Rupsa Rani Mishra, D. Chandrasekhar Rao, Ajaya Kumar Tripathy
Manual observation and monitoring of individual cows for disease detection present significant challenges in large-scale farming operations, as the process is labor-intensive, time-consuming, and prone to reduced accuracy. The reliance on human observation often leads to delays in identifying symptoms, as the sheer number of animals can hinder timely attention to each cow. Consequently, the accuracy and precision of disease detection are significantly compromised, potentially affecting animal health and overall farm productivity. Furthermore, organizing and managing human resources for the manual observation and monitoring of cow health is a complex and economically demanding task. It necessitates the involvement of skilled personnel, thereby contributing to elevated farm maintenance costs and operational inefficiencies. Therefore, the development of an automated, low-cost, and reliable smart system is essential to address these challenges effectively. Although several studies have been conducted in this domain, very few have simultaneously considered the detection of multiple common diseases with high prediction accuracy. However, advancements in Internet of Things (IoT), Machine Learning (ML), and Cyber-Physical Systems have enabled the automation of cow health monitoring with enhanced accuracy and reduced operational costs. This study proposes an IoT-enabled Cyber-Physical System framework designed to monitor the daily activities and health status of cow. A novel ML algorithm is proposed for the diagnosis of common cow diseases using collected physiological and behavioral data. The algorithm is designed to predict multiple diseases by analyzing a comprehensive set of recorded physiological and behavioral features, enabling accurate and efficient health assessment.
ABSTRACT Compared to skin wounds, oral mucosal wounds heal quicker with less inflammation, faster re‐epithelialization, and minimal scarring. Site‐specific keratinocytes may be one differentiating factor. This study used immortalized skin and oral keratinocytes (HaCaT and TIGK), which maintain fidelity to their primary cell counterpart, to examine functional and transcriptional differences that might contribute to the differential wound healing at the two sites. Oral keratinocytes were found to have an enhanced migratory and proliferative capacity. To examine the transcriptomic differences, we generated an mRNA‐sequencing gene expression dataset utilizing HaCaT and TIGK. Differentially expressed genes (DEGs) were identified between HaCaT and TIGK at baseline and throughout in vitro healing. DEGs in HaCaT and TIGK following injury were also identified when compared to each respective cell type's unwounded gene expression levels. Gene set enrichment analyses were performed to understand the biological significance of the DEGs. Processes related to interferon (IFN) signaling were uniquely enriched in TIGK. TIGK also exhibited a faster transcriptional response to injury and differential expression of integrins and matrix metalloproteinases (MMPs). When grown on extracellular matrix (ECM) proteins, TIGK retained its enhanced migratory capacity over HaCaT. Lastly, TIGK displayed a post‐injury secretome that promoted keratinocyte migration. Our comparative analyses suggest that specific transcriptomic differences between oral and skin keratinocytes at unwounded baseline and in response to injury may underlie the distinct wound healing phenotypes observed in these two tissues. This work also provides a new resource of HaCaT and TIGK gene expression data that can be used for future analyses.
Introduction: Denosumab (Xgeva®) is a standard treatment for the prevention of skeletal-related events (SREs) in patients with bone metastases (BM). This trial was designed to assess the equivalence of LY01011 to denosumab in terms of efficacy and safety. Materials and methods: Eligible patients with BM from solid tumors were randomized at a 1:1 ratio to receive 120 mg of LY01011 or 120 mg of denosumab subcutaneously every four weeks during a 12-week double-blind treatment period, and then all enrolled patients continued to receive LY01011 until week 53. The primary endpoint was the natural logarithm of change of the urinary N-terminal crosslinked telopeptide of type I collagen level normalized to the urine creatinine level (uNTX/uCr) at week 13 from baseline. Other endpoints included the uNTX/uCr ratio, serum bone-specific alkaline phosphatase level alteration, status of anti-drug antibodies and neutralizing antibodies, adverse events and SREs. Results: 850 eligible patients were randomized into the LY01011 group (n = 424) or the denosumab group (n = 426). The least-squares means (SEs) of the natural logarithms of the changes in the uNTX/uCr ratios at week 13 from baseline were −1.810 (0.0404) in the LY01011 group and −1.791 (0.0406) in the denosumab group. The LSM difference [90 % CI] between two arms was −0.019 [-0.110, 0.073] within the equivalence margins (−0.135, 0.135) and met the predetermined primary endpoint. The AEs, ADAs and the PK data showed no statistically significant difference. Conclusions: This study demonstrated the equivalent efficacy and safety of LY01011 to denosumab in patients with BM.
