Separate Tests Research Articles

Simulating federated learning for steatosis detection using ultrasound images

We aimed to implement four data partitioning strategies evaluated with four federated learning (FL) algorithms and investigate the impact of data distribution on FL model performance in detecting steatosis using B-mode US images. A private dataset (153 patients; 1530 images) and a public dataset (55 patient; 550 images) were included in this retrospective study. The datasets contained patients with metabolic dysfunction-associated fatty liver disease (MAFLD) with biopsy-proven steatosis grades and control individuals without steatosis. We employed four data partitioning strategies to simulate FL scenarios and we assessed four FL algorithms. We investigated the impact of class imbalance and the mismatch between the global and local data distributions on the learning outcome. Classification performance was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. AUCs were 0.93 (95% CI 0.92, 0.94) for source-based partitioning scenario with FedAvg, 0.90 (95% CI 0.89, 0.91) for a centralized model, and 0.83 (95% CI 0.81, 0.85) for a model trained in a single-center scenario. When data was perfectly balanced on the global level and each site had an identical data distribution, the model yielded an AUC of 0.90 (95% CI 0.88, 0.92). When each site contained data exclusively from one single class, irrespective of the global data distribution, the AUC fell in the range of 0.34–0.70. FL applied to B-mode US images provide performance comparable to a centralized model and higher than single-center scenario. Global data imbalance and local data heterogeneity influenced the learning outcome.

Predicting cardiovascular disease risk using photoplethysmography and deep learning.

Cardiovascular diseases (CVDs) are responsible for a large proportion of premature deaths in low- and middle-income countries. Early CVD detection and intervention is critical in these populations, yet many existing CVD risk scores require a physical examination or lab measurements, which can be challenging in such health systems due to limited accessibility. We investigated the potential to use photoplethysmography (PPG), a sensing technology available on most smartphones that can potentially enable large-scale screening at low cost, for CVD risk prediction. We developed a deep learning PPG-based CVD risk score (DLS) to predict the probability of having major adverse cardiovascular events (MACE: non-fatal myocardial infarction, stroke, and cardiovascular death) within ten years, given only age, sex, smoking status and PPG as predictors. We compare the DLS with the office-based refit-WHO score, which adopts the shared predictors from WHO and Globorisk scores (age, sex, smoking status, height, weight and systolic blood pressure) but refitted on the UK Biobank (UKB) cohort. All models were trained on a development dataset (141,509 participants) and evaluated on a geographically separate test (54,856 participants) dataset, both from UKB. DLS's C-statistic (71.1%, 95% CI 69.9-72.4) is non-inferior to office-based refit-WHO score (70.9%, 95% CI 69.7-72.2; non-inferiority margin of 2.5%, p<0.01) in the test dataset. The calibration of the DLS is satisfactory, with a 1.8% mean absolute calibration error. Adding DLS features to the office-based score increases the C-statistic by 1.0% (95% CI 0.6-1.4). DLS predicts ten-year MACE risk comparable with the office-based refit-WHO score. Interpretability analyses suggest that the DLS-extracted features are related to PPG waveform morphology and are independent of heart rate. Our study provides a proof-of-concept and suggests the potential of a PPG-based approach strategies for community-based primary prevention in resource-limited regions.

A New Sufficient & Necessary Condition for Testing Linear Separability Between Two Sets.

As a fundamental mathematical problem in the field of machine learning, the linear separability test still lacks a theoretically complete and computationally efficient method. This paper proposes and proves a sufficient and necessary condition for linear separability test based on a sphere model. The advantage of this test method is two-fold: (1) it provides not only a qualitative test of linear separability but also a quantitative analysis of the separability of linear separable instances; (2) it has low time cost and is more efficient than existing test methods. The proposed method is validated through a large number of experiments on benchmark datasets and artificial datasets, demonstrating both its correctness and efficiency.

Empirically testing a relationship between cooperation and the prime numbers.

