Search

This study models milk product processing and sustainable of the shelf-life extension in a dairy factory using artificial intelligence. The Cappadocia dairy factory was used to study chemical processes and computational system modeling and simulation. Levenberg–Marquardt algorithm was used to create an artificial neural network model from real-time data. An AI-based method utilizing a Multilayer Perceptron (MLP) Artificial Neural Network (ANN) model was employed to precisely analyze productivity data in dairy factories. There are 9 product types and production quantities used as input parameters, and 90 datasets of actual dairy products used as output values. The model was trained using the Levenberg–Marquardt algorithm on 62 datasets for training, 14 for validation, and 14 for testing. The accuracy of the model is affected by the optimal data segmentation. The model showed how AI algorithms can improve processes and industrial production by increasing dairy production efficiency from 20 to 40%. Model efficiency values were compared to observed values to determine prediction accuracy. Model mean squared error was 4.02E-06, and coefficient of determination was 0.99984. Model efficiency predictions and observed values differed by −0.04% on average. This study investigated using artificial intelligence to optimize salvage processes and systems to increase energy efficiency and reduce environmental impact. The results show that a neural network model trained with real data can predict dairy plant productivity.

The formulation of heat transfer in non-Newtonian fluid models remains a topic of great interest for researchers. The ultimate flow differential equations in this direction are non-linear and hence difficult to solve analytically. Therefore, we offer state of the art determination of film effectiveness (heat transfer coefficient) by using artificial intelligence (AI). To be more specific, the Carreau fluid model is formulated at a flat surface along with thermal slip, heat generation, velocity slip, chemical reaction, and magnetohydrodynamics (MHD) effects. The developed equations are reduced by the application of the Lie symmetry approach and solved by the shooting method. The artificial neural networking model is built by using 132 sample values of the Nusselt number (NN) as an output. Porosity parameter, Prandtl number, magnetic field parameter, and heat production parameter are all inputs. 92 (70 %) is designated for training, whereas 20 (15 %) is designated for validation and testing. The Levenberg-Marquardt algorithm is used to train the neural network. The constructed artificial neural networking (ANN) is best to predict the NN at a flat surface. It is observed that for large Prandtl numbers, the magnitude of the Nusselt number is greater for porous surface, but the converse is true for magnetic field parameter.

The core objective of this research is to describe the behavior of the distribution using the MLE method to estimate its parameters, as well as to determine the optimal Artificial Neural Network method by comparing it to the maximum likelihood estimation method and applying it to real data for breast cancer patients to determine survival, risk, and other survival study functions of the log-logistic distribution. The parameters were defined in the input layer of the artificial neural network developed for the purpose of survival analysis and reliability function, hazard rate function, probability density function, reserved hazard rate function, Mills ratio, Odd function and CHR values were obtained in the output layer. The findings show that risk function increases with the increase in the time of infection and then decreases for a group of breast cancer patients under study, which corresponds to the theoretical properties of this according to the practical conclusions. The examination of survival analysis reveals that practical conclusions correspond to the theoretical properties of log-logistic distribution. Artificial neural networks have proven to be one of the ideal tools that can be used to predict various vital parameters, especially survival of cancer patients, with their high predictive capabilities.

Shell and helically coiled tube heat exchangers (SHCTHEXs) are heat exchangers that only take up a small space and enable greater heat transfer area compared to traditional models. Information on 21 different SHCTHEXs obtained from catalog was considered for the modeling. Two other artificial neural network structures have been created to forecast the heat transfer coefficient, pressure drop, Nusselt number, and performance evaluation criteria values as outputs. In contrast, tubing and coil diameters, Reynolds and Dean numbers, curvature ratio, and mass flow rate are designed as inputs. In the network structures with 105 data points, 70% of the data was used for training, 15% for validation, and 15% for the testing stages. The Levenberg-Marquardt procedure was evaluated as the training algorithm in multi-layer perceptron network models. The coefficient of determination was as higher than 0.99. The mean deviation was less than 0.01%. The results show that the created artificial neural network structures can acqurately estimate the outputs.