Diseases of the musculoskeletal system, Neoplasms. Tumors. Oncology. Including cancer and carcinogens
Arturo Cano-Uceda, Luis De Sousa-De Sousa, Rebeca Bueno-Fermoso
et al.
<b>Background:</b> Cancer treatments often reduce quality of life (QoL), and non-pharmacological options are limited. Supervised exercise shows promise, but its effectiveness across exercise types and patient subgroups is unclear. <b>Objective:</b> This study aimed to assess the impact of supervised exercise on QoL in breast and prostate cancer patients, considering exercise type, duration, and patient characteristics. <b>Methods:</b> A systematic review and meta-analysis including 26 randomized controlled trials (RCTs) and approximately 3500 participants was conducted according to PRISMA guidelines. PubMed, Web of Science, PEDro, SciELO, Cochrane, and Scopus were searched for randomized controlled trials (RCTs) published between 2014 and 2024. Eligible studies involved adults with breast or prostate cancer undergoing supervised exercise versus usual care or unsupervised activity. Risk of bias was assessed with the Cochrane RoB 2.0 tool, methodological quality with the PEDro scale, and certainty of evidence using the GRADE approach. <b>Results:</b> Supervised exercise was associated with significant improvements in QoL (SMD = 0.46; 95% CI: 0.22–0.70; <i>p</i> < 0.001), with considerable heterogeneity (I<sup>2</sup> = 91.5%). Combined programs had the greatest effect (SMD = 0.77), followed by high-intensity interval training (HIIT) (SMD = 0.30). Shorter interventions (≤12 weeks) yielded larger improvements. Effects were more consistent in women with breast cancer. Overall, the certainty of the evidence was low. <b>Conclusions:</b> Supervised therapeutic exercise is associated with significant improvements in QoL in breast and prostate cancer patients. Combined and well-structured programs, particularly of short duration, appear especially beneficial. These findings support the integration of supervised exercise into standard oncological care. Further research should explore long-term sustainability and optimize interventions for specific patient profiles.
Mark A. Plantz, Rachel Bergman, Erik Gerlach
et al.
Abstract Background Transmetatarsal amputation (TMA) is a commonly performed procedure for gangrene in the setting of diabetes or peripheral vascular disease. The purpose of this study is to investigate the incidence of and risk factors for reoperation and perioperative complications after TMA in patients undergoing surgery for primarily infectious/diabetic wounds versus peripheral vascular disease. Methods Patients undergoing TMA between January 1, 2015 and December 31, 2020 were identified using the American College of Surgeons National Surgical Quality Improvement Program database. The indication for surgery was reported using the International Classification of Disease 9/10 codes. Patients were categorized into two groups: patients undergoing surgery for primarily infectious/diabetic wounds versus peripheral vascular disease. The incidence of 30‐day mortality, readmission, reoperation, nonhome discharge, and various medical and surgical complications was reported. Outcome measures were compared between the diabetic and peripheral vascular disease groups. Logistic regression was used to identify independent risk factors for each outcome measure of interest. Results 3392 patients were included in the final cohort. There was a 30‐day mortality rate of 2.9%, reoperation rate of 13.8%, readmission rate of 16.8%, surgical complication rate of 22.2%, and medical complication rate of 15.8%. Patients undergoing surgery for a vascular indication had a higher rate of mortality, reoperation, hospital readmission, nonhome discharge, and various medical complications (p < 0.05). Patients undergoing surgery for infectious/diabetic wounds had a higher rate of deep surgical site infection and systemic sepsis (p < 0.05). A vascular surgical indication was independently associated with reoperation and overall medical complications (p < 0.05). Various factors, including age, body mass index, medical comorbidities, and the presence of preoperative sepsis were associated with poor outcomes. Conclusion Significant rates of mortality, reoperation, and hospital readmission were reported after TMA. The presence of peripheral vascular disease was independently associated with reoperation and medical complications. Patients undergoing TMA, particularly for peripheral vascular disease, should be counseled about perioperative risks and indicated for surgery carefully.
