Seafloor primary production in a changing Arctic Ocean.

Phytoplankton and sea ice algae are traditionally considered to be the main primary producers in the Arctic Ocean. In this Perspective, we explore the importance of benthic primary producers (BPPs) encompassing microalgae, macroalgae, and seagrasses, which represent a poorly quantified source of Arctic marine primary production. Despite scarce observations, models predict that BPPs are widespread, colonizing ~3 million km2 of the extensive Arctic coastal and shelf seas. Using a synthesis of published data and a novel model, we estimate that BPPs currently contribute ~77 Tg C y-1 of primary production to the Arctic, equivalent to ~20 to 35% of annual phytoplankton production. Macroalgae contribute ~43 Tg C y-1, seagrasses contribute ~23 Tg C y-1, and microalgae-dominated shelf habitats contribute ~11 to 16 Tg C y-1. Since 2003, the Arctic seafloor area exposed to sunlight has increased by ~47,000 km2 y-1, expanding the realm of BPPs in a warming Arctic. Increased macrophyte abundance and productivity is expected along Arctic coastlines with continued ocean warming and sea ice loss. However, microalgal benthic primary production has increased in only a few shelf regions despite substantial sea ice loss over the past 20 y, as higher solar irradiance in the ice-free ocean is counterbalanced by reduced water transparency. This suggests complex impacts of climate change on Arctic light availability and marine primary production. Despite significant knowledge gaps on Arctic BPPs, their widespread presence and obvious contribution to coastal and shelf ecosystem production call for further investigation and for their inclusion in Arctic ecosystem models and carbon budgets.

CORN-Condition Orientated Regulatory Networks: bridging conditions to gene networks.

A transcriptional regulatory network (TRN) is a collection of transcription regulators with their associated downstream genes, which is highly condition-specific. Understanding how cell states can be programmed through small molecules/drugs or conditions by modulating the whole gene expression system granted us the potential to amend abnormal cells and cure diseases. Condition Orientated Regulatory Networks (CORN, https://qinlab.sysu.edu.cn/home) is a library of condition (small molecule/drug treatments and gene knockdowns)-based transcriptional regulatory sub-networks (TRSNs) that come with an online TRSN matching tool. It allows users to browse condition-associated TRSNs or match those TRSNs by inputting transcriptomic changes of interest. CORN utilizes transcriptomic changes data after specific conditional treatment in cells, and in vivo transcription factor (TF) binding data in cells, by combining TF binding information and calculations of significant expression alterations of TFs and genes after the conditional treatments, TRNs under the effect of different conditions were constructed. In short, CORN associated 1805 different types of specific conditions (small molecule/drug treatments and gene knockdowns) to 9553 TRSNs in 25 human cell lines, involving 204TFs. By linking and curating specific conditions to responsive TRNs, the scientific community can now perceive how TRNs are altered and controlled by conditions alone in an organized manner for the first time. This study demonstrated with examples that CORN can aid the understanding of molecular pathology, pharmacology and drug repositioning, and screened drugs with high potential for cancer and coronavirus disease 2019 (COVID-19) treatments.

Integrative analysis of individual-level data and high-dimensional summary statistics.

MOTIVATION: Researchers usually conduct statistical analyses based on models built on raw data collected from individual participants (individual-level data). There is a growing interest in enhancing inference efficiency by incorporating aggregated summary information from other sources, such as summary statistics on genetic markers' marginal associations with a given trait generated from genome-wide association studies. However, combining high-dimensional summary data with individual-level data using existing integrative procedures can be challenging due to various numeric issues in optimizing an objective function over a large number of unknown parameters. RESULTS: We develop a procedure to improve the fitting of a targeted statistical model by leveraging external summary data for more efficient statistical inference (both effect estimation and hypothesis testing). To make this procedure scalable to high-dimensional summary data, we propose a divide-and-conquer strategy by breaking the task into easier parallel jobs, each fitting the targeted model by integrating the individual-level data with a small proportion of summary data. We obtain the final estimates of model parameters by pooling results from multiple fitted models through the minimum distance estimation procedure. We improve the procedure for a general class of additive models commonly encountered in genetic studies. We further expand these two approaches to integrate individual-level and high-dimensional summary data from different study populations. We demonstrate the advantage of the proposed methods through simulations and an application to the study of the effect on pancreatic cancer risk by the polygenic risk score defined by BMI-associated genetic markers. AVAILABILITY AND IMPLEMENTATION: R package is available at https://github.com/fushengstat/MetaGIM.

