Pre-processing Parameters Research Articles

An optimized deep hybrid learning for multi-channel EEG-based driver drowsiness detection

Driver drowsiness is a severe issue that has contributed to numerous fatal accidents and injuries. Thus, detecting driver drowsiness is an important task that has been the subject of intensive research in recent years. There have been numerous proposed physiological signals for detecting driver drowsiness. However, the Electroencephalographic (EEG) signal is the most commonly used due to its direct relationship with drowsiness and its simplicity of acquisition. Recently, different Machine Learning (ML) and Deep Learning (DL) models have been proposed to detect driver drowsiness. This study utilized a publicly accessible dataset containing twelve healthy participants. Reading numerous research papers, we determined no specific EEG-based drowsiness preprocessing parameter values. Consequently, as a first step, and for the first time, to our knowledge in this field, we applied an optimization algorithm to determine the optimal preprocessing parameter values using a CNN model and accuracy as the objective function. The obtained results demonstrated the importance of selecting the correct values, as the mean accuracy score increased from 91% before optimization to 95% after optimization for the proposed CNN. The training time has been reduced. Also, as a second step, we have used the Optuna Hyperparameter optimization framework to select the optimal CNN Hyperparameters, which increased the mean accuracy from 95% to 97%. Finally, to take advantage of Deep Hybrid learning, we have fused the CNN “features extractor” with seven ML classifiers, with the CNN-SVM classifier achieving the highest average accuracy of 99.9%, and the training time has been reduced to a shallow value.

Texture analysis of contrast enhancement CT in the differential diagnosis of tumor and tumor-like cystic lesions of the pancreas: possibilities in texture preprocessing and various segmentation parameters

Texture analysis of contrast enhancement CT in the differential diagnosis of tumor and tumor-like cystic lesions of the pancreas: possibilities in texture preprocessing and various segmentation parameters

Impact of Preprocessing Parameters in Medical Imaging-Based Radiomic Studies: A Systematic Review.

Lately, radiomic studies featuring the development of a signature to use in prediction models in diagnosis or prognosis outcomes have been increasingly published. While the results are shown to be promising, these studies still have many pitfalls and limitations. One of the main issues of these studies is that radiomic features depend on how the images are preprocessed before their computation. Since, in widely known and used software for radiomic features calculation, it is possible to set these preprocessing parameters before the calculation of the radiomic feature, there are ongoing studies assessing the stability and repeatability of radiomic features to find the most suitable preprocessing parameters for every used imaging modality. We performed a comprehensive literature search using four electronic databases: PubMed, Cochrane Library, Embase, and Scopus. Mesh terms and free text were modeled in search strategies for databases. The inclusion criteria were studies where preprocessing parameters' influence on feature values and model predictions was addressed. Records lacking information on image acquisition parameters were excluded, and any eligible studies with full-text versions were included in the review process, while conference proceedings and monographs were disregarded. We used the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to investigate the risk of bias. We synthesized our data in a table divided by the imaging modalities subgroups. After applying the inclusion and exclusion criteria, we selected 43 works. This review examines the impact of preprocessing parameters on the reproducibility and reliability of radiomic features extracted from multimodality imaging (CT, MRI, CBCT, and PET/CT). Standardized preprocessing is crucial for consistent radiomic feature extraction. Key preprocessing steps include voxel resampling, normalization, and discretization, which influence feature robustness and reproducibility. In total, 44% of the included works studied the effects of an isotropic voxel resampling, and most studies opted to employ a discretization strategy. From 2021, several studies started selecting the best set of preprocessing parameters based on models' best performance. As for comparison metrics, ICC was the most used in MRI studies in 58% of the screened works. From our work, we highlighted the need to harmonize the use of preprocessing parameters and their values, especially in light of future studies of prospective studies, which are still lacking in the current literature.