We propose an epidemic model for the spread of vector-borne diseases. The model, which is built extending the classical susceptible-infected-susceptible model, accounts for two populations -- humans and vectors -- and for cross-contagion between the two species, whereby humans become infected upon interaction with carrier vectors, and vectors become carriers after interaction with infected humans. We formulate the model as a system of ordinary differential equations and leverage monotone systems theory to rigorously characterize the epidemic dynamics. Specifically, we characterize the global asymptotic behavior of the disease, determining conditions for quick eradication of the disease (i.e., for which all trajectories converge to a disease-free equilibrium), or convergence to a (unique) endemic equilibrium. Then, we incorporate two control actions: namely, vector control and incentives to adopt protection measures. Using the derived mathematical tools, we assess the impact of these two control actions and determine the optimal control policy.
Disease progression modeling aims to characterize and predict how a patient's disease complications worsen over time based on longitudinal electronic health records (EHRs). For diseases such as type 2 diabetes, accurate progression modeling can enhance patient sub-phenotyping and inform effective and timely interventions. However, the problem is challenging due to the need to learn continuous-time progression dynamics from irregularly sampled clinical events amid patient heterogeneity (e.g., different progression rates and pathways). Existing mechanistic and data-driven methods either lack adaptability to learn from real-world data or fail to capture complex continuous-time dynamics on progression trajectories. To address these limitations, we propose Temporally Detailed Hypergraph Neural Ordinary Differential Equation (TD-HNODE), which represents disease progression on clinically recognized trajectories as a temporally detailed hypergraph and learns the continuous-time progression dynamics via a neural ODE framework. TD-HNODE contains a learnable TD-Hypergraph Laplacian that captures the interdependency of disease complication markers within both intra- and inter-progression trajectories. Experiments on two real-world clinical datasets demonstrate that TD-HNODE outperforms multiple baselines in modeling the progression of type 2 diabetes and related cardiovascular diseases.
Ocular disease affects billions of individuals unevenly worldwide. It continues to increase in prevalence with trends of growing populations of diabetic people, increasing life expectancies, decreasing ophthalmologist availability, and rising costs of care. We present EyeAI, a system designed to provide artificial intelligence-assisted detection of ocular diseases, thereby enhancing global health. EyeAI utilizes a convolutional neural network model trained on 1,920 retinal fundus images to automatically diagnose the presence of ocular disease based on a retinal fundus image input through a publicly accessible web-based application. EyeAI performs a binary classification to determine the presence of any of 45 distinct ocular diseases, including diabetic retinopathy, media haze, and optic disc cupping, with an accuracy of 80%, an AUROC of 0.698, and an F1-score of 0.8876. EyeAI addresses barriers to traditional ophthalmologic care by facilitating low-cost, remote, and real-time diagnoses, particularly for equitable access to care in underserved areas and for supporting physicians through a secondary diagnostic opinion. Results demonstrate the potential of EyeAI as a scalable, efficient, and accessible diagnostic tool. Future work will focus on expanding the training dataset to enhance the accuracy of the model further and improve its diagnostic capabilities.
Jason Tang, Dana Weisenfeld, Linshanshan Wang
et al.