Bioinformatics analysis of potential common pathogenic mechanisms for COVID-19 and venous thromboembolism.

BACKGROUND: A growing body of research has shown that patients with coronavirus disease 2019 (COVID-19) have significantly higher rates of venous thromboembolism (VTE) than healthy. However, the mechanism remains incompletely elucidated. This study aimed to further investigate the molecular mechanisms underlying the development of this complication. METHODS: The gene expression profiles of COVID-19 and VTE were downloaded from the Gene Expression Omnibus (GEO) database. After identifying the common differentially expressed genes (DEGs) for COVID-19 and VTE, functional annotation, a protein-protein interactions (PPI) network, module construction, and hub gene identification were performed. Finally, we constructed a transcription factor (TF)-gene regulatory network and a TF-miRNA regulatory network for hub genes. RESULTS: A total of 42 common DEGs were selected for subsequent analyses. Functional analyses showed that biological function and signaling pathways collectively participated in the development and progression of VTE and COVID-19. Finally, 8 significant hub genes were identified using the cytoHubba plugin, including RSL24D1, RPS17, RPS27, HINT1, COX7C, RPL35, RPL34, and NDUFA4, which had preferable values as diagnostic markers for COVID-19 and VTE. CONCLUSIONS: Our study revealed the common pathogenesis of COVID-19 and VTE. These common pathways and pivotal genes may provide new ideas for further mechanistic studies.

Improve the model of disease subtype heterogeneity by leveraging external summary data.

Researchers are often interested in understanding the disease subtype heterogeneity by testing whether a risk exposure has the same level of effect on different disease subtypes. The polytomous logistic regression (PLR) model provides a flexible tool for such an evaluation. Disease subtype heterogeneity can also be investigated with a case-only study that uses a case-case comparison procedure to directly assess the difference between risk effects on two disease subtypes. Motivated by a large consortium project on the genetic basis of non-Hodgkin lymphoma (NHL) subtypes, we develop PolyGIM, a procedure to fit the PLR model by integrating individual-level data with summary data extracted from multiple studies under different designs. The summary data consist of coefficient estimates from working logistic regression models established by external studies. Examples of the working model include the case-case comparison model and the case-control comparison model, which compares the control group with a subtype group or a broad disease group formed by merging several subtypes. PolyGIM efficiently evaluates risk effects and provides a powerful test for disease subtype heterogeneity in situations when only summary data, instead of individual-level data, is available from external studies due to various informatics and privacy constraints. We investigate the theoretic properties of PolyGIM and use simulation studies to demonstrate its advantages. Using data from eight genome-wide association studies within the NHL consortium, we apply it to study the effect of the polygenic risk score defined by a lymphoid malignancy on the risks of four NHL subtypes. These results show that PolyGIM can be a valuable tool for pooling data from multiple sources for a more coherent evaluation of disease subtype heterogeneity.

Efficient data integration under prior probability shift.

Conventional supervised learning usually operates under the premise that data are collected from the same underlying population. However, challenges may arise when integrating new data from different populations, resulting in a phenomenon known as dataset shift. This paper focuses on prior probability shift, where the distribution of the outcome varies across datasets but the conditional distribution of features given the outcome remains the same. To tackle the challenges posed by such shift, we propose an estimation algorithm that can efficiently combine information from multiple sources. Unlike existing methods that are restricted to discrete outcomes, the proposed approach accommodates both discrete and continuous outcomes. It also handles high-dimensional covariate vectors through variable selection using an adaptive least absolute shrinkage and selection operator penalty, producing efficient estimates that possess the oracle property. Moreover, a novel semiparametric likelihood ratio test is proposed to check the validity of prior probability shift assumptions by embedding the null conditional density function into Neyman's smooth alternatives (Neyman, 1937) and testing study-specific parameters. We demonstrate the effectiveness of our proposed method through extensive simulations and a real data example. The proposed methods serve as a useful addition to the repertoire of tools for dealing dataset shifts.