Theoretical models suggest a relationship between cooperation and the prime numbers. In environments where agents play multiple one-shot prisoner's dilemma games per generation, cooperators evolve to fixation more frequently when cooperating on a cyclical schedule with a prime-number period length. This finding parrots classic predator-prey models showing selection for prime-number prey life cycles. Here, I report an empirical test of the former models using previously published data concerning humans playing one-shot public goods games across multiple time points-i.e. an analogue to multiple one-shot prisoner's dilemma games. I find very modest evidence of cyclicality at prime-numbered time intervals, though results indicate rough agreement between theoretical predictions and observed rates of full cooperation across time points. Analyses of individual decisions find increased contributions to the public good at prime-number time points and separate placebo tests indicate a 4-in-1000 chance of spuriously estimating this effect. However, when exploratory analyses exclude low-value prime-numbered time points, the magnitude of the estimated effect decreases and the hypothesis of no effect cannot be rejected, implying that low-value, prime-number time points drive estimates, contrary to theoretical model predictions. These findings cast doubt on the hypothesis of increased cooperation at prime-number time points-at least among humans playing public goods games.

A randomized, double-blind, study to evaluate the efficacy, pharmacodynamics, safety and immunogenicity of FKS518 proposed biosimilar to denosumab with the originator in postmenopausal women with osteoporosis (LUMIADE-3 study).

3155 Background: Biosimilars can increase patient access to treatment. FKS518 is a candidate biosimilar of denosumab, a RANKL inhibitor used in patients with bone metastases from certain solid tumors and in multiple myeloma. To establish biosimilarity, comparative studies are conducted in the most sensitive patient population to detect if there are clinically meaningful differences. LUMIADE-3 was designed to assess the safety and efficacy of FKS518 compared to the originator in postmenopausal women with osteoporosis (PMO). Methods: A randomized, double-blind, multicenter, 2-arm study recruited female patients aged 55 to 85 years with confirmed postmenopausal status and lumbar spine bone mineral density (LS-BMD) T-score ≤ -2.5 and ≥ -4.0, as measured by central dual-energy X-ray absorptiometry (DXA) assessment. Subjects with prior osteoporosis treatment that could add risk for cumulative effect or affect the interpretation of results were excluded. Patients were randomized and received three 60 mg administrations. At week 52, patients receiving denosumab originator were re-randomized to continue their treatment or switch to FKS518 for the third dose. Those receiving FKS518 continued receiving FKS518. The primary efficacy endpoint was the percent change from baseline in LS-BMD DXA at week 52. An analysis of the covariance model was used to compare the two treatments and two separate one-sided tests at alpha=0.05 were performed to assess equivalence. Secondary efficacy endpoints included the percent change from baseline in BMD at the femoral neck and total hip. Results: A total of 553 patients were randomized to FKS518 (n= 276) or the originator (n=277). Clinically relevant increases in LS-BMD were evident at week 52 in both the FKS518 and originator product groups. The results demonstrated therapeutic equivalence: the lower bound of the 90% CI for non-inferiority (-0.05) was above -1.45, and the upper bound of the 90% CI for non-superiority (1.20) was below 1.45. All secondary objectives were met. At week 52, a similar percent change from baseline in BMD at the femoral neck and total hip was observed between the two groups. 374 patients (67.6%) experienced treatment-emergent adverse events: 185 (66.8%) in the FKS518 group and 189 (68.5%) in the originator product group. Safety evaluation did not point to notable differences between FKS518 and the originator product groups. Conclusions: We demonstrated the therapeutic equivalence of FKS518 and originator product. The safety data showed similar safety profiles for the FKS518 and the originator product groups. Results from this study add to the totality of evidence supporting the similarity of FKS518 as a proposed biosimilar to denosumab originator product, a RANKL inhibitor used in patients with bone metastases from solid tumors. Clinical trial information: NCT04934072 .

