Correspondence to "association of sleep patterns and cardiovascular disease risk is modified by glucose tolerance status".

After reading the article written by Wang et al., we have encountered several concerns that may compromise the credibility of the article. There are some factors, such as changes in sleep patterns, glucose tolerance status, and the use of hypnotics, which may interfere with the research results. Additionally, the design of the sleep pattern could lead to biased outcomes. Therefore, we are writing this letter to recommend that further research should take these concerns into consideration.

The intrinsic substrate specificity of the human tyrosine kinome.

Phosphorylation of proteins on tyrosine (Tyr) residues evolved in metazoan organisms as a mechanism of coordinating tissue growth1. Multicellular eukaryotes typically have more than 50 distinct protein Tyr kinases that catalyse the phosphorylation of thousands of Tyr residues throughout the proteome1-3. How a given Tyr kinase can phosphorylate a specific subset of proteins at unique Tyr sites is only partially understood4-7. Here we used combinatorial peptide arrays to profile the substrate sequence specificity of all human Tyr kinases. Globally, the Tyr kinases demonstrate considerable diversity in optimal patterns of residues surrounding the site of phosphorylation, revealing the functional organization of the human Tyr kinome by substrate motif preference. Using this information, Tyr kinases that are most compatible with phosphorylating any Tyr site can be identified. Analysis of mass spectrometry phosphoproteomic datasets using this compendium of kinase specificities accurately identifies specific Tyr kinases that are dysregulated in cells after stimulation with growth factors, treatment with anti-cancer drugs or expression of oncogenic variants. Furthermore, the topology of known Tyr signalling networks naturally emerged from a comparison of the sequence specificities of the Tyr kinases and the SH2 phosphotyrosine (pTyr)-binding domains. Finally we show that the intrinsic substrate specificity of Tyr kinases has remained fundamentally unchanged from worms to humans, suggesting that the fidelity between Tyr kinases and their protein substrate sequences has been maintained across hundreds of millions of years of evolution.

Association of the oral microbiome with cognitive function among older adults: NHANES 2011-2012.

BACKGROUND: An association between the gut microbiome and cognitive function has been demonstrated in prior studies. However, whether the oral microbiome, the second largest microbial habitant in humans, has a role in cognition remains unclear. DESIGN, SETTING, PARTICIPANTS: Using weighted data from the 2011 to 2012 National Health and Nutrition Examination Survey, we examined the association between oral microbial composition and cognitive function in older adults. The oral microbiome was characterized by 16S ribosomal RNA gene sequencing. Cognitive status was assessed using the Consortium to Establish a Registry for Alzheimer's Disease immediate recall and delayed recall, Animal Fluency Test, and Digit Symbol Substitution Test (DSST). Subjective memory changes over 12 months were also assessed. Linear and logistic regression models were conducted to quantify the association of α-diversity with different cognitive measurements controlling for potential confounding variables. Differences in ß-diversity were analyzed using permutational analysis of variance. RESULTS: A total of 605 participants aged 60-69 years were included in the analysis. Oral microbial α-diversity was significantly and positively correlated with DSST (ß, 2.92; 95% CI, 1.01-4.84). Participants with higher oral microbial α-diversity were more likely to have better cognitive performance status based on DSST (adjusted odds ratio, 2.35; 95% CI, 1.28-4.30) and were less likely to experience subjective memory changes (adjusted odds ratio, 0.43; 95% CI, 0.25-0.74). In addition, ß-diversity was statistically significant for the cognitive performance status based on DSST (P = 0.031) and subjective memory changes (P = 0.023). CONCLUSIONS: Oral microbial composition was associated with executive function and subjective memory changes among older adults among older U.S. adults in a nationally representative population sample. Oral dysbiosis is a potential biomarker or therapeutic target for cognitive decline. Further work is needed to elucidate the mechanisms underpinning the association between the oral microbiome and cognitive function.

Machine learning-based longitudinal prediction for GJB2-related sensorineural hearing loss.