Nickel-Catalyzed Reductive Cross-Coupling of Propargylic Acetates with Chloro(vinyl)silanes: Access to Silylallenes.

Because of their various reactivities, propargyl acetates are refined chemical intermediates that are extensively applied in pharmaceutical synthesis. Currently, reactions between propargyl acetates and chlorosilanes may be the most effective method for synthesizing silylallenes. Nevertheless, owing to the adaptability and selectivity of substrates, transition metal catalysis is difficult to achieve. Herein, nickel-catalyzed reductive cross-coupling reactions between propargyl acetates and substituted vinyl chlorosilanes for the synthesis of tetrasubstituted silylallenes are described. Therein, metallic zinc is a crucial reductant that effectively enables two electrophilic reagents to selectively construct C(sp2)-Si bonds. Additionally, a Ni-catalyzed reductive mechanism involving a radical process is proposed on the basis of deuteration-labeled experiments.

Visible-Light-Induced Photoredox 1,2-Dialkylation of Styrenes with α-Carbonyl Alkyl Bromides and Pyridin-1-ium Salts.

A visible-light-driven photoredox dialkylation of styrenes with α-carbonyl alkyl bromides and pyridin-1-ium salts for the synthesis of polysubstituted 1,4-dihydropyridines is reported. This reaction enables the formation of two new C(sp3)-C(sp3) bonds in a single reaction step and provides a strategy that employs pyridin-1-ium salts as the functionalized alkylating reagents via dearomatization to directly trap the resulting alkyl radicals from radical addition of alkenes and then terminate the alkene dialkylation.

The role of microbiota in gastric cancer: A comprehensive review.

BACKGROUND: Gastric cancer (GC) continues to pose a significant global threat in terms of cancer-related fatalities. Despite notable advancements in medical research and therapies, further investigation is warranted to elucidate its underlying etiology and risk factors. Recent times have witnessed an escalated emphasis on comprehending the role of the microbiota in cancer development. METHODS: This review briefly delves into recent developments in microbiome-related research pertaining to gastric cancer. RESULTS: According to studies, the microbiota can influence GC growth by inciting inflammation, disrupting immunological processes, and generating harmful microbial metabolites. Furthermore, there is ongoing research into how the microbiome can impact a patient's response to chemotherapy and immunotherapy. CONCLUSION: The utilization of the microbiome for detecting, preventing, and managing stomach cancer remains an active area of exploration.

Impact of crosslinking agents with steric cyclic groups on the properties of polymer-dispersed liquid crystals.

As a type of intelligent dimming film, polymer-dispersed liquid crystals (PDLCs) have been widely applied in various fields, such as smart windows, light shutters and displays. The properties of PDLCs are greatly influenced by the structure of the raw materials. In this work, the impact of crosslinking agents with different cyclic or chain groups was investigated by comparing the electro-optical performance and the morphology of the polymer matrix in the as-made PDLC films. It was found that the incorporation of large steric groups into the crosslinking agents can alter the morphology of the polymer matrix and thus affect the electro-optical properties. However, the impact is distinct when the spatial structure or rigidity is different. Besides, a combination of crosslinking agents with flexible alkyl-chain structures and steric structures can further reduce the threshold voltage while keeping the high contrast ratio. After detailed comparison, an optimized combination of BDDA/TCDDA in a weight ratio of 1/1 is selected to demonstrate the enhanced properties of the as-constructed film with a thickness of 20 µm. It exhibits low threshold voltage (8.2 V), low saturation voltage (21.2 V) and a high contrast ratio (203) simultaneously. This research offers an optimizing method from the crosslinking agent perspective and is anticipated to promote the further improvement of the PDLC's performance.

