Predictive Value Of Model Research Articles

Co-pyrolysis of coal-derived sludge and low-rank coal: Thermal behaviour and char yield prediction

Coal-derived sludge, a solid waste produced by the coal industry, offers potential opportunities for resource recovery due to its high organic matter. However, its products face challenges related to low utilization efficiency and economic value. Effective and clean treatment of coal-derived sludge is essential for sustainable development. Herein, we studied the co-pyrolysis treatment of coal-derived sludge and low-rank coal at different temperatures (500 °C−900 °C) and pretreatment methods (mechanical mixing and hydrothermal co-treatment). The co-pyrolysis of sludge and coal could increase the pyrolysis char yield and H2 yield, as well as reduce CO2 emissions. The hydrothermal co-treatment significantly improved the cleanliness of the co-pyrolysis treatment. Then we conducted a comprehensive analysis of the properties of the pyrolysis char using different characterization techniques. In order to better evaluate the distribution of co-pyrolysis product yield, six machine learning models were developed to predice co-pyrolysis char yield. The best model-predicted values showed excellent predictive performance when compared to the experimental values at high pyrolysis temperatures (≥700 °C). This study provided a new perspective on the resource utilization of coal-derived sludge and low-rank coal.

CNV-Finder: Streamlining Copy Number Variation Discovery.

Copy Number Variations (CNVs) play pivotal roles in the etiology of complex diseases and are variable across diverse populations. Understanding the association between CNVs and disease susceptibility is of significant importance in disease genetics research and often requires analysis of large sample sizes. One of the most cost-effective and scalable methods for detecting CNVs is based on normalized signal intensity values, such as Log R Ratio (LRR) and B Allele Frequency (BAF), from Illumina genotyping arrays. In this study, we present CNV-Finder, a novel pipeline integrating deep learning techniques on array data, specifically a Long Short-Term Memory (LSTM) network, to expedite the large-scale identification of CNVs within predefined genomic regions. This facilitates the efficient prioritization of samples for subsequent, costly analyses such as short-read and long-read whole genome sequencing. We focus on five genes-Parkin (PRKN), Leucine Rich Repeat And Ig Domain Containing 2 (LINGO2), Microtubule Associated Protein Tau (MAPT), alpha-Synuclein (SNCA), and Amyloid Beta Precursor Protein (APP)-which may be relevant to neurological diseases such as Alzheimer's disease (AD), Parkinson's disease (PD), or related disorders such as essential tremor (ET). By training our models on expert-annotated samples and validating them across diverse cohorts, including those from the Global Parkinson's Genetics Program (GP2) and additional dementia-specific databases, we demonstrate the efficacy of CNV-Finder in accurately detecting deletions and duplications. Our pipeline outputs app-compatible files for visualization within CNV-Finder's interactive web application. This interface enables researchers to review predictions and filter displayed samples by model prediction values, LRR range, and variant count in order to explore or confirm results. Our pipeline integrates this human feedback to enhance model performance and reduce false positive rates. Through a series of comprehensive analyses and validations using both short-read and long-read sequencing data, we demonstrate the robustness and adaptability of CNV-Finder in identifying CNVs with regions of varied sparsity, noise, and size. Our findings highlight the significance of contextual understanding and human expertise in enhancing the precision of CNV identification, particularly in complex genomic regions like 17q21.31. The CNV-Finder pipeline is a scalable, publicly available resource for the scientific community, available on GitHub (https://github.com/GP2code/CNV-Finder; DOI 10.5281/zenodo.14182563). CNV-Finder not only expedites accurate candidate identification but also significantly reduces the manual workload for researchers, enabling future targeted validation and downstream analyses in regions or phenotypes of interest.

