Development Of Model Research Articles

Patients’ Preferences for Models of Follow-Up Care During or After Initial Cancer Treatment in Greece: Development of the Qualitative Phase, and Protocol for a Discrete Choice Experiment

Cancer survivors face a range of physical symptoms, emotional and practical difficulties, and late and long-term effects of treatment. Follow-up care aims to monitor the effectiveness and safety of treatments, and detect recurrence or metastasis. However, survivorship care extends beyond clinical aspects, and should include all forms of necessary support, such as psychological, informational, and practical assistance. The European Cancer Patient’s Bill of Rights emphasises patient-centred care, and the right to access information, receive personalised care, participate in decision-making, and receive psychological and social support. There are national plans for cancer care in place in Greece, and it is essential to acknowledge patient preferences and the acceptability of emerging plans for the ever-expanding population of survivors of cancer. A discrete choice experiment (DCE) will be conducted to identify and quantify the preferences of Greek patients with cancer towards a care model that reflects the current state of cancer care, while also providing valuable insights into what patients consider important. By understanding patients’ preferences, the study aims to identify areas for improvement, and contribute to the development of more patient-centred care models in Greece. This study will mark the first systematic measurement and quantification of preferences of patients with cancer in the Greek context. This paper presents the development of the qualitative phase of the DCE, which focused on identifying the characteristics that are both important and relevant to patients with cancer. Further, it outlines the protocol for the subsequent stages of the study, which involve the DCE experimental design, the data collection, and analysis and dissemination of the findings.

Investigation of Antibody Pharmacokinetics in the Brain Following Intra-CNS Administration and Development of PBPK Model to Characterize the Data.

Despite the promising potential of direct central nervous system (CNS) antibody administration to enhance brain exposure, there remains a significant gap in understanding the disposition of antibodies following different intra-CNS injection routes. To bridge this knowledge gap, this study quantitatively investigated the brain pharmacokinetics (PK) of antibodies following intra-CNS administration. The microdialysis samples from the striatum (ST), cerebrospinal fluid (CSF) samples through cisterna magna (CM) puncture, plasma, and brain homogenate samples were collected to characterize the pharmacokinetics (PK) profiles of a non-targeting antibody, trastuzumab, following intracerebroventricular (ICV), intracisternal (ICM), and intrastriatal (IST) administration. For a comprehensive analysis, these intra-CNS injection datasets were juxtaposed against our previously acquired intravenous (IV) injection data obtained under analogous experimental conditions. Our findings highlighted that direct CSF injections, either through ICV or ICM, resulted in ~ 5-6-fold higher interstitial fluid (ISF) drug exposure than IV administration. Additionally, the low bioavailability observed following IST administration indicates the existence of a local degradation process for antibody elimination in the brain ISF along with the ISF bulk flow. The study further refined a physiologically based pharmacokinetic (PBPK) model based on new observations by adding the perivascular compartments, oscillated CSF flow, and the nonspecific uptake and degradation of antibodies by brain parenchymal cells. The updated model can well characterize the antibody PK following systemic and intra-CNS administration. Thus, our research offers quantitative insight into antibody brain disposition pathways and paves the way for determining optimal dosing and administration strategies for antibodies targeting CNS disorders.

A variational PDNet network using a learning reaction–diffusion equation

Due to their high performance in modeling and forecasting a large amount of real-world complex phenomena, deep convolutional neural networks have received a great deal of attention over the past ten years. It has been extensively utilized in several recent vision problems, such as image denoising and deblurring. By incorporating recent developments in learning-based nonlinear diffusion models and highlighting the connection between partial differential equations (PDEs) and networks, especially residual networks, we propose a flexible learning reaction–diffusion system with spatially computed convolution kernels. This trained PDE is employed to prevent the low-level features from deteriorating, which is needed for tasks involving denoising. In fact, we introduce an improved network architecture for a denoising network entitled VPDNet through an optimal control problem. More precisely, the network architecture is governed by an explicit Euler discretization of a reaction–diffusion system. We give the main algorithm to identify the kernel parameters using the Alternating Direction Method of Multipliers (ADMM) combined with a Primal–Dual algorithm. Finally, numerical simulations are provided with appropriate comparisons to demonstrate the efficiency of the elaborated network.

Accurate preoperative prediction of nodal metastasis in papillary thyroid microcarcinoma: Towards optimal management of patients.

