Multiple Classifier Systems Research Articles

Ensemble Classifier Design Based on Perturbation Binary Salp Swarm Algorithm for Classification

Multiple classifier system exhibits strong classification capacity compared with single classifiers, but they require significant computational resources. Selective ensemble system aims to attain equivalent or better classification accuracy with fewer classifiers. However, current methods fail to identify precise solutions for constructing an ensemble classifier. In this study, we propose an ensemble classifier design technique based on the perturbation binary salp swarm algorithm (ECDPB). Considering that extreme learning machines (ELMs) have rapid learning rates and good generalization ability, they can serve as the basic classifier for creating multiple candidates while using fewer computational resources. Meanwhile, we introduce a combined diversity measure by taking the complementarity and accuracy of ELMs into account; it is used to identify the ELMs that have good diversity and low error. In addition, we propose an ECDPB with powerful optimizing ability; it is employed to find the optimal subset of ELMs. The selected ELMs can then be used to form an ensemble classifier. Experiments on 10 benchmark datasets have been conducted, and the results demonstrate that the proposed ECDPB delivers superior classification capacity when compared with alternative methods.

Narrative Review of Classification Systems Describing Laryngeal Vascularity Using Advanced Endoscopic Imaging.

Endoscopic methods are critical in the early diagnosis of mucosal lesions of the head and neck. In recent years, new examination methods and classification systems have been developed and introduced into clinical practice. All of these new techniques target the notion of optical biopsy, which tries to assess the nature of the lesion before histology examination. Many methods suffer from interpretation issues due to subjective interpretation of the findings. Therefore, multiple classification systems have been developed to assist the proper interpretation of mucosal findings and reduce the error rate. They provide various perspectives on the assessment and interpretation of mucosa changes. This article provides a comprehensive and critical view of the available classification systems as well as their advantages and disadvantages.

A SURVEY ON BIOMEDICAL TEXT DOCUMENT CLASSIFICATION

Information extraction, information retrieval, and text classification are only a few of the important study areas that fall under the heading of "bio medical text classification." In order to increase understanding of various information extraction opportunities in the field of data mining, this study analyses several text categorization approaches used in practise, their strengths and shortcomings. We have gathered a dataset with a strong emphasis on three categories, including "Thyroid Cancer," "Lung Cancer," and "Colon Cancer." This essay offers an empirical investigation of a classifier. Benchmarks for biomedical text were used to conduct the experiment. We study many metaheuristic algorithms, including genetic algorithms, particle swarm optimization, firefly, cuckoo, and bat algorithms. The suggested multiple classifier system also outperforms ensemble learning, ensemble pruning, and conventional classification algorithms. In the data we use predict the Biomedical text document classification is whether it's Thyroid Cancer, Lung Cancer, Colon Cancer based on the performed basic EDA, text pre-processing, build different models, such as LogisticRegression, DecisiontreeClassification, RandomForest Classification

A Comparison of Thoracolumbar Injury Classification in Spine Trauma Patients Among Neurosurgeons in East Africa Versus North America.

Background In January 2021, we published findings evaluating the validity of thoracolumbar injury classification and biomechanical approach in the clinical outcome of operative and non-operative treatments. A notable result in our study was patients with unstable burst fractures received an Arbeitsgemeinschaft für Osteosynthesefragen System (AO) score that recommended conservative treatment compared to a Thoracolumbar Injury Classification and Severity Scale (TLICS) score that recommended surgical intervention. We designed a survey to determine reported differences in thoracolumbar injury classification, including the percentage of thoracolumbar spine fractures, type of classification system(s) used, use of classification system by board-certified neurosurgeons and neurosurgical residents, reliance on classification system to guide management, use of MRI in the evaluation of the posterior ligamentous complex, and readmission rate < 90 days at treating facilities. This study aims to determine which areas of neurosurgical practice in spine trauma patients differ among surgeons in North America and EastAfrica, including Ethiopia, Kenya, and Sudan. Multiple classification systems have been proposed to describe thoracolumbar spine injuries. We hypothesized that there would be marked variability in the classification systems used to evaluate thoracolumbar spine injury among neurosurgeons in North America and East Africa. Methods The survey consisted of seven questions and was sent to 440 neurosurgeons practicing on the continents of North America and EastAfrica. Results A total of 67 surgeons responded, 50 from North America and 17 from EastAfrica, including Ethiopia, Kenya, and Sudan. A significant percentage of African respondents reported a higher thoracolumbar spine fracture rate than respondents in North America (53% and 30%, respectively). Regarding the classification system used, 65% of surgeons in EastAfrica reported using TLICS, whereas 62% of surgeons in North America reported using Denis 3-column classification. For patients with spine trauma, surgeons in EastAfrica and North America reported a similar percentage of readmission <90 days (47% and 52%, respectively). Conclusion Our findings vary in spine trauma classification for American and EastAfrican patients and still highlight crucial areas for improvement due to patient load, education, and resource accessibility.