Unexpectedly strong heat stress induction of monoterpene, methylbutenol, and other volatile emissions for conifers in the cypress family (Cupressaceae)

We investigated the biogenic volatile organic compound (BVOC) emission rates and composition of Cupressaceae species and how the emissions change in response to moderate warming and more severe heat stress. A total of 8 species from 7 distinct Cupressaceae genera were targeted in this study and exposed to laboratory-simulated heatwaves. Each plant was enclosed in a temperature-controlled glass chamber and allowed to equilibrate at 30 °C for 24 h. The temperature was then increased stepwise from 33 °C to 43 °C in 2 °C increments, with each step lasting 2 h, and was finally kept at 45 °C for 12 h. The BVOC emissions were measured periodically using an automated air sampler coupled to a gas chromatograph.Most of the sampled Cupressaceae species (6 out of 8) were low BVOC emitters (<0.3 μgC g−1 h−1) at 30 °C. However, the BVOC emissions of all 8 species increased strongly with temperature, and in most species (5 out of 8), the emissions continued to increase with longer exposure times to heat stress. The largest increase was observed in Thuja occidentalis and Chamaecyparis thyoides, which reached maximum emissions of 350 and 190 μgC g−1 h−1, respectively. Of the different BVOCs, monoterpenes responded most strongly to heat stress, with Q10 temperature coefficients typically ranging between 7.6 and 22, which were significantly greater than the model-predicted value of 2.7. Other BVOCs including sesquiterpenes, C9 aromatics (only detected in Calocedrus decurrens), methylbutenols, and other C5 oxygenates were also induced by heat stress, but generally at a lower magnitude than monoterpenes.Our results indicate that Cupressaceae are a large but typically dormant source of reactive volatile hydrocarbons (mostly monoterpenes) whose emissions can be activated by heat stress. This phenomenon could have important implications for ozone and aerosol formation, air quality, and human health, particularly in urban areas that are prone to heatwaves.

Assessing the need for coronary angiography in high-risk non-ST-elevation acute coronary syndrome patients using artificial intelligence and computed tomography.

This study aimed to evaluate the efficacy of the Chat Generative Pre-trained Transformer (ChatGPT) in guiding the need for invasive coronary angiography (ICA) in high-risk non-ST-elevation (NSTE) acute coronary syndrome (ACS) patients based on both standard clinical data and coronary computed tomography angiography (CCTA) findings. This investigation is a sub-study of a larger prospective multicentric double blinded project where high-risk NSTE-ACS patients underwent CCTA prior to ICA to compare coronary lesion by both modalities. ChatGPT analyzed clinical vignettes containing patient data, electrocardiograms, troponin levels, and CCTA results to determine the necessity of ICA. The AI's recommendations were then compared to actual ICA findings to assess its decision-making accuracy. In total, 86 patients (age: 62 ± 13 years old, female 27%) were included. ChatGPT recommended against ICA for 19 patients, 16 of whom indeed had no significant findings. For 67 patients, ChatGPT advised proceeding with ICA, and a significant lesion was confirmed in 58 of them. Consequently, ChatGPT's overall accuracy stood at 86%, with a sensitivity of 95% (95% confidence interval (CI) 0.76-0.92) and a specificity of 64% (95% CI 0.62-0.94). The model's negative predictive value was 84% (95% CI 0.44-0.79), and its positive predictive value was 87% 95% CI 0.86-0.97). Preliminary evidence suggests that ChatGPT can effectively assist in making ICA decisions for high-risk NSTE-ACS patients, potentially reducing unnecessary procedures. However, the study underscores the importance of data accuracy and calls for larger, more diverse investigations to refine artificial intelligence's role in clinical decision-making.

Quantification of Size-Binned Particulate Matter in Electronic Cigarette Aerosols Using Multi-Spectral Optical Sensing and Machine Learning.

To monitor health risks associated with vaping, we introduce a multi-spectral optical sensor powered by machine learning for real-time characterization of electronic cigarette aerosols. The sensor can accurately measure the mass of particulate matter (PM) in specific particle size channels, providing essential information for estimating lung deposition of vaping aerosols. For the sensor's input, wavelength-specific optical attenuation signals are acquired for three separate wavelengths in the ultraviolet, red, and near-infrared range, and the inhalation pressure is collected from a pressure sensor. The sensor's outputs are PM mass in three size bins, specified as 100-300 nm, 300-600 nm, and 600-1000 nm. Reference measurements of electronic cigarette aerosols, obtained using a custom vaping machine and a scanning mobility particle sizer, provided the ground truth for size-binned PM mass. A lightweight two-layer feedforward neural network was trained using datasets acquired from a wide range of puffing conditions. The performance of the neural network was tested using unseen data collected using new combinations of puffing conditions. The model-predicted values matched closely with the ground truth, and the accuracy reached 81-87% for PM mass in three size bins. Given the sensor's straightforward optical configuration and the direct collection of signals from undiluted vaping aerosols, the achieved accuracy is notably significant and sufficiently reliable for point-of-interest sensing of vaping aerosols. To the best of our knowledge, this work represents the first instance where machine learning has been applied to directly characterize high-concentration undiluted electronic cigarette aerosols. Our sensor holds great promise in tracking electronic cigarette users' puff topography with quantification of size-binned PM mass, to support long-term personalized health and wellness.