Psilocybin and 2C-B at Encoding Distort Episodic Familiarity

BackgroundAs research on psychedelics (hallucinogenic serotonin receptor 2A agonists) progresses, it is important to delineate the reliability of supposedly unique effects across this drug class. One such effect is how psychedelics impair the formation (i.e., encoding) of hippocampal-dependent recollections (retrieval of specific details) while potentially enhancing the encoding of cortical-dependent familiarity (a feeling of knowing that a stimulus has been previously experienced). MethodsIn a double-blind, placebo-controlled, within-participants study (N = 20), we tested the acute effects of 2 distinct psychedelics, psilocybin and 2C-B, on the encoding of emotional episodic memories. During acute drug effects, participants viewed negative, neutral, and positive pictures. The following day (while sober), participants completed 2 separate memory tests for these pictures. ResultsUsing computational models of memory confidence, we found trends for psilocybin and 2C-B at encoding to impair estimates of recollection that were supported by other measures/analyses. Surprisingly, psilocybin and 2C-B at encoding impaired estimates of familiarity, but these impairments were likely due to a misattribution of heightened familiarity, because both drugs at encoding selectively increased familiarity-based false alarms, especially for negative and positive stimuli. Psilocybin and 2C-B at encoding also tended to impair estimates of metamemory (understanding one’s own memory) for negative and neutral memories but enhanced estimates of metamemory for positive memories, although these effects were less reliable in additional analyses. ConclusionsDespite differences in their chemistry, pharmacology, and subjective effects, both psilocybin and 2C-B distorted episodic familiarity, suggesting a common neurocognitive mechanism across psychedelics that may drive other phenomena.

Advancements in Agricultural Technology: Vision Transformer-Based Potato Leaf Disease Classification

Potato (Solanum tuberosum) is an essential global food crop that is susceptible to various leaf diseases, which can drastically reduce agricultural productivity. Accurate and timely detection of these diseases is crucial for effective management and ensuring food security. This research investigates the application of Vision Transformer (ViT) models, particularly the ViT_B_16 architecture, for detecting and classifying potato leaf diseases such as early blight, late blight, and healthy leaves. Utilizing a comprehensive dataset from Kaggle, which includes 2,152 images across three categories, along with an additional custom dataset, the ViT model is fine-tuned and evaluated using separate training, testing, and validation sets. The findings reveal an impressive accuracy of 99.55%, underscoring the efficacy of ViT-based methods for precise and dependable detection of potato leaf diseases. This study enhances agricultural technological practices by providing a robust tool for early disease diagnosis and strategic agricultural planning.

The effect of crack orientation on the mode I fracture resistance of pinewood

AbstractThe fracture resistance of pinewood under mode I loading is investigated experimentally for different crack plane orientations and the crack propagation direction parallel to longitudinal cells. Experiments are conducted on double cantilever beams using a digital image correlation system to evaluate the crack tip opening displacement. The compliance based beam method is used to determine the energy release rate at various crack lengths. The decomposition of crack propagation into the pre-peak and post-peak propagations is proposed to find the fracture energy contributions from individual toughening mechanisms in pinewood. The cohesive strengths measured in the experiments are confirmed by comparison with the tensile strengths obtained from separate tests performed on pinewood. An analytical model for evaluating the fracture process zone is used to validate the experimental results. The difference between the fracture energy values in different crack propagation systems is explained by using X-ray microtomography images of the fracture surfaces.

Effect of Endovascular Thrombectomy for Acute Ischemic Stroke on Cognitive Outcomes: A Secondary Analysis of the ESCAPE Trial.