Regulation of the PD-1/PD-L1 Axis and NK Cell Dysfunction by Exosomal miR-552-5p in Gastric Cancer.

OBJECTIVE: NK cells play a vital role in tumor immune resistance. Various factors affect NK cell activity. While NK cell dysfunction has been observed in numerous malignancies, the underlying mechanisms in gastric cancer remain unclear. METHOD: Flow cytometry was used to identify the phenotypic distribution and expression of activated receptors on NK cells. ELISA was used to determine the expression of cytokines. We examined the expression of NK cell-related genes and explored their association with survival and prognosis. Additionally, we conducted PCR detection of miR-552-5p expression levels in plasma exosomes of patients and investigated its correlation with phenotypic distribution and activated receptors. We used flow cytometry and ELISA to verify the role of miR-552-5p in NK cell dysfunction. Furthermore, we investigated the potential role of PD-1/PD-L1 in regulating NK cell dysfunction in patients' cells. RESULTS: We observed a significant decrease in the percentage of NKG2D and NKp30 and IFN-γ and TNF-α in patients than in healthy volunteers. Patients with low levels of CD56, CD16, NKG2D, and NKP46 exhibited poorer survival prognoses. Moreover, increased expression levels of plasma exosomal miR-552-5p in patients were negatively associated with NK cell phenotypic distribution and activated receptor expression. MiR-552-5p downregulated the secretion of perforin, granzyme, and IFN-γ as well as the expression of NKp30, NKp46, and NKG2D. Additionally, it suppressed the cytotoxicity of NK cells. The inhibitory effect of miR-552-5p, on NK cell function was reversed when anti-PD-L1 antibodies were used. CONCLUSION: Exosomal miR-552-5p targets the PD-1/PD-L1 axis, leading to impaired NK cell function.

Loss of ß-arrestin2 aggravated condylar cartilage degeneration at the early stage of temporomandibular joint osteoarthritis.

OBJECTIVE: Temporomandibular joint osteoarthritis (TMJOA) is a chronic degenerative joint disorder characterized by extracellular matrix degeneration and inflammatory response of condylar cartilage. ß-arrestin2 is an important regulator of inflammation response, while its role in TMJOA remains unknown. The objective of this study was to investigate the role of ß-arrestin2 in the development of TMJOA at the early stage and the underlying mechanism. METHODS: A unilateral anterior crossbite (UAC) model was established on eight-week-old wild-type (WT) and ß-arrestin2 deficiency mice to simulate the progression of TMJOA. Hematoxylin-eosin (HE) staining and microcomputed tomography (micro-CT) analysis were used for histological and radiographic assessment. Immunohistochemistry was performed to detect the expression of inflammatory and degradative cytokines, as well as autophagy related factors. Terminal-deoxynucleotidyl transferase mediated nick end labeling (TUNEL) assay was carried out to assess chondrocyte apoptosis. RESULTS: The loss of ß-arrestin2 aggravated cartilage degeneration and subchondral bone destruction in the model of TMJOA at the early stage. Furthermore, in UAC groups, the expressions of degradative (Col-X) and inflammatory (TNF-α and IL-1ß) factors in condylar cartilage were increased in ß-arrestin2 null mice compared with WT mice. Moreover, the loss of ß-arrestin2 promoted apoptosis and autophagic process of chondrocytes at the early stage of TMJOA. CONCLUSION: In conclusion, we demonstrated for the first time that ß-arrestin2 plays a protective role in the development of TMJOA at the early stage, probably by inhibiting apoptosis and autophagic process of chondrocytes. Therefore, ß-arrestin2 might be a potential therapeutic target for TMJOA, providing a new insight for the treatment of TMJOA at the early stage.

Investigating the Pharmacological Mechanisms of Total Flavonoids from Eucommia ulmoides Oliver Leaves for Ischemic Stroke Protection.

