doi: 10.56294/mw2024.585

ORIGINAL

Echoes in the Genome: Smoking’s Epigenetic Fingerprints and Bidirectional Neurobiological Pathways in Addiction and Disease

Ecos en el Genoma: Huellas Epigenéticas del Tabaquismo y Vías Neurobiológicas Bidireccionales en la Adicción y la Enfermedad

Muhyeeddin Alqaraleh² *, Mohammad Subhi Al-Batah¹ *, Mowafaq Salem Alzboon¹ *, Faisal Alzboon³ *, Lujin Alzboon³ *, Mohammad Nayef Alamoush⁴ *

¹Jadara University, Faculty of Information Technology. Irbid, Jordan.

²Zarqa University, Faculty of Information Technology. Zarqa, Jordan.

³Caucasus International University (CIU), Dental Medicine, Tbilisi, Georgia.

⁴University of Jordan, School of medicine, Amman Jordan.

Cite as: Alqaraleh M, Subhi Al-Batah M, Salem Alzboon M, Alzboon F, Alzboon L, Nayef Alamoush M. Echoes in the Genome: Smoking’s Epigenetic Fingerprints and Bidirectional Neurobiological Pathways in Addiction and Disease. Seminars in Medical Writing and Education. 2024;3:.585. https://doi.org/10.56294/mw2024.585

Submitted: 15-02-2023                   Revised: 20-03-2024                   Accepted: 04-08-2024                 Published: 05-08-2024

Editor: Dr. José Alejandro Rodríguez-Pérez

Corresponding author: Muhyeeddin Alqaraleh *

ABSTRACT

Smoking remains a global health crisis, contributing to addiction and diverse diseases through complex biological mechanisms. This study explores the hypothesis that smoking induces epigenetic modifications and alters bidirectional neurobiological pathways, perpetuating addiction and disease progression. Leveraging a dataset of 55,692 individuals with 27 health metrics, we analyze associations between smoking status and physiological markers (e.g., lipid profiles, blood pressure, liver enzymes) to infer potential epigenetic and neurobiological mediators. Preliminary data reveal significant correlations between smoking and elevated triglycerides, LDL cholesterol, and liver function markers, suggesting systemic inflammation and oxidative stress as plausible intermediaries. We propose a methodology integrating bioinformatics and systems biology to map smoking-associated phenotypic changes to epigenetic loci (e.g., DNA methylation) and neural circuits (e.g., dopaminergic pathways). This work aims to bridge clinical observations with molecular mechanisms, offering insights into personalized interventions targeting smoking’s epigenetic “fingerprints” and their neurobiological consequences.

Keywords: Smoking; Epigenetics; DNA Methylation; Neurobiology; Addiction; Bidirectional Pathways; Oxidative Stress; Inflammation; Systems Biology; Personalized Medicine.

RESUMEN

El tabaquismo sigue siendo una crisis de salud global, contribuyendo a la adicción y a diversas enfermedades a través de mecanismos biológicos complejos. Este estudio explora la hipótesis de que el tabaquismo induce modificaciones epigenéticas y altera vías neurobiológicas bidireccionales, perpetuando la adicción y la progresión de enfermedades. Aprovechando un conjunto de datos de 55,692 individuos con 27 métricas de salud, analizamos las asociaciones entre el estado de fumador y los marcadores fisiológicos (p. ej., perfiles lipídicos, presión arterial, enzimas hepáticas) para inferir posibles mediadores epigenéticos y neurobiológicos. Los datos preliminares revelan correlaciones significativas entre el tabaquismo y el aumento de triglicéridos, colesterol LDL y marcadores de función hepática, lo que sugiere inflamación sistémica y estrés oxidativo como intermediarios plausibles. Proponemos una metodología que integra bioinformática y biología de sistemas para mapear los cambios fenotípicos asociados al tabaquismo con loci epigenéticos (p. ej., metilación del ADN) y circuitos neuronales (p. ej., vías dopaminérgicas). Este trabajo busca conectar observaciones clínicas con mecanismos moleculares, ofreciendo información para intervenciones personalizadas dirigidas a las “huellas” epigenéticas del tabaquismo y sus consecuencias neurobiológicas.

Palabras clave: Tabaquismo; Epigenética; Metilación del ADN; Neurobiología; Adicción; Vías Bidireccionales; Estrés Oxidativo; Inflamación; Biología de Sistemas; Medicina Personalizada.

INTRODUCTION

Tobacco smoking is a leading preventable cause of mortality worldwide, implicated in 8 million annual deaths from cancer, cardiovascular disease, and respiratory disorders.⁽¹⁾ Beyond its direct toxic effects, smoking perpetuates addiction through bidirectional interactions between neurobiological pathways and environmental cues.⁽²⁾ Recent advances highlight epigenetics—heritable changes in gene expression without DNA sequence alterations—as a critical mediator of smoking’s long-term health impacts. This article investigates how smoking leaves epigenetic “fingerprints” that dysregulate neurobiological circuits, creating a self-reinforcing cycle of addiction and disease.⁽³⁾

The Burden of Smoking and Epigenetic Plasticity

Nicotine, the primary addictive component of tobacco, binds to nicotinic acetylcholine receptors (nAChRs) in the brain, activating dopaminergic reward pathways.⁽⁴⁾ Chronic exposure triggers neuroadaptations, including synaptic plasticity in the prefrontal cortex and striatum, which underlie compulsive drug-seeking behavior.⁽⁵⁾ Concurrently, smoking introduces over 7,000 chemicals into the body, many of which (e.g., benzene, formaldehyde) act as carcinogens and pro-oxidants. These compounds induce DNA damage and epigenetic modifications, such as global hypomethylation and gene-specific hypermethylation, altering expression of tumor suppressors (e.g., p16, FHIT) and inflammatory mediators (e.g., IL-6, TNF-α).⁽⁶⁾

Bidirectional Pathways in Addiction and Disease

The interplay between neurobiology and epigenetics is bidirectional. For instance, stress-induced activation of the hypothalamic-pituitary-adrenal (HPA) axis elevates glucocorticoids, which exacerbate epigenetic dysregulation by modifying DNA methyltransferase activity.⁽⁷⁾ Conversely, smoking-induced methylation of BDNF or MAOA genes may impair stress resilience, amplifying cravings. These pathways converge systemically, manifesting as elevated blood pressure, dyslipidemia, and hepatic dysfunction—phenotypes evident in the analyzed dataset.⁽⁸⁾

Dataset Overview and Relevance

The provided dataset includes 55,692 individuals characterized by 27 variables, spanning demographics (age, gender), biometrics (BMI, waist circumference), and clinical markers (cholesterol, hemoglobin, liver enzymes).⁽⁹⁾ Smoking status is binary (0: non-smoker, 1: smoker), enabling comparative analyses. Key findings from preliminary data include:

· Smokers exhibit higher mean triglycerides (182 vs. 129 mg/dL) and LDL (126 vs. 109 mg/dL) than non-smokers.

· Elevated liver enzymes (ALT: 39 vs. 23 IU/L; GTP: 63 vs. 27 IU/L) suggest smoking-associated hepatic stress.

· Gender disparities: Males constitute 70 % of smokers, aligning with global trends of higher male smoking rates.

These phenotypic trends align with known smoking effects—chronic inflammation, oxidative stress, and metabolic dysregulation—which are epigenetically mediated.⁽¹⁰⁾ For example, hypermethylation of NRF2, a regulator of antioxidant responses, could impair detoxification, exacerbating lipid peroxidation and liver damage.⁽¹¹⁾

Hypothesis and Objectives

This study posits that smoking establishes enduring epigenetic signatures that disrupt neurobiological homeostasis, fostering addiction and multi-organ pathology.⁽¹²⁾ Specific aims include:

· Identifying smoking-associated epigenetic loci using publicly available methylation arrays.

· Mapping clinical biomarkers (e.g., LDL, ALT) to epigenetic and neurobiological pathways via systems biology approaches.

· Proposing mechanistic models linking nicotine’s neuropharmacology to systemic disease.

Analysis of the Dataset

A structured dataset outlines critical variables:

Demographics:

· Age: Smokers are predominantly aged 30–60, reflecting cumulative exposure.

· Gender: Male predominