A Comparative Analysis for Predicting Paediatric Appendicitis Using Machine Learning Models and Genetic Optimisation Technique

A Comparative Analysis for Predicting Paediatric Appendicitis Using Machine Learning Models and Genetic Optimisation Technique | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article A Comparative Analysis for Predicting Paediatric Appendicitis Using Machine Learning Models and Genetic Optimisation Technique Iliyas Ibrahim Iliyas, Souley Boukari, Abdulsalam Ya’u Gital This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9169732/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 14 You are reading this latest preprint version Abstract Paediatric appendicitis is a known medical emergency that affects adolescents and children, possibly leading to life-threatening difficulties if it is not diagnosed and treated on time. Diagnosing Paediatric appendicitis earlier plays an important role in preventing severe outcomes. Recent developments in Machine Learning (ML) have proven to be efficient in enhancing diagnostic accuracy. This study proposed a comparative analysis of ML models such as Decision Tree, Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), K-Nearest Neighbours (KNN), Adaptive Boosting (AdaBoost), Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost) for the prediction of paediatric appendicitis, the analysis was conducted on a dataset consisting of 782 patients records with 53 clinical features obtained from UCI Machine Learning Repository. An optimisation technique called Genetic Algorithm (GA) was utilised for hyperparameter tuning the models, a nature-inspired optimisation that iteratively evolves model parameters for value imputation. The dataset was preprocessed by handling missing values with value imputation and categorical values with LabelEncoder. The models were evaluated using accuracy, precision, recall, and F1-score metrics. The analysis results show that AdaBoost and DT classifiers achieved the highest accuracy of 97.45%. The GA significantly improved model performance by optimising hyperparameters such as learning rate, maximum depth, and estimators. NB achieved the lowest performance, demonstrating the importance of model selection and tuning. This research highlights the effectiveness of ML models, particularly when combined with GA optimisation in diagnosing paediatric appendicitis. These findings contribute to the growing body of evidence supporting the use of AI and ML in clinical decision-making, reducing diagnostic delays and improving patient outcomes. Paediatric Appendicitis Machine Learning Genetic Algorithm Optimisation Hyperparameter Tuning and Clinical Disease Prediction Figures Figure 1 Figure 2 Figure 3 1.0 Introduction Paediatric appendicitis is a disease that causes abdominal pain in children. Appendicitis indicates a health concern with a lifetime risk of 6 to 9% and occurs in people from 10 to 19 years of age [ 1 ]. The risk of developing life-threatening issues increases with the length of time that appendicitis is left untreated [ 2 ]. With the advancements of technology, we have witnessed notable advancements in the medical sector, which have made it possible to employ data mining techniques to identify trends in the dataset. Medical experts can now accurately diagnose any medical disease due to this analysis. This reduced treatment costs and offered better healthcare [ 3 ]. The use of data mining in healthcare has evolved due to its potential to reduce expenses, support healthcare providers with treatment plans, and enhance patient care through early disease diagnosis. Early diagnosis is essential, which drives the use of emerging technologies like machine learning (ML) [ 4 ]. A field of data science known as machine learning (ML) utilises machines to learn, rather than being manually programmed. ML is a collection of methods that let software applications make precise output predictions without any interference [ 5 ].ML is becoming an important solution to assist in diagnosing diseases in patients. ML is an analytical tool used when a task has a large dataset and is difficult to program, such as transforming medical records into knowledge, genomic data analysis, and disease prediction [ 6 ]. The process of fitting an ML model to data involves the selection of an ML algorithm, training the algorithm on a dataset, and evaluating the performance of the trained model on new data. The goal of the ML algorithm is to process a training dataset that has a collection of input and target attributes [ 7 ]. ML considers two main parameters, hyperparameters and parameters. Parameters are internal parameters and are estimated based on the provided dataset, while hyperparameters are external parameters that are set before the training process and used to control the learning process of ML, chosen good parameters guarantees better performance [ 8 ]. In this study, a comparative analysis of ML models for the prediction of paediatric appendicitis and hyperparameter tuning was conducted on each model using a Genetic Algorithm (GA). The contribution of this study is highlighted below: Exploration of Paediatric appendicitis Disease dataset Comparative analysis of different ML models for the prediction of Paediatric appendicitis Hyperparameter tuning implementation using Genetic Algorithm Evaluation of the ML models for the prediction of Paediatric appendicitis This paper consists of five sections, following the introduction in section 1, the related work is discussed in section 2. Section 3 discusses the methodology, including the dataset, genetic algorithm, classification techniques, and performance measures. The environmental setup with the results is discussed in Section 4. Section 5 discussed the conclusion of the study. 2.0 Related Work A study by Aparicio et al (2021) proposed a risk super space linear integer model (risk SLIM) to predict paediatric appendicitis to enhance diagnosis, treatment, and complication prediction. The study applied the model on 430 datasets, and the work evaluated the performance of their proposed study with other traditional scores and RF. Their model achieved an AUROC of 0.85 ± 0.04 and an AUPR of 0.90 ± 0.03 for diagnosing appendicitis, both with and without ultrasound data, respectively. A study by İlyas (2024) developed a model for diagnosing paediatric appendicitis using a multi-output neural network. The study involves using both ultrasound and clinical data from the Children’s Hospital St. Hedwig. The proposed study achieved the best scores of 94.23%, 97.44%, and 100% for management classification, severity classification, and diagnosis, respectively. A study by [ 2 ] also proposed a technique for predicting paediatric appendicitis, the study includes a preprocessing stage involving the use of Correlation Feature Selection (CFS) as feature selection and Elephant Search Algorithm (ESA) for optimization and the models developed are LR, Adaboost, and RF, the ensemble model achieved 92.15% accuracy. Chadaga et al (2024) proposed a ML-based ensemble model (APPSTACK) for paediatric appendicitis detection. The study combined multiple models and hyperparameter-tuned the models’ structures with the Hybrid Bat Algorithm. The study also used five explainable AI (XAI) techniques for interpreting the models’ outcomes. The study achieved the best accuracy of 94% and interpreted the model’s outcome, which showcased a model with diagnostic efficiency in the health sector. The proposed work by Marcinkevics et al (2021) developed a machine learning (ML) model to predict paediatric appendicitis diagnosis, management, and severity. The study improved diagnostic accuracy and streamlined management decisions. The model was trained on 430 records with LR, RF and gradient boosting models. RF achieved an average AUROC of 0.96 for diagnosis, 0.90 for severity and 0.94 for management. Ugne et al (2022) proposed a Multiview concept bottleneck model (MVCBM) to predict paediatric appendicitis using ultrasound images from a cohort of 275 paediatric patients. The study used ResNet-18 for feature extraction and feature fusion through LSTM, concept prediction, and final label prediction. The proposed MVCBM model performed better than the traditional methods, such as ResNet-18 and Radiomics, with an AUROC of 0.96 and AUPR of 0.92 for appendicitis diagnosis. The proposed work by Maffezzoni et al (2025) used the ML model to improve the diagnosis and management of paediatric appendicitis. The models include logistic regression (LR), random forests (RF), XGBoost, and Multilayer Perceptron (MLP). The results show that the RF model achieved high performance with an AUC of 0.94 for diagnosis, 0.92 for management, and 0.70 for severity, reducing unnecessary surgeries by up to 17%. The study by Reismann et al (2019) proposed an artificial intelligence-based model for diagnosing paediatric acute appendicitis, focusing on the use of routine clinical and laboratory parameters like C-reactive protein (CRP), white blood cell counts, and appendiceal diameter from ultrasound images. The study created a biomarker signature for diagnosing appendicitis and differentiating between complicated and uncomplicated appendicitis using ML. The results show that the developed model outperforms traditional methods, with an accuracy of 90% for diagnosing appendicitis and a 95% sensitivity for distinguishing complicated appendicitis, offering a more reliable and objective approach to clinical decision-making. The architecture of the work is shown in Fig. 1 . 