Prognostic Value of Systemic Inflammation Response Index and N-Terminal Pro-B-Type Natriuretic Peptide in Patients with Myocardial Infarction with Nonobstructive Coronary Arteries- A Retrospective Study.

The Systemic Inflammation Response Index (SIRI) and N-terminal Pro-B-type natriuretic peptide (NT-proBNP) have been proposed as reliable predictors of poor prognosis in cardiovascular disease and all-cause mortality, However, their validity has not been extensively evaluated in patients with myocardial infarction with nonobstructive coronary arteries (MINOCA). 259 patients diagnosed with MINOCA were enrolled in this study from January 2015 to December 2022, and serum levels of SIRI and NT-proBNP were detected. The primary endpoints were major adverse cardiovascular events (MACE). According to the occurrence of MACE during the follow-up period, patients were grouped into MACE and Non-MACE groups, and divided by the median values for SIRI and NT-proBNP into groups: low SIRI, high SIRI, low NT-proBNP, and high NT-proBNP. A statistically significant difference in the levels of SIRI and NT-proBNP was observed between the MACE group and the non-MACE group. Kaplan-Meier survival curve analysis revealed that patients with high SIRI and high NT-proBNP had a significantly higher risk of MACE (log-rank P < 0.001). Furthermore, even after adjusting for covariates, the high SIRI and high NT-proBNP were associated with an increased risk of MACE (P<0.001, HR: 3.188, 95% CI 1.940-5.241; P<0.001, HR: 2.245, 95% CI 1.432-3.519). Additionally, the combined prognosis prediction of SIRI and NT-proBNP was superior to a single prediction, and adding SIRI and NT-proBNP to the traditional risk factor model improved the model's predictive value. High levels of SIRI and NT-proBNP exhibit a significant correlation with an increased risk of MACE, thereby suggesting that SIRI can be used as a reliable inflammatory indicator for predicting the risk in MINOCA patients, with significantly improved prognostic value when combined with NT-proBNP.

Multimodal approach to optimize biopsy decision-making for PI-RADS 3 lesions on multiparametric MRI

PurposeTo develop and evaluate a multimodal approach including clinical parameters and biparametric MRI-based artificial intelligence (AI) model for determining the necessity of prostate biopsy in patients with PI-RADS 3 lesions. MethodsThis retrospective study included a prospectively recruited patient cohort with PI-RADS 3 lesions who underwent prostate MRI and MRI/US fusion-guided biopsy between April 2019 and February 2024 in a single institution. The study examined demographic data, PSA and PSA density (PSAD) levels, prostate volumes, prospective PI-RADS v2.1-compliant interpretations of a genitourinary radiologist, lesion characteristics, history of prior biopsies, and AI evaluations, focusing mainly on the detection of clinically significant prostate cancer (csPCa) (International Society of Urological Pathology grade group ≥2) on MRI/US fusion-guided biopsy. The AI model lesion segmentations were compared to manual segmentations and biopsy results. The statistical methods employed included Fisher's exact test and logistic regression. ResultsThe cohort was comprised of 248 patients with 312 PI-RADS 3 lesions in total (n = 268 non-csPCa, n = 44 csPCa). The AI model's negative predictive value (NPV) was 89.2 % for csPCa in all lesions. In patient-level analysis, the NPV was 91.2 % for patients with a highest PI-RADS score of 3. PSAD was a significant predictor of csPCa (odds ratio = 5.8, p = 0.038). Combining AI and PSAD, where AI correctly mapped a lesion or PSAD ≥0.15 ng/mL2, achieved higher sensitivity (77.8 %) while maintaining a high NPV (93.1 %). ConclusionCombining AI and PSAD has the potential to enhance biopsy decision-making for PI-RADS 3 lesions by minimizing missed csPCa occurrences and reducing unnecessary biopsies.