Genome-Wide Methylation and Haplotype-Resolved Aberrant Somatic Hypermutation Patterns in B-Cell Lymphomas

Introduction Diffuse large B-cell lymphoma (DLBCL) is a genetically, phenotypically, and clinically heterogenous disease. Multiple molecular classification systems using either genomic aberrations or gene expression profiles are used to delineate subgroups with shared biology. The cell of origin (COO) gene expression-based classification system stratifies DLBCLs into germinal center B-cell-like (GCB) and activated B-cell-like subgroups of DLBCL. More recently, the double-hit signature (DHITsig) has been used to further stratify GCB DLBCLs into DHITsig+ and DHITsig-, where the former is characterized by a gene expression profile reminiscent of the GC dark zone and inferior outcomes. Currently, patterns of somatic driver mutations can only partially explain the expression of DHITsig in some tumors. Genetic features such as DNA methylation have been shown to be associated with transcriptional repression and altered chromatin structure. We hypothesized that resolving DNA methylation patterns genome-wide using long read whole genome sequencing (LR-WGS) may reveal epigenetic differences associated with differential gene expression profiles within the DHITsig+ and DHITsig- subgroups and in the context of histologic transformation from follicular lymphoma. Methods Whole genome sequencing data of 10 patient samples and 4 cell line GCB DLBCL samples were generated using both short read (SR-WGS; Illumina) and LR-WGS (Oxford Nanopore Technologies, PromethION). The complementary approach combines somatic variant calling from highly accurate SR data with DNA methylation calling from LR data. GCB samples were selected based on the NanoString DLBCL90 assay and further subdivided into DHITsig+ (N=4) and DHITsig- (N=3). RNA sequencing data of 9 patient samples and 3 GCB DLBCL cell lines were generated and analyzed using Salmon and DESeq2. Simple somatic mutations from SR-WGS data were called using an ensemble of somatic variant callers, which confirmed all cases to belong to the EZB genetic subgroup. Methylated bases were called with Nanopolish followed by a differential methylation analysis using the DSS package in R to identify differences in methylation between both subgroups. Differentially methylated regions (DMRs) were annotated for GC B-cell specific superenhancers, CpG islands, and genes. Using WhatsHap and Nanomethphase, heterozygous single nucleotide polymorphisms (SNPs) from SR and LR data were used to phase LRs into haplotypes. Haplotype analyses were performed to determine the phase of aberrant somatic hypermutation (aSHM) and methylation patterns in the context of proximal translocation breakpoints. Results Most DMRs were found to be associated with regulatory regions such as promoters, superenhancers, and CpG islands. We found methylation differences between DHITsig+ and DHITsig- subgroups in 1430 superenhancers known to be active in GC B-cells. Within these superenhancer regions, DHITsig+ tumors were typically hypomethylated relative to DHITsig-. Several DHITsig classifier genes, including WNK2, TNFSF8, and IL21R, had methylation patterns inverted relative to the typical expression pattern (i.e. low methylation with high expression). Similarly, among 633 differentially methylated promoters, several including TCF3 and WNK2 demonstrated the same inverted methylation pattern. CpG islands showed distinct patterns of methylation in both subgroups that were inversely associated with expression, this also included genes differentially expressed between DHITsig+ and DHITsig- tumors. The DHITsig- group had increased levels of methylation of DHITsig genes in both promoters and gene bodies suggesting a functional role for gene body methylation. Finally, we observed that a high density of mutations near the BCL2 transcription start site consistently phased into the same haplotype as the BCL2-IGH translocation in five tumours, demonstrating the allele specificity of aSHM associated with these events (Panel B). Conclusions These results demonstrate differences in methylation between the subgroups. The association of hypomethylated superenhancers, promoters, and CpG islands with genes over-expressed in DHITsig+ suggests these methylation patterns may contribute to the DHITsig phenotype. These results may aid in improving GCB DLBCL patient classification and reveal factors contributing to its heterogeneity. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Intracranial dural arteriovenous fistula: a comprehensive review of the history, management, and future prospective.