Typically, success in the estimation of machine learning is expected to rise with increasing input parameters, whereas the noise issue may rarely arise owing to redundant input factors undesirably influencing the learning algorithm. The parameters such as overall heat transfer coefficient, pressure drop, and overall cost have been determined by two different artificial neural networks evaluated by a multi-layer perceptron model. Using the Levenberg-Marquardt training algorithm, in the first model input layer, a total of 10 input parameters ρ, np, k1, Re1, fi, Re2, fo, ns, P1 and P2 have been defined, while the second involves 8 input parameters by subtracting pumping powers from the first one, thus the noise issue has been investigated using unnecessary input parameters. Overall heat transfer coefficient, tube/annulus sides pressure drops, and overall cost have been estimated with deviations of 0.16%, 0.23%, 0.02%, and 0.003% via Model 1, 0.02%, 0.18%, 0.16%, and 0.15% via Model 2, respectively. Moreover, Model 1 results in the best mean squared errors for annulus side pressure drop and overall cost with the values of 2.54E-04 and 1.93E-04, correspondingly, whereas Model 2 yields the best values of 1.11E-04 and 1.90E-04 for overall heat transfer coefficient and tube side pressure drop, sequentially.

The regulators for thermal energy transfer, performances of heat exchangers, turbine blades subject to cooling structure, and energy storage procedures claim the use of a heated fluid with partially heated circular obstructions rooted in confined domains. Owing to such importance we consider a partially heated double forward-facing step (DFFS). To be more specific, from the inlet of DFFS, the viscous stream flows in parabolic form and the Neumann condition is implemented at the outlet. At each wall, no slip is incorporated. The mathematical formulation is constructed to narrate the flow field. The translation of the centers of mounted heated obstructions is considered in three separate situations. For every event, the strength of the Nusselt number is debated numerically. For all cases, the drag coefficient for partially heated obstruction is found a decreasing function of the Reynolds number. Besides this, for better estimation of Drag Coefficient (DC) and Lift Coefficient (LC), an artificial neural network (ANN) model with multilayer perceptron (MLP) is developed. MoD values shows that the error rates of the ANN model are very low. The findings show that the constructed ANN model can accurately predict DC and LC values with very low error rates.

Abstract In current investigation, a novel implementation of intelligent numerical computing solver based on multi-layer perceptron (MLP) feed-forward back-propagation artificial neural networks (ANN) with the Levenberg–Marquard algorithm is provided to interpret heat generation/absorption and radiation phenomenon in unsteady electrically conducting Williamson liquid flow along porous stretching surface. Heat phenomenon is investigated by taking convective boundary condition along with both velocity and thermal slip phenomena. The original nonlinear coupled PDEs representing the fluidic model are transformed to an analogous nonlinear ODEs system via incorporating appropriate transformations. A data set for proposed MLP-ANN is generated for various scenarios of fluidic model by variation of involved pertinent parameters via Galerkin weighted residual method (GWRM). In order to predict the (MLP) values, a multi-layer perceptron (MLP) artificial neural network (ANN) has been developed. There are 10 neurons in hidden layer of feed forward (FF) back propagation (BP) network model. The predictive performance of ANN model has been analyzed by comparing the results obtained from the ANN model using Levenberg-Marquard algorithm as the training algorithm with the target values. When the obtained Mean Square Error (MSE), Coefficient of Determination (R) and error rate values have been analyzed, it has been concluded that the ANN model can predict SFC and NN values with high accuracy. According to the findings of current analysis, ANN approach is accurate, effective and conveniently applicable for simulating the slip flow of Williamson fluid towards the stretching plate with heat generation/absorption. The obtained results showed that ANNs are an ideal tool that can be used to predict Skin Friction Coefficients and Nusselt Number values.