Design and Experimental Optimization of an Automated Longline-Suspended Oyster Spat Insertion Device

To address the challenges of labor-intensive and costly manual oyster spat insertion in longline-suspended farming, an automated oyster spat insertion device was designed based on negative pressure suction and bundling fixation technologies. Using this device as the experimental platform, a three-factor, three-level Box–Behnken experiment was conducted, with fixation mechanism inclination, negative pressure suction cup span, and horizontal distance between turnover and fixation mechanisms as the experimental factors. The performance of the device was evaluated using the effective fixation rate and damage rate as the experimental indicators. The quadratic polynomial regression models were established to assess the impact of these factors on operational performance, while the response surface method was employed to analyze the interaction effects between factors. Parameter optimization and experimental validation were also performed. The results indicate that the factors affecting the effective fixation rate, in order of significance, are as follows: fixation mechanism inclination, horizontal distance between turnover and fixation mechanisms, and negative pressure suction cup span. For the damage rate, the order of significance is as follows: fixation mechanism inclination &gt; negative pressure suction cup span &lt; horizontal distance between turnover and fixation mechanisms. The optimization results show that when the fixation mechanism inclination is set at 43°, the negative pressure suction cup span at 27 mm, and the horizontal distance between turnover and fixation mechanisms at 179 mm, the effective fixation rate reaches 92.08%, and the damage rate is 4.71%. The relative errors between the measured and model-predicted values are less than 5%, indicating that the regression models are reliable. This research provides valuable insights for advancing the mechanization of the oyster farming industry and replacing manual labor with mechanized equipment.

Assessing the need for coronary angiography in high-risk acute coronary syndrome patients using artificial intelligence and computed tomography

Abstract Background/Introduction The use of coronary computed tomography angiography (CCTA) in managing high-risk acute coronary syndrome (ACS) patients is increasingly common. Yet, its role remains unvalidated in this context, posing challenges to traditional clinical decision-making algorithms. Physicians, accustomed to a hierarchical and structured approach involving symptom assessment, electrocardiograms, and biomarkers for deciding on the necessity of invasive coronary angiography (ICA), now face dilemmas when CCTA results challenge established diagnostic pathways and contradict clinical decisions based on usual criteria. Meanwhile, the potential of artificial intelligence (AI) which processes information in a way fundamentally different from human clinical reasoning, has been shown to aid decision-making in cardiovascular medicine. Yet, it has not been tested in this acute setting. Purpose This study aimed to evaluate the efficacy of the Chat Generative Pre-trained Transformer (ChatGPT) in guiding the need for ICA in high-risk ACS patients based on both standard clinical data and CCTA findings. Methods This investigation is a sub-study of a larger research project where high-risk ACS patients (all having a theoretical guideline-based indication for ICA) underwent CCTA prior to ICA. ChatGPT analyzed clinical vignettes containing patient data, electrocardiograms, troponin levels, and CCTA results to determine the necessity of ICA. The AI's recommendations were then compared to actual ICA findings to assess its decision-making accuracy. Results Among 86 patients with a clear indication for ICA, ChatGPT recommended against it for 19 patients, 16 of whom indeed had no significant findings at ICA (Figure). For 67 patients, ChatGPT advised proceeding with ICA, and a significant lesion was confirmed in 58 of them. Consequently, ChatGPT's overall accuracy stood at 86%, with a sensitivity of 95% and a specificity of 64%. The model's negative predictive value was 84%, and its positive predictive value was 87%. Conclusion These preliminary data suggest that ChatGPT can effectively assist in guiding the need for ICA among high-risk ACS patients, potentially reducing unnecessary procedures but further clinical studies to refine AI's role in clinical decision-making are required.ChatGPT's decision as per ICA's results