The effect of endovascular therapy (EVT) for large vessel occlusion stroke on cognitive outcomes is not well understood. We evaluated the effect of EVT on cognitive function in the Endovascular Treatment for Small Core and Anterior Circulation Proximal Occlusion With Emphasis on Minimizing CT to Recanalization Times (ESCAPE) trial. Patient data from the ESCAPE randomized trial were analyzed. Cognitive assessments completed at 90 days after stroke were the Montreal Cognitive Assessment (MoCA), the Sunnybrook Neglect Assessment Procedure (SNAP), the Boston Naming Test (BNT), Trail-making test A (Trails A), and Trail-making test B (Trails B). We used logistic regression to evaluate the association between EVT and favorable cognitive outcome on the 5 separate tests, adjusting for demographic and clinical factors. We used generalized estimating equations and ordinal regression to determine the odds of favorable outcome with EVT on global cognition incorporating the 5 tests. We added final infarct volume (FIV) to the models to assess the relationship of FIV with cognitive outcome. The ESCAPE trial included 315 patients, 165 randomized to EVT and 150 randomized to control. There was higher odds of favorable outcome with EVT for MoCA (adjusted odds ratio [aOR] 2.32, 95% CI 1.30-4.16), SNAP (aOR 3.85, 95% CI 2.00-7.45), BNT (aOR 2.33, 95% CI 1.30-4.17), trails A (aOR 3.50, 95% CI 1.93-6.36), and trails B (aOR 2.56, 95% CI 1.46-4.48). There was higher odds of favorable outcome with EVT on global binary (aOR 2.57, 95% CI 1.67-3.94) and ordinal analyses (aOR 2.83, 95% CI 1.68-4.76) of cognitive function. After adding FIV to the models, both FIV and EVT were significantly associated with cognitive outcome. There was a significant correlation between global cognitive performance and mRS at day 90 (r = -0.78, p < 0.001), with the largest reductions in favorable cognitive outcome from mRS score 4 to 5 and from mRS 2 to 3. In this secondary analysis of the ESCAPE trial, EVT was associated with favorable outcome on 5 separate cognitive tests and in global analyses of cognitive benefit. These results provide novel evidence for the effect of EVT on cognition and support the global benefit of treatment with EVT. This study provides Class II evidence that in patients with acute ischemic stroke due to intracranial internal carotid artery (ICA) or M1 segment MCA occlusion, including tandem extracranial ICA occlusions, EVT compared with best medical therapy increased odds of favorable cognitive outcome.

Evaluating the between-day reliability and likelihood of change of a test battery incorporating vastus lateralis muscle thickness, ankle-brachial pressure index, maximal voluntary torque, and six-minute walk test in patients with claudication.

The study aims to evaluate the between-day reliability of a proposed test battery for patients with claudication that can be used for monitoring the effectiveness of exercise interventions and other therapeutic strategies tailored to this patient population. Twenty-five men with claudication were recruited. The test battery consisted of the Vastus Lateralis muscle thickness (VL-MT), ankle-brachial pressure index (ABI), unilateral isometric knee extension maximal voluntary torque (MVT) and 6-minute walk test (6MWT). A single investigator conducted the tests for each patient on two separate testing sessions (T1 and T2) 5-7days apart. Good to excellent reliability was observed for VL-MT (ICC = 0.95, 95% LOA = ±3.10mm, SEM = 0.81mm), ABI (ICC = 0.97, 95% LOA = ±0.10, SEM = 0.02), MVT (ICC = 0.97, 95% LOA = ±24.0N·m, SEM = 6.31N·m), 6MWT distance (ICC = 0.99, 95% LOA = ±39.6m, SEM = 11.0m), 6MWT time to claudication (ICC = 0.99, 95% LOA = ±30.8s, SEM = 7.8s), and 6MWT ratings of pain (ICC = 0.87, 95% LOA = ±2.4 CR-10+, SEM = 0.7 CR-10+ ). Analysis derived from reliability data indicates a change of 1.4mm for VL-MT, 0.14 for ABI, 12N·m for MVT, 25m for 6MWT distance, 15s for 6MWT time to claudication and 1 CR-10+ for 6MWT ratings of pain is required to be interpreted as the minimum 'likely' change (76% chance). The test battery provides a reliable assessment of patients with claudication and can be widely used to evaluate the effects of exercise programmes and other therapeutic interventions. For the individual, changes in VL-MT, ABI, MVT, and 6MWT greater than the minimum likely change as a result of an exercise programme or an intervention are likely changes and less influenced by error associated with the test.

Extraction and characterization of Cucumis melon seeds (Muskmelon seed oil) biodiesel and studying its blends impact on performance, combustion, and emission characteristics in an internal combustion engine