The aim of this study was to explore how the total flavonoids from Eucommia ulmoides leaves (EULs) regulate ischemia-induced nerve damage, as well as the protective effects mediated by oxidative stress. The cell survival rate was significantly improved compared to the ischemic group (p < 0.05) after treatment with the total flavonoids of EULs. The levels of reactive oxygen species (ROS), lactate dehydrogenase (LDH), and malondialdehyde (MDA) decreased, while catalase (CAT) and glutathione (GSH) increased, indicating that the total flavonoids of EULs can significantly alleviate neurological damage caused by ischemic stroke by inhibiting oxidative stress (p < 0.01). The mRNA expression level of VEGF increased (p < 0.01), which was consistent with the protein expression results. Meanwhile, the protein expression of ERK and CCND1 increased (p < 0.01), suggesting that the total flavonoids of EULs could protect PC12 cells from ischemic injury via VEGF-related pathways. MCAO rat models indicated that the total flavonoids of EULs could reduce brain ischemia-reperfusion injury. In conclusion, this study demonstrates the potential mechanisms of the total flavonoids of EULs in treating ischemic stroke and their potential therapeutic effects in reducing ischemic injury, which provides useful information for ischemic stroke drug discovery.

Robustness of the synergistic partial-denitrification, anammox, and fermentation process for treating domestic and nitrate wastewaters under fluctuating C/N ratios.

The synergistic partial-denitrification, anammox, and fermentation (SPDAF) process presents a promising solution to treat domestic and nitrate wastewaters. However, its capability to handle fluctuating C/N ratios (the ratios of COD to total inorganic nitrogen) in practical applications remains uncertain. In this study, the SPDAF process was operated for 236 days with C/N ratios of 0.7-3.5, and a high and stable efficiency of nitrogen removal (84.9 ± 7.8%) was achieved. The denitrification and anammox contributions were 6.1 ± 7.1% and 93.9 ± 7.1%, respectively. Batch tests highlighted the pivotal role of in situ fermentation at low biodegradable chemical oxygen demand (BCOD)/NO3- ratios. As the BCOD/NO3- ratios increased from 0 to 6, the NH4+ and NO3- removal rates increased, while the anammox contribution decreased from 100% to 80.1% but remained the primary pathway of nitrogen removal. The cooperation and balanced growth of denitrifying bacteria, anammox bacteria, and fermentation bacteria contributed to the system's robustness under fluctuating C/N ratios.

E-bibliotherapy for improving the psychological well-being of informal caregivers of people with dementia: a randomized controlled trial protocol.

BACKGROUND: Providing informal care for individuals with dementia is frequently a challenging and demanding experience that can have detrimental effects on the psychological well-being of caregivers. Regrettably, community-based caregiver services often prove inadequate, highlighting the necessity for innovative approaches to support caregivers. AIM: To test the efficacy of e-bibliotherapy in improving the psychological well-being of informal caregivers of people with dementia. METHOD: The study is divided into two phases. In phase 1, the research team will co-design the e-bibliotherapy app with caregivers. In phase 2, a randomized controlled trial will be conducted among 192 informal caregivers of people with dementia in Hong Kong. Caregivers will be randomly assigned to either the e-bibliotherapy group or the control group using simple randomization. Outcome measures will encompass caregivers' psychological well-being, caregiving appraisal, mental health, saliva cortisol levels as an indicator of stress, and health-related quality of life for caregivers. Data will be collected at baseline, immediately post intervention, and 3 months and 6 months post intervention. General linear mixed model will be employed to analyze intervention effects. Qualitative interviews will be undertaken to explore caregiver experiences within this study and evaluate intervention acceptability using conventional content analysis methods. DISCUSSION: This study represents a pioneering effort in utilizing e-bibliotherapy to enhance the psychological well-being of informal caregivers of individuals with dementia, addressing the existing gap in caregiver services and facilitating knowledge dissemination within the community. TRIAL REGISTRATION: The trial has been registered on ClinicalTrial.gov (Ref: NCT05927805).

Associations of combined lifestyle index with migraine prevalence and headache frequency: a cross-sectional study from the MECH-HK study.