To enhance the accuracy in predicting lymph node metastasis (LNM) preoperatively in patients with papillary thyroid microcarcinoma (PTMC), refining the "low-risk" classification for tailored treatment strategies. This study involves the development and validation of a predictive model using a cohort of 1004 patients with PTMC undergoing thyroidectomy along with central neck dissection. The data was divided into a training cohort (n = 702) and a validation cohort (n = 302). Multivariate logistic regression identified independent LNM predictors in PTMC, leading to the construction of a predictive nomogram model. The model's performance was assessed through ROC analysis, calibration curve analysis, and decision curve analysis. Identified LNM predictors in PTMC included age, tumor maximum diameter, nodule-capsule distance, capsular contact length, bilateral suspicious lesions, absence of the lymphatic hilum, microcalcification, and sex. Especially, tumors larger than 7 mm, nodules closer to the capsule (less than 3 mm), and longer capsular contact lengths (more than 1 mm) showed higher LNM rates. The model exhibited AUCs of 0.733 and 0.771 in the training and validation cohorts respectively, alongside superior calibration and clinical utility. This study proposes and substantiates a preoperative predictive model for LNM in patients with PTMC, honing the precision of "low-risk" categorization. This model furnishes clinicians with an invaluable tool for individualized treatment approach, ensuring better management of patients who might be proposed observation or ablative options in the absence of such predictive information.

Electro-thermal performance evaluation of a prismatic battery pack for an electric vehicle

Abstract In recent years, electric vehicles (EVs) have grown in popularity as a viable way to reduce greenhouse gas emissions by replacing conventional vehicles. The need for EV batteries is steadily increasing. An essential and expensive part of electric transportation is the battery. The operating temperature of the lithium-ion (Li-ion) battery significantly impacts the performance of the EV battery pack. Battery packs undergo temperature fluctuations during the charging and discharging procedures due to internal heat generation, necessitating an examination of the temperature distribution of the battery pack. The geometrical spacing between cells is considered larger and identical and is kept open on two sides for free air circulation. A novel battery thermal management system (BTMS) design is required to effectively dissipate heat from the prismatic battery pack module. The electro-thermal behaviour of the prismatic Li-ion battery pack module was investigated based on the high charge/discharge rate. This study presents the development of a three-dimensional free open-source OpenFOAM computational fluid dynamics model for prismatic cell battery packs that simulates heat generation, air flow field, and temperature distribution across the width and depth of the battery pack module. The prismatic battery pack simulation results are compared with the experimental and simulation results of the cylindrical battery pack. It was also revealed that prismatic cells generate more heat on the backside, requiring battery packs to have increased cooling and space between individual cells to ensure sufficient air circulation for cooling and gas removal. The BTMS is improved by designing with increased space among the prismatic battery cells as compared with the conventional prismatic cell battery pack design.

The role of early cerebral edema and hematoma assessment in aneurysmal subarachnoid hemorrhage (a-SAH) in predicting structural brain abnormalities in cognitive impairments-- case controlled study.

Early assessment and management of cerebral edema and hematoma following aneurysmal subarachnoid hemorrhage (a-SAH) can significantly impact clinical cognitive outcomes. However, current clinical practices lack predictive models to identify early structural brain abnormalities affecting cognition. To address this gap, we propose the development of a predictive model termed the a-SAH Early Brain Edema/Hematoma Compression Neural (Structural Brain) Networks Score System (SEBE-HCNNSS). In this study, 202 consecutive patients with spontaneous a-SAH underwent initial computed tomography (CT) or magnetic resonance imaging (MRI) scans within 24 hours of ictus with follow-up 2 months after discharge. Using logistic regression analysis (univariate and multivariate), we evaluated the association of clinically relevant factors and various traditional scale ratings with cognitive impairment (CI). Risk factors with the highest area under the curve (AUC) values were included in the multivariate analysis and least absolute shrinkage and selection operator (LASSO) analysis or Cox regression analysis. A total of 177 patients were enrolled in the study, and 43 patients were classified with a high SEBE-HCNNSS grade (3 to 5). After a mean follow-up of 2 months, 121 individuals (68.36%) with a-SAH and 3 control subjects developed incident CI. The CT inter-observer reliability of the SEBE-HCNNSS scale was high, with a Kappa value of 1. Furthermore, ROC analysis identified the SEBE-HCNNSS scale (OR 3.322, 95% CI 2.312-7.237, P=0.00025) as an independent predictor of edema, CI, and unfavorable prognosis. These results were also replicated in a validation cohort. Overall, the SEBE-HCNNSS scale represents a simple assessment tool with promising predictive value for CI and clinical outcomes post-a-SAH. Our findings indicate its practical utility as a prognostic instrument for risk evaluation after a-SAH, potentially facilitating early intervention and treatment.