This study examines the performance, combustion, and emissions characteristics of a single-cylinder internal combustion diesel engine when fueled with a blend of diesel and biodiesel derived from muskmelon seeds. The kinematic viscosity of the extracted muskmelon seed oil was 6.1 cSt at 40 °C, which is higher than the kinematic viscosity of petroleum diesel of 2.6 cSt. Muskmelon biodiesel was further analyzed using thin-layer chromatography (TLC) and high-voltage separator tests. A comparison of the fuel properties of muskmelon biodiesel with conventional diesel fuel revealed that muskmelon biodiesel could be used alone or in a diesel–biodiesel blend to fuel compression diesel engines. In this study, muskmelon seed biodiesel was blended with diesel fuel at proportions of 10 %, 20 %, and 50 % (BD10, BD20, and BD50, respectively). At a relatively low rotational speed of 1200 rpm, the brake thermal efficiency (BTE) of the engine operated with BD10 and BD20 blends were 36.1 % and 36.0 %, respectively, while the brake-specific fuel consumption (BSFC) of the two blends were 0.260 kg/kWh, and 0.262 kg/kWh, respectively. These values closely resemble those typically observed in diesel fuel engines. Indeed, the average BTE of the BD20 blend was only 3.24 % less than the average BTE of diesel fuel. Diesel fuel generates less NOx and SO2 emissions compared to biodiesel blends: BD100 emitted the most NOx pollution of all fuels tested. In addition, BD10 released significantly more SO2 emissions compared to the other fuels tested. However, the BD20 blend outperformed all other blends in terms of CO, NOx, and SO2 emissions at high engine speeds. The only exception was H2S emissions, which were higher than BD50 and BD100. BD20 also exhibited significantly reduced CO emissions compared to diesel fuel, while BD10 emitted significantly more CO emissions than the other biodiesel blends. Our findings revealed that BD20 exhibited the best engine performance and lower emissions among all fuels tested. In other words, BD20 is the ideal fuel blend for use in diesel engines and does not require any alterations to the engine. Muskmelon waste seeds represent a non-edible waste stream that can be exploited in the production of biodiesel fuel, allowing for the upcycling of a potentially problematic thermochemical conversion feedstock. This potentially valuable use for waste muskmelon seeds in the energy sector could address the wastefulness associated with this particular waste stream.

Effective use of adaptive slicing in binder jetting using Taguchi method and surface roughness measurement with image processing

PurposeThe use of additive manufacturing in many branches of industry is increasing significantly because of its many advantages, such as being able to produce complex parts that cannot be produced by classical methods, using fewer materials, easing the supply chain with on-site production, being able to produce with all kinds of materials and producing lighter parts. The binder jetting technique, one of the additive manufacturing methods researched within the scope of this work, is predicted to be the additive manufacturing method that will grow the most in the next decade, according to many economic reports. Although additive manufacturing methods have many advantages, they can be slower than classical manufacturing methods regarding production speed. For this reason, this study aims to increase the manufacturing speed in the binder jetting method.Design/methodology/approachAdaptive slicing and variable binder amount algorithm (VBAA) were used to increase manufacturing speed in binder jetting. Taguchi method was used to optimize the layer thickness and saturation ratio in VBAA. According to the Taguchi experimental design, 27 samples were produced in nine different conditions, three replicates each. The width of the samples in their raw form was measured. Afterward, the samples were sintered at 1,500 °C for 2 h. After sintering, surface roughness and density tests were performed. Therefore, the methods used have been proven to be successful. In addition, measurement possibilities with image processing were investigated to make surface roughness measurements more accessible and more economical.FindingsAs a result of the tests, the optimum printing condition was decided to be 180–250 µm for layer thickness and 50% for saturation. A separate test sample was then designed to implement adaptive slicing. This test sample was produced in three pieces: adaptive (180–250 µm), thin layer (180 µm) and thick layer (250 µm) with the determined parameters. The roughness values of the adaptive sliced sample and the thin layer sample were similar and better than the thick layer sample. A similar result was obtained using 12.31% fewer layers in the adaptive sample than in the thin layer sample.Originality/valueThe use of adaptive slicing in binder jetting has become more efficient. In this way, it will increase the use of adaptive slicing in binder jetting. In addition, a cheap and straightforward image processing method has been developed to calculate the surface roughness of the parts.