Optimized design and performance testing of hydraulic electrostatic actuator

ABSTRACT Hydraulic electrostatic actuators have become a research hotspot for their inherent flexibility and safety of human-machine interaction. This paper aims to combine the characteristics of dielectric elastomers and fluid actuators, enhancing the dielectric constant and breakdown field strength by modifying Al2O3 on the surface of nanostructured BaTiO3 and in order to develop a hydraulic electrostatic actuator with silicone rubber as the matrix material. Single-factor experiments were firstly conducted to confirm the range of three factors affecting the actuation strain of the actuator: BaTiO3@Al2O3 content, thickness of the silicone rubber elastomer film, and pre-stretching ratio coefficient. The response surface methodology was used to study the interactive influence of the above three influencing factors on the actuation strain. It was obtained that A has an insignificant influence on the actuation strain, AB has a significant influence on the actuation strain, and B, C, AC, and BC have a highly influence on the actuation strain. Maximizing actuation strain as the optimization objective yielded the combination results of each factor: BaTiO3@Al2O3 content of 2.57%, thickness of 0.60 mm, and pre-stretching ratio coefficient of 2.50. Actuation strain tests were conducted with optimized parameters under no-load. The experimental results of the actuation strain test show that the relative error between the test value and the model prediction value of 16.47% is less than 5%, and the optimization model results are reliable. The optimized hydraulic electrostatic actuator was tested for actuation strain and electrical performance under different loads. The experiment showed that the maximum actuation strain of the hydraulic electrostatic actuator was 17.20% under a load of 100 g. The critical breakdown current of the actuator ranged from 115 μA to 130 μA, and the maximum electromechanical conversion efficiency of the actuator under different loads was 67.93%. Finally, a joint actuating device was developed based on the structure of the actuator, amplifying the output displacement of the actuator to 30 mm, and the linear displacement of the soft electro-fluid actuator can be converted into a 20° rotation angle through the gear steering mechanism, thus validating the effectiveness of the hydraulic electrostatic actuator.

Passenger flow prediction at rail transit station entrances and exits: A case study of Beijing

Accurate prediction of passenger flow at station entrances and exits is a hot topic in rail transit passenger flow prediction work, and provides important support for the refined and humanized design of stations. This paper comprehensively considers factors such as land use around the station, traffic connection conditions, station attributes and attractiveness, and constructs a two-layer passenger flow prediction model, including traffic zone layer passenger flow prediction based on multivariate nonlinear regression and entrance and exit layer passenger flow prediction based on the CRITIC method. Based on available data, the model first predicts the total passenger flow at all entrances and exits in the traffic zone, and then distributes the total passenger flow to each entrance and exit of the traffic zone. Different types of rail transit stations were randomly selected to verify the effectiveness of the model. The results show that the error between the model prediction value and the actual value of the daily entrance and exit volume is within , and the average error is , which has a high prediction accuracy.

Optimization of Combined Hydrothermal and Mechanical Refining Pretreatment of Forest Residue Biomass for Maximum Sugar Release during Enzymatic Hydrolysis

This study aimed to investigate the effect of chemical-free two-stage hydrothermal and mechanical refining pretreatment on improving the sugar yields during enzymatic hydrolysis of forest residue biomass (FRB) and optimize the pretreatment conditions. Hot-water pretreatment experiments were performed using a central composite design for three variables: temperature (160–200 °C), time (10–20 min), and solid loading (10–20%). Hydrothermally pretreated biomass was subsequently pretreated using three cycles of disk refining. The combined pretreatment was found to be highly effective in enhancing sugar yields during enzymatic hydrolysis, with almost 99% cellulose conversion for biomass pretreated at 213.64 °C, 15 min, and 15% solid loading. However, the xylose concentrations in the hydrolysate were found to be low under these conditions due to sugar degradation. Thus, less severe optimum pretreatment conditions (194.78 °C, 12.90 min, and 13.42% solid loading) were predicted using a second-order polynomial model. The response surface model optimized the hydrothermal pretreatment of FRB and predicted the glucan, xylan, and overall conversions of 94.57%, 79.78%, and 87.84%, respectively, after the enzymatic hydrolysis. The model-predicted biomass conversion values were validated by the experimental results.