BACKGROUND: Recessive GJB2 variants, the most common genetic cause of hearing loss, may contribute to progressive sensorineural hearing loss (SNHL). The aim of this study is to build a realistic predictive model for GJB2-related SNHL using machine learning to enable personalized medical planning for timely intervention. METHOD: Patients with SNHL with confirmed biallelic GJB2 variants in a nationwide cohort between 2005 and 2022 were included. Different data preprocessing protocols and computational algorithms were combined to construct a prediction model. We randomly divided the dataset into training, validation, and test sets at a ratio of 72:8:20, and repeated this process ten times to obtain an average result. The performance of the models was evaluated using the mean absolute error (MAE), which refers to the discrepancy between the predicted and actual hearing thresholds. RESULTS: We enrolled 449 patients with 2184 audiograms available for deep learning analysis. SNHL progression was identified in all models and was independent of age, sex, and genotype. The average hearing progression rate was 0.61 dB HL per year. The best MAE for linear regression, multilayer perceptron, long short-term memory, and attention model were 4.42, 4.38, 4.34, and 4.76 dB HL, respectively. The long short-term memory model performed best with an average MAE of 4.34 dB HL and acceptable accuracy for up to 4 years. CONCLUSIONS: We have developed a prognostic model that uses machine learning to approximate realistic hearing progression in GJB2-related SNHL, allowing for the design of individualized medical plans, such as recommending the optimal follow-up interval for this population.

High-fat diet during early life reshapes the gut microbiome and is associated with the disrupted mammary microenvironment in later life in mice.

The influence of gut microbiota on gut health is well-documented, but it remains obscure for extraintestinal diseases such as breast cancer. Moreover, it is entirely unknown how gut dysbiosis during early life contributes to breast tumorigenesis later in life. In this study, we hypothesized that a high-fat diet during early life leads to alterations in the gut microbiome and is associated with disruptions in the mammary microenvironment. Female C57BL/6 mice were fed a low-fat diet (10% kcal fat) or a high-fat diet (HF, 60% kcal fat) for 8 weeks from the age of 4 to 12 weeks, which is equivalent to human childhood and adolescence. Twelve mice were sacrificed immediately after the 8-week feeding, the remainder were euthanized after switching to a normal lifecycle-supporting diet for an additional 12 weeks; the gut microbiome was then sequenced. The 8-week HF diet feeding altered the beta-diversity (Bray & Jaccard P < .01), and the difference remained significant after switching the diet (Bray & Jaccard P < .05). Immediately after HF feeding, a greater number of microbial taxa (>50) were altered, and about half of the taxa (25) remained significantly changed after switching the diet. The abundance of Alistipes, Bilophila, and Rikenellaceae stood out as significantly associated with multiple metabolic and inflammatory biomarkers in mammary tissue, including aromatase, Ccl2, and Cox2. In conclusion, an 8-week early-life HF feeding reshaped the gut microbiome, which connected with disrupted mammary microenvironments.

Proteomics appending a complementary dimension to precision oncotherapy.

Recent advances in high-throughput proteomic profiling technologies have facilitated the precise quantification of numerous proteins across multiple specimens concurrently. Researchers have the opportunity to comprehensively analyze the molecular signatures in plentiful medical specimens or disease pattern cell lines. Along with advances in data analysis and integration, proteomics data could be efficiently consolidated and employed to recognize precise elementary molecular mechanisms and decode individual biomarkers, guiding the precision treatment of tumors. Herein, we review a broad array of proteomics technologies and the progress and methods for the integration of proteomics data and further discuss how to better merge proteomics in precision medicine and clinical settings.

Exploring Temporal and Intensity Effects of Resistance Exercise on Inhibition: A Four-Arm Crossover Randomized Controlled Trial.