Enhancing Explainability in Predictive Maintenance : Investigating the Impact of Data Preprocessing Techniques on XAI Effectiveness

In predictive maintenance, the complexity of the data often requires the use of Deep Learning models. These models, called “black boxes”, have proved their worth in predicting the Remaining Useful Life (RUL) of industrial machines. However, the inherent opacity of these models requires the incorporation of post-hoc explanation methods to enhance transparency. The quality of the explanations provided is then assessed using so-called evaluation metrics. Modeling is a whole process that includes an important data preprocessing phase, with parameter selection such as time window, smoothing parameter, or rectified RUL when dealing with multivariate time series dataset. We propose to analyze the impact of these preprocessing methods on the quality of explanations provided by the local post-hoc models LIME, KernelSHAP, and L2X, utilizing six evaluation metrics: stability, consistency, congruence, selectivity, completeness, and acumen. This analysis will be based on NASA's Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset with the LSTM model. Our findings reveal that the choice of specific pre-processing parameters can significantly improve predictive performance. Furthermore, the quality of explanations depends on the selection of explicability methods. In addition, a factorial analysis of the evaluation metrics reveals that they do not all point in the same direction.Indeed, understanding the nuanced relationships between evaluation metrics is essential for a comprehensive and accurate assessment of explainability methods.

Effects of three different powder pre-processing and two-step sintering processes on the microstructure and mechanical properties of Cu–Sn–Ti porous matrix materials

It is difficulty to utilize the pore formation function of TiH2 in the copper-based matrices of diamond tools due to the mismatch between dehydrogenation temperature and densification temperature. In this study, Cu–Sn–Ti porous materials were prepared by innovative powder pre-processing and two-step sintering processes. The results showed that Cu–Sn–TiH2 powder with uniform composition, high alloying degree and high TiH2 retention rate were achieved by optimizing pre-processing parameters. During the subsequent sintering process, Sn and Ti elements were precipitated from the copper matrix, leading to the formation of Ti-rich phases at grain boundaries and pore walls. Simultaneously, pores with higher sphericity and uniform distribution were formed due to the thermal decomposition of TiH2. The porosity, average pore size, bending strength, and bending elastic modulus of Cu–Sn–Ti porous material were measured as 30.6%, 2.15 μm, 245 MPa, and 2.23 GPa, respectively. The comprehensive properties were better than the reported results.

Investigation on three-dimensional printed prosthetics leg sockets coated with different reinforcement materials: analysis on mechanical strength and microstructural

Previous research has primarily focused on pre-processing parameters such as design, material selection, and printing techniques to improve the strength of 3D-printed prosthetic leg sockets. However, these methods fail to address the major challenges that arise post-printing, namely failures at the distal end of the socket and susceptibility to shear failure. Addressing this gap, the study aims to enhance the mechanical properties of 3D-printed prosthetic leg sockets through post-processing techniques. Fifteen PLA + prosthetic leg sockets are fabricated and reinforced with four materials: carbon fiber, carbon-Kevlar fiber, fiberglass, and cement. Mechanical and microstructural properties of the sockets are evaluated through axial compression testing and scanning electron microscopy (SEM). Results highlight superior attributes of cement-reinforced sockets, exhibiting significantly higher yield strength (up to 89.57% more than counterparts) and higher Young’s modulus (up to 76.15% greater). SEM reveals correlations between microstructural properties and socket strength. These findings deepen the comprehension of 3D-printed prosthetic leg socket post-processing, presenting optimization prospects. Future research can focus on refining fabrication techniques, exploring alternative reinforcement materials, and investigating the long-term durability and functionality of post-processed 3D-printed prosthetic leg sockets.

Exploring Latent Dirichlet Allocation (LDA) in Topic Modeling: Theory, Applications, and Future Directions