Dural arteriovenous fistulas (DAVF) are abnormal acquired intracranial vascular malformationsconsisting of pathological connections located within the dura between the pial arteries and the veno vasora, comprising the walls of the dural sinuses, bridging veins, or transosseous emissary veins. Dural arteriovenous fistulas are distinguished from arteriovenous malformations by their arterial supply from the vessels that perfuse the dura mater and lack of a parenchymal nidus. They are most commonly situated at the transverse and cavernous sinuses. The mechanism of development behind dural arteriovenous fistula can be explained by the molecular and anatomical factors. Multiple classification systems have been proposed throughout history including; Djindjian and Merland, Cognard, and Borden classification systems. The aggressiveness of the clinical course in intracranial dural arteriovenous fistula can be predicted through the angiographic patterns of venous drainage, more specifically, the presence of cortical venous drainage, the presence of venous ectasia, and the aggressiveness of clinical presentation. Intracranial dural arteriovenous fistulas might be discovered incidentally. However, if symptomatic, the clinical presentation ranges from mild neurological deficits to severe, lethal intracranial hemorrhage. Angiography is the imaging of choice to investigate, diagnose, and plan treatment for intracranial dural arteriovenous fistula. The management algorithm of intracranial dural arteriovenous fistula can be broadly divided into conservative, surgical, endovascular, and/or radiosurgical options. With the advent of endovascular therapies, surgery has fallen out of favor for managing intracranial dural arteriovenous fistulas. In the present article, the pathophysiology, classifications, natural history, clinical manifestations, radiological features, management, and complications are comprehensively reviewed.

OLP++: An online local classifier for high dimensional data

Ensemble diversity is an important characteristic of Multiple Classifier Systems (MCS), which aim at improving the overall performance of a classification system by combining the response of several models. While diversity may be introduced through various manipulations at the data level and the model level, some MCSs incorporate local information in order to increase it and/or take advantage of it, based on the idea that the different classifiers in the ensemble may have expertise in distinct areas of the feature space.11Code available at: https://github.com/marianaasouza/olp_plusplus.Following a similar reasoning, we introduced in a previous work an ensemble method which produces in test time a few experts in the local region where each given query sample is located. These local experts, which are generated with slightly differing views of the target area, are then used to label the corresponding unknown instance. While the framework was shown to perform well especially over imbalanced problems, the locality definition in the method is based on the nearest neighbors rule and Euclidian distance, as is the case of various local-based ensembles, which may suffer from the effects of the curse of dimensionality over high dimensional problems. Thus, in this work, we propose a local ensemble method in which we leverage the data partitions given by decision trees for locality definition. More specifically, the partitions defined at different levels of the decision path that a given query instance traverses in the tree(s) are used as the regions over which the local experts are produced. By using different node levels from the path, each classifier in the local pool has a moderately distinct view of the target region without resorting to a dissimilarity metric, which might be susceptible to high dimensional spaces. Experimental results over 39 high dimensional problems showed that the proposed approach was significantly superior to our previous, distance-based framework in balanced accuracy rate. Compared to other six local-based ensemble methods, including dynamic selection and weighting schemes, the proposed method achieved competitive results, outperforming the random forest baseline and two state-of-the-art dynamic ensemble selection techniques.

Exploring diversity in data complexity and classifier decision spaces for pool generation

This paper introduces a novel method for classifier pool generation in which a two-level strategy explores diversity in both data complexity and classifier decision spaces. The rationale is to induce pool members using data subsets representing subproblems with different difficulties while promoting diversity in classifiers’ decisions. Two possible variants of the proposed method with a focus on maximum dispersion and maximum accuracy are presented. These differ in the property used to define the best pool of classifiers provided by an optimization process. A robust experimental protocol encompassing 28 classification datasets shows that the proposed pool generation provided the best accuracy on 327 over 336 experiments (97.3%) when compared to well-known pool generation methods to provide multiple classifier systems with and without dynamic selection.