Objective Rheumatoid arthritis (RA) is a heterogeneous disease, with patients experiencing varied disease courses and responses to treatment. The objective of this study was to apply topic modeling to RA patient electronic health record (EHR) data and determine (1) the clinical topics/subgroups in those with RA before initiation of a biologic/targeted synthetic disease‐modifying antirheumatic drug (b/tsDMARD) and (2) whether the clinical topics were associated with subsequent RA treatment course. Methods We studied patients from a validated EHR‐based RA cohort who initiated a b/tsDMARD between 2011 and 2019. Diagnoses codes, laboratory data, and medication prescriptions in the year before their first b/tsDMARD initiation were extracted. Latent Dirichlet allocation, a topic modeling method, was applied to define the underlying “topics” representing clinical subgroups. We used multinomial regression to test association between the clinical topic with four previously published treatment trajectories: tumor necrosis factor inhibitor (TNFi) persisters, TNFi to abatacept, and those prescribed multiple b/tsDMARDs enriched with tocilizumab or rituximab. Results From the data of 1,102 patients with RA, diagnoses codes, laboratory data, and prescriptions from the year before b/tsDMARD initiation resulted in four main clinical topics/subgroups: (A) RA codes/methotrexate (MTX), (B) arthralgia/osteoarthritis, (C) hypertension (HTN)/cardiovascular (CV) comorbidities, and (D) mood disorders. Those with RA codes/MTX topic were more likely to persist on TNFi. Conversely, those associated with the HTN/CV topic were more likely to cycle through multiple b/tsDMARDs. Conclusion Clinical topics derived from the EHR data of patients with RA before b/tsDMARD differentiated future RA treatment course. HTN/CV comorbidities were associated with a future need for multiple b/tsDMARD therapies.
ABSTRACT Purpose To propose a signal acquisition and modeling framework for multi‐component tissue quantification that encompasses transmit field inhomogeneity, multi‐component relaxation and magnetization transfer (MT) effects. Theory and Methods By applying off‐resonance irradiation between excitation and acquisition within an RF‐spoiled gradient‐echo scheme, in combination with multiple echo‐time acquisitions, both Bloch‐Siegert shift and magnetization transfer effects are simultaneously induced while relaxation and spin exchange processes occur concurrently. The spin dynamics are modeled using a three‐pool framework, from which an analytical signal equation is derived and validated through numerical Bloch simulations. Monte Carlo simulations were further performed to analyze and compare the model's performance. Finally, the feasibility of this novel approach was investigated in vivo in human brain and knee tissues. Results Simulation results showed excellent agreement with the derived analytical signal equation across a wide range of flip angles and echo times. Monte Carlo analyses further validated that the three‐pool parameter estimation pipeline performed robustly over various signal‐to‐noise ratio conditions. Multi‐parameter fitting results from in vivo brain and knee studies yielded values consistent with previously reported literature. Collectively, these findings confirm that the proposed method can reliably characterize multi‐component tissue parameters in macromolecule‐rich environments while effectively compensating for inhomogeneity. Conclusion A signal acquisition and modeling framework for multi‐component tissue quantification that accounts for magnetization transfer effects and inhomogeneity has been developed and validated. Both simulation and experimental results confirmed the robustness of this method and its applicability to various tissue types in the brain and knee.
Simone Radavelli‐Bagatini, Helen Macpherson, David Scott
et al.