Gold nanoclusters and amino-modified mesoporous silica-encapsulated carbon dot fluorescence nanosensors combined with LightGBM algorithm for ultra-fast detection of Co2+

In this study, we develop a novel ratiometric fluorescent nanosensor for the detection excess Co2+ in soil. This fluorescent nanosensor is fabricated using mesoporous silica-encapsulated nitrogen-doped carbon dots (N-CDs@mSiO2) and gold nanoclusters stabilized by bovine serum albumin (BSA-AuNCs). The green fluorescence of the carbon dots within the mesoporous silica spheres (mSiO2) serves as an internal reference signal. The red fluoresence BSA-AuNCs are covalently connected onto the surface of amino-functionalized nanospheres (N-CDs@mSiO2-NH2), providing the response signal. This nanosensor has dual emission peaks at 520 nm and 650 nm under excitation wavelength of 380 nm. The addition of Co2+ to this nanosensor causes the fluorescence quenching at 650 nm while the green fluorescence at 520 nm remains unchanged, resulting in fluorescence color change from yellow to green. The developed ratiometric fluorescence nanosensor exhibits excellent selectivity to Co2+ with a range of 2.00–200.00 μM and a detection limit as low as 0.74 μM. In addition, a Co2+ prediction model is developed using the Light Gradient Boosting Machine (LightGBM) algorithm. The entire detection process is within 10 s and the model prediction value is as high as 0.991 on average. This shows that the proposed fluorescent nanosensor, optimized with the LightGBM algorithm, provides an efficient, environmentally friendly and potentially practical solution for Co2+ detection.

A QbD-Navigated Approach to the Development and Evaluation of Etodolac-Phospholipid Complex Containing Polymeric Films for Improved Anti-Inflammatory Effect.

The current study focuses on development of phospholipid complex-loaded films of etodolac for enhanced transdermal permeation and anti-inflammatory effect. An etodolac-phospholipid complex was developed using the solvent evaporation method and was characterized by DSC, XRD, FTIR, and 1H-NMR studies. The formation of the complex led to conversion of a crystalline drug to an amorphous form. A stoichiometric ratio of 1:1 (drug-phospholipid) was selected as the optimized ratio. Further, the developed complex was incorporated into films and systematic optimization using a central composite design was carried out using a response surface methodological approach. The desirable design space based on minimum contact angle and maximum tensile strength was selected, while the water vapour transmission rate and swelling index were set within limits. The results for swelling index, contact angle, tensile strength, and water vapour transmission rate were 60.14 ± 1.01%, 31.6 ± 0.03, 2.44 ± 0.39 kg/cm2, and 15.38 g/hm2, respectively. These values exhibited a good correlation with the model-predicted values. The optimized formulation exhibited improved diffusion and permeation across skin. In vivo studies revealed enhanced anti-inflammatory potential of the developed films in comparison to the un-complexed drug. Hence, the study demonstrated that etodolac-phospholipid complex-loaded films improve the transdermal permeation and provided enhanced anti-inflammatory effect.

Seasonal climate forecasts show skill in predicting winter chill for specialty crops in California

Many fruits and nuts crops in California require sufficient winter chill to break dormancy, and insufficient chill can harm fruit quantity and quality. Early information on winter chill forecast can help growers prepare for a low chill year. Here we evaluate use of dynamic climate models for chill accumulation forecast in California. Using temperature forecasts from seasonal prediction systems, we found that the multimodel forecasts can predict chill. This is evident from the anomaly correlation coefficients exceeding 0.5 between the model-predicted and reference chill values for most California regions. The forecasts correctly identified chill categories in over 50% instances in more than 40% of the Central Valley and southern parts of California. The forecasts also demonstrated skill in capturing the interannual variability of chill, especially during years with substantial decrease in chill. Additionally, the seasonal forecast can provide potentially useful crop specific chill sufficiency prediction. However, forecasts beyond a one-month lead time showed reduced forecast skills.