Applying machine learning methods to predict geology using soil sample geochemistry

In this study we compared various machine learning techniques that used soil geochemistry to aid in geologic mapping. We tested six different sampling methods (undersample, oversample, Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), SMOTE and Edited Nearest Neighbor (SMOTEENN), and SMOTE and Tomek links (SMOTETomek)). SMOTE performed best with ADASYN and SMOTETomek having slightly lower effectiveness. Nine machine learning algorithms (naïve Bayes, logistic regression, quadratic discriminant analysis, nearest neighbors, radial basis function support-vector machine, artificial neural network, random forest, AdaBoost classifier, and gradient boosting classifier) were compared and AdaBoost classifiers and gradient boosting classifiers were found to be most effective. Finally, we experimented with multiple classifier systems (MCS) testing different combinations of algorithms and various combinatorial functions. It was found that MCS can outperform individual models, and the best MCS combined nearest neighbors, radial basis function support-vector machine, artificial neural network, random forest, AdaBoost classifiers, and gradient boosting classifier, then applied a logistic regression to the probabilities output by the models. Ultimately, we created a tool that is able to adequately predict underlying geology in the study area using soil geochemistry.

Avulsion Fracture of the Tibial Tubercle in Adolescents: 3 Cases and Review of the Literature

Tibial tubercle avulsion fractures are an uncommon injury occurring due to strong contraction of the quadriceps femoris muscle. Of all proximal tibial fractures, approximately 3% are tibial tubercle avulsion fractures. We report 3 cases of anterior tibial tubercle fractures in 3 adolescents treated at the pediatric surgical emergency department in Rabat. Standard radiographs of the knee will reveal the avulsed tibia tubercle and also allow fracture classification. There are multiple classification systems with multiple modifiers. The most commonly used is the modified Ogden classification. Tibial tubercle avulsion fractures can be associated with concomitant soft tissue damage, periosteal damage, and compartment syndrome leading to extensor mechanism disruption, joint laxity, or vascular compromise. Treatment can be nonsurgical or surgical, and indications depend on fracture type. Most fractures are surgical candidates and can be repaired with open reduction and internal fixation (ORIF) or arthroscopy. Satisfactory results are usually achieved.

A multiple classifiers system with roulette-based feature subspace selection for one-vs-one scheme

A multiple classifiers system with roulette-based feature subspace selection for one-vs-one scheme

Data-driven learning fatigue detection system: A multimodal fusion approach of ECG (electrocardiogram) and video signals

Fatigue could lead to low efficiency and even serious disaster. In the educational field, detecting fatigue could help adjust teaching strategies accordingly when a student is inactive, which can potentially improve learning efficiency. Despite numerous studies in fatigue detection, there is still a lack of multiple classifier systems capable of detecting fatigue in daily life (without specific stimulations). To initially alleviate this problem, this study develops a learning fatigue detection system using a multimodal approach with ECG and video signals, classifying a learner’s state into three categories: alert, normal, and fatigued. To validate performance, the proposed system is tested on (i) an open-source dataset DROZY (n = 35) and (ii) a self-collected dataset captured in a learning environment (n = 92). The experimental results based on 10-fold cross-validation demonstrate that the system outperforms the state-of-the-art approaches, achieving a detection accuracy of 99.6% and 91.8% on the two datasets, respectively.

Homogenous Multiple Classifier System for Software Quality Assessment Based on Support Vector Machine

In today&amp;#39;s society, almost all human endeavours depend on software products. Lack of quality software is one of the software industry&amp;#39;s most important problems. Hence, it would be beneficial to access the quality of software to improve and enhance software products while increasing customer satisfaction. This paper assesses software product quality using a Support Vector Machine-based ensemble classifier. The ISO/IEC-9126 (International Organization for Standardization 2001) software quality (SQ) framework was adopted in this work. Dimension reduction of the product metric category dataset and the entire PM dataset was conducted using linear discriminant analysis (LDA). SVM kernel functions (linear, quadratic, cubic, fine gaussian, medium gaussian and coarse gaussian) were used to model each classifier. The combinations of the results from the multiple SVMs used AdaBoost, bagging, and random subspace ensemble methods for the assessment of SQ. All three ensemble learning methods performed better than the individual SVM, however, the bagging stood out with an accuracy of 93.0%. Hence, it was adopted in the fusion of the SVM results and classification of SQ into classes. Results from the confusion matrix and receivers&amp;rsquo; operating characteristics were greater than 97.99% and confirm significant improvements with an ensemble of homogenous classifiers based on SVM.