Objective: Given the recognized benefits of resistance exercise on both physical and cognitive domains, elucidating how to maximize its benefit is pivotal. This study aims to evaluate these effects in terms of their timing and intensity on cognitive performance. Methods: This was a four-arm, crossover randomized controlled trial. Healthy college-aged male adults with recreational resistance training experience participated in this study. Participants completed three separate sessions of circuit barbell resistance exercises, including back squat, press, and deadlift. Each session corresponded to a different intensity level: 65% 1RM, 72% 1RM, and 78% 1RM. Each session consisted of 5 repetitions across 3 sets, with a 3-minute rest between exercises and sets. For the control condition, participants engaged in a reading activity for the same duration. The subjective exercise intensity was measured using the rating of perceived exertion and repetitions in reserve immediately after each set. The primary outcome was the temporal effect of acute resistance exercise on inhibition, measured by the Stroop color-word task. The secondary outcome was the effect of different intensities. Results: 30 out of 31 recruited participants were randomized, with 28 completing all experiment sessions. Using repeated measures correlation (rrm), a linear temporal effect was observed on accuracy-adjusted congruent reaction time: rrm = 0.114, p = 0.045, 95% CI [0.002, 0.223]. Participants responded 19.1 ms faster than the control condition approximately 10 minutes post-intervention. This advantage, however, gradually declined at a rate of 4.3 ms every 15 minutes between 10-55 minutes post-intervention. In contrast, no significant effects were detected for incongruent trials or the Stroop effect. When examining the linear relationship across exercise intensities, no significant correlations emerged for congruent trials. Conclusion: Resistance exercise demonstrates a temporal effect on cognitive performance, particularly in reaction speed for congruent trials, without significant changes in incongruent trials or the overall Stroop effect. The findings highlight the importance of timing in leveraging the cognitive benefits of acute resistance exercise, suggesting a window of enhanced cognitive performance following exercise. However, this study has a limitation regarding Type I error inflation, due to multiple measurements of cognitive performance being undertaken, suggesting caution in interpreting the observed temporal effects. Practically, scheduling crucial, cognitively demanding tasks within 10-60 minutes post-exercise may maximize benefits, as positive effects diminish after this period.

Ultrapotent influenza hemagglutinin fusion inhibitors developed through SuFEx-enabled high-throughput medicinal chemistry.

Seasonal and pandemic-associated influenza strains cause highly contagious viral respiratory infections that can lead to severe illness and excess mortality. Here, we report on the optimization of our small-molecule inhibitor F0045(S) targeting the influenza hemagglutinin (HA) stem with our Sulfur-Fluoride Exchange (SuFEx) click chemistry-based high-throughput medicinal chemistry (HTMC) strategy. A combination of SuFEx- and amide-based lead molecule diversification and structure-guided design led to identification and validation of ultrapotent influenza fusion inhibitors with subnanomolar EC50 cellular antiviral activity against several influenza A group 1 strains. X-ray structures of six of these compounds with HA indicate that the appended moieties occupy additional pockets on the HA surface and increase the binding interaction, where the accumulation of several polar interactions also contributes to the improved affinity. The compounds here represent the most potent HA small-molecule inhibitors to date. Our divergent HTMC platform is therefore a powerful, rapid, and cost-effective approach to develop bioactive chemical probes and drug-like candidates against viral targets.

Genetic predisposition to bone mineral density and their health conditions in East Asians.

Osteoporosis, a condition defined by low bone mineral density (BMD) (typically < -2.5 SD), cause a higher fracture risk and lead to significant economic, social, and clinical impacts. Genome-wide studies mainly in Caucasians have found many genetic links to osteoporosis, fractures, and BMD, with limited research in East Asians. We investigated the genetic aspects of BMD in 86,716 individuals from the Taiwan Biobank and their causal links to health conditions within East Asians. A genome-wide association study (GWAS) was conducted, followed by observational studies, polygenic risk score assessments, and genetic correlation analyses to identify associated health conditions linked to BMD. GWAS and gene-based GWAS studies identified 78 significant SNPs and 75 genes related to BMD, highlighting pathways like Hedgehog, WNT-mediated, and TGF-ß. Our cross-trait linkage disequilibrium score regression analyses for BMD and osteoporosis consistently validated their genetic correlations with body mass index (BMI) and type 2 diabetes (T2D) in East Asians. Higher BMD was linked to lower osteoporosis risk but increased BMI and T2D, whereas osteoporosis linked to lower BMI, waist circumference, HbA1c, and reduced T2D risk. Bidirectional Mendelian randomization (MR) analyses revealed that a higher BMI causally increases BMD in East Asians. However, no direct causal relationships were found between BMD and T2D, or between osteoporosis and either BMI or T2D. This study identified key genetic factors for bone health in Taiwan, and revealed significant health conditions in East Asians, particularly highlighting the genetic interplay between bone health and metabolic traits like T2D and BMI.