Energy consumption model of flow-through electrolyzer considering mass transfer overpotential for hydrogen production from alkaline water splitting

Flow-through electrolyzer can improve the efficiency of hydrogen production from alkaline water splitting and determining the optimal electrolyte velocity through electrode pores is crucial for reducing energy consumption. In this study, an energy consumption model of flow-through electrolyzer considering mass transfer overpotential (Emass) has been developed. The model of Emass due to gas hold-up (ϕ) in the electrolyzer accounts for the density, viscosity, surface tension, linear velocity, and current density. The model-predicted value is in good agreement with the experimental results, which indicated that the increase of velocity effectively reduces ϕ and Emass. Then, Voltage-Current curve models combining reversible voltage, activation overpotential, ohmic overpotential, and Emass are developed. Based on this, an energy consumption model, combining both consumption from electrolyzer and pumps, is established to evaluate the overall energy consumption of hydrogen production. It can be calculated the Emass at 400 mA cm−2, 6 M KOH, 353 K can be reduced from 0.363 V to 0.048 V if the circulation velocity rises from 0.001 m s−1 to 0.1 m s−1. The model predicts that total energy consumption is 4.36 kWh Nm−3 with energy consumption for pump being 0.02 kWh Nm−3 at 400 mA cm−2 and 0.063 m s−1.

Atherosclerosis quantification and cardiovascular risk: the ISCHEMIA trial.

The aim of this study was to determine the prognostic value of coronary computed tomography angiography (CCTA)-derived atherosclerotic plaque analysis in ISCHEMIA. Atherosclerosis imaging quantitative computed tomography (AI-QCT) was performed on all available baseline CCTAs to quantify plaque volume, composition, and distribution. Multivariable Cox regression was used to examine the association between baseline risk factors (age, sex, smoking, diabetes, hypertension, ejection fraction, prior coronary disease, estimated glomerular filtration rate, and statin use), number of diseased vessels, atherosclerotic plaque characteristics determined by AI-QCT, and a composite primary outcome of cardiovascular death or myocardial infarction over a median follow-up of 3.3 (interquartile range 2.2-4.4) years. The predictive value of plaque quantification over risk factors was compared in an area under the curve (AUC) analysis. Analysable CCTA data were available from 3711 participants (mean age 64 years, 21% female, 79% multivessel coronary artery disease). Amongst the AI-QCT variables, total plaque volume was most strongly associated with the primary outcome (adjusted hazard ratio 1.56, 95% confidence interval 1.25-1.97 per interquartile range increase [559 mm3]; P = .001). The addition of AI-QCT plaque quantification and characterization to baseline risk factors improved the model's predictive value for the primary outcome at 6 months (AUC 0.688 vs. 0.637; P = .006), at 2 years (AUC 0.660 vs. 0.617; P = .003), and at 4 years of follow-up (AUC 0.654 vs. 0.608; P = .002). The findings were similar for the other reported outcomes. In ISCHEMIA, total plaque volume was associated with cardiovascular death or myocardial infarction. In this highly diseased, high-risk population, enhanced assessment of atherosclerotic burden using AI-QCT-derived measures of plaque volume and composition modestly improved event prediction.

Automatic measurement of anatomical parameters of the lumbar vertebral body and the intervertebral disc on radiographs by deep learning.

Lumbar spine disorders are one of the common causes of low back pain (LBP). Objective and reliable measurement of anatomical parameters of the lumbar spine is essential in the clinical diagnosis and evaluation of lumbar disorders. However, manual measurements are time-consuming and laborious, with poor consistency and repeatability. Here, we aim to develop and evaluate an automatic measurement model for measuring the anatomical parameters of the vertebral body and intervertebral disc based on lateral lumbar radiographs and deep learning (DL). A model based on DL was developed with a dataset consisting of 1,318 lateral lumbar radiographs for the prediction of anatomical parameters, including vertebral body heights (VBH), intervertebral disc heights (IDH), and intervertebral disc angles (IDA). The mean of the values obtained by 3 radiologists was used as a reference standard. Statistical analysis was performed in terms of standard deviation (SD), mean absolute error (MAE), Percentage of correct keypoints (PCK), intraclass correlation coefficient (ICC), regression analysis, and Bland-Altman plot to evaluate the performance of the model compared with the reference standard. The percentage of intra-observer landmark distance within the 3 mm threshold was 96%. The percentage of inter-observer landmark distance within the 3 mm threshold was 94% (R1 and R2), 92% (R1 and R3), and 93% (R2 and R3), respectively. The PCK of the model within the 3mm distance threshold was 94-99%. The model-predicted values were 30.22±3.01 mm, 10.40±3.91 mm, and 10.63°±4.74° for VBH, IDH, and IDA, respectively. There were good correlation and consistency in anatomical parameters of the lumbar vertebral body and disc between the model and the reference standard in most cases (R2=0.89-0.95, ICC =0.93-0.98, MAE =0.61-1.15, and SD =0.89-1.64). The newly proposed model based on a DL algorithm can accurately measure various anatomical parameters on lateral lumbar radiographs. This could provide an accurate and efficient measurement tool for the quantitative evaluation of spinal disorders.