3.0 Methodology 3.1 Appendicitis Dataset Appendicitis is a disease where inflammation occurs in the appendix, which is a small organ that appears along the large intestine. It is mostly affecting children and needs urgent attention. The appendicitis dataset used in this study was obtained from the UCI machine learning repository of a dataset of the cohort of patients with suspected appendicitis admissions with abdominal pain at ST Hedwig in Rehensburg, Germany [ 15 ]. The dataset has 782 records and 53 features, with Diagnosis as the target variable. The target variable has appendicitis and no appendicitis, with a total of 307 and 317 for appendicitis and no appendicitis, respectively. The dataset is from 2016 to 2021, and the target feature is “Diagnosis”. Table 1 summarises the Paediatric appendicitis dataset used in this study. Table 1 Paediatric Appendicitis Dataset Description S/No. Feature Name Description Value Type Range Missing Values 1 Age Age of the patient Integer 0–18 1 2 BMI Body Mass Index Float 7.83–38.16 27 3 Sex The gender of the patient Categorical male, female 2 4 Height Height of the patient in cm Integer 50–200 26 5 Weight Weight of the patient in kg Integer 10–150 3 6 Length of Stay Duration of hospital stay in days Integer 0–28 4 7 Management Management type (conservative or surgical) Categorical conservative, surgical 1 8 Severity The severity of the condition Categorical complicated, uncomplicated 1 9 Diagnosis Presumptive Presumptive diagnosis Categorical appendicitis, no appendicitis 2 10 Diagnosis Final Diagnosis Categorical appendicitis, no appendicitis 2 11 Alvarado Score Score used for the diagnosis of appendicitis Integer 0–10 52 12 Paediatric Appendicitis Score Pediatric score used for appendicitis diagnosis Integer 0–10 52 13 Appendix on US Presence of appendix on ultrasound Categorical yes, no 5 14 Appendix Diameter The diameter of the appendix in mm Float 0–100 284 15 Migratory Pain Presence of migratory pain Categorical yes, no 9 16 Lower Right Abd Pain Pain in the lower right abdomen Categorical yes, no 8 17 Contralateral Rebound Tenderness Presence of contralateral rebound tenderness Categorical yes, no 15 18 Coughing Pain Pain while coughing Categorical yes, no 16 19 Nausea Presence of nausea Categorical yes, no 8 20 Loss of Appetite Loss of appetite Categorical yes, no 10 21 Body Temperature Body temperature in Celsius Float 35–42 7 22 WBC Count White blood cell count Integer 0–20,000 6 23 Neutrophil Percentage Percentage of neutrophils in blood Float 0–100 103 24 Segmented Neutrophils Percentage of segmented neutrophils Float 0–100 728 25 Neutrophilia Presence of neutrophilia Categorical yes, no 50 26 RBC Count Red blood cell count Integer 0–10,000,000 18 27 Haemoglobin Haemoglobin level Float 0–20 18 28 RDW Red cell distribution width Float 0–30 26 29 Thrombocyte Count Platelet count Integer 0–1,000,000 18 30 Ketones_in_Urine Presence of ketones in urine Categorical yes, no 200 31 RBC in Urine Presence of red blood cells in urine Categorical yes, no 206 32 WBC in Urine Presence of white blood cells in urine Categorical yes, no 199 33 CRP C-reactive protein level Float 0–200 11 34 Dysuria Painful urination Categorical yes, no 29 35 Stool Characteristics of stool Categorical normal, abnormal 17 36 Peritonitis Presence of peritonitis Categorical yes, no 9 37 Psoas Sign Presence of the psoas sign, a clinical test for appendicitis. Categorical yes, no 37 38 Ipsilateral Rebound Tenderness Presence of pain upon palpation of the abdomen on the same side as the inflamed appendix. Categorical yes, no 163 39 US Performed Indicates whether an ultrasound examination was performed. Categorical yes, no 4 40 US Number Number of ultrasound scans performed for the patient. Integer 1-992 22 41 Free Fluids Presence of free fluids in the abdomen Categorical yes, no 63 42 Appendix Wall Layers Layers of the appendix wall Categorical normal, abnormal 564 43 Target_Sign Presence of the target sign on imaging Categorical yes, no 644 44 Appendicolith Presence of appendicolith Categorical yes, no 713 45 Perfusion Tissue perfusion status Categorical normal, abnormal 719 46 Perforation Appendix perforation Categorical yes, no 701 47 Surrounding Tissue Reaction Reaction of the surrounding tissue Categorical yes, no 530 48 Appendicular Abscess The presence of an abscess in the appendix Categorical yes, no 697 49 Abscess Location Location of abscess, if present Categorical reUB-reAL 769 50 Pathological Lymph Nodes Presence of pathological lymph nodes Categorical yes, no 579 51 Lymph Nodes Location Location of lymph nodes Categorical reUB-reAL 661 52 Bowel Wall Thickening Presence of bowel wall thickening Categorical yes, no 683 53 Conglomerate of Bowel Loops The presence of a conglomerate of bowel loops Categorical yes, no 739 54 Ileus Presence of ileus Categorical yes, no 722 55 Coprostasis Presence of coprostasis Categorical yes, no 711 56 Meteorism Presence of meteorism Categorical yes, no 642 57 Enteritis Presence of enteritis Categorical yes, no 716 58 Gynaecological Findings Gynaecological findings, if present Categorical yes, no 756 3.2 Data Preprocessing The preprocessing in the study includes handling missing values by filling numerical columns with their median and categorical columns with their mode. Categorical features are encoded into numerical values using LabelEncoder. The dataset is then split into features and the target variable, with an 80 − 20 train-test split, preserving class proportions. Finally, the features are standardised using StandardScaler to ensure that all variables are on the same scale before being used for model training. 3.3 Genetic Algorithm (GA) Genetic algorithms (GA) are inspired by the principles of natural selection and evolution, enabling them to handle discrete values. GA works by iteratively generating a set of models, which are evaluated based on a global criterion, leading to the formation of subsequent sets of models. Selection is the act of choosing the best solutions from the current population based on their performance, where the solutions represent the hyperparameters. Crossover involves combining the best solutions to create a new one by merging their hyperparameters to form a potentially better solution. Mutation introduces random changes to the solutions by adjusting the hyperparameters, promoting diversity, and preventing the algorithm from converging prematurely on suboptimal solutions [ 16 ]. 3.4 Classification Techniques 3.4.1 Decision Tree The decision tree classifier used tree-like structures, where the structure represents root nodes as conditions, while the child nodes as class labels, and the branches of the root nodes in the tree structure, which means the effects of the conditions [ 17 ]. 3.4.2 Random Forest Random forest is an ML algorithm based on an ensemble of trees derived from a selection of decision trees from randomly chosen training set subsets. It evaluates the final class form votes achieved from various decision trees [ 17 ]. 3.4.3 Logistic Regression Logistic Regression is an ML model based on a mathematical model that uses logistic functions that form a binary-dependent feature. The statistical binary logistic model has two possible values that represent the dependent variable, which are 0 or 1 [ 17 ]. 3.4.4 K-Nearest Neighbours (KNN) K-nearest neighbours (KNN) is a non-parametric ML algorithm that is used in both regression and classification tasks. Its working principles are based on the classification of data points based on either the average values of the majority class or the closest neighbours within the feature space. KNN brings similar data points close to each other in the feature space, which are referred to as the nearest neighbours [ 18 ] 3.4.5 Naïve Bayes Naïve Bayes is a classification model that is logically centred based on the Bayes theorem. It comprises a group of algorithms with similar definitions, such as multinomial naive bayes used on categorical values and Gaussian naive bayes for continuous values [ 17 ]. 3.4.6 Artificial Neural Network Artificial neural network (ANN) is a type of ML algorithm that got its working principles from the human brain, it consists of so many connected neurons (nodes) that process data, and it enhances its learning by adjusting weights during training with the help of backpropagation, ANN is used for both regression and classification tasks [ 19 ]. 3.4.7 Extreme Gradient Boosting (XGBoost) Extreme Gradient Boosting (XGBoost) is a type of ML model based on the framework of gradient boosting, it is applied for both classification and regression tasks and on large datasets with high dimensional feature spaces, it forms an ensemble of decision trees in sequence, were every single tree will correct the error from a previous tree and it prevents overfitting with the help of regularization making it an effective model [ 7 ]. 3.4.8 Adaptive Boosting (AdaBoost) Adaptive Boosting (AdaBoost) is a type of ML model which combines multiple weak classifiers to generate a strong classifier. It has a weight which adjusts based on how well the previous model misclassified instances by adding a higher weight for the subsequent model to focus on them during the training process [ 17 ]. 3.5 Performance Metrics The evaluation of the model’s performance was conducted using four matrices’ names: accuracy, precision, recall and F1 score. The matrices are briefly described below, and Fig. 2 shows the confusion matrix. $$ \text{ Accuracy: }\frac{TP+TN}{TP+FP+FN+TN}$$ $$ \text{ Precision: }\frac{TP}{TP+FP}$$ $$ \text{ F1 Score: }\frac{2*\text{ Precision }*\text{ Recall }}{\text{ Precision }+\text{ Recall }}$$ $$ \text{ Recall: }\frac{TP}{TP+FN}$$ True Positive (TP): TP represents an appendicitis instance that was predicted correctly as appendicitis. False Positive (FP): FP represents an appendicitis instance that is falsely predicted as no appendicitis False Negative (FN): FN represents a no-appendicitis instance that was falsely predicted as appendicitis True Negative (TN): TN represents no appendicitis instances that were predicted as no appendicitis 4.0 Results of the Models 4.1 Environmental Setup The study was conducted on an HP computer equipped with an Intel Core i7 processor, 13th generation, running at 2.8 GHz, with 16 GB of RAM and a 1 TB hard drive. The code was executed using Python version 3.13.2. The machine learning models were implemented using the scikit-learn (sklearn) library, while the DEAP library was utilised to implement the genetic algorithm for hyperparameter tuning. 