In an era dominated by an unprecedented deluge of textual information, the need for effective methods to make sense of large datasets is more pressing than ever. This article takes a pragmatic approach to unraveling the intricacies of topic modeling, with a specific focus on the widely used Latent Dirichlet Allocation (LDA) algorithm. The initial segment of the article lays the groundwork by exploring the practical relevance of topic modeling in real-world scenarios. It addresses the everyday challenges faced by researchers and professionals dealing with vast amounts of unstructured text, emphasizing the potential of topic modeling to distill meaningful insights from seemingly chaotic data. Moving beyond theoretical abstraction, the article then delves into the mechanics of Latent Dirichlet Allocation. Developed in 2003 by Blei, Ng, and Jordan, LDA provides a probabilistic framework to identify latent topics within documents. The article takes a step-by-step approach to demystify LDA, offering a practical understanding of its components and the Bayesian principles governing its operation. A significant portion of the article is dedicated to the practical implementation of LDA. It provides insights into preprocessing steps, parameter tuning, and model evaluation, offering readers a hands-on guide to applying LDA in their own projects. Real-world examples and case studies showcase how LDA can be a valuable tool for tasks such as document clustering, topic summarization, and sentiment analysis. However, the journey through LDA is not without challenges, and the article candidly addresses these hurdles. Topics such as determining the optimal number of topics, the sensitivity of results to parameter settings, and the interpretability of outcomes are discussed. This realistic appraisal adds depth to the article, helping readers navigate the nuances and potential pitfalls of employing LDA in practice. Beyond the technical intricacies, the article explores the broad spectrum of applications where LDA has proven its efficacy. From text mining and information retrieval to social network analysis and healthcare informatics, LDA has left an indelible mark on diverse domains. Through practical examples, the article illustrates how LDA can be adapted to different contexts, showcasing its versatility as a tool for uncovering latent patterns. Keywords: Topic Modeling, Latent Dirichlet Allocation, Text Mining, Natural Language Processing, Document Clustering, Bayesian Inference.

Investigation of mechanical properties of luffa fibre reinforced natural rubber composites: Implications of process parameters

Natural fiber-reinforced composite materials are highly beneficial due to their excellent strength-to-weight ratio, and the compression molding process is frequently used to prepare natural fiber composites. The primary objective of the present work is to optimize the process parameters of the compression molding method to prepare luffa fiber-reinforced natural rubber composite and investigate the influence of process parameters on mechanical properties. Pre-processing parameters, specifically oven-dry temperature and time, processing parameters such as soaking temperature, time, and compression pressure, and post-processing parameters, such as oven-dry temperature and time, were considered to optimize. Natural rubber in its latex phase is utilized as a matrix material, and luffa fiber is used as reinforcement. The Plackett-Burman screening design technique was employed to identify the impact of different processing parameters on the mechanical properties of the luffa fiber-reinforced natural rubber (LNR) composite, and based on Taguchi's design of experiments, several process parameters were utilized to create L27 orthogonal array and the mentioned composites prepared accordingly. The ASTM standard is followed while testing the composite samples to determine their density, shore A hardness, and tensile strength. The density of the composite is unaffected by the process parameters; however, the shore A hardness of the composite is significantly affected. All the processing parameters most significantly impacted the tensile strength of LNR composites. The optimized process parameters for preparing LNR composite are the pre-oven temperature of 65 °C and time of 150min, the soaking temperature of 75 °C and time of 5min, compression pressure of 1.5 MPa, and the post-oven dry temperature of 55 °C and time of 45min. LNR composite can absorb energy due to its rubber matrix, making it useful for high-impact applications.

Sodium fluoride preserves blood metabolite integrity for biomarker discovery in large-scale, multi-site metabolomics investigations.

Background: Metabolite profiling of blood by nuclear magnetic resonance (NMR) is invaluable to clinical biomarker discovery. To ensure robustness, biomarkers require validation in large cohorts and across multiple centres. However, collection procedures are known to impact on the stability of biofluids that may, in turn, degrade biomarker signals. We trialled three blood collection tubes with the aim of solving technical challenges due to preanalytical variation in blood metabolite levels that are common in cohort studies. Methods: We first investigated global NMR-based metabolite variability between biobanks, including the large-scale UK Biobank and TwinsUK biobank of the general UK population, and more targeted biobanks derived from multicentre clinical trials relating to inflammatory bowel disease. We then compared the blood metabolome of 12 healthy adult volunteers when collected into either sodium fluoride/potassium oxalate, lithium heparin, or serum blood tubes using different pre-processing parameters. Results: Preanalytical variation in the method of blood collection strongly influences metabolite composition within and between biobanks. This variability can largely be attributed to glucose and lactate. In the healthy control cohort, the fluoride oxalate collection tube prevented fluctuation in glucose and lactate levels for 24 hours at either 4 °C or room temperature (20 °C). Conclusions: Blood collection into a fluoride oxalate collection tube appears to preserve the blood metabolome with delayed processing up to 24 hours at 4 °C. This method may be considered as an alternative when rapid processing is not feasible.