We investigated how genetics affect bone health and related conditions like diabetes and obesity in 86,716 East Asians. Previously, most studies focused on Caucasian populations, but our work helps to understand these issues in East Asians. Our findings show that stronger bones are linked to a lower chance of osteoporosis but a higher risk of obesity and type 2 diabetes. On the other hand, those with osteoporosis tend to have lower body weight and a decreased risk of diabetes, illustrating a complex relationship between bone health and body metabolism. Future research will focus on deeper genetic interactions and developing targeted interventions for bone health and related metabolic disorders in East Asians.

Cryo-EM structures of the human Elongator complex at work.

tRNA modifications affect ribosomal elongation speed and co-translational folding dynamics. The Elongator complex is responsible for introducing 5-carboxymethyl at wobble uridine bases (cm5U34) in eukaryotic tRNAs. However, the structure and function of human Elongator remain poorly understood. In this study, we present a series of cryo-EM structures of human ELP123 in complex with tRNA and cofactors at four different stages of the reaction. The structures at resolutions of up to 2.9 Å together with complementary functional analyses reveal the molecular mechanism of the modification reaction. Our results show that tRNA binding exposes a universally conserved uridine at position 33 (U33), which triggers acetyl-CoA hydrolysis. We identify a series of conserved residues that are crucial for the radical-based acetylation of U34 and profile the molecular effects of patient-derived mutations. Together, we provide the high-resolution view of human Elongator and reveal its detailed mechanism of action.

Precision Colorectal Cancer Fecal Immunological Test Screening With Fecal-Hemoglobin-Concentration-Guided Interscreening Intervals.

Importance: Given a gradient relationship between fecal hemoglobin (f-Hb) concentration and colorectal neoplasia demonstrated previously, using f-Hb-guided interscreening interval has increasingly gained attention in population-based fecal immunological test (FIT), but it is very rare to address how to implement such a precision strategy and whether it can economize the use of FIT and colonoscopy. Objective: To demonstrate the applicability of personalized colorectal cancer (CRC) screening with f-Hb-guided screening intervals to reduce the number of FITs and colonoscopy with as equivalent efficacy as universal biennial screening equivalent efficacy as universal biennial screening. Design, Setting, and Participants: A retrospective cohort study for developing f-Hb-guided precision interscreening interval was conducted using data on a Taiwanese biennial nationwide FIT screening program that enrolled more than 3 million participants aged 50 to 74 years between 2004 and 2014. The cohort was followed up over time until 2019 to ascertain colorectal neoplasia and causes of death. A comparative study was further designed to compare the use of FIT and colonoscopy between the personalized f-Hb-guided group and the universal biennial screening group given the equivalent efficacy of reducing CRC-related outcomes. Main Outcomes and Measurements: A spectrum of f-Hb-guided intervals was determined by using the Poisson regression model given the equivalent efficacy of a universal biennial screening. The use of FIT and colonoscopy for the pragmatic f-Hb-guided interval group was measured compared with the universal biennial screening group. Data analysis was performed from September 2022 to October 2023. Results: Using data from the 3 500 250 participants (mean [SD] age, 57.8 [6.0] years) enrolled in the Taiwanese biennial nationwide FIT screening program, an incremental increase in baseline f-Hb associated with colorectal neoplasia and CRC mortality consistently was observed. Participants with different f-Hb levels were classified into distinct risk categories. Various screening intervals by different f-Hb levels were recommended. Using the proposed f-Hb-guided screening intervals, it was found that the personalized method was imputed to reduce the number of FIT tests and colonoscopies by 49% and 28%, respectively, compared with the universal biennial screening. Conclusion and Relevance: The gradient relationship between f-Hb and colorectal neoplasia and CRC mortality was used to develop personalized FIT screening with f-Hb-guided screening intervals. Such a precision interscreening interval led to the reduced use of FIT test and colonoscopy without compromising the effectiveness of universal biennial screening.