Multi-Task Learning for Design Under Uncertainty With Multi-Fidelity Partially Observed Information

Abstract The assessment of system performance and identification of failure mechanisms in complex engineering systems often requires the use of computation-intensive finite element software or physical experiments, which are both costly and time-consuming. Moreover, when accounting for uncertainties in the manufacturing process, material properties, and loading conditions, the process of reliability-based design optimization (RBDO) for complex engineering systems necessitates the repeated execution of expensive tasks throughout the optimization process. To address this problem, this paper proposes a novel methodology for RBDO. First, a multi-fidelity surrogate modeling strategy is presented, leveraging partially observed information (POI) from diverse sources with varying fidelity and dimensionality to reduce computational cost associated with evaluating expensive high-dimensional complex systems. Second, a multi-task surrogate modeling framework is proposed to address the concurrent evaluation of multiple constraints for each design point. The multi-task framework aids in the development of surrogate models and enhances the effectiveness of reliability analysis and design optimization. The proposed multi-fidelity multi-task machine learning model utilizes a Bayesian framework, which significantly improves the performance of the predictive model and provides uncertainty quantification of the prediction. Additionally, the model provides a highly accurate and efficient framework for reliability-based design optimization through knowledge sharing. The proposed method was applied to two design case studies. By incorporating POI from various sources, the proposed approach improves the accuracy and efficiency of system performance prediction, while simultaneously addressing the cost and complexity associated with the design of complex systems.

Open Science Recommendation Systems for Academic Libraries

An interdisciplinary academic team offers a comprehensive case study describing the development of a predictive model as the cornerstone for an open science recommendation system tailored to the Carnegie Mellon University community. This initiative will empower users in choosing open science services that align with their academic requirements, introduce academics to resources they find valuable, and bridge gaps within academic library service offerings.As an institution with a longstanding commitment to a science-informed approach and a focus on computer science, engineering, and artificial intelligence, Carnegie Mellon University has enthusiastically embraced open science practices. The Carnegie Mellon University’s Libraries has been instrumental in bringing these practices into our academic landscape.The authors strive to develop a predictive model which will evolve into a recommendation system. The pursuit of this endeavor has led the authors through several ethical considerations, such as data privacy, the involvement of student contributors, and the design of a persuasive recommendation system. We are committed to exploring ethical approaches for delivering user-centered recommendations and to preserving individual autonomy.The authors have actively engaged with diverse academic departments, students, and faculty, embarking on data exploration, and applying open science principles throughout the process. The resulting system will raise awareness of library services and deliver tailored recommendations for the adoption of proven research tools and practices.This case study serves as an exemplar of how universities can enact open science principles and develop systems that prioritize the user's interests, navigate institutional complexities to forge interdisciplinary collaboration, and muster resources to support innovative, multi-disciplinary efforts. 

Development and Application of a New Exponential Model for Hydraulic Conductivity with Depth of Rock Mass

Hydraulic conductivity generally decreases with depth in the Earth’s crust. The hydraulic conductivity–depth relationship has been assessed through mathematical models, enabling predictions of hydraulic conductivity in depths beyond the reach of direct measurements. However, it is observed that beyond a certain depth, hydraulic conductivity tends to stabilize; this phenomenon cannot be effectively characterized by the previous models. Thus, these models may make inaccurate predictions at deeper depths. In this work, we introduce an innovative exponential model to effectively assess the conductivity–depth relationship, particularly addressing the stabilization at greater depths. This model, in comparison with an earlier power-like model, has been applied to a globally sourced dataset encompassing a range of lithologies and geological structures. Results reveal that the proposed exponential model outperforms the power-like model in correctly representing the stabilized conductivity, and it well captures the fast stabilization effect of multiple datasets. Further, the proposed model has been utilized to analyze three distinct groups of datasets, revealing how lithology, geological stabilization, and faults impact the conductivity–depth relationship. The hydraulic conductivity decays to the residual hydraulic conductivity in the order (fast to slow): metamorphic rocks, sandstones, igneous rock, mudstones. The mean hydraulic conductivity in stable regions is roughly an order of magnitude lower than unstable regions. The faults showcase a dual role in both promoting and inhibiting hydraulic conductivity. The new exponential model has been successfully applied to a dataset from a specific engineering site to make predictions, demonstrating its practical usage. In the future, this model may serve as a potential tool for groundwater management, geothermal energy collection, pollutant transport, and other engineering projects.