Since the previous two years, a new coronavirus (COVID-19) has found a major global problem. The speedy pathogen over the globe was followed by a shockingly large number of afflicted people and a gradual increase in the number of deaths. If the survival analysis of active individuals can be predicted, it will help to contain the epidemic significantly in any area. In medical diagnosis, prognosis and survival analysis, neural networks have been found to be as successful as general nonlinear models. In this study, a real application has been developed for estimating the COVID-19 mortality rates in Italy by using two different methods, artificial neural network modeling and maximum likelihood estimation. The predictions obtained from the multilayer artificial neural network model developed with 9 neurons in the hidden layer were compared with the numerical results. The maximum deviation calculated for the artificial neural network model was −0.14% and the R value was 0.99836. The study findings confirmed that the two different statistical models that were developed had high reliability.

This study focused on the analysis of partial slip effect of Arrhenius activation energy and temperature dependent viscosity on non-Newtonian Maxwell nanofluid bio-convective flow using artificial intelligence approach. Local Nusselt number, local Sherwood number and local density number values, which are dimensionless flow parameters, have been used to examine the said effect. Three different artificial neural network models have been developed using the numerically obtained data sets. Each of the feed forward back propagation multilayer perceptron network models has been developed with different input parameters. 80% of the data set has been used for training the model and 20% for the testing phase. The estimation performance of the network models developed with the Bayesian regularization training algorithm has been extensively analyzed, and the compatibility between the estimation values and the target data has been examined. The findings have shown that artificial neural network models have been developed to make predictions with high accuracy. In addition, artificial neural networks have also proven to be an ideal engineering tool that can be used to analyze the partial slip effect of non-Newtonian Maxwell nanofluids on bio-convective flow.

In this study, the viscous dissipation effects of copper-polyvinyl alcohol (Cu-PVA) Jeffrey nanofluid on magnetohydrodynamic (MHD) heat transfer flow across a stretchable surface have been analyzed with an artificial intelligence approach. The flow parameters, skin friction and Nusselt number, are numerically obtained with a closed Keller-box and partial differential equations converted to a non-linear ordinary differential equation system using the appropriate similarity transformation. Using the obtained data set, two different artificial neural network (ANN) models have been developed. In the multi-layer perceptron (MLP) network model developed with Bayesian Regularization training algorithm, solid volume fraction (φ), Deborah number (β), magnetic parameter (M), Prandtl number (Pr) and Eckert number (Ec) values have been defined as input parameters and skin friction and Nusselt number values ​​have been obtained in the output layer. R values ​​for skin friction and Nusselt number have been calculated as 0.99020 and 0.99394, respectively. The study findings show that the developed ANN model can predict with high accuracy and is a high-performance engineering tool that can be used in modeling viscous dissipation effects.

We have examined the magnetized stagnation point flow of non-Newtonian fluid towards an inclined cylindrical surface. The mixed convection, thermal radiation, viscous dissipation, heat generation, first-order chemical reaction, and temperature-dependent thermal conductivity are the physical effects being carried for better novelty. Mathematical equations are constructed for four different flow regimes. The shooting method is used to evaluate the heat transfer coefficient at the cylindrical surface with and without heat generation/thermal radiation effects. For better examination, we have constructed artificial neural networking models with the aid of the Levenberg–Marquardt training technique and Purelin and Tan-Sig transfer functions. The Nusselt number strength is greater for fluctuations in the Casson fluid parameter, Prandtl number, heat generation, curvature, and Eckert number when thermal radiations are present.

In this article, we constructed an artificial neural networking model for the stagnation point flow of Casson fluid towards an inclined stretching cylindrical surface. The Levenberg–Marquardt training technique is used in multilayer perceptron network models. Tan–Sig and purelin transfer functions are carried in the layers. For better novelty, heat and mass transfer aspects are taken into account. The viscous dissipation, thermal radiations, variable thermal conductivity, and heat generation effects are considered by way of an energy equation while the chemical reaction effect is calculated by use of the concentration equation. The flow is mathematically modelled for magnetic and non-magnetic flow fields. The flow equations are solved by the shooting method and the outcomes are concluded by means of line graphs and tables. The skin friction coefficient is evaluated at the cylindrical surface for two different flow regimes and the corresponding artificial neural networking estimations are presented. The coefficient of determination values’ proximity to one and the low mean squared error values demonstrate that each artificial neural networking model predicts the skin friction coefficient with high accuracy.