Magnetic resonance imaging preprocessing and radiomic features for classification of autosomal dominant polycystic kidney disease genotype.

Our study aims to investigate the impact of preprocessing on magnetic resonance imaging (MRI) radiomic features extracted from the noncystic kidney parenchyma of patients with autosomal dominant polycystic kidney disease (ADPKD) in the task of classifying PKD1 versus PKD2 genotypes, which differ with regard to cyst burden and disease outcome. The effect of preprocessing on radiomic features was investigated using a single T2-weighted fat saturated (T2W-FS) MRI scan from PKD1 and PKD2 subjects (29 kidneys in total) from the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease study. Radiomic feature reproducibility using the intraclass correlation coefficient (ICC) was computed across MRI normalizations (-score, reference-tissue, and original image), gray-level discretization, and upsampling and downsampling pixel schemes. A second dataset for genotype classification from 136 subjects T2W-FS MRI images previously enrolled in the HALT Progression of Polycystic Kidney Disease study was matched for age, gender, and Mayo imaging classification class. Genotype classification was performed using a logistic regression classifier and radiomic features extracted from (1)the noncystic kidney parenchyma and (2)the entire kidney. The area under the receiver operating characteristic curve (AUC) was used to evaluate the classification performance across preprocessing methods. Radiomic features extracted from the noncystic kidney parenchyma were sensitive to preprocessing parameters, with varying reproducibility depending on the parameter. The percentage of features with good-to-excellent ICC scores ranged from 14% to 58%. AUC values ranged between 0.47 to 0.68 and 0.56 to 0.73 for the noncystic kidney parenchyma and entire kidney, respectively. Reproducibility of radiomic features extracted from the noncystic kidney parenchyma was dependent on the preprocessing parameters used, and the effect on genotype classification was sensitive to preprocessing parameters. The results suggest that texture features may be indicative of genotype expression in ADPKD.

An explainable AI framework for robust and transparent data-driven wind turbine power curve models

In recent years, increasingly complex machine learning methods have become state-of-the-art in modelling wind turbine power curves based on operational data. While these methods often exhibit superior performance on test sets, they face criticism due to a perceived lack of transparency and concerns about their robustness in dynamic, non-stationary environments encountered by wind turbines. In this work, we address these issues and present a framework that leverages explainable artificial intelligence methods to gain systematic insights into data-driven power curve models. At its core, we propose a metric to quantify how well a learned model strategy aligns with the underlying physical principles of the problem. This novel tool enables model validation beyond the conventional error metrics in an automated manner. We demonstrate, for instance, its capacity as an indicator for model generalization even when limited data is available. Moreover, it facilitates understanding how decisions made during the machine learning development process, such as data selection, pre-processing, or training parameters, affect learned strategies. As a result, we obtain physically more reasonable models, a prerequisite not only for robustness but also for meaningful insights into turbine operation by domain experts. The latter, we illustrate in the context of wind turbine performance monitoring. In summary, the framework aims to guide researchers and practitioners alike toward a more informed selection and utilization of data-driven wind turbine power curve models.

Feasibility study of assessing cotton fiber maturity from near infrared hyperspectral imaging technique

BackgroundFiber maturity is a key cotton quality property, and its variability in a sample impacts fiber processing and dyeing performance. Currently, the maturity is determined by using established protocols in laboratories under a controlled environment. There is an increasing need to measure fiber maturity using low-cost (in general less than $20 000) and small portable systems. In this study, a laboratory feasibility was performed to assess the ability of the shortwave infrared hyperspectral imaging (SWIR HSI) technique for determining the conditioned fiber maturity, and as a comparison, a bench-top commercial and expensive (in general greater than $60 000) near infrared (NIR) instrument was used.ResultsAlthough SWIR HSI and NIR represent different measurement technologies, consistent spectral characteristics were observed between the two instruments when they were used to measure the maturity of the locule fiber samples in seed cotton and of the well-defined fiber samples, respectively. Partial least squares (PLS) models were established using different spectral preprocessing parameters to predict fiber maturity. The high prediction precision was observed by a lower root mean square error of prediction (RMSEP) (< 0.046), higher Rp2 (> 0.518), and greater percentage (97.0%) of samples within the 95% agreement range in the entire NIR region (1 000∼2 500 nm) without the moisture band at 1 940 nm.ConclusionSWIR HSI has a good potential for assessing cotton fiber maturity in a laboratory environment.