Process Optimization of Spark Plasma Sintered Parameters for Ti-Al-Cr-Nb-Ni-Cu-Co High Entropy Alloy by Response Surface Methodology

In this study, the influence of operating parameters on the relative density and microhardness property of a septenary equiatomic Ti-Al-Cr-Nb-Ni-Cu-Co high entropy alloy developed via spark plasma sintering (SPS) process was investigated at constant heating rate (100 °C/min), dwell time (5 min), pressure (50 MPa). Using response surface methodology (RSM) on the sintering temperature (ST) and milling time (MT) as the process variable parameters, a predictive model was established. The design of experiment approach was employed to minimize numbers of runs of experiment, which invariably eliminates trial by error associated with traditional experimental methods. MT and ST were taken as the variables towards the development of the design model. The optimum operating parameters were predicted using the user-defined design (UDD) under RSM and the result was validated through experiments. Observation from the results shows that MT and ST play a significant role in achieving high densification, which translates to high hardness. At 900 °C ST and MT of 10 hours, the highest hardness value of 580.1 HV, densification of 99.98%, and percentage porosity of 0.02% were recorded.

Hybrid RANS/LES modeling of hypersonic turbulent boundary layers with cold walls

Various strategies for hybrid RANS/LES modeling of hypersonic turbulent boundary layers subjected to strong wall-cooling are developed and analyzed. By defining a turbulent thermal length scale, the eddy viscosity and diffusivity of the hybrid model are calculated by the same formula, ℓ2ω. This allows a similar blending of the length scales and the development of analogous dynamic models for turbulent stress and heat flux. The dynamic procedure is applied to heat transfer by equating norms, rather than invoking least-squares with a lower bound, which improves robustness. The shielding function, as used in detached eddy simulations models, is revised to prevent a spurious early switch from the RANS to the LES mode. This revision significantly improves the accuracy of hybrid models on coarse grids. Finally, the proposed models are tested and validated for Mach numbers between 2.5 and 14, and wall-to-recovery temperature ratios between 0.18 and 1.

Zero-valent iron enhanced methane production of anaerobic digestion by reinforcing microbial electron bifurcation coupled with direct inter-species electron transfer

Zero-valent iron (ZVI) can facilitate methanogens of anaerobic digestion (AD). However, the impact of ZVI on the micro-energetic strategies of AD microorganisms remains uncertain. This study aimed to elucidate the development of an energy conservation model involving direct interspecies electron transfer (DIET) and electron bifurcate (EB) by using four types of ZVI. Overall, the ZVI addition resulted in a substantial increase in methane production (1.26 to 2.18 times higher), and the effect of boron (B) doped ZVI was particularly pronounced. The underlying mechanism may be the formation of energy harvest pathway related to DIET. In detail, B-doped ZVI could enhance its interfacial binding to cytochrome c. Decreased polar solvation energy from 20.473 to 1.509 kJ/mol is beneficial for electron transfer, thereby augmenting the flavin-bounded Cytc activity and DIET process. Besides, ZVI-enhanced EB enzyme activity like HdrA2B2C2-MvhAGD could improve the EB process, which can couple with DIET for electron transfer and energy conservation. Energy analysis based on EB-coupled DIET metabolism pathways demonstrated that the ATP saved in this coupled model theoretically line in 0.25 to 0.5 mol ATP/mol substrate. Overall, this study offers valuable insights into microbial energetic strategies pertaining to the utilization of conductive materials, with the target of enhancing methane recovery efficiency from organic waste.