In this study, the Casson fluid flow through an inclined, stretching cylindrical surface is considered. The flow field is manifested with pertinent physical effects, namely heat generation, viscous dissipation, thermal radiations, stagnation point flow, variable thermal conductivity, a magnetic field, and mixed convection. In addition, the flow field is formulated mathematically. The shooting scheme is used to obtain the numerical data of the heat transfer coefficient at the cylindrical surface. Further, for comparative analysis, three different thermal flow regimes are considered. In order to obtain a better estimation of the heat transfer coefficient, three corresponding artificial neural networks (ANN) models were constructed by utilizing Tan-Sig and Purelin transfer functions. It was observed that the heat transfer rate exhibits an inciting nature for the Eckert and Prandtl numbers, curvature, and heat generation parameters, while the Casson fluid parameter, temperature-dependent thermal conductivity, and radiation parameter behave oppositely. The present ANN estimation will be helpful for studies related to thermal energy storage that have Nusselt number involvements.

The use of enormous amounts of material is required for production. Due to the current emphasis on the environment and sustainability of materials, waste products and by-products, including silica fume and fly ash (FA), are incorporated into concrete as a substitute partially for cement. Additionally, concrete fine aggregate has indeed been largely replaced by waste materials like crumb rubber (CR), thus it reduces the mechanical properties but improved some other properties of the concrete. To decrease the detrimental effects of the CR, concrete is therefore enhanced with nanomaterials such nano silica (NS). The concrete mechanical properties are essential for the designing and constRuction of concrete structures. Concrete with several variables can have its mechanical characteristics predicted by an artificial neural network (ANN) technique. Using ANN approaches, this paper predict the mechanical characteristics of concrete constructed with FA as a partial substitute for cement, CR as a partial replacement for fine aggregate, and NS as an addition. Using an artificial neural network (ANN) technique, the mechanical characteristics investigated comprise splitting tensile strength (Fs), compressive strength (Fc), modulus of elasticity (Ec) and flexural strength (Ff). The ANN model was used to train and test the dataset obtained from the experimental program. Fc, Fs, Ff and Ec were predicted from added admixtures such as CR, NS, FA and curing age (P). The modelling result indicated that ANN predicted the strength with high accuracy. The proportional deviation mean (MoD) values calculated for Fc, Fs, Ff and Ec values were −0.28%, 0.14%, 0.87% and 1.17%, respectively, which are closed to zero line. The resulting ANN model’s mean square error (MSE) values and coefficient of determination (R2) are 6.45 × 10−2 and 0.99496, respectively.

Nanotechnology is a fundamental component of modern technology. Researchers have concentrated their efforts in recent years on inventing various algorithms to increase heat transmission rates. Using nanoparticles in host fluids to dramatically improve the thermal properties of ordinary fluids is one way to address this problem. The article deals with the bio-convective Walter’s B nanofluid with thermophoresis and Brownian diffusion through a cylindrical disk under artificial neural networks (ANNs). In addition, the thermal conductivity, radiation, and motile density of microorganisms are taken into consideration. The Buongiorno model is utilized to investigate the properties of nanofluids in motile microorganisms. By using appropriate similarity variables, a dimensionless system of a differential system is attained. The non-linear simplified system of equations has been numerically calculated via the Runge–Kutta fourth-order shooting process. The consequences of flow parameters on the velocity field, temperature distribution, species volumetric concentration, and microorganism fields are all addressed. Two distinct artificial neural network models were produced using numerical data, and their prediction performance was thoroughly examined. It is noted that according to the error histograms, the ANN model’s training phase has very little error. Furthermore, mean square error values calculated for local Nusselt number, local Sherwood number, and local motile density number, parameters were obtained as 3.58×10−3, 1.24×10−3, and 3.55×10−5, respectively. Both artificial neural network models can predict with high accuracy, according to the findings of the calculated performance parameters.

