries caused by residual chlorpyrifos in vivo, we explored the alleviation effect of chitosan oligosaccharide (COS) on CHP toxicity in rats by exploiting its high water solubility and natural biological activity. The results showed that CHP can induce the toxicological effects of intestinal antioxidant changes, inflammation, apoptosis, intestinal barrier damage, and metabolic dysfunction in rats, and COS has excellent removal and mitigation effects on the toxic damage caused by residual CHP in the environment. In summary, COS showed significant biological effects in removing and mitigating blood biochemistry, antioxidants, inflammation, apoptosis, gut barrier structure, and metabolic function changes induced by residual CHP in the environment.

#ChronicPain: Automated Building of a Chronic Pain Cohort from Twitter Using Machine Learning.

Background: Due to the high burden of chronic pain, and the detrimental public health consequences of its treatment with opioids, there is a high-priority need to identify effective alternative therapies. Social media is a potentially valuable resource for knowledge about self-reported therapies by chronic pain sufferers. Methods: We attempted to (a) verify the presence of large-scale chronic pain-related chatter on Twitter, (b) develop natural language processing and machine learning methods for automatically detecting self-disclosures, (c) collect longitudinal data posted by them, and (d) semiautomatically analyze the types of chronic pain-related information reported by them. We collected data using chronic pain-related hashtags and keywords and manually annotated 4,998 posts to indicate if they were self-reports of chronic pain experiences. We trained and evaluated several state-of-the-art supervised text classification models and deployed the best-performing classifier. We collected all publicly available posts from detected cohort members and conducted manual and natural language processing-driven descriptive analyses. Results: Interannotator agreement for the binary annotation was 0.82 (Cohen's kappa). The RoBERTa model performed best (F1 score: 0.84; 95% confidence interval: 0.80 to 0.89), and we used this model to classify all collected unlabeled posts. We discovered 22,795 self-reported chronic pain sufferers and collected over 3 million of their past posts. Further analyses revealed information about, but not limited to, alternative treatments, patient sentiments about treatments, side effects, and self-management strategies. Conclusion: Our social media based approach will result in an automatically growing large cohort over time, and the data can be leveraged to identify effective opioid-alternative therapies for diverse chronic pain types.

Evaluation of deep learning models in contactless human motion detection system for next generation healthcare.

Recent decades have witnessed the growing importance of human motion detection systems based on artificial intelligence (AI). The growing interest in human motion detection systems is the advantages of automation in the monitoring of patients remotely and giving warnings to doctors promptly. Currently, wearable devices are frequently used for human motion detection systems. However, such devices have several limitations, such as the elderly not wearing devices due to lack of comfort or forgetfulness and/or battery limitations. To overcome the problems of wearable devices, we propose an AI-driven human motion detection system (deep learning-based system) using channel state information (CSI) extracted from Radio Frequency (RF) signals. The main contribution of this paper is to improve the performance of the deep learning models through techniques, including structure modification and dimension reduction of the original data. In this work, We firstly collected the CSI data with the center frequency 5.32 GHz and implemented the structure of the basic deep learning network in our previous work. After that, we changed the basic deep learning network by increasing the depth, increasing the width, adapting some advanced network structures, and reducing dimensions. After finishing those modifications, we observed the results and analyzed how to further improve the deep learning performance of this contactless AI-enabled human motion detection system. It can be found that reducing the dimension of the original data can work better than modifying the structure of the deep learning model.