BACKGROUND: Prior research has shown that individual lifestyles were associated with migraine. Yet, few studies focused on combined lifestyles, particularly in Chinese populations. This cross-sectional study aimed to investigate the relationships of a combined lifestyle index with migraine in Hong Kong Chinese women. METHODS: Baseline data from a cohort study named Migraine Exposures and Cardiovascular Health in Hong Kong Chinese Women (MECH-HK) were used for analysis. In total 3510 women aged 55.2 ± 9.1 years were included. The combined lifestyle index comprised eight lifestyle factors: smoking, physical activity, sleep, stress, fatigue, diet, body mass index, and alcohol. Each component was attributed a point of 0 (unhealthy) or 1 (healthy). The overall index was the sum of these points, ranging from 0 (the least healthy) to 8 points (the healthiest). Migraine was diagnosed by the International Classification of Headache Disorders 3rd edition. Additionally, for women with migraine, the data on migraine attack frequency (attacks/month) was collected. RESULTS: A total of 357 women with migraine (10.2%) were identified. The prevalence of migraine for the 0-3-point, 4-point, 5-point, 6-point, and 7-8-point groups were 18.0% (162/899), 10.9% (86/788), 6.6% (51/776), 6.0% (38/636), and 4.9% (20/411), respectively. In the most-adjusted model, compared to the 0-3-point group, the odds ratios and 95% confidence intervals for the 4-point, 5-point, 6-point, and 7-8-point groups were 0.57 (0.43-0.75), 0.33 (0.24-0.46), 0.30 (0.21-0.44), and 0.25 (0.15-0.41), respectively (all p < 0.001). For each component, migraine was significantly associated with sleep, stress, fatigue, and diet; but was unrelated to smoking, physical activity, body mass index, and alcohol. Among women with migraine, per point increase in the combined lifestyle index was associated with a reduced migraine attack frequency (ß = - 0.55; 95% confidence interval = - 0.82, - 0.28; p < 0.001). CONCLUSIONS: A combined lifestyle index was inversely associated with migraine and migraine attack frequency in Hong Kong Chinese women. Adhering to a healthy lifestyle pattern might be beneficial to the prevention of migraine attacks. Conversely, it is also plausible that women with migraine might have a less healthy lifestyle pattern compared to those without headaches.

Comparison of Levels of Nasal, Salivary, and Plasma Antibody to Severe Acute Respiratory Syndrome Coronavirus 2 During Natural Infection and After Vaccination.

BACKGROUND: Most studies of immunity to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) measure antibody or cellular responses in blood; however, the virus infects mucosal surfaces in the nose and conjunctivae and infectious virus is rarely if ever present in the blood. METHODS: We used luciferase immunoprecipitation assays to measure SARS-CoV-2 antibody levels in the plasma, nose, and saliva of infected persons and vaccine recipients. These assays measure antibody that can precipitate the SAR-CoV-2 spike and nucleocapsid proteins. RESULTS: Levels of plasma anti-spike antibody declined less rapidly than levels of anti-nucleocapsid antibody in infected persons. SARS-CoV-2 anti-spike antibody levels in the nose declined more rapidly than antibody levels in the blood after vaccination of infected persons. Vaccination of previously infected persons boosted anti-spike antibody in plasma more than in the nose or saliva. Nasal and saliva anti-spike antibody levels were significantly correlated with plasma antibody in infected persons who had not been vaccinated and after vaccination of uninfected persons. CONCLUSIONS: Persistently elevated SARS-CoV-2 antibody in plasma may not indicate persistence of antibody at mucosal sites such as the nose. The strong correlation of SARS-CoV-2 antibody in the nose and saliva with that in the blood suggests that mucosal antibodies are derived primarily from transudation from the blood rather than local production. While SARS-CoV-2 vaccine given peripherally boosted mucosal immune responses in infected persons, the increase in antibody titers was higher in plasma than at mucosal sites. Taken together, these observations indicate the need for development of mucosal vaccines to induce potent immune responses at sites where SARS-CoV-2 infection occurs. CLINICAL TRIALS REGISTRATION: NCT01306084.

Cell fate conversion prediction by group sparse optimization method utilizing single-cell and bulk OMICs data.