4.2 Optimal Hyperparameters The genetic algorithm (GA) optimises key hyperparameters for models like XGBClassifier, AdaBoost, and Decision Tree Classifier by refining parameters such as n_estimators, learning_rate, max_depth, subsample, and colsample_bytree for XGBClassifier, and n_estimators and learning_rate for AdaBoost. It also fine-tunes max_depth, min_samples_split, min_samples_leaf, and criterion for the decision tree. The GA evaluates these parameters using a fitness function that measures model accuracy, employing selection, crossover, and mutation operations across generations to find the optimal hyperparameter configuration that maximises model performance. The parameters of XGBoost are shown in Table 2 , DT parameters in Table 3 and AdaBoost parameters in Table 4 . Table 2 Decision Tree Parameters Parameter Value max_depth 5–20 min_samples_split 2–10 min_samples_leaf 1–2 Criterion [Gini, entropy] Table 3 Random Forest Parameters Parameter Value n_estimators 50–200 learning_rate [0.01, 0.2] max_depth 3–10 Subsample [0.0, 1.0] colsample_bytree [0.0, 1.0] Table 4 Adaboost Parameter Parameter Value n_estimators 50–200 learning_rate 0.01-1.0 4.3 Results The results achieved in this study are discussed in this section. The study performed a comparative analysis of an optimised ML model using a Genetic algorithm on the ML models. For optimising the parameters of the Models, GA was used for hyperparameter tuning the models to get the optimal scores. The parameters of the GA were shown in Table 5 , where a population size of 10 was used, the number of generations was 10, and the fitness function used was an XGB classifier for evaluating the performance of each individual. Table 5 Genetic Algorithm Parameters Parameter Values Population size 10 No. of Generation 10 Cross Over Probability 0.7 Mutation Probability 0.2 Cross Method 0.5 Match Method SelTournament Fitness Function XGB Classifier Figure 3 shows the accuracy achieved by each model compared in the study, with AdaBoost and DT having achieved the best accuracy of 97.45% for both, followed by RF with 96.82%, ANN and XGBoost with 95.45% each, LR with 93.63%, KNN with 82.17% and NB achieved the lowest accuracy of 67.52%. Table 6 shows the summary of performances achieved by the evaluated models, in terms of F1 score, Precision and Recall. DT and Adaboost achieved the best scores of 97.45, 97.45and 97.45, respectively. NB achieved the lowest score in terms of F1 score, precision and recall with 66.56, 78.35 and 67.52, respectively. Table 6 Performance Evaluation of the Models with Other Metrics LR F1 Score Precision Recall Confusion matrix 93.61 93.63 93.63 89 4 6 58 XGBoost 95.52 95.57 95.54 91 2 5 59 RF 96.81 96.82 96.82 91 2 3 61 NB 66.56 78.35 67.52 45 48 3 61 ANN 95.55 95.56 95.54 89 4 3 61 KNN 82.17 82.17 82.17 79 14 14 50 AdaBoost 97.45 97.45 97.45 91 2 2 62 DT 97.45 97.45 97.45 91 2 2 62 Figure 4 shows the time it takes for GA to finish tuning the parameters of the models, which are XGBoost, Adaboost and DT, based on the ranges of the parameters chosen to achieve an optimal score. GA took 22.65 secs to finish the hyperparameter tuning process, it took 0.49 secs to finish on AdaBoost and 0.7 secs on DT. Conclusion In conclusion, this comparative analysis on predicting paediatric appendicitis using machine learning demonstrates the potential of various models, including RF, LR, XGBoost, AdaBoost, NB, DT, KNN, and ANN, in achieving high accuracy. Among the models tested, AdaBoost and Decision Trees (DT) achieved the best accuracy, scoring 97.45%. The incorporation of hyperparameter tuning using Genetic Algorithms (GA) proved effective in selecting optimal parameters, contributing to improved model performance. The findings underscore the importance of machine learning models and optimisation techniques, such as GA, in achieving robust preditive accuracy. Future research should focus on expanding the dataset size, exploring other medical tasks beyond appendicitis diagnosis, and utilising more advanced models to further enhance prediction accuracy and clinical applicability. Abbreviations AI Artificial Intelligence ML Machine Learning GA Genetic Algorithm DT Decision Tree RF Random Forest LR Logistic Regression NB Naïve Bayes KNN K–Nearest Neighbours ANN Artificial Neural Network XGBoost Extreme Gradient Boosting AdaBoost Adaptive Boosting UCI University of California Irvine (Machine Learning Repository) CRP C–reactive Protein WBC White Blood Cell AUROC Area Under the Receiver Operating Characteristic Curve AUPR Area Under the Precision–Recall Curve XAI Explainable Artificial Intelligence Declarations Ethics approval and consent to participate Ethics declaration: not applicable. Consent to publish declaration: not applicable. Consent for Publication Consent to publication declaration: not applicable. Competing Interests The authors declare no competing interests. Funding This research received no external funding. Author Contribution Iliyas Ibrahim Iliyas: Conceptualization, methodology, software implementation, data preprocessing, formal analysis, writing – original draft preparation. Souley Boukari: Supervision, validation, review and editing of the manuscript. Abdulsalam Ya’u Gital: Supervision, methodology guidance, review and editing of the manuscript.All authors have read and approved the final version of the manuscript. All authors have read and approved the final version of the manuscript. Acknowledgements The authors are grateful to colleagues and reviewers whose valuable feedback and suggestions helped improve the quality of this work. Data Availability The datasets generated and analysed during the current study are available in the UCI Machine Learning Repository at https://archive.ics.uci.edu/dataset/938/regensburg+pediatric+appendicitis References İlyas Ö. Utilizing Machine Learning for Enhanced Diagnosis and Management of Utilizing Machine Learning for Enhanced Diagnosis and Management of Pediatric Appendicitis: A Multilayer Neural Network Approach. Aintelia, 2, 2, 2024. Pati A, Parhi M, Pattanayak BK. An Ensemble Deep Learning Approach for Chronic Kidney Disease (CKD) Prediction, AIP Conf. Proc. , vol. 2819, no. January, 2023, 10.1063/5.0136894 Dev S, Wang H, Nwosu CS, Jain N, Veeravalli B, John D. A predictive analytics approach for stroke prediction using machine learning and neural networks. Healthc Anal. 2022;2:100032. 10.1016/j.health.2022.100032 . Kabir MF, Chen T, Ludwig SA. A performance analysis of dimensionality reduction algorithms in machine learning models for cancer prediction, Healthc. Anal. , vol. 3, no. October 2022, p. 100125, 2023. 10.1016/j.health.2022.100125 Iliyas II, Boukari S, Ya A. Recent trends in prediction of chronic kidney disease using different learning approaches: a systematic literature review, J. Med. Artif. Intell. , no. July 2024, pp. 0–2, 2025. 10.21037/jmai-24-256 Gárate-Escamila AK, Hajjam El A, Hassani, Andrès E. Classification models for heart disease prediction using feature selection and PCA. Inf Med Unlocked. 2020;19. 10.1016/j.imu.2020.100330 . Islam MA, Majumder MZH, Hussein MA. Chronic kidney disease prediction based on machine learning algorithms. J Pathol Inf. 2023;14:100189. 10.1016/j.jpi.2023.100189 . September 2022. Ogunsanya M, Isichei J, Desai S. Grid search hyperparameter tuning in additive manufacturing processes. Manuf Lett. 2023;35:1031–42. 10.1016/j.mfglet.2023.08.056 . Aparicio PR et al. Learning Medical Risk Scores for Pediatric Appendicitis, Proc. – 20th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2021, no. December, pp. 1507–1512, 2021. 10.1109/ICMLA52953.2021.00243 Chadaga K, et al. An interpretable and transparent machine learning framework for appendicitis detection in pediatric patients. Sci Rep. 2024;14(1):24454. 10.1038/s41598-024-75896-y . Marcinkevics R, Reis Wolfertstetter P, Wellmann S, Knorr C, Vogt JE. Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis. Front Pediatr. 2021;9:1–12. 10.3389/fped.2021.662183 . Ugne K et al. Multiview Concept Bottleneck Models Applied to Diagnosing Pediatric Appendicitis, in Workshop on Interpretable ML in Healthcare at International Con- ference on Machine Learning (ICML) , 2022. [Online]. Available: https://www.researchgate.net/publication/361908982 Maffezzoni D, Barbierato E, Gatti A. Data-Driven Diagnostics for Pediatric Appendicitis: Machine Learning to Minimize Misdiagnoses and Unnecessary Surgeries, pp. 1–24, 2025. Reismann J, et al. Diagnosis and classification of pediatric acute appendicitis by artificial intelligence methods: An investigator-independent approach. PLoS ONE. 2019;14:1–11. 10.1371/journal.pone.0222030 . Marcinkevičs R et al. Regensburg Pediatric Appendicitis Dataset (1.01). https://doi.org/10.5281/zenodo.7669442 Shah N. Optimization of Convolutional Neural Network hyperparameters using Genetic Algorithms. J High Sch Sci. 2024;8(1):166–79. Emon MU, Imran AM, Islam R, Keya MS, Zannat R, Ohidujjaman. Performance Analysis of Chronic Kidney Disease through Machine Learning Approaches, Proc. 6th Int. Conf. Inven. Comput. Technol. ICICT 2021, no. February, pp. 713–719, 2021. 10.1109/ICICT50816.2021.9358491 Juna A, et al. Water Quality Prediction Using KNN Imputer and Multilayer Perceptron. Water. 2022;14(2592):1–19. https://doi.org/10.3390/w14172592 . Singh C, Singh J. Biomedical Signal Processing, Artificial Neural Network : A Review rtificial Neural Networks, vol. 9, no. December, pp. 2–5, 2016, 10.17485/ijst/2016/v9i47/106889 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 15 May, 2026 Reviewers agreed at journal 13 May, 2026 Reviews received at journal 11 May, 2026 Reviewers agreed at journal 10 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 07 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers invited by journal 30 Apr, 2026 Editor assigned by journal 26 Apr, 2026 Editor invited by journal 08 Apr, 2026 Submission checks completed at journal 03 Apr, 2026 First submitted to journal 03 Apr, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9169732","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":636427340,"identity":"c1cb43c9-9719-487b-8112-e0f045319cd2","order_by":0,"name":"Iliyas Ibrahim Iliyas","email":"data:image/png;base64,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","orcid":"","institution":"University of Maiduguri","correspondingAuthor":true,"prefix":"","firstName":"Iliyas","middleName":"Ibrahim","lastName":"Iliyas","suffix":""},{"id":636427345,"identity":"776c5e85-f9f9-4f37-8df0-3cee60830a82","order_by":1,"name":"Souley Boukari","email":"","orcid":"","institution":"Abubakar Tafawa Balewa University","correspondingAuthor":false,"prefix":"","firstName":"Souley","middleName":"","lastName":"Boukari","suffix":""},{"id":636427348,"identity":"1e54075e-81c3-4ea5-a264-5bfe3378b653","order_by":2,"name":"Abdulsalam Ya’u Gital","email":"","orcid":"","institution":"Abubakar Tafawa Balewa University","correspondingAuthor":false,"prefix":"","firstName":"Abdulsalam","middleName":"Ya’u","lastName":"Gital","suffix":""}],"badges":[],"createdAt":"2026-03-19 12:55:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9169732/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9169732/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108969021,"identity":"31669cad-9488-432d-a260-da761ecee483","added_by":"auto","created_at":"2026-05-11 10:07:36","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":101197,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eResearch Flowchart\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-9169732/v1/b0e4d6f03b42f2c0950d449d.png"},{"id":108969022,"identity":"4b84fd8f-8c8d-4c41-8871-9e7ac48729fb","added_by":"auto","created_at":"2026-05-11 10:07:36","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":24378,"visible":true,"origin":"","legend":"\u003cp\u003eConfusion Matrix\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-9169732/v1/e0a3422fe3816b0bad155607.png"},{"id":108969023,"identity":"7b6d9f76-0d64-4f06-b8c8-547cbf46b9da","added_by":"auto","created_at":"2026-05-11 10:07:36","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":39724,"visible":true,"origin":"","legend":"\u003cp\u003ePerformance Evaluation of the Comparative Analysis