Tool-pin profile effects on thermal and material flow in friction stir butt welding of AA2219-T87 plates: computational fluid dynamics model development and study

Tool-pin profile effects on thermal and material flow in friction stir butt welding of AA2219-T87 plates: computational fluid dynamics model development and study

Inlet Guide Vane Stagger Effects on Multistage Compressor Performance and Stall Inception

The effects of variable inlet guide vanes on compressors have been evaluated throughout the turbomachinery industry for decades. These vanes improve both the performance and stability of a machine—the extent to which is highly dependent on the individual machine and the conditions of operation. Evaluating their effects on compressor stall inception via experimental investigations can inform model development and validation since commonly used RANS and URANS tools face limitations in accurately predicting and modeling stall events. The current literature on variable inlet guide vane restaggering, however, is dominated by numerical investigations. This study offers a unique experimental investigation into restaggering effects on compressor stall behavior by evaluating experimental results from different variable inlet guide vane stagger angles in a high-pressure axial compressor. Previous investigations have shown that variable inlet guide vane restaggering may change the stall inception mechanism of axial flow compressors. This investigation found a distinct change in the stage matching of the machine without altering the stall inception mechanism, further demonstrating the need for experimental investigations to inform the specific effects that restaggering inlet guide vanes offers comparable compressors.

Abstract B052: Ovarian cancer risk prediction: a systematic assessment of the state of the art and development of a new model

Abstract B052: Ovarian cancer risk prediction: a systematic assessment of the state of the art and development of a new model

Abstract B092: Development of predictive models for expression of a tumor specific biomarker and CD3 on H&E digital slides

Abstract Characterization of a patient’s tumor microenvironment is fundamental to advancing translational strategies in immuno-oncology. Histopathological evaluation of tissue slides from patients can provide this invaluable information, informing disease heterogeneity, tumor contexture, and target expression - all important to identifying patients more likely to benefit from therapy. However, availability of sufficient tissue is often a challenge to produce such a comprehensive tumor characterization. Measurement of target expression using an H&E slide could greatly reduce the usage of tissue for IHC making sections available for other investigative purposes. Here, an AI-driven predictive model was developed on H&E digital slides to simulate the expression of a tumor specific biomarker and CD3 across 4 different tumor types. Four epithelial tumor types (TNBC, NSCLC, ovarian, and cervical cancer) consisted of 400 H&E slides, 400 CD3 slides and 400 tumor specific biomarker IHC slides (100 cases per tumor) were used for this study. The Bio-AI Predict-X platform was utilized for the optimization of separate tumor models using pathology annotations as basis for development. The network output included tumor tiles as well as the tiles from adjacent stromal/normal tissue. Models were optimized until an AUC > 0.8 was achieved and prediction results were approved by the combined pathology teams. Predict-X was used for IHC marker quantification on a tile basis for both CD3 and the tumor specific biomarker slides with significant correlation to manual counts (p<0.001, r>0.8). Images from each case were co-registered so that ground truth for each tile with the IHC count was used in the predictive model. Tiles from tumor and corresponding adjacent stroma/normal tissue from all cases were subdivided into 3 groups for predictive model development. A training, validation, and test set were used, the latter of which was not used for development, only as a final assessment of model performance. A pan-tumor predictive model was developed for CD3 IHC on TNBC, cervical and ovarian cancers. The test set AUC values on cases from all 4 tumors were >0.7. Since the tumor specific biomarker stain was specific to tumor morphology, 4 separate predictive models were developed - one for each of the indications used with a test AUC >0.86. These findings suggest that deep learning can be used as a complementary method to prescreen H&E-stained images to enhance the detection rate of the tumor specific biomarker and CD3 positivity in patient tumors. Additional work will involve the optimization of these models for implementation in a clinical setting. Citation Format: Alan Jerusalmi, Krishna Bairavi, Ayushi Shah, Tom Chittenden, Mike Bonham, Chung-Wein Lee, Brandon Higgs, Anantharaman Muthuswamy. Development of predictive models for expression of a tumor specific biomarker and CD3 on H&E digital slides [abstract]. In: Proceedings of the AACR Special Conference on Ovarian Cancer; 2023 Oct 5-7; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(5 Suppl_2):Abstract nr B092.