Creep-type all-solid-state cathode achieving long life.

Electrochemical-mechanical coupling poses enormous challenges to the interfacial and structural stability but create new opportunities to design innovative all-solid-state batteries from scratch. Relying on the solid-solid constraint in the space-limited domain structure, we propose to exploit the lithiation-induced stress to drive the active materials creep, thereby improving the structural integrity. For demonstration, we fabricate the creep-type all-solid-state cathode using creepable Se material and an all-in-one rigid ionic/electronic conducting Mo6Se8 framework. As indicated by the in-situ experiment and numerical simulation, this cathode presents unique capabilities in improving interparticle contact and avoiding particle fracture, leading to its superior electrochemical performance, including a superior long-cycle life of more than 3000 cycles at 0.5 C and a high volumetric energy density of 2460 Wh/L at the cathode level. We believe this innovative strategy to utilize mechanics to boost the electrochemical performance could shed light on the future design of all-solid-state batteries for practical applications.

Baroreflex Sensitivity as a Surrogate Biomarker for Concurrently Assessing the Severity of Arterial Stiffness and Cardiovascular Autonomic Neuropathy in Individuals with Type 2 Diabetes.

This study aimed to investigate whether baroreflex sensitivity (BRS) could serve as a reliable metric for assessing cardiovascular autonomic neuropathy (CAN) and concurrently act as a surrogate biomarker for evaluating the severity of arterial stiffness and CAN in individuals diagnosed with type 2 diabetes mellitus (T2DM). Participants underwent brachial-ankle pulse wave velocity (baPWV) as well as autonomic function evaluations encompassing the Sudoscan-based modified composite autonomic scoring scale (CASS), baroreflex sensitivity, and heart rate variability in time domains and frequency domains. Linear regression analysis was performed to evaluate the influence of independent variables on baPWV and modified CASS. Participants with higher baPWV values were older, with longer diabetes duration, lower body weight, body mass index, waist circumference, elevated systolic and diastolic blood pressure, and mean arterial blood pressure. They also exhibited a higher prevalence of retinopathy as the underlying disease and reduced estimated glomerular filtration rate. Multiple linear regression analysis revealed that age and BRS were significantly associated with baPWV while diabetes duration, UACR, and BRS were significantly associated with modified CASS. Our study confirms the significant association of BRS with baPWV and modified CASS in T2DM, highlighting its pivotal role in linking microvascular and macrovascular complications. This supports BRS as a surrogate marker for assessing both the severity of arterial stiffness and cardiovascular autonomic neuropathy in T2DM, enabling the early identification of complications.

An Edge Computing System with AMD Xilinx FPGA AI Customer Platform for Advanced Driver Assistance System.

The convergence of edge computing systems with Field-Programmable Gate Array (FPGA) technology has shown considerable promise in enhancing real-time applications across various domains. This paper presents an innovative edge computing system design specifically tailored for pavement defect detection within the Advanced Driver-Assistance Systems (ADASs) domain. The system seamlessly integrates the AMD Xilinx AI platform into a customized circuit configuration, capitalizing on its capabilities. Utilizing cameras as input sensors to capture road scenes, the system employs a Deep Learning Processing Unit (DPU) to execute the YOLOv3 model, enabling the identification of three distinct types of pavement defects with high accuracy and efficiency. Following defect detection, the system efficiently transmits detailed information about the type and location of detected defects via the Controller Area Network (CAN) interface. This integration of FPGA-based edge computing not only enhances the speed and accuracy of defect detection, but also facilitates real-time communication between the vehicle's onboard controller and external systems. Moreover, the successful integration of the proposed system transforms ADAS into a sophisticated edge computing device, empowering the vehicle's onboard controller to make informed decisions in real time. These decisions are aimed at enhancing the overall driving experience by improving safety and performance metrics. The synergy between edge computing and FPGA technology not only advances ADAS capabilities, but also paves the way for future innovations in automotive safety and assistance systems.