Conducted on the ML Models\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-9169732/v1/ec52040a9e8e6f84fa0f9478.png"},{"id":108977599,"identity":"f008cdf4-1eb4-4720-8f79-276d27951f76","added_by":"auto","created_at":"2026-05-11 11:32:17","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":682908,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9169732/v1/63ec94e5-cb36-4736-aab0-6b854abeab4f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Comparative Analysis for Predicting Paediatric Appendicitis Using Machine Learning Models and Genetic Optimisation Technique","fulltext":[{"header":"1.0 Introduction","content":"\u003cp\u003ePaediatric appendicitis is a disease that causes abdominal pain in children. Appendicitis indicates a health concern with a lifetime risk of 6 to 9% and occurs in people from 10 to 19 years of age [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. The risk of developing life-threatening issues increases with the length of time that appendicitis is left untreated [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. With the advancements of technology, we have witnessed notable advancements in the medical sector, which have made it possible to employ data mining techniques to identify trends in the dataset. Medical experts can now accurately diagnose any medical disease due to this analysis. This reduced treatment costs and offered better healthcare [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. The use of data mining in healthcare has evolved due to its potential to reduce expenses, support healthcare providers with treatment plans, and enhance patient care through early disease diagnosis. Early diagnosis is essential, which drives the use of emerging technologies like machine learning (ML) [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. A field of data science known as machine learning (ML) utilises machines to learn, rather than being manually programmed. ML is a collection of methods that let software applications make precise output predictions without any interference [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].ML is becoming an important solution to assist in diagnosing diseases in patients. ML is an analytical tool used when a task has a large dataset and is difficult to program, such as transforming medical records into knowledge, genomic data analysis, and disease prediction [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The process of fitting an ML model to data involves the selection of an ML algorithm, training the algorithm on a dataset, and evaluating the performance of the trained model on new data. The goal of the ML algorithm is to process a training dataset that has a collection of input and target attributes [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. ML considers two main parameters, hyperparameters and parameters. Parameters are internal parameters and are estimated based on the provided dataset, while hyperparameters are external parameters that are set before the training process and used to control the learning process of ML, chosen good parameters guarantees better performance [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. In this study, a comparative analysis of ML models for the prediction of paediatric appendicitis and hyperparameter tuning was conducted on each model using a Genetic Algorithm (GA).\u003c/p\u003e \u003cp\u003eThe contribution of this study is highlighted below:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eExploration of Paediatric appendicitis Disease dataset\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eComparative analysis of different ML models for the prediction of Paediatric appendicitis\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eHyperparameter tuning implementation using Genetic Algorithm\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eEvaluation of the ML models for the prediction of Paediatric appendicitis\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eThis paper consists of five sections, following the introduction in section 1, the related work is discussed in section 2. Section 3 discusses the methodology, including the dataset, genetic algorithm, classification techniques, and performance measures. The environmental setup with the results is discussed in Section 4. Section 5 discussed the conclusion of the study.\u003c/p\u003e"},{"header":"2.0 Related Work","content":"\u003cp\u003eA study by Aparicio et al (2021) proposed a risk super space linear integer model (risk SLIM) to predict paediatric appendicitis to enhance diagnosis, treatment, and complication prediction. The study applied the model on 430 datasets, and the work evaluated the performance of their proposed study with other traditional scores and RF. Their model achieved an AUROC of 0.85\u0026thinsp;\u0026plusmn;\u0026thinsp;0.04 and an AUPR of 0.90\u0026thinsp;\u0026plusmn;\u0026thinsp;0.03 for diagnosing appendicitis, both with and without ultrasound data, respectively. A study by İlyas (2024) developed a model for diagnosing paediatric appendicitis using a multi-output neural network. The study involves using both ultrasound and clinical data from the Children\u0026rsquo;s Hospital St. Hedwig. The proposed study achieved the best scores of 94.23%, 97.44%, and 100% for management classification, severity classification, and diagnosis, respectively. A study by [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e] also proposed a technique for predicting paediatric appendicitis, the study includes a preprocessing stage involving the use of Correlation Feature Selection (CFS) as feature selection and Elephant Search Algorithm (ESA) for optimization and the models developed are LR, Adaboost, and RF, the ensemble model achieved 92.15% accuracy.\u003c/p\u003e \u003cp\u003eChadaga et al (2024) proposed a ML-based ensemble model (APPSTACK) for paediatric appendicitis detection. The study combined multiple models and hyperparameter-tuned the models\u0026rsquo; structures with the Hybrid Bat Algorithm. The study also used five explainable AI (XAI) techniques for interpreting the models\u0026rsquo; outcomes. The study achieved the best accuracy of 94% and interpreted the model\u0026rsquo;s outcome, which showcased a model with diagnostic efficiency in the health sector. The proposed work by Marcinkevics et al (2021) developed a machine learning (ML) model to predict paediatric appendicitis diagnosis, management, and severity. The study improved diagnostic accuracy and streamlined management decisions. The model was trained on 430 records with LR, RF and gradient boosting models. RF achieved an average AUROC of 0.96 for diagnosis, 0.90 for severity and 0.94 for management. Ugne et al (2022) proposed a Multiview concept bottleneck model (MVCBM) to predict paediatric appendicitis using ultrasound images from a cohort of 275 paediatric patients. The study used ResNet-18 for feature extraction and feature fusion through LSTM, concept prediction, and final label prediction. The proposed MVCBM model performed better than the traditional methods, such as ResNet-18 and Radiomics, with an AUROC of 0.96 and AUPR of 0.92 for appendicitis diagnosis. The proposed work by Maffezzoni et al (2025) used the ML model to improve the diagnosis and management of paediatric appendicitis. The models include logistic regression (LR), random forests (RF), XGBoost, and Multilayer Perceptron (MLP). The results show that the RF model achieved high performance with an AUC of 0.94 for diagnosis, 0.92 for management, and 0.70 for severity, reducing unnecessary surgeries by up to 17%. The study by Reismann et al (2019) proposed an artificial intelligence-based model for diagnosing paediatric acute appendicitis, focusing on the use of routine clinical and laboratory parameters like C-reactive protein (CRP), white blood cell counts, and appendiceal diameter from ultrasound images. The study created a biomarker signature for diagnosing appendicitis and differentiating between complicated and uncomplicated appendicitis using ML. The results show that the developed model outperforms traditional methods, with an accuracy of 90% for diagnosing appendicitis and a 95% sensitivity for distinguishing complicated appendicitis, offering a more reliable and objective approach to clinical decision-making. The architecture of the work is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e"},{"header":"3.0 Methodology","content":"\u003ch2\u003e3.1 Appendicitis Dataset\u003c/h2\u003e\n\u003cp\u003eAppendicitis is a disease where inflammation occurs in the appendix, which is a small organ that appears along the large intestine. It is mostly affecting children and needs urgent attention. The appendicitis dataset used in this study was obtained from the UCI machine learning repository of a dataset of the cohort of patients with suspected appendicitis admissions with abdominal pain at ST Hedwig in Rehensburg, Germany [\u003cspan class=\"CitationRef\"\u003e15\u003c/span\u003e]. The dataset has 782 records and 53 features, with Diagnosis as the target variable. The target variable has appendicitis and no appendicitis, with a total of 307 and 317 for appendicitis and no appendicitis, respectively. The dataset is from 2016 to 2021, and the target feature is \u0026ldquo;Diagnosis\u0026rdquo;. Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e summarises the Paediatric appendicitis dataset used in this study.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003ePaediatric Appendicitis Dataset Description\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eS/No.\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eFeature Name\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eDescription\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eValue Type\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eRange\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMissing Values\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge of the patient\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBMI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBody Mass Index\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7.83\u0026ndash;38.16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSex\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThe gender of the patient\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003emale, female\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHeight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHeight of the patient in cm\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e50\u0026ndash;200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWeight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWeight of the patient in kg\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10\u0026ndash;150\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLength of Stay\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDuration of hospital stay in days\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eManagement\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eManagement type (conservative or surgical)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003econservative, surgical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSeverity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThe severity of the condition\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ecomplicated, uncomplicated\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiagnosis Presumptive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresumptive diagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eappendicitis, no appendicitis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDiagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFinal Diagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eappendicitis, no appendicitis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAlvarado Score\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eScore used for the diagnosis of appendicitis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePaediatric Appendicitis Score\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePediatric score used for appendicitis diagnosis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAppendix on US\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of appendix on ultrasound\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAppendix Diameter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThe diameter of the appendix in mm\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e284\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMigratory Pain\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of migratory pain\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLower Right Abd Pain\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePain in the lower right abdomen\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eContralateral Rebound Tenderness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of contralateral rebound tenderness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCoughing Pain\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePain while coughing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNausea\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of nausea\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLoss of Appetite\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLoss of appetite\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBody Temperature\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBody temperature in Celsius\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e35\u0026ndash;42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWBC Count\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWhite blood cell count\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;20,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNeutrophil Percentage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePercentage of neutrophils in blood\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e103\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSegmented Neutrophils\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePercentage of segmented neutrophils\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e728\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNeutrophilia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of neutrophilia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRBC Count\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRed blood cell count\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;10,000,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHaemoglobin\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHaemoglobin level\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRDW\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRed cell distribution width\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThrombocyte Count\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePlatelet count\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;1,000,000\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eKetones_in_Urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of ketones in urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e200\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eRBC in Urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of red blood cells in urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e206\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eWBC in Urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of white blood cells in urine\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e199\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCRP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eC-reactive protein level\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFloat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0\u0026ndash;200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eDysuria\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePainful urination\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStool\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCharacteristics of stool\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003enormal, abnormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePeritonitis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of peritonitis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePsoas Sign\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of the psoas sign, a clinical test for appendicitis.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIpsilateral Rebound Tenderness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of pain upon palpation of the abdomen on the same side as the inflamed appendix.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e163\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUS Performed\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIndicates whether an ultrasound examination was performed.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e40\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eUS Number\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eNumber of ultrasound scans performed for the patient.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eInteger\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1-992\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eFree Fluids\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of free fluids in the abdomen\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e63\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAppendix Wall Layers\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLayers of the appendix wall\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003enormal, abnormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e564\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTarget_Sign\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of the target sign on imaging\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e644\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAppendicolith\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of appendicolith\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e713\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePerfusion\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eTissue perfusion status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003enormal, abnormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e719\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePerforation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAppendix perforation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e701\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e47\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSurrounding Tissue Reaction\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eReaction of the surrounding tissue\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e530\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAppendicular Abscess\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThe presence of an abscess in the appendix\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e697\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAbscess Location\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLocation of abscess, if present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ereUB-reAL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e769\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePathological Lymph Nodes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of pathological lymph nodes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e579\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLymph Nodes Location\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLocation of lymph nodes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ereUB-reAL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e661\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBowel Wall Thickening\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of bowel wall thickening\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e683\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eConglomerate of Bowel Loops\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eThe presence of a conglomerate of bowel loops\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e739\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eIleus\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of ileus\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e722\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCoprostasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of coprostasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e711\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMeteorism\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of meteorism\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e642\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eEnteritis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePresence of enteritis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e716\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e58\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGynaecological Findings\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGynaecological findings, if present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCategorical\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eyes, no\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\"\u003e\n \u003cp\u003e756\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\n \u003ch2\u003e3.2 Data Preprocessing\u003c/h2\u003e\n \u003cp\u003eThe preprocessing in the study includes handling missing values by filling numerical columns with their median and categorical columns with their mode. Categorical features are encoded into numerical values using LabelEncoder. The dataset is then split into features and the target variable, with an 80\u0026thinsp;\u0026minus;\u0026thinsp;20 train-test split, preserving class proportions. Finally, the features are standardised using StandardScaler to ensure that all variables are on the same scale before being used for model training.