Prediction of the success of electrical cardioversion in patients with atrial fibrillation using parameters obtained by spectral and vectorcardiographic analysis of the ECG

Abstract Introduction Electrical cardioversion (ECV) still presents a treatment option for atrial fibrillation (AF). Despite the great success rate in the acute setting, its long-term success rate is low. The aim of the study was to find predictors of SR maintenance after ECV using spectral and vectorcardiographic (VCG) analysis of the ECG curve. Methods Consecutive patients with AF referred for elective ECV were prospectively enrolled. The digital ECG recording obtained before the ECV was analyzed using spectral and VCG analysis. All patients had Holter monitoring and clinical follow-up three months after cardioversion to assess SR maintenance. Atrial fibrillation activity was analyzed by spectral analysis, determining the dominant frequency (DF), RI (regularity index) and OI (organization index). QRS complexes were analyzed by vectorcardiography and dXmean, dYmean and dZmean (derivation of VCG signals) parameters were determined. Using logistic regression (LR) with backward parameter reduction, separate and combined predictive models of SR maintenance were calculated based on both the analysis from the VCG data and the spectral analysis data. Additional models with a forward selection of clinical variables were also calculated. The efficiency of the models was evaluated on a separate test subset of the data (N=32). Results A total of 80 patients were enrolled (age 70+10 years, 48 (64%) men, CHADSVASc 3.17+1.5, BMI 29.75kg/m2). At the 3-month follow-up, AF recurrence was present in 36 patients (45%). Using only vectorcardiographic parameters, dXmean (OR 3.07, 95 %CI 1.14- 8.63), p=0.001) and dYmean (OR 0.26, 95% CI 0.09-0.72), p &amp;lt;0.001) best predicted the SR maintenance (AUC of 0.72). Using only spectral analysis parameters, the best predictor was DF (OR 3.07, 95%CI 1.14-8.63), p=0.012) with AUC of 0.66. By combining the results of spectral analysis and vectorcardiography, an AUC of 0.78 was achieved. Among the clinical parameters, the most significant predictors were insufficiently controlled arterial hypertension and previous history of stroke. Conclusion Digital analysis of ECG curves using deeper mathematical models provides a better predictive model than classical clinical and echocardiographic models. The combination of spectral analysis of fibrillation atrial activity and vectorocardiographic analysis of QRS complexes revealed more accurate predictive information compared to both analyses alone.

Comparative Analysis of Chemical Descriptors by Machine Learning Reveals Atomistic Insights into Solute-Lipid Interactions.

This study explores the research area of drug solubility in lipid excipients, an area persistently complex despite recent advancements in understanding and predicting solubility based on molecular structure. To this end, this research investigated novel descriptor sets, employing machine learning techniques to understand the determinants governing interactions between solutes and medium-chain triglycerides (MCTs). Quantitative structure-property relationships (QSPR) were constructed on an extended solubility data set comprising 182 experimental values of structurally diverse drug molecules, including both development and marketed drugs to extract meaningful property relationships. Four classes of molecular descriptors, ranging from traditional representations to complex geometrical descriptions, were assessed and compared in terms of their predictive accuracy and interpretability. These include two-dimensional (2D) and three-dimensional (3D) descriptors, Abraham solvation parameters, extended connectivity fingerprints (ECFPs), and the smooth overlap of atomic position (SOAP) descriptor. Through testing three distinct regularized regression algorithms alongside various preprocessing schemes, the SOAP descriptor enabled the construction of a superior performing model in terms of interpretability and accuracy. Its atom-centered characteristics allowed contributions to be estimated at the atomic level, thereby enabling the ranking of prevalent molecular motifs and their influence on drug solubility in MCTs. The performance on a separate test set demonstrated high predictive accuracy (RMSE = 0.50) for 2D and 3D, SOAP, and Abraham Solvation descriptors. The model trained on ECFP4 descriptors resulted in inferior predictive accuracy. Lastly, uncertainty estimations for each model were introduced to assess their applicability domains and provide information on where the models may extrapolate in chemical space and, thus, where more data may be necessary to refine a data-driven approach to predict solubility in MCTs. Overall, the presented approaches further enable computationally informed formulation development by introducing a novel in silico approach for rational drug development and prediction of dose loading in lipids.

Artificial intelligence algorithms and three-dimensional volumetric rendering for basal cell carcinoma detection and tumour depth assessment in reflectance confocal microscopy-optical coherence tomography images: a pilot study.