Stargardt Disease

Stargardt disease is a slowly progressing macular dystrophy with an onset of disease most commonly in children and young adults. Numerous genes have been found to be associated with this disease, with variants in the retina specific ATP- binding cassette transporter (ABCA4) gene being most common. Each variant may have distinct clinical features, however, patients generally experience bilateral central vision loss and poor visual acuity ranging from 20/70 to 20/200. Diagnosis is often made through clinical presentation and may be assisted by fluorescein angiography (FA), spectral domain optical coherence tomography (OCT), fundus autofluorescence (FAF) or electrophysiological assessment. Currently, there are multiple classification systems of Stargardt disease that include Fishman STGD classification system, groupings due to electroretinography (ERG) findings, and types based on FAF imaging. Though there are currently no clinically proven treatments for Stargardt disease, physicians often recommend patients avoid direct sunlight, smoking cigarettes, and excessive intake of vitamin A. Potential treatments currently under investigation include strategies using gene replacement therapy, stem cell therapy, and pharmacologic agents. The purpose of this paper is to review the current knowledge of the genetics, classifications, and treatments of Stargardt disease, while underscoring the need for further research in potential treatment routes.

Enhancing classification in correlative microscopy using multiple classifier systems with dynamic selection

Correlative microscopy combines data from different microscopical techniques to gain unique insights about specimens. A key requirement to unlocking the full potential is an advanced classification method that can combine the various analytical signals into physically meaningful phases. The prevalence of highly imbalanced class distributions and high intra-class variability in such real applications makes this a difficult task, yet no study of classifier performance exists in the context of correlative microscopy. This paper investigates the application of both single classifiers as well as multiple classifier systems with dynamic selection. The test sample used for evaluation and comparison of the results is a volcanic rock where data from correlative Raman spectroscopy, Scanning Electron Microscopy (SEM) and Energy Dispersive X-ray Spectroscopy (EDS) are available and prepared for algorithmic evaluation. The results show that multiple classifier systems outperform single classifiers reaching an area under the curve of the receiver operating characteristic of 99% demonstrating the applicability of automated classification in correlative microscopy. Thus, this paper contributes by highlighting the potential of combining the research fields of correlative microscopy and machine learning.

Reassessment of Reliability and Reproducibility for Triple-Negative Breast Cancer Subtyping.

Simple SummaryTriple-negative breast cancer (TNBC) is a heterogeneous disease. A proper classification system is needed to develop targetable biomarkers and guide personalized treatment in clinical practice. However, there has been no consensus on the molecular subtypes of TNBC, probably due to discrepancies in technical and computational methods chosen by different research groups. In this paper, we reassessed each major step for TNBC subtyping and provided suggestions, which promote rational workflow design and ensure reliable and reproducible results for future studies. We presented a recommended pipeline to the existing data, validated established TNBC subtypes with a larger sample size, and revealed two intermediate subtypes with prognostic significance. This work provides perspectives on issues and limitations regarding TNBC subtyping, indicating promising directions for developing targeted therapy based on the molecular characteristics of each TNBC subtype.Triple-negative breast cancer (TNBC) is a heterogeneous disease with diverse, often poor prognoses and treatment responses. In order to identify targetable biomarkers and guide personalized care, scientists have developed multiple molecular classification systems for TNBC based on transcriptomic profiling. However, there is no consensus on the molecular subtypes of TNBC, likely due to discrepancies in technical and computational methods used by different research groups. Here, we reassessed the major steps for TNBC subtyping, validated the reproducibility of established TNBC subtypes, and identified two more subtypes with a larger sample size. By comparing results from different workflows, we demonstrated the limitations of formalin-fixed, paraffin-embedded samples, as well as batch effect removal across microarray platforms. We also refined the usage of computational tools for TNBC subtyping. Furthermore, we integrated high-quality multi-institutional TNBC datasets (discovery set: n = 457; validation set: n = 165). Performing unsupervised clustering on the discovery and validation sets independently, we validated four previously discovered subtypes: luminal androgen receptor, mesenchymal, immunomodulatory, and basal-like immunosuppressed. Additionally, we identified two potential intermediate states of TNBC tumors based on their resemblance with more than one well-characterized subtype. In summary, we addressed the issues and limitations of previous TNBC subtyping through comprehensive analyses. Our results promote the rational design of future subtyping studies and provide new insights into TNBC patient stratification.