The convective heat transfer in non-Newtonian fluid flow in the presence of temperature stratification, heat generation, and heat absorption effects is debated by using artificial neural networking. The heat transfer rate is examined for the four different thermal flow regimes namely (I) thermal flow field towards a flat surface along with thermal radiations, (II) thermal flow field towards a flat surface without thermal radiations, (III) thermal flow field over a cylindrical surface with thermal radiations, and (IV) thermal flow field over a cylindrical surface without thermal radiations. For each regime, a Nusselt number is carried out to construct an artificial neural networking model. The model prediction performance is reported by using varied neuron numbers and input parameters, and the results are assessed. The ANN model is designed by using the Bayesian regularization training procedure, and a high-performing MLP network model is used. The data used in the creation of the MLP network was 80 percent for model training and 20 percent for testing. The graph shows the degree of agreement between the ANN model projected values and the goal values. We discovered that an artificial neural network model can provide high-efficiency forecasts for heat transfer rates having engineering standpoints. For both flat and cylindrical surfaces, the heat transfer normal to the surface reflects inciting nature towards the Prandtl number and heat absorption parameter, while the opposite is the case for the temperature stratification parameter and heat generation parameter. It is important to note that the magnitude of heat transfer is significantly larger for Flow Regime-IV in comparison with Flow Regimes-I, -II, and -III.

For various obstacles in the path of a flowing liquid stream, an artificial neural networking (ANN) model is constructed to study the hydrodynamic force depending on the object. The multilayer perceptron (MLP), back propagation (BP), and feed-forward (FF) network models were employed to create the ANN model, which has a high prediction accuracy and a strong structure. To be more specific, circular-, octagon-, hexagon-, square-, and triangular-shaped cylinders are installed in a rectangular channel. The fluid is flowing from the left wall of the channel by following two velocity profiles explicitly linear velocity and parabolic velocity. The no-slip condition is maintained on the channel upper and bottom walls. The Neumann condition is applied to the outlet. The entire physical design is mathematically regulated using flow equations. The result is presented using the finite element approach, with the LBB-stable finite element pair and a hybrid meshing scheme. The drag coefficient values are calculated by doing line integration around installed obstructions for both linear and parabolic profiles. The values of the drag coefficient are predicted with high accuracy by developing an ANN model toward various obstacles.

In this paper, we study a new model that represents the symmetric connection between capacitance–voltage and Schottky diode. This model has a symmetrical shape towards the horizontal direction. In recent times, works conducted on artificial neural network structure, which is one of the greatest actual artificial intelligence apparatuses used in various fields, stated that artificial neural networks are apparatuses that proposal very high forecast performance by the side of conventional structures. In the current investigation, an artificial neural network structure has been generated to guess the capacitance voltage productions of the Schottky diode with organic polymer edge, contingent on the frequency with a symmetrical shape. Of the dataset, 130 were grouped for training, 28 for validation, and 28 for testing. In order to evaluate the effect of the number of neurons on the prediction accuracy, three different models with different neuron numbers have been developed. This study, in which an artificial neural network model, although well-trained, could not predict the output values correctly, is a first in the literature. With this aspect, the study can be considered as a pioneering study that brings a novelty to the literature.