Cell fate conversion by overexpressing defined factors is a powerful tool in regenerative medicine. However, identifying key factors for cell fate conversion requires laborious experimental efforts; thus, many of such conversions have not been achieved yet. Nevertheless, cell fate conversions found in many published studies were incomplete as the expression of important gene sets could not be manipulated thoroughly. Therefore, the identification of master transcription factors for complete and efficient conversion is crucial to render this technology more applicable clinically. In the past decade, systematic analyses on various single-cell and bulk OMICs data have uncovered numerous gene regulatory mechanisms, and made it possible to predict master gene regulators during cell fate conversion. By virtue of the sparse structure of master transcription factors and the group structure of their simultaneous regulatory effects on the cell fate conversion process, this study introduces a novel computational method predicting master transcription factors based on group sparse optimization technique integrating data from multi-OMICs levels, which can be applicable to both single-cell and bulk OMICs data with a high tolerance of data sparsity. When it is compared with current prediction methods by cross-referencing published and validated master transcription factors, it possesses superior performance. In short, this method facilitates fast identification of key regulators, give raise to the possibility of higher successful conversion rate and in the hope of reducing experimental cost.

Compressed sensing framework for BCG signals based on the optical fiber sensor.

A compressed sensing (CS) framework is built for ballistocardiography (BCG) signals, which contains two parts of an optical fiber sensor-based heart monitoring system with a CS module and an end-to-end deep learning-based reconstruction algorithm. The heart monitoring system collects BCG data, and then compresses and transmits the data through the CS module at the sensing end. The deep learning-based algorithm reconstructs compressed data at the received end. To evaluate results, three traditional CS reconstruction algorithms and a deep learning method are adopted as references to reconstruct the compressed BCG data with different compression ratios (CRs). Results show that our framework can reconstruct signals successfully when the CR grows from 50% to 95% and outperforms other methods at high CRs. The mean absolute error (MAE) of the estimated heartbeat rate (HR) is lower than 1 bpm when the CR is below 95%. The proposed CS framework for BCG signals can be integrated into the IoMT system, which has great potential in health care for both medical and home use.

Novel deep learning-based computer-aided diagnosis system for predicting inflammatory activity in ulcerative colitis.

BACKGROUND AND AIMS: Endoscopy is increasingly performed for evaluating patients with ulcerative colitis (UC). However, its diagnostic accuracy is largely affected by the subjectivity of endoscopists' experience and scoring methods, and scoring of selected endoscopic images cannot reflect the inflammation of the entire intestine. We aimed to develop an automatic scoring system using deep-learning technology for consistent and objective scoring of endoscopic images and full-length endoscopic videos of patients with UC. METHODS: We collected 5875 endoscopic images and 20 full-length videos from 332 patients with UC who underwent colonoscopy between January 2017 and March 2021. We trained the artificial intelligence (AI) scoring system using these images, which was then used for full-length video scoring. To more accurately assess and visualize the full-length intestinal inflammation, we divided the large intestine into a fixed number of "areas" (cecum, 20; transverse colon, 20; descending colon, 20; sigmoid colon, 15; rectum, 10). The scoring system automatically scored inflammatory severity of 85 areas from every video and generated a visualized result of full-length intestinal inflammatory activity. RESULTS: Compared with endoscopist scoring, the trained convolutional neural network achieved 86.54% accuracy in the Mayo-scored task, whereas the kappa coefficient was .813 (95% confidence interval [CI], .782-.844). The metrics of the Ulcerative Colitis Endoscopic Index of Severity-scored task were encouraging, with accuracies of 90.7%, 84.6%, and 77.7% and kappa coefficients of .822 (95% CI, .788-.855), .784 (95% CI, .744-.823), and .702 (95% CI, .612-.793) for vascular pattern, erosions and ulcers, and bleeding, respectively. The AI scoring system predicted each bowel segment's score and displayed distribution of inflammatory activity in the entire large intestine using a 2-dimensional colorized image. CONCLUSIONS: We established a novel deep learning-based scoring system to evaluate endoscopic images from patients with UC, which can also accurately describe the severity and distribution of inflammatory activity through full-length intestinal endoscopic videos.