The effect of antiarrhythmic medications on the risk of cardiovascular outcomes in patients with atrial fibrillation and coronary artery disease.

BACKGROUND: While current guidelines recommend amiodarone and dronedarone for rhythm control in patients with atrial fibrillation (AF) and coronary artery disease (CAD), there was no comparative study of antiarrhythmic drugs (AADs) on the cardiovascular outcomes in general practice. METHODS: This study included patients with AF and CAD who received their first prescription of amiodarone, class Ic AADs (flecainide, propafenone), dronedarone or sotalol between January 2016 and December 2020. The primary outcome was a composite of hospitalization for heart failure (HHF), stroke, acute myocardial infarction (AMI), and cardiovascular death. We used Cox proportional regression models, including with inverse probability of treatment weighting (IPTW), to estimate the relationship between AADs and cardiovascular outcomes. RESULTS: Among the AF cohort consisting of 8752 patients, 1996 individuals had CAD, including 477 who took dronedarone and 1519 who took other AADs. After a median follow-up of 38 months, 46.3% of patients who took dronedarone and 54.4% of patients who took other AADs experienced cardiovascular events. Compared to dronedarone, the use of other AADs was associated with increased cardiovascular events after adjusting for covariates (hazard ratio [HR] 1.531, 95% confidence interval [CI] 1.112-2.141, p = 0.023) and IPTW (HR 1.491, 95% CI 1.174-1.992, p = 0.012). The secondary analysis showed that amiodarone and class Ic drugs were associated with an increased risk of HHF. The low number of subjects in the sotalol group limits data interpretation. CONCLUSION: For patients with AF and CAD, dronedarone was associated with better cardiovascular outcomes than other AADs. Amiodarone and class Ic AADs were associated with a higher risk of cardiovascular events, particularly HHF.

Taurine reduces the risk for metabolic syndrome: a systematic review and meta-analysis of randomized controlled trials.

BACKGROUND: Metabolic syndrome (MetS) is a cluster of interconnected risk factors that significantly increase the likelihood of cardiovascular disease and type 2 diabetes. Taurine has emerged as a potential therapeutic agent for MetS. This meta-analysis of randomized controlled trials (RCTs) aimed to evaluate the effects of taurine supplementation on MetS-related parameters. METHODS: We conducted electronic searches through databases like Embase, PubMed, Web of Science, Cochrane CENTRAL, and ClinicalTrials.gov, encompassing publications up to December 1, 2023. Our analysis focused on established MetS diagnostic criteria, including systolic blood pressure (SBP), diastolic blood pressure (DBP), fasting blood glucose (FBG), triglyceride (TG), and high-density lipoprotein cholesterol (HDL-C). Meta-regression explored potential dose-dependent relationships based on the total taurine dose administered during the treatment period. We also assessed secondary outcomes like body composition, lipid profile, and glycemic control. RESULTS: Our analysis included 1024 participants from 25 RCTs. The daily dosage of taurine in the studies ranged from 0.5 g/day to 6 g/day, with follow-up periods varying between 5 and 365 days. Compared to control groups, taurine supplementation demonstrated statistically significant reductions in SBP (weighted mean difference [WMD] = -3.999 mmHg, 95% confidence interval [CI] = -7.293 to -0.706, p = 0.017), DBP (WMD = -1.509 mmHg, 95% CI = -2.479 to -0.539, p = 0.002), FBG (WMD: -5.882 mg/dL, 95% CI: -10.747 to -1.018, p = 0.018), TG (WMD: -18.315 mg/dL, 95% CI: -25.628 to -11.002, p < 0.001), but not in HDL-C (WMD: 0.644 mg/dl, 95% CI: -0.244 to 1.532, p = 0.155). Meta-regression analysis revealed a dose-dependent reduction in DBP (coefficient = -0.0108 mmHg per g, p = 0.0297) and FBG (coefficient = -0.0445 mg/dL per g, p = 0.0273). No significant adverse effects were observed compared to the control group. CONCLUSION: Taurine supplementation exhibits positive effects on multiple MetS-related factors, making it a potential dietary addition for individuals at risk of or already experiencing MetS. Future research may explore dose-optimization strategies and potential long-term benefits of taurine for MetS management.