Purpose: Despite several factors that may have been associated with poor disease-free survival (DFS) in patients with medullary thyroid carcinoma (MTC), only a few studies have evaluated the prognostic factors affecting DFS in MTC patients. Therefore, this study evaluated the prognostic factors affecting DFS, in a large number of patients with MTC., Methods: Patients treated for MTC were retrospectively analyzed. Patients were stratified as having persistent/recurrent disease and no evidence of disease (NOD) at the last follow-up. The factors affecting DFS after the initial therapy and during the follow-up period were investigated., Results: This study comprised 257 patients [females 160 (62.3%), hereditary disease 48 (18.7%), with a mean follow-up time of 66.8 ± 48.5 months]. Persistent/recurrent disease and NOD were observed in 131 (51%) and 126 (49%) patients, respectively. In multivariate analysis, age > 55 (HR: 1.65, p = 0.033), distant metastasis (HR: 2.41, p = 0.035), CTN doubling time (HR: 2.7, p = 0.031), and stage III vs. stage II disease (HR 3.02, p = 0.048) were independent predictors of persistent/recurrent disease. Although 9 (8%) patients with an excellent response after the initial therapy experienced a structural recurrence, the absence of an excellent response was the strongest predictor of persistent/recurrent disease (HR: 5.74, p < 0.001)., Conclusions: The absence of an excellent response after initial therapy is the strongest predictor of a worse DFS. However, a significant proportion of patients who achieve an excellent response could experience a structural recurrence. Therefore, careful follow-up of patients, including those achieving an excellent response is essential., (© 2024. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Introduction: Lymphovascular invasion is an independent prognostic marker in papillary thyroid carcinomas. In addition, integrin β4 is associated with advanced progression and metastasis in many malignancies. We aimed to investigate the relationship between integrin β4 and lymphovascular invasion in papillary thyroid carcinoma., Material and Methods: 73 patients with papillary thyroid cancer (48 patients with lymphovascular invasion and 25 patients without) were included in our study. The immunohistochemical staining score for integrin b4 was evaluated according to the percentage and intensity of staining. The staining intensity was scored as 0 (no staining), 1 (weak staining - light yellow), 2 (medium staining - yellow-brown), and 3 (strong staining - brown). The staining was scored by multiplying the percentage and intensity of staining., Results: The mean percentage of integrin b4 staining was 63.54 ± 22.26% in the group with lymphovascular invasion and 10.2 ± 22.48% in the group without lymphovascular invasion (p < 0.001). When evaluated in terms of staining score, it was found to be 107.08 ± 45.29 in the group with lymphovascular invasion and 16.2 ± 40.03 in the group without lymphovascular invasion (p < 0.001). There was a linear relationship between the percentage of integrin β4 and the staining scores (r² = 0.881; p < 0.001). In the by receiver-operating characteristic (ROC) curve analysis for the cut-off value of the percentage of integrin b4 staining, the area under the curve was found to be 0.916. The cut-off value for the percentage of integrin b4 was found to be 35 (sensitivity 91.7% and specificity 88%) (odds 80.66%)., Conclusions: A significant relationship was found between integrin b4 expression and lymphovascular invasion in papillary thyroid carcinomas. Integrin b4 expression level can be used as a marker to predict the presence of lymphovascular invasion in papillary thyroid carcinomas, especially in large tumours where it may not be possible to sample the entire tumour.

I-131 radioiodine (RAI) ablation removes postoperative residual tissue and facilitates follow-up in low- and intermediate-risk differentiated thyroid cancer (DTC). Although low doses have been reported to be as effective as higher doses for ablation, the doses administered still vary depending on the patient and the practitioner. We aimed to evaluate the ablation efficiency, complications, and length of stay (LOS) of patients with DTC treated with 3 different doses for ablation. Patients with DTC who received RAI therapy were retrospectively reviewed. One hundred thirty patients with low-intermediate-risk, according to American Thyroid Association classification, without known lymph nodes or distant metastases were included. Patients were divided into 3 groups as 30 to 50 mCi, 75 mCi, and 100 mCi. Residue thyroid and salivary glands were evaluated from 9 to 12 months post-RAI I-131 scans. No significant difference was found between groups regarding ablation success (P = .795). In multivariable analyses, pretreatment thyroglobulin (hazard ratio = 0.8, 95% confidence interval 0.601-0.952, P = .017) and anti- thyroglobulin antibody (hazard ratio = 1.0, 95% confidence interval 0.967-0.998, P = .024) were 2 independent predictors of ablation success. The mean LOS was 2.1 ± 0.3, 2.6 ± 0.6, and 2.9 ± 0.4 days, respectively, (P = .001). LOS rates of ≥ 3 days were 13.2%, 54.3%, and 84.8%, respectively. Mild decreases in hemoglobin, white blood cell (WBC), and platelet counts were observed in all groups after 6 weeks without any clinically significant findings. A lower rate of change in WBC counts was observed in the 30 to 50 mCi group compared to others. There was no dose-dependent difference regarding the early complaints questioned. Ablation with 30 to 50 mCi provides benefits such as shorter LOS, better patient comfort, less salivary gland dysfunction, and less WBC suppression, thus reducing costs without decreasing efficacy., Competing Interests: The authors have no funding and conflicts of interest to disclose., (Copyright © 2023 the Author(s). Published by Wolters Kluwer Health, Inc.)