The reflectance confocal microscopy (RCM)-optical coherence tomography (OCT) device has shown utility in detecting and assessing the depth of basal cell carcinoma (BCC) in vivo but is challenging for novices to interpret. Artificial intelligence (AI) applied to RCM-OCT could aid readers. We trained AI models, using OCT rasters of biopsy-confirmed BCC, to detect BCC, create three-dimensional rendering and automatically measure tumour depth. Trained AI models were applied to a separate test set containing rasters of BCC, benign lesions, and healthy skin. Blinded reader analysis and tumour depth correlation with histopathology were conducted. BCC detection improved from viewing OCT rasters only (sensitivity 73.3%, specificity 45.5%) to viewing rasters with AI-generated BCC rendering (sensitivity 86.7%, specificity 48.5%). A Pearson correlation r2 = 0.59 (P = 0.02) was achieved for the tumour depth measurement between AI and histological measured depths. Thus, addition of AI to the RCM-OCT device may expand its utility widely.

TiO2 deposited dual functional hydrogel coatings with superhydrophilic and photocatalytic properties for efficient oil/water separation and dye photodegradation

Hydrogel coatings have been applied in oil/water separation owing to the underwater superoleophobic and anti-oil fouling property. However, the intrinsic relatively poor mechanical performance of hydrogel coatings and inevitably polluted by organic pollutants induce the separation performance reduction in the long-term operation and even possibly cause the coatings to peel off. In this work, we developed a simple and robust TiO2 deposited polyacrylamide-sodium alginate (TiO2@PAS) composite hydrogel coating with underwater superoleophobic and dye photodegradation abilities. PDA/TiO2 nanoparticles were deposited on the substrate surface through the mussel inspired chemistry strategy. Moreover, Polyacrylamide and calcium alginate were crosslinked into the double network hydrogel to enhance mechanical performance. The prepared hydrogel coating was introduced onto different substrates to endow the coated substrates with robust superwetting and anti-oil fouling properties. Separation efficiency of TiO2@PAS hydrogel coated copper mesh for oil/water mixtures reached 99.1% after 50 cycle separation tests. The hydrogel coated PVDF membrane was prepared through the same method and separation efficiency for oil-in-water emulsion keeps above 99.3% during multiple cycles separation. Moreover, the photocatalysis active TiO2 nanoparticles allowed the TiO2@PAS composite hydrogel coating to degrade the organic dye methylene blue (MB) through the photo-Fenton-like photodegradation process with degradation efficiency as high as 98.7%. Notedly, the TiO2@PAS hydrogel coating shows robust superwetting performance even underwent abrasion test and acid-base immersing, which has the potential for adapting extreme operating condition. Overall, the study on the TiO2@PAS composite hydrogel coatings provides a general and simple design strategy for superwetting and photocatalytic hydrogel coatings for multi-demand water treatment application.

Effect of surface engineering of nanofillers using plasma-treated water for carbon dioxide capture in mixed matrix membranes: Experimental and molecular dynamics

This work introduces an innovative approach to enhance carbon dioxide (CO2) capture performance in mixed-matrix membranes (MMMs) by incorporating plasma-treated ceria (CeO2) nanoparticles into a polyurethane (PU)-based membrane. Functionalization of CeO2 by means of plasma aimed at improving interfacial interactions with both polymer matrix and CO2 gas molecules, with the consequent enhancement of CeO2 nanoparticles dispersion within the matrix and improvement of gas separation performance. Based on the results of the gas separation tests, the PU membrane containing 5 wt% plasma-treated CeO2 exhibited a CO2 permeability of 51.2 barrer and a CO2/N2 ideal selectivity of approximately 76.5, demonstrating a 26.1% increase in CO2/N2 ideal selectivity compared to the pristine PU membrane. However, a further increase in filler content to 10 wt% led to nanoparticle agglomeration, resulting in a decrease in selectivity due to the formation of non-selective pathways through the membrane. Molecular dynamics (MD) simulations corroborated these experimental findings, providing additional insights into the interaction mechanisms between the polymer matrix and the functionalized nanoparticles.