Population Pharmacokinetics and Exposure-Response Relationship of Zimberelimab in Chinese Patients with Advanced Tumors.

This study aimed to establish a population pharmacokinetic (PopPK) model using data from 2 clinical trials of zimberelimab, evaluate the pharmacokinetics (PKs) of zimberelimab, explore the feasibility of 360mg once every 3 weeks (Q3W) and 480mg once every 4 weeks (Q4W) as alternative dosage regimens, and analyze the exposure-response relationship of the efficacy and safety of zimberelimab for advanced tumors. The PKs of zimberelimab were described using the 2-compartment model with time-dependent nonlinear elimination. The prediction-corrected visual predictive check was used to evaluate the model's predictive value on blood drug concentrations. In total, 2165 PK observations from 321 participants were included. The PopPK model demonstrated a high level of concordance between the observed data and the predicted values, indicative of a robust fit to the PK data of zimberelimab. The PK variables were similar for the 240mg once every 2 weeks, 360mg Q3W, and 480mg Q4W regimens. No covariates significantly affecting the PK variables in the final model were found. The exposure variables of zimberelimab have no obvious correlations with efficacy and safety, and 360mg Q3W and 480mg Q4W are worthy of further study. This study establishes a PopPK model and analyzes the exposure-response relationship of zimberelimab, which helps to explore the potential for alternative dosing regimens and offers a foundation for optimizing therapeutic strategies for advanced cancer patients through simulation-based methods.

Derivation and validation of the first web-based nomogram to predict the spontaneous pregnancy after reproductive surgery using machine learning models.

Infertility remains a significant global burden over the years. Reproductive surgery is an effective strategy for infertile women. Early prediction of spontaneous pregnancy after reproductive surgery is of high interest for the patients seeking the infertility treatment. However, there are no high-quality models and clinical applicable tools to predict the probability of natural conception after reproductive surgery. The eligible data involving 1013 patients who operated for infertility between June 2016 and June 2021 in Yantai Yuhuangding Hospital in China, were randomly divided into training and internal testing cohorts. 195 subjects from the Linyi People's Hospital in China were considered for external validation. Both univariate combining with multivariate logistic regression and the least absolute shrinkage and selection operator (LASSO) algorithm were performed to identify independent predictors. Multiple common machine learning algorithms, namely logistic regression, decision tree, random forest, support vector machine, k-nearest neighbor, and extreme gradient boosting, were employed to construct the predictive models. The optimal model was verified by evaluating the model performance in both the internal and external validation datasets. Six clinical indicators, including female age, infertility type, duration of infertility, intraoperative diagnosis, ovulation monitoring, and anti-Müllerian hormone (AMH) level, were screened out. Based on the logistic regression model's superior clinical predictive value, as indicated by the area under the receiver operating characteristic curve (AUC) in both the internal (0.870) and external (0.880) validation sets, we ultimately selected it as the optimal model. Consequently, we utilized it to generate a web-based nomogram for predicting the probability of spontaneous pregnancy after reproductive surgery. Furthermore, the calibration curve, Hosmer-Lemeshow (H-L) test, the decision curve analysis (DCA) and clinical impact curve analysis (CIC) demonstrated that the model has superior calibration degree, clinical net benefit and generalization ability, which were confirmed by both internal and external validations. Overall, our developed first nomogram with online operation provides an early and accurate prediction for the probability of natural conception after reproductive surgery, which helps clinicians and infertile couples make sensible decision of choosing the mode of subsequent conception, natural or IVF, to further improve the clinical practices of infertility treatment.