Abstract Background Impaired muscle function has been identified as a risk factor for declining cognitive function and cardiovascular health, both of which are risk factors for late‐life dementia (after 80 years of age). We examined whether hand grip strength and timed‐up‐and‐go (TUG) performance, including their change over 5 years, were associated with late‐life dementia events in older women and whether any associations provided independent information to Apolipoprotein E ℇ4 (APOE ℇ4) genotype. Methods Grip strength and TUG were assessed in community‐dwelling older women (mean ± SD; age 75.0 ± 2.6 years) at baseline (n = 1225) and 5 years (n = 1052). Incident 14.5‐year late‐life dementia events (dementia‐related hospitalization/death) were obtained from linked health records. Cardiovascular risk factors (Framingham Risk Score), APOE genotyping, prevalent atherosclerotic vascular disease and cardiovascular‐related medications were evaluated at baseline. These were included in multivariable‐adjusted Cox‐proportional hazards models assessing the relationship between muscle function measures and late‐life‐dementia events. Results Over follow‐up, 207 (16.9%) women had a late‐life dementia event. Compared with women with the highest grip strength (Quartile [Q] 4, 25.8 kg), those with the lowest grip strength (Q1, 16.0 kg) had greater hazard for a late‐life dementia event (HR 2.27 95% CI 1.54–3.35, P < 0.001). For TUG, the slowest women (Q4, 12.4 vs. Q1, 7.4 s) also recorded a greater hazard for a late‐life dementia event (HR 2.10 95% CI 1.42–3.10, P = 002). Weak hand grip (<22 kg) or slow TUG (>10.2 s) provided independent information to the presence of an APOE ℇ4 allele (n = 280, 22.9%). Compared with women with no weakness and no APOE ℇ4 allele, those with weakness and APOE ℇ4 allele had a greater hazard (HR 3.19 95% CI 2.09–4.88, P < 0.001) for a late‐life dementia event. Women presenting with slowness and the APOE ℇ4 allele also recorded a greater hazard for a late‐life dementia event (HR 2.59 95% CI 1.64–4.09, P < 0.001). For 5‐year muscle function changes, compared with women with the lowest performance decrement (Q1), those with the largest decrement (Q4) had higher hazards for a late‐life dementia event (grip strength HR 1.94 95% CI 1.22–3.08, P = 0.006; TUG HR 2.52 95% CI 1.59–3.98, P < 0.001) over the next 9.5 years. Conclusions Weaker grip strength and slower TUG, and a greater decline over 5 years, were significant risk factors for a late‐life‐dementia event in community‐dwelling older women, independent of lifestyle and genetic risk factors. Incorporating muscle function measures as part of dementia screening appears useful to identify high‐risk individuals who might benefit from primary prevention programmes.
Diseases of the musculoskeletal system, Human anatomy
As road accident cases are increasing due to the inattention of the driver, automated driver monitoring systems (DMS) have gained an increase in acceptance. In this report, we present a real-time DMS system that runs on a hardware-accelerator-based edge device. The system consists of an InfraRed camera to record the driver footage and an edge device to process the data. To successfully port the deep learning models to run on the edge device taking full advantage of the hardware accelerators, model surgery was performed. The final DMS system achieves 63 frames per second (FPS) on the TI-TDA4VM edge device.
This paper describes the NPU-MSXF system for the IWSLT 2023 speech-to-speech translation (S2ST) task which aims to translate from English speech of multi-source to Chinese speech. The system is built in a cascaded manner consisting of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS). We make tremendous efforts to handle the challenging multi-source input. Specifically, to improve the robustness to multi-source speech input, we adopt various data augmentation strategies and a ROVER-based score fusion on multiple ASR model outputs. To better handle the noisy ASR transcripts, we introduce a three-stage fine-tuning strategy to improve translation accuracy. Finally, we build a TTS model with high naturalness and sound quality, which leverages a two-stage framework, using network bottleneck features as a robust intermediate representation for speaker timbre and linguistic content disentanglement. Based on the two-stage framework, pre-trained speaker embedding is leveraged as a condition to transfer the speaker timbre in the source English speech to the translated Chinese speech. Experimental results show that our system has high translation accuracy, speech naturalness, sound quality, and speaker similarity. Moreover, it shows good robustness to multi-source data.
We numerically study disease dynamics that lead to the disease switching from one host species to another, resulting in diseases gaining the ability to infect, e.g., humans. Unlike previous studies that focused on branching processes starting with the first infected humans, we begin by considering a disease pathogen that initially cannot infect humans. We model the entire process, starting from an infection in the animal population, including mutations that eventually enable the disease to cause an epidemic outbreak in the human population. We use an SIR model on a network consisting of 132 dog and 1320 human nodes, with a single parameter representing the gene of the pathogen. We use numerical large-deviation techniques, specifically the $1/t$ Wang-Landau algorithm, to calculate the potentially very small probability of the host switching event. With this approach we are able to resolve probabilities as small as $10^{-120}$. Additionally the $1/t$ Wang-Landau algorithm allows us to obtain the complete probability density function $P(C)$ of the cumulative fraction $C$ of infected humans, which is an indicator for the severity of the disease in the human population. We also calculate correlations of $C$ with selected quantities $q$ that characterize the outbreak. Due to the application of the rare-event algorithm, this is possible for the entire range of $C$ values.