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\n \u003ch2\u003e3.3 Genetic Algorithm (GA)\u003c/h2\u003e\n \u003cp\u003eGenetic algorithms (GA) are inspired by the principles of natural selection and evolution, enabling them to handle discrete values. GA works by iteratively generating a set of models, which are evaluated based on a global criterion, leading to the formation of subsequent sets of models. Selection is the act of choosing the best solutions from the current population based on their performance, where the solutions represent the hyperparameters. Crossover involves combining the best solutions to create a new one by merging their hyperparameters to form a potentially better solution. Mutation introduces random changes to the solutions by adjusting the hyperparameters, promoting diversity, and preventing the algorithm from converging prematurely on suboptimal solutions [\u003cspan class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\n \u003ch2\u003e3.4 Classification Techniques\u003c/h2\u003e\n \u003cdiv id=\"Sec8\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.1 Decision Tree\u003c/h2\u003e\n \u003cp\u003eThe decision tree classifier used tree-like structures, where the structure represents root nodes as conditions, while the child nodes as class labels, and the branches of the root nodes in the tree structure, which means the effects of the conditions [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec9\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.2 Random Forest\u003c/h2\u003e\n \u003cp\u003eRandom forest is an ML algorithm based on an ensemble of trees derived from a selection of decision trees from randomly chosen training set subsets. It evaluates the final class form votes achieved from various decision trees [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec10\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.3 Logistic Regression\u003c/h2\u003e\n \u003cp\u003eLogistic Regression is an ML model based on a mathematical model that uses logistic functions that form a binary-dependent feature. The statistical binary logistic model has two possible values that represent the dependent variable, which are 0 or 1 [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec11\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.4 K-Nearest Neighbours (KNN)\u003c/h2\u003e\n \u003cp\u003eK-nearest neighbours (KNN) is a non-parametric ML algorithm that is used in both regression and classification tasks. Its working principles are based on the classification of data points based on either the average values of the majority class or the closest neighbours within the feature space. KNN brings similar data points close to each other in the feature space, which are referred to as the nearest neighbours [\u003cspan class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec12\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.5 Na\u0026iuml;ve Bayes\u003c/h2\u003e\n \u003cp\u003eNa\u0026iuml;ve Bayes is a classification model that is logically centred based on the Bayes theorem. It comprises a group of algorithms with similar definitions, such as multinomial naive bayes used on categorical values and Gaussian naive bayes for continuous values [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec13\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.6 Artificial Neural Network\u003c/h2\u003e\n \u003cp\u003eArtificial neural network (ANN) is a type of ML algorithm that got its working principles from the human brain, it consists of so many connected neurons (nodes) that process data, and it enhances its learning by adjusting weights during training with the help of backpropagation, ANN is used for both regression and classification tasks [\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec14\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.7 Extreme Gradient Boosting (XGBoost)\u003c/h2\u003e\n \u003cp\u003eExtreme Gradient Boosting (XGBoost) is a type of ML model based on the framework of gradient boosting, it is applied for both classification and regression tasks and on large datasets with high dimensional feature spaces, it forms an ensemble of decision trees in sequence, were every single tree will correct the error from a previous tree and it prevents overfitting with the help of regularization making it an effective model [\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec15\" class=\"Section3\"\u003e\n \u003ch2\u003e3.4.8 Adaptive Boosting (AdaBoost)\u003c/h2\u003e\n \u003cp\u003eAdaptive Boosting (AdaBoost) is a type of ML model which combines multiple weak classifiers to generate a strong classifier. It has a weight which adjusts based on how well the previous model misclassified instances by adding a higher weight for the subsequent model to focus on them during the training process [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\n \u003ch2\u003e3.5 Performance Metrics\u003c/h2\u003e\n \u003cp\u003eThe evaluation of the model\u0026rsquo;s performance was conducted using four matrices\u0026rsquo; names: accuracy, precision, recall and F1 score. The matrices are briefly described below, and Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e shows the confusion matrix.\u003c/p\u003e\n \u003cdiv id=\"Equa\" class=\"Equation\"\u003e\n \u003cdiv id=\"FileID_Equa\" class=\"mathdisplay\"\u003e$$ \\text{ Accuracy: }\\frac{TP+TN}{TP+FP+FN+TN}$$\u003c/div\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Equb\" class=\"Equation\"\u003e\n \u003cdiv id=\"FileID_Equb\" class=\"mathdisplay\"\u003e$$ \\text{ Precision: }\\frac{TP}{TP+FP}$$\u003c/div\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Equc\" class=\"Equation\"\u003e\n \u003cdiv id=\"FileID_Equc\" class=\"mathdisplay\"\u003e$$ \\text{ F1 Score: }\\frac{2*\\text{ Precision }*\\text{ Recall }}{\\text{ Precision }+\\text{ Recall }}$$\u003c/div\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Equd\" class=\"Equation\"\u003e\n \u003cdiv id=\"FileID_Equd\" class=\"mathdisplay\"\u003e$$ \\text{ Recall: }\\frac{TP}{TP+FN}$$\u003c/div\u003e\n \u003c/div\u003e\n \u003cp\u003eTrue Positive (TP): TP represents an appendicitis instance that was predicted correctly as appendicitis.\u003c/p\u003e\n \u003cp\u003eFalse Positive (FP): FP represents an appendicitis instance that is falsely predicted as no appendicitis\u003c/p\u003e\n \u003cp\u003eFalse Negative (FN): FN represents a no-appendicitis instance that was falsely predicted as appendicitis\u003c/p\u003e\n \u003cp\u003eTrue Negative (TN): TN represents no appendicitis instances that were predicted as no appendicitis\u003c/p\u003e\n\u003c/div\u003e"},{"header":"4.0 Results of the Models","content":"\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Environmental Setup\u003c/h2\u003e \u003cp\u003eThe study was conducted on an HP computer equipped with an Intel Core i7 processor, 13th generation, running at 2.8 GHz, with 16 GB of RAM and a 1 TB hard drive. The code was executed using Python version 3.13.2. The machine learning models were implemented using the scikit-learn (sklearn) library, while the DEAP library was utilised to implement the genetic algorithm for hyperparameter tuning.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003e4.2 Optimal Hyperparameters\u003c/h2\u003e \u003cp\u003eThe genetic algorithm (GA) optimises key hyperparameters for models like XGBClassifier, AdaBoost, and Decision Tree Classifier by refining parameters such as n_estimators, learning_rate, max_depth, subsample, and colsample_bytree for XGBClassifier, and n_estimators and learning_rate for AdaBoost. It also fine-tunes max_depth, min_samples_split, min_samples_leaf, and criterion for the decision tree. The GA evaluates these parameters using a fitness function that measures model accuracy, employing selection, crossover, and mutation operations across generations to find the optimal hyperparameter configuration that maximises model performance. The parameters of XGBoost are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, DT parameters in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e and AdaBoost parameters in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDecision Tree Parameters\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameter\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emax_depth\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5\u0026ndash;20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emin_samples_split\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2\u0026ndash;10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emin_samples_leaf\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1\u0026ndash;2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCriterion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e[Gini, entropy]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eRandom Forest Parameters\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameter\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003en_estimators\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e50\u0026ndash;200\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003elearning_rate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e[0.01, 0.2]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emax_depth\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3\u0026ndash;10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSubsample\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e[0.0, 1.0]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ecolsample_bytree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e[0.0, 1.0]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eAdaboost Parameter\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameter\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003en_estimators\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e50\u0026ndash;200\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003elearning_rate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.01-1.0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Results\u003c/h2\u003e \u003cp\u003eThe results achieved in this study are discussed in this section. The study performed a comparative analysis of an optimised ML model using a Genetic algorithm on the ML models. For optimising the parameters of the Models, GA was used for hyperparameter tuning the models to get the optimal scores. The parameters of the GA were shown in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, where a population size of 10 was used, the number of generations was 10, and the fitness function used was an XGB classifier for evaluating the performance of each individual.