A novel committee machine to predict the quantity of impurities in hot metal produced in blast furnace

In recent years, interest in artificial intelligence and the integration of Industry 4.0 technologies to improve and monitor steel production conditions has increased. Every day, several models are proposed to simulate industrial processes. In this sense, committee machines are presented as competitive alternatives to solve this task. A committee machine uses a multiple classification system in which the responses from multiple ANNs are combined into a single response. In this context, the purpose of this work was to develop committee machines using 108 independent artificial neural networks to predict the amount of impurities (silicon, phosphorus, and sulfur) in the production of cast iron in a blast furnace. It is concluded that neural networks operating in committee mode may be used in practice as a prediction and control tool due to the low RMSE values and high mathematical correlation between the database values and the values calculated by the committee machine.

Deforestation by Afforestation: Land Use Change in the Coastal Range of Chile

In southern Chile, an establishment of a plantation-based forest industry occurred early in the industrial era. Forest companies claim that plantations were established on eroded lands. However, the plantation industry is under suspicion to have expanded its activities by clearing near-natural forests since the early 1970s. This paper uses a methodologically complex classification approach from own previously published research to elucidate land use dynamics in southern Chile. It uses spatial data (extended morphological profiles) in addition to spectral data from historical Landsat imagery, which are fusioned by kernel composition and then classified in a multiple classifier system (based on support, import and relevance vector machines). In a large study area (~67,000 km2), land use change is investigated in a narrow time frame (five-year steps from 1975 to 2010) in a two-way (prospective and retrospective) analysis. The results are discussed synoptically with other results on Chile. Two conclusions can be drawn for the coastal range. Near-natural forests have always been felled primarily in favor of the plantation industry. Vice versa, industrial plantations have always been primarily established on sites, that were formerly forest covered. This refutes the claim that Chilean plantations were established primarily to restore eroded lands; also known as badlands. The article further shows that Chile is not an isolated case of deforestation by afforestation, which has occurred in other countries alike. Based on the findings, it raises the question of the extent to which the Chilean example could be replicated in other countries through afforestation by market economy and climate change mitigation.

Probability-driven scoring functions in combining linear classifiers

Although linear classifiers are one of the oldest methods in machine learning, they are still very popular in the machine learning community. This is due to their low computational complexity and robustness to overfitting. Consequently, linear classifiers are often used as base classifiers of multiple ensemble classification systems. This research is aimed at building a new fusion method dedicated to the ensemble of linear classifiers. The fusion scheme uses both measurement space and geometrical space. Namely, we proposed a probability-driven scoring function which shape depends on the orientation of the decision hyperplanes generated by the base classifiers. The proposed fusion method is compared with the reference method using multiple benchmark datasets taken from the KEEL repository. The comparison is done using multiple quality criteria. The statistical analysis of the obtained results is also performed. The experimental study shows that, under certain conditions, some improvement may be obtained.

Gram Stain Prediction with Machine Learning Techniques Using Biochemical Parameters in ICU Patients with Urinary Tract Infections

Purpose: The aim of this study was to develop a useful algorithm based on complete blood count (CBC), urinalysis, and biochemical parameters that could be an alternative to gram staining in the prediction of UTI and the determination of initial antibiotic treatment in ICU patients. Methods: All the specimens included in the study were obtained from ICU patients and were subjected to gram staining in the laboratory. Simultaneously, CBC, urinalysis, and biochemical tests were performed for each specimen. A classification based on biochemical parameters was performed for the estimation of gram-negative and gram-positive bacteria, as an alternative to gram staining. Results: Classification was achieved using multiple classification systems including Artificial Neural Networks (ANN), Support Vector Machine (SVM), the K-Nearest Neighbors (KNN), and Decision Tree Language (DTL) and the best classification performance was achieved by ANN, with an accuracy of 84.6%, sensitivity of 88.5%, and specificity of 73.5%. Conclusion: The high specificity and accuracy of the algorithm indicated that this algorithm can be effectively used in the selection of empirical antibiotic treatment for ICU patients with UTI and can provide more advanced and technological opportunities by combining laboratory parameters with machine learning techniques.