MR-based radiomics predictive modelling of EGFR mutation and HER2 overexpression in metastatic brain adenocarcinoma: a two-centre study

ObjectivesMagnetic resonance (MR)-based radiomics features of brain metastases are utilised to predict epidermal growth factor receptor (EGFR) mutation and human epidermal growth factor receptor 2 (HER2) overexpression in adenocarcinoma, with the aim to identify the most predictive MR sequence.MethodsA retrospective inclusion of 268 individuals with brain metastases from adenocarcinoma across two institutions was conducted. Utilising T1-weighted imaging (T1 contrast-enhanced [T1-CE]) and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequences, 1,409 radiomics features were extracted. These sequences were randomly divided into training and test sets at a 7:3 ratio. The selection of relevant features was done using the least absolute shrinkage selection operator, and the training cohort’s support vector classifier model was employed to generate the predictive model. The performance of the radiomics features was evaluated using a separate test set.ResultsFor contrast-enhanced T1-CE cohorts, the radiomics features based on 19 selected characteristics exhibited excellent discrimination. No significant differences in age, sex, and time to metastasis were observed between the groups with EGFR mutations or HER2 + and those with wild-type EGFR or HER2 (p > 0.05). Radiomics feature analysis for T1-CE revealed an area under the curve (AUC) of 0.98, classification accuracy of 0.93, sensitivity of 0.92, and specificity of 0.93 in the training cohort. In the test set, the AUC was 0.82. The 19 radiomics features for the T2-FLAIR sequence showed AUCs of 0.86 in the training set and 0.70 in the test set.ConclusionsThis study developed a T1-CE signature that could serve as a non-invasive adjunctive tool to determine the presence of EGFR mutations and HER2 + status in adenocarcinoma, aiding in the direction of treatment plans.Clinical relevance statementWe propose radiomics features based on T1-CE brain MR sequences that are both evidence-based and non-invasive. These can be employed to guide clinical treatment planning in patients with brain metastases from adenocarcinoma.

Oil-recovery performance of a superhydrophobic sponge-covered disc skimmer

Frequent oil spill accidents caused by transportation, storage and usage may lead to severe damage on aquatic and ecological environments. Effective methods for rapid oil recovery are urgently in demand. Polyvinyl chloride, hydrophobic nano-SiO2, expanded graphite were separately applied to polyurethane and melamine sponge to fabricate superhydrophobic sponge material. The selected superhydrophobic sponge was introduced to establish sponge - covered disc skimmer. Oil recovery tests of the device were conducted to determine the optimum parameters. The examined operating conditions encompassed sponge thickness, immersion depth, rotational speed, oil slick thickness, operation time. The results showed that the melamine sponge modified by both polyvinyl chloride and hydrophobic nano-SiO2 exhibits super-hydrophobicity with a water contact angle of 150.3°. The absorption capacity for diesel oil can reach 53.89 g/g. The absorption capacity can still achieve 90 % of its initial capacity even after 500 extrusion-absorption separation tests. The results indicate the superiority of the superhydrophobic sponge covered surface in oil recovery over the standard steel surface regardless of the operating conditions. The recovery rate of the device can still achieve 96.4 % of its initial capacity with 95 % efficiency even after 85 h operation. The results suggest the superhydrophobic sponge - covered disc skimmer may have great application perspectives in oil spill recovery.

A SURVEY ON PREDICTION OF DIABETIC LEVELS USING MACHINE LEARNING ALGORITHAM

Diabetes is a serious, long-lasting illness that makes blood sugar levels high. It can lead to many health problems. By 2040, it's expected that 1 in 10 adults worldwide will have diabetes, reaching a staggering 642 million people. This is a big concern and needs attention. Scientists are using advanced technology like machine learning to predict diabetes. They studied data from hospital check-ups in Luzhou, China, which had 14 pieces of information about each person. They used two different methods like decision trees, random forests to make predictions. They tested these methods to see how well they worked, using a technique called five-fold cross-validation. To make sure their findings were reliable; they also did separate tests with a large group of healthy people and those with diabetes. Because the data wasn't evenly balanced between healthy and diabetic people, they adjusted it to make it fair. They found that random forests were the best at predicting diabetes accurately, with about 81% accuracy when using all the information available. They also used techniques like principal component analysis and minimum redundancy maximum relevance to make the data easier to work with. KEYWORDS : Diabetes, blood sugar, predictions, hospital, China, methods, tests, data, balance, forests, accuracy, analysis.