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eGenetic Algorithm Parameters\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eParameter\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eValues\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePopulation size\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo. of Generation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCross Over Probability\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMutation Probability\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCross Method\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMatch Method\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelTournament\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFitness Function\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eXGB Classifier\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the accuracy achieved by each model compared in the study, with AdaBoost and DT having achieved the best accuracy of 97.45% for both, followed by RF with 96.82%, ANN and XGBoost with 95.45% each, LR with 93.63%, KNN with 82.17% and NB achieved the lowest accuracy of 67.52%.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e shows the summary of performances achieved by the evaluated models, in terms of F1 score, Precision and Recall. DT and Adaboost achieved the best scores of 97.45, 97.45and 97.45, respectively. NB achieved the lowest score in terms of F1 score, precision and recall with 66.56, 78.35 and 67.52, respectively.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePerformance Evaluation of the Models with Other Metrics\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eLR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eF1 Score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eConfusion matrix\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e93.61\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.63\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e93.63\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89 4\u003c/p\u003e \u003cp\u003e6 58\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e95.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91 2\u003c/p\u003e \u003cp\u003e5 59\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e96.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e96.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91 2\u003c/p\u003e \u003cp\u003e3 61\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e66.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e78.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e67.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e45 48\u003c/p\u003e \u003cp\u003e3 61\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eANN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e95.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89 4\u003c/p\u003e \u003cp\u003e3 61\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e82.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e82.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e82.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79 14\u003c/p\u003e \u003cp\u003e14 50\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdaBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e97.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e97.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e97.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91 2\u003c/p\u003e \u003cp\u003e2 62\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e97.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e97.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e97.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91 2\u003c/p\u003e \u003cp\u003e2 62\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e shows the time it takes for GA to finish tuning the parameters of the models, which are XGBoost, Adaboost and DT, based on the ranges of the parameters chosen to achieve an optimal score. GA took 22.65 secs to finish the hyperparameter tuning process, it took 0.49 secs to finish on AdaBoost and 0.7 secs on DT.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, this comparative analysis on predicting paediatric appendicitis using machine learning demonstrates the potential of various models, including RF, LR, XGBoost, AdaBoost, NB, DT, KNN, and ANN, in achieving high accuracy. Among the models tested, AdaBoost and Decision Trees (DT) achieved the best accuracy, scoring 97.45%. The incorporation of hyperparameter tuning using Genetic Algorithms (GA) proved effective in selecting optimal parameters, contributing to improved model performance. The findings underscore the importance of machine learning models and optimisation techniques, such as GA, in achieving robust preditive accuracy. Future research should focus on expanding the dataset size, exploring other medical tasks beyond appendicitis diagnosis, and utilising more advanced models to further enhance prediction accuracy and clinical applicability.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArtificial Intelligence\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eML\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMachine Learning\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eGA\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eGenetic Algorithm\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eDT\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eDecision Tree\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eRF\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eLR\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eLogistic Regression\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eNB\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eNa\u0026iuml;ve Bayes\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eKNN\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eK\u0026ndash;Nearest Neighbours\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eANN\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArtificial Neural Network\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eXGBoost\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eExtreme Gradient Boosting\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAdaBoost\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eAdaptive Boosting\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eUCI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eUniversity of California Irvine (Machine Learning Repository)\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCRP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eC\u0026ndash;reactive Protein\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eWBC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eWhite Blood Cell\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAUROC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArea Under the Receiver Operating Characteristic Curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAUPR\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArea Under the Precision\u0026ndash;Recall Curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eXAI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eExplainable Artificial Intelligence\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003ch2\u003eEthics approval and consent to participate\u003c/h2\u003e \u003cp\u003eEthics declaration: not applicable. Consent to publish declaration: not applicable.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eConsent for Publication\u003c/strong\u003e \u003cp\u003eConsent to publication declaration: not applicable.\u003c/p\u003e \u003c/p\u003e\u003cp\u003e \u003ch2\u003eCompeting Interests\u003c/h2\u003e \u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e \u003cp\u003eThis research received no external funding.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eIliyas Ibrahim Iliyas: Conceptualization, methodology, software implementation, data preprocessing, formal analysis, writing \u0026ndash; original draft preparation. Souley Boukari: Supervision, validation, review and editing of the manuscript. Abdulsalam Ya\u0026rsquo;u Gital: Supervision, methodology guidance, review and editing of the manuscript.All authors have read and approved the final version of the manuscript.\u003c/p\u003e\u003cp\u003eAll authors have read and approved the final version of the manuscript.\u003c/p\u003e\n\u003ch2\u003eAcknowledgements\u003c/h2\u003e \u003cp\u003eThe authors are grateful to colleagues and reviewers whose valuable feedback and suggestions helped improve the quality of this work.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets generated and analysed during the current study are available in the UCI Machine Learning Repository at https://archive.ics.uci.edu/dataset/938/regensburg+pediatric+appendicitis\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eİlyas \u0026Ouml;. Utilizing Machine Learning for Enhanced Diagnosis and Management of Utilizing Machine Learning for Enhanced Diagnosis and Management of Pediatric Appendicitis: A Multilayer Neural Network Approach. Aintelia, 2, 2, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePati A, Parhi M, Pattanayak BK. An Ensemble Deep Learning Approach for Chronic Kidney Disease (CKD) Prediction, \u003cem\u003eAIP Conf. Proc.\u003c/em\u003e, vol. 2819, no. January, 2023, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1063/5.0136894\u003c/span\u003e\u003cspan address=\"10.1063/5.0136894\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDev S, Wang H, Nwosu CS, Jain N, Veeravalli B, John D. A predictive analytics approach for stroke prediction using machine learning and neural networks. Healthc Anal. 2022;2:100032. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.health.2022.100032\u003c/span\u003e\u003cspan address=\"10.1016/j.health.2022.100032\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKabir MF, Chen T, Ludwig SA. A performance analysis of dimensionality reduction algorithms in machine learning models for cancer prediction, \u003cem\u003eHealthc. Anal.\u003c/em\u003e, vol. 3, no. October 2022, p. 100125, 2023. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.health.2022.100125\u003c/span\u003e\u003cspan address=\"10.1016/j.health.2022.100125\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIliyas II, Boukari S, Ya A. Recent trends in prediction of chronic kidney disease using different learning approaches: a systematic literature review, \u003cem\u003eJ. Med. Artif. Intell.\u003c/em\u003e, no. July 2024, pp. 0\u0026ndash;2, 2025. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21037/jmai-24-256\u003c/span\u003e\u003cspan address=\"10.21037/jmai-24-256\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eG\u0026aacute;rate-Escamila AK, Hajjam El A, Hassani, Andr\u0026egrave;s E. Classification models for heart disease prediction using feature selection and PCA. Inf Med Unlocked. 2020;19. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.imu.2020.100330\u003c/span\u003e\u003cspan address=\"10.1016/j.imu.2020.100330\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIslam MA, Majumder MZH, Hussein MA. Chronic kidney disease prediction based on machine learning algorithms. J Pathol Inf. 2023;14:100189. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jpi.2023.100189\u003c/span\u003e\u003cspan address=\"10.1016/j.jpi.2023.100189\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. September 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOgunsanya M, Isichei J, Desai S. Grid search hyperparameter tuning in additive manufacturing processes. Manuf Lett. 2023;35:1031\u0026ndash;42. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.mfglet.2023.08.056\u003c/span\u003e\u003cspan address=\"10.1016/j.mfglet.2023.08.056\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAparicio PR et al. Learning Medical Risk Scores for Pediatric Appendicitis, \u003cem\u003eProc. \u0026ndash;\u0026thinsp;20th IEEE Int. Conf. Mach. Learn. Appl. ICMLA\u003c/em\u003e 2021, no. December, pp. 1507\u0026ndash;1512, 2021. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/ICMLA52953.2021.00243\u003c/span\u003e\u003cspan address=\"10.1109/ICMLA52953.2021.00243\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChadaga K, et al. An interpretable and transparent machine learning framework for appendicitis detection in pediatric patients. Sci Rep. 2024;14(1):24454. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41598-024-75896-y\u003c/span\u003e\u003cspan address=\"10.1038/s41598-024-75896-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMarcinkevics R, Reis Wolfertstetter P, Wellmann S, Knorr C, Vogt JE. Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis. Front Pediatr. 2021;9:1\u0026ndash;12. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fped.2021.662183\u003c/span\u003e\u003cspan address=\"10.3389/fped.2021.662183\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUgne K et al. Multiview Concept Bottleneck Models Applied to Diagnosing Pediatric Appendicitis, in \u003cem\u003eWorkshop on Interpretable ML in Healthcare at International Con- ference on Machine Learning (ICML)\u003c/em\u003e, 2022. [Online]. Available: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.researchgate.net/publication/361908982\u003c/span\u003e\u003cspan address=\"https://www.researchgate.net/publication/361908982\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMaffezzoni D, Barbierato E, Gatti A. Data-Driven Diagnostics for Pediatric Appendicitis: Machine Learning to Minimize Misdiagnoses and Unnecessary Surgeries, pp. 1\u0026ndash;24, 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eReismann J, et al. Diagnosis and classification of pediatric acute appendicitis by artificial intelligence methods: An investigator-independent approach. PLoS ONE. 2019;14:1\u0026ndash;11. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1371/journal.pone.0222030\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0222030\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMarcinkevičs R et al. Regensburg Pediatric Appendicitis Dataset (1.01). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5281/zenodo.7669442\u003c/span\u003e\u003cspan address=\"10.5281/zenodo.7669442\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShah N. Optimization of Convolutional Neural Network hyperparameters using Genetic Algorithms. J High Sch Sci. 2024;8(1):166\u0026ndash;79.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEmon MU, Imran AM, Islam R, Keya MS, Zannat R, Ohidujjaman. Performance Analysis of Chronic Kidney Disease through Machine Learning Approaches, \u003cem\u003eProc. 6th Int. Conf. Inven. Comput. Technol. ICICT\u003c/em\u003e 2021, no. February, pp. 713\u0026ndash;719, 2021. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/ICICT50816.2021.9358491\u003c/span\u003e\u003cspan address=\"10.1109/ICICT50816.2021.9358491\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJuna A, et al. Water Quality Prediction Using KNN Imputer and Multilayer Perceptron. Water. 2022;14(2592):1\u0026ndash;19. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/w14172592\u003c/span\u003e\u003cspan address=\"10.3390/w14172592\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh C, Singh J. Biomedical Signal Processing, Artificial Neural Network : A Review rtificial Neural Networks, vol. 9, no. December, pp. 2\u0026ndash;5, 2016, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.17485/ijst/2016/v9i47/106889\u003c/span\u003e\u003cspan address=\"10.17485/ijst/2016/v9i47/106889\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Paediatric Appendicitis, Machine Learning, Genetic Algorithm Optimisation, Hyperparameter Tuning and Clinical Disease Prediction","lastPublishedDoi":"10.21203/rs.3.rs-9169732/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9169732/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePaediatric appendicitis is a known medical emergency that affects adolescents and children, possibly leading to life-threatening difficulties if it is not diagnosed and treated on time. Diagnosing Paediatric appendicitis earlier plays an important role in preventing severe outcomes. Recent developments in Machine Learning (ML) have proven to be efficient in enhancing diagnostic accuracy. This study proposed a comparative analysis of ML models such as Decision Tree, Logistic Regression (LR), Na\u0026iuml;ve Bayes (NB), Random Forest (RF), K-Nearest Neighbours (KNN), Adaptive Boosting (AdaBoost), Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost) for the prediction of paediatric appendicitis, the analysis was conducted on a dataset consisting of 782 patients records with 53 clinical features obtained from UCI Machine Learning Repository. An optimisation technique called Genetic Algorithm (GA) was utilised for hyperparameter tuning the models, a nature-inspired optimisation that iteratively evolves model parameters for value imputation. The dataset was preprocessed by handling missing values with value imputation and categorical values with LabelEncoder. The models were evaluated using accuracy, precision, recall, and F1-score metrics. The analysis results show that AdaBoost and DT classifiers achieved the highest accuracy of 97.45%. The GA significantly improved model performance by optimising hyperparameters such as learning rate, maximum depth, and estimators. NB achieved the lowest performance, demonstrating the importance of model selection and tuning. This research highlights the effectiveness of ML models, particularly when combined with GA optimisation in diagnosing paediatric appendicitis. These findings contribute to the growing body of evidence supporting the use of AI and ML in clinical decision-making, reducing diagnostic delays and improving patient outcomes.\u003c/p\u003e","manuscriptTitle":"A Comparative Analysis for Predicting Paediatric Appendicitis Using Machine Learning Models and Genetic Optimisation Technique","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-11 10:07:32","doi":"10.21203/rs.3.rs-9169732/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-16T03:59:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"31381109140459816175110342773904228962","date":"2026-05-13T16:23:47+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T17:46:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"88612704126971305589569236723407012489","date":"2026-05-10T18:10:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"164627382105003425962261867003263879320","date":"2026-05-07T19:43:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"210885298253043382168251833975107025268","date":"2026-05-07T18:30:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"199523233768558226176654474961597532254","date":"2026-05-05T13:33:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T18:11:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"176367786999113179341977766804529687710","date":"2026-04-30T13:20:40+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-30T12:55:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-26T21:19:57+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-08T23:36:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-03T21:08:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2026-04-03T21:04:23+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"600f129a-ea5a-49a2-9b44-d1018971ac15","owner":[],"postedDate":"May 11th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-16T03:59:56+00:00","index":64,"fulltext":""},{"type":"reviewerAgreed","content":"31381109140459816175110342773904228962","date":"2026-05-13T16:23:47+00:00","index":63,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T17:46:47+00:00","index":62,"fulltext":""},{"type":"reviewerAgreed","content":"88612704126971305589569236723407012489","date":"2026-05-10T18:10:05+00:00","index":61,"fulltext":""},{"type":"reviewerAgreed","content":"164627382105003425962261867003263879320","date":"2026-05-07T19:43:14+00:00","index":59,"fulltext":""},{"type":"reviewerAgreed","content":"210885298253043382168251833975107025268","date":"2026-05-07T18:30:11+00:00","index":57,"fulltext":""},{"type":"reviewerAgreed","content":"199523233768558226176654474961597532254","date":"2026-05-05T13:33:35+00:00","index":41,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T18:11:16+00:00","index":39,"fulltext":""},{"type":"reviewerAgreed","content":"176367786999113179341977766804529687710","date":"2026-04-30T13:20:40+00:00","index":37,"fulltext":""},{"type":"reviewersInvited","content":"30","date":"2026-04-30T12:55:19+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T10:07:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-11 10:07:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9169732","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9169732","identity":"rs-9169732","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}