The incidence and risk factors of proximal lower extremity deep vein thrombosis without pharmacologic prophylaxis in critically ill surgical Taiwanese patients: A prospective study.

Background: Venous thromboembolism (VTE) in critically ill patients has been well-studied in Western countries. Many studies have developed risk assessments and established pharmacological protocols to prevent deep venous thrombosis (DVT). However, the DVT rate and need for pharmacologic VTE prophylaxis in critically ill Taiwanese patients are limited. This study aimed to prospectively determine the DVT incidence, risk factors, and outcomes in critically ill Taiwanese patients who do not receive pharmacologic VTE prophylaxis. Methods: We conducted a prospective study in a surgical intensive care unit (SICU) of a tertiary academic medical center in Taiwan. Adult patients admitted to SICU from March 2021 to June 2022 received proximal lower extremities DVT surveillance with venous duplex ultrasound. No patient received pharmacologic VTE prophylaxis. The outcomes were the incidence and risk factors of DVT. Results: Among 501 enrolled SICU patients, 21 patients (4.2%) were diagnosed with proximal lower extremities DVT. In a multivariate regression analysis, hypoalbuminemia (odd ratio (OR) = 6.061, 95% confidence interval (CI): 1.067-34.421), femoral central venous catheter (OR = 4.515, 95% CI: 1.547-13.174), ICU stays more than 10 days (OR = 4.017, 95% CI: 1.270-12.707), and swollen leg (OR = 3.427, 95% CI: 1.075-10.930) were independent risk factors for DVT. In addition, patients with proximal lower extremities DVT have more extended ventilator days (p = 0.045) and ICU stays (p = 0.044). Conclusion: Our findings indicate critically ill Taiwanese patients have a higher incidence of DVT than results from prior retrospective studies in the Asian population. Physicians who care for this population should consider the specific risk factors for DVT and prescribe pharmacologic prophylaxis in high-risk groups.

Longitudinal artificial intelligence-based deep learning models for diagnosis and prediction of the future occurrence of polyneuropathy in diabetes and prediabetes.

OBJECTIVE: The objective of this study was to develop artificial intelligence-based deep learning models and assess their potential utility and accuracy in diagnosing and predicting the future occurrence of diabetic distal sensorimotor polyneuropathy (DSPN) among individuals with type 2 diabetes mellitus (T2DM) and prediabetes. METHODS: In 394 patients (T2DM=300, Prediabetes=94), we developed a DSPN diagnostic and predictive model using Random Forest (RF)-based variable selection techniques, specifically incorporating the combined capabilities of the Clinical Toronto Neuropathy Score (TCNS) and nerve conduction study (NCS) to identify relevant variables. These important variables were then integrated into a deep learning framework comprising Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. To evaluate temporal predictive efficacy, patients were assessed at enrollment and one-year follow-up. RESULTS: RF-based variable selection identified key factors for diagnosing DSPN. Numbness scores, sensory test results (vibration), reflexes (knee, ankle), sural nerve attributes (sensory nerve action potential [SNAP] amplitude, nerve conduction velocity [NCV], latency), and peroneal/tibial motor NCV were candidate variables at baseline and over one year. Tibial compound motor action potential amplitudes were used for initial diagnosis, and ulnar SNAP amplitude for subsequent diagnoses. CNNs and LSTMs achieved impressive AUC values of 0.98 for DSPN diagnosis prediction, and 0.93 and 0.89 respectively for predicting the future occurrence of DSPN. RF techniques combined with two deep learning algorithms exhibited outstanding performance in diagnosing and predicting the future occurrence of DSPN. These algorithms have the potential to serve as surrogate measures, aiding clinicians in accurate diagnosis and future prediction of DSPN.