Andrew R. Findlay, Sarah E. Robinson, Stephanie Poelker
et al.
ABSTRACTObjectiveTo delineate the full phenotypic spectrum and characterize the natural history of limb girdle muscular dystrophy type D1 (LGMDD1).MethodsWe extracted age at clinical events of interest contributing to LGMDD1 disease burden via a systematic literature and chart review. Manual muscle testing and quantitative dynamometry data were used to estimate annualized rates of change. We also conducted a cross‐sectional observational study using previously validated patient‐reported outcome assessments (ACTIVLIM, PROMIS‐57) and a new LGMDD1 questionnaire. Some individuals underwent repeat ACTIVLIM and LGMDD1 questionnaire assessments at 1.5 and 2.5 years.ResultsA total of 122 LGMDD1 patients were included from 14 different countries. We identified two new variants (p.E54K, p.V99A). In vitro assays and segregation support their pathogenicity. The mean onset age was 29.7 years. Genotype appears to impact onset age, weakness pattern, and median time to loss of ambulation (34 years). Dysphagia was the most frequent abnormality (51.4%). Deltoids, biceps, grip, iliopsoas, and hamstrings strength decreased by (0.5‐1 lb/year). Cross‐sectional ACTIVLIM and LGMDD1 questionnaire scores correlated with years from disease onset. Longitudinally, only the LGMDD1 questionnaire detected significant progression at both 1.5 and 2.5 years. Treatment trials would require 62 (1.5 years) or 30 (2.5 years) patients to detect a 70% reduction in the progression of the LGMDD1 questionnaire.InterpretationThis study is the largest description of LGMDD1 patients to date and highlights potential genotype‐dependent differences that need to be verified prospectively. Future clinical trials will need to account for variability in these key phenotypic features when selecting outcome measures and enrolling patients.
Christine Anastasiou, Laura Trupin, David V. Glidden
et al.
ObjectiveTo evaluate time trends in mortality for hospitalized adults with systemic lupus erythematosus (SLE) compared to the general hospitalized population (GHP), and to identify factors associated with increased risk of death among hospitalized SLE patients.MethodsWe used the National (Nationwide) Inpatient Sample to estimate all‐cause mortality for adults discharged from community hospitals in the US between 2006 and 2016. Poisson regression models were used to estimate the risk of in‐hospital death among all patients, including demographic characteristics, socioeconomic factors, comorbidity score, hospital region, SLE diagnosis, and race/ethnicity as covariates.ResultsAmong 340,467,049 hospitalizations analyzed, 1,903,279 had a discharge diagnosis of SLE. In adjusted analysis, the risk of inpatient death decreased among hospitalizations for patients with SLE from 2.2% to 1.5% (P < 0.001) between 2006 and 2016. All of the decrease in SLE mortality occurred between 2006 and 2008; after 2008, mortality stabilized at a rate statistically similar to the GHP. Hospitalizations for Black, Hispanic, and Asian/Pacific Islander patients with SLE were more likely to end in death compared to hospitalizations for either White patients with SLE or individuals of the same non‐White race/ethnicity without SLE.ConclusionIn the largest study of in‐hospital SLE mortality published to date, we found significant improvements in mortality for hospitalized patients with SLE in the US from 2006 until 2008, after which mortality stabilized at a level similar to that of the GHP. Our results also demonstrate a persistently high mortality burden among Black and Hispanic patients with SLE in the US and contribute new data revealing high mortality among Asian/Pacific Islander patients with SLE.