Survey on AI Applications for Product Quality Control and Predictive Maintenance in Industry 4.0

Survey on AI Applications for Product Quality Control and Predictive Maintenance in Industry 4.0

Personalized decision support system for tailoring IgA nephropathy treatment strategies

BackgroundThe ongoing debate surrounding the use of immunosuppressive treatments for IgA nephropathy (IgAN) underscores the demand for personalized and effective strategies. MethodsAnalyzed data from 807 IgAN patients over 5+ years using three methods: Random Forest with molecular biomarkers, network biomarkers with graph engineering, and an auto-encoder model. All models were trained using identical demographic, clinical, and pathological data, employing an 80–20 split for training and testing purposes. ResultsIn the comprehensive assessment of IgAN prognosis, the Random Forest model, employing molecular biomarkers, demonstrated strong performance metrics (AUC = 0.83, sensitivity = 0.51, specificity = 0.96). However, traditional graph feature engineering on patient-specific networks outperformed these results with an AUC of 0.90, sensitivity of 0.64, and specificity of 0.94. The Auto-encoder model showed the best accuracy (AUC = 0.91, sensitivity = 0.46, specificity = 0.96). The findings highlighted the superior predictive capabilities of network biomarkers over molecular biomarkers for adverse renal outcome prediction in IgAN. Consequently, we integrated Auto-encoder-derived Network Biomarkers with Random Forest Models to enhance prognostic precision in diverse IgAN treatment scenarios. The prediction for the prognosis of patients receiving supportive care, glucocorticoid therapy, and immunosuppressant treatment yielded AUC values of 0.95, 0.96, and 1, respectively, indicating high specificity. Drawing from these insights, we pioneered the development of an innovative decision support model for IgAN treatment. This model demonstrated the ability to make medical decisions comparable to those by experienced nephrologists, enabling the customization of personalized disease management strategies. ConclusionOur system accurately predicted IgAN prognosis and evaluated various treatment efficacies, aiding physicians in devising optimal therapeutic strategies for patients.

Tree belowground biomass in Congo Basin forests: allometric equations and scaling with aboveground biomass

Abstract Many allometric models to predict tree aboveground biomass have been developed in tropical moist forests, but few models are available for tree belowground biomass. Theory predicts that belowground biomass scales in an isometric way with aboveground biomass. Estimates of belowground biomass could then be derived from aboveground biomass using the root:shoot ratio. Using a dataset of 118 tropical trees for which both aboveground and belowground biomass and other tree and species characteristics were measured in Gabon and Cameroon, we found a near isometric, yet significantly allometric, relationship between belowground biomass (B, in kilograms) and aboveground biomass (A, in kilograms): B = 0.324 A0.939. The root:shoot ratio was 0.20–0.22, regardless of tree size. An efficient model to predict belowground biomass from tree diameter (D, in centimeters), height (H, in meters) and wood density (ρ, in grams per cubic centimeter) was B = 0.0188 (ρD2H)0.977. A significant residual effect of species and leaf habit was found in this model, indicating that further tree and species characteristics are likely to explain additional variation in belowground biomass. Yet, the future development of belowground allometric models can benefit from the many models already developed for aboveground biomass. On the basis of this unprecedented sampling effort on tree belowground biomass in the dense tropical forests of the Congo Basin, we conclude that the scaling of belowground biomass with aboveground biomass should be the relationship to focus on.

Machine Learning Method to Explore the Correlation between Fly Ash Content and Chloride Resistance.

Chloride ion corrosion has been considered to be one of the main reasons for durability deterioration of reinforced concrete structures in marine or chlorine-containing deicing salt environments. This paper studies the relationship between the amount of fly ash and the durability of concrete, especially the resistance to chloride ion erosion. The heat trend map of total chloride ion factor correlation displayed that the ranking of factor correlations was as follows: sampling depth > cement dosage > fly ash dosage. In order to verify the effect of fly ash dosage on chloride ion resistance, three different machine learning algorithms (RF, GBR, DT) are employed to predict the total chloride content of fly ash proportioned concrete with varying admixture ratios, which are evaluated based on R2, MSE, RMSE, and MAE. The results predicted by the RF model show that the threshold of fly ash admixture in chlorinated salt environments is 30-40%. Replacing part of cement with fly ash in the mixture of concrete below this threshold of fly ash, it could change the phase structure and pore structure, which could improve the permeability of fly ash concrete and reduce the content of free chloride ions in the system. Machine learning modeling using sample data can accurately predict concrete properties, which effectively reduce engineering tests. The development of machine learning models is essential for the decarbonization and intelligence of engineering.