Context: The aims of the study are to compare characteristics of subacute thyroiditis (SAT) related to different etiologies, and to identify predictors of recurrence of SAT and incident hypothyroidism., Methods: This nationwide, multicenter, retrospective cohort study included 53 endocrinology centers in Turkey. The study participants were divided into either COVID-19-related SAT (Cov-SAT), SARS-CoV-2 vaccine-related SAT (Vac-SAT), or control SAT (Cont-SAT) groups., Results: Of the 811 patients, 258 (31.8%) were included in the Vac-SAT group, 98 (12.1%) in the Cov-SAT group, and 455 (56.1%) in the Cont-SAT group. No difference was found between the groups with regard to laboratory and imaging findings. SAT etiology was not an independent predictor of recurrence or hypothyroidism. In the entire cohort, steroid therapy requirement and younger age were statistically significant predictors for SAT recurrence. C-reactive protein measured during SAT onset, female sex, absence of antithyroid peroxidase (TPO) positivity, and absence of steroid therapy were statistically significant predictors of incident (early) hypothyroidism, irrespective of SAT etiology. On the other hand, probable predictors of established hypothyroidism differed from that of incident hypothyroidism., Conclusion: Since there is no difference in terms of follow-up parameters and outcomes, COVID-19- and SARS-CoV-2 vaccine-related SAT can be treated and followed up like classic SATs. Recurrence was determined by younger age and steroid therapy requirement. Steroid therapy independently predicts incident hypothyroidism that may sometimes be transient in overall SAT and is also associated with a lower risk of established hypothyroidism., (© The Author(s) 2023. Published by Oxford University Press on behalf of the Endocrine Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Objective: The role of the tumor microenvironment in tumor progression and treatment response is being investigated for different types of cancer. This study aimed to determine the relationships between tumor microenvironment, histopathology, 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT)-based metabolic parameters, treatment response, and overall survival (OS) in metastatic differentiated thyroid cancer (DTC).  Methods: Metastatic DTC patients who underwent 18F-FDG PET/CT between 2015-2019 were evaluated. Clinicopathological, histopathological features and PET/CT parameters of patients were recorded. Microenvironmental characteristics of the primary tumor, such as mitosis, intratumoral and peritumoral lymphocytosis, intratumoral and peritumoral fibrosis, were evaluated from the tissue samples. The relationships between these factors were statistically analyzed., Results:  Sixty-five patients (38 females, 27 males, age: 49±15 years) were included. Mitosis, intra/peritumoral lymphocytosis, and intra/peritumoral fibrosis were frequent; however, none of them had a statistically significant association with PET-positive metastases, treatment response, or OS. Univariate analysis showed that gender, size, thyroglobulin values, residual thyroid tissue, PET-positive metastases, and maximum standardized uptake value (SUVmax) were significant predictors of OS. At multivariate analysis, PET-positive metastases (HR=-2.65, 95%CI 0.007-0.707, p=0.024) and SUVmax (HR=-2.74, 95%CI 0.006-0.687, p=0.023) were the only independent predictors for OS.  Conclusion: Our study revealed that microenvironmental characteristics of the primary tumor did not show prognostic significance in metastatic DTC. PET-positive metastases and SUVmax levels were the only significant factors that predicted overall survival in DTC. Supporting the results of our study with further studies with a larger sample size may be necessary to determine the relationship between the tumor microenvironment and prognosis in DTC., Competing Interests: The authors have declared that no competing interests exist., (Copyright © 2023, Soyluoglu et al.)