The impact of pre-processing and disease characteristics on reproducibility of T2-weighted MRI radiomics features

PurposeTo evaluate the reproducibility of radiomics features derived via different pre-processing settings from paired T2-weighted imaging (T2WI) prostate lesions acquired within a short interval, to select the setting that yields the highest number of reproducible features, and to evaluate the impact of disease characteristics (i.e., clinical variables) on features reproducibility.Materials and methodsA dataset of 50 patients imaged using T2WI at 2 consecutive examinations was used. The dataset was pre-processed using 48 different settings. A total of 107 radiomics features were extracted from manual delineations of 74 lesions. The inter-scan reproducibility of each feature was measured using the intra-class correlation coefficient (ICC), with ICC values > 0.75 considered good. Statistical differences were assessed using Mann–Whitney U and Kruskal–Wallis tests.ResultsThe pre-processing parameters strongly influenced the reproducibility of radiomics features of T2WI prostate lesions. The setting that yielded the highest number of features (25 features) with high reproducibility was the relative discretization with a fixed bin number of 64, no signal intensity normalization, and outlier filtering by excluding outliers. Disease characteristics did not significantly impact the reproducibility of radiomics features.ConclusionThe reproducibility of T2WI radiomics features was significantly influenced by pre-processing parameters, but not by disease characteristics. The selected pre-processing setting yielded 25 reproducible features.

Robust phenotyping of highly multiplexed tissue imaging data using pixel-level clustering

While technologies for multiplexed imaging have provided an unprecedented understanding of tissue composition in health and disease, interpreting this data remains a significant computational challenge. To understand the spatial organization of tissue and how it relates to disease processes, imaging studies typically focus on cell-level phenotypes. However, images can capture biologically important objects that are outside of cells, such as the extracellular matrix. Here, we describe a pipeline, Pixie, that achieves robust and quantitative annotation of pixel-level features using unsupervised clustering and show its application across a variety of biological contexts and multiplexed imaging platforms. Furthermore, current cell phenotyping strategies that rely on unsupervised clustering can be labor intensive and require large amounts of manual cluster adjustments. We demonstrate how pixel clusters that lie within cells can be used to improve cell annotations. We comprehensively evaluate pre-processing steps and parameter choices to optimize clustering performance and quantify the reproducibility of our method. Importantly, Pixie is open source and easily customizable through a user-friendly interface.

Detection of Oriented Scene Text in Natural Images

Recently, in the field of computer vision, people are paying more attention to extracting and understanding text information in natural scenes, which are widely used in real life, such as image OCR, image retrieval, and multi-language translation. Text detection plays a vital role in the process of text information extraction and understanding. Diverse text patterns and highly cluttered backgrounds are the main challenges of precise text detection. This paper studies oriented scene text detection, the horizontal scene text detector, and CTPN network architecture, which is improved and extended for oriental scene text detection. The main proposed improvements include: 1. The pre-processing method and parameter setting in the post-processing are improved to make the annotation more accurate; 2. The anchor mechanism is improved by setting a series of different anchor widths depending on the anchor heights instead of the fixed width. The improved model was trained with the training set of ICDAR2015 and part of ICDAR2017 MLT. Then it was tested on the ICDAR online platform with test sets of ICDAR2013 and ICDAR2015. Finally, it was tested with some images outside the datasets. The results show that the improved model can detect text with a tilt angle more precisely.

An Introduction to Bayesian Knowledge Tracing with pyBKT

This study aims to introduce Bayesian Knowledge Tracing (BKT), a probabilistic model used in educational data mining to estimate learners’ knowledge states over time. It also provides a practical guide to estimating BKT models using the pyBKT library available in Python. The first section presents an overview of BKT by explaining its theoretical foundations and advantages in modeling individual learning processes. In the second section, we describe different variants of the standard BKT model based on item response theory (IRT). Next, we demonstrate the estimation of BKT with the pyBKT library in Python, outlining data pre-processing steps, parameter estimation, and model evaluation. Different cases of knowledge tracing tasks illustrate how BKT estimates learners’ knowledge states and evaluates prediction accuracy. The results highlight the utility of BKT in capturing learners’ knowledge states dynamically. We also show that the model parameters of BKT resemble the parameters from logistic IRT models.

Effect of preprocessing and simulation parameters on the performance of molecular docking studies.

Molecular docking is an important and rapid tool that provides a comprehensive view of different molecular mechanisms. It is often used to verify the binding interactions of many pairs of molecules and is much faster than more rigorous approaches. However, its application requires carefully preprocessing each molecule and selecting a series of simulation parameters, which is not always done correctly. We show how preprocessing and simulation parameters can positively or negatively impact molecular docking performance. For example, the inclusion of hydrogen atoms leads to better redocking scores, but molecular dynamics simulations must be performed under certain constraints; otherwise, it may worsen performance rather than improve it. This study clarifies the importance and influence of these different parameters in the simulation results. We analyzed the influence of different parameters on the predictive ability of molecular docking techniques using two software packages: AutoDock Vina and AutoDock-GPU. Thus, 90 receptor-ligand complexes were redocked, evaluating the root mean square deviation (RMSD) between the original position of the ligand (receptor-ligand complex obtained experimentally) and that obtained by the software for every analysis. We investigated the influence of hydrogen atoms (on the receptor and on the receptor-ligand complex), partial charges (QEq, QTPIE, EEM, EEM2015ha, MMFF94, Gasteiger-Marsili, and no charge), search boxes (size and exhaustiveness), ligand characteristics (size and number of torsions), and the use of molecular dynamics (of the receptor or the receptor-ligand complex) before docking analyses.

Coefficient Extraction of SAC305 Solder Constitutive Equations Using Equation-Informed Neural Networks.

Equation-Informed Neural Networks (EINNs) are developed as an efficient method for extracting the coefficients of constitutive equations. Subsequently, numerical Bayesian Inference (BI) iterations were applied to estimate the distribution of these coefficients, thereby further refining them. We could generate coefficients optimally aligned with the targeted application scenario by carefully adjusting pre-processing mapping parameters and identifying dataset preferences. Leveraging graphical representation techniques, the EINNs formulation is implemented in temperature- and strain-rate-dependent hyperbolic Garofalo, Anand, and Chaboche constitutive models to extract the corresponding coefficients for lead-free SAC305 solder material. The performance of the EINNs-based extracted coefficients, obtained from experimental results of SAC305 solder material, is comparable to existing studies. The methodology offers the dual advantage of providing the coefficients' value and distribution against the training dataset.

Improving the Accuracy of Spiking Neural Networks for Radar Gesture Recognition Through Preprocessing.

Event-based neural networks are currently being explored as efficient solutions for performing AI tasks at the extreme edge. To fully exploit their potential, event-based neural networks coupled to adequate preprocessing must be investigated. Within this context, we demonstrate a 4-b-weight spiking neural network (SNN) for radar gesture recognition, achieving a state-of-the-art 93% accuracy within only four processing time steps while using only one convolutional layer and two fully connected layers. This solution consumes very little energy and area if implemented in event-based hardware, which makes it suited for embedded extreme-edge applications. In addition, we demonstrate the importance of signal preprocessing for achieving this high recognition accuracy in SNNs compared to deep neural networks (DNNs) with the same network topology and training strategy. We show that efficient preprocessing prior to the neural network is drastically more important for SNNs compared to DNNs. We also demonstrate, for the first time, that the preprocessing parameters can affect SNNs and DNNs in antagonistic ways, prohibiting the generalization of conclusions drawn from DNN design to SNNs. We demonstrate our findings by comparing the gesture recognition accuracy achieved with our SNN to a DNN with the same architecture and similar training. Unlike previously proposed neural networks for radar processing, this work enables ultralow-power radar-based gesture recognition for extreme-edge devices.

Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis

Objective. The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data. Approach. We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification. Main results. Our method improved the macro F1 score of the state-of-the-art model in two independent datasets, from St. Anne’s University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively. Significance. By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar’s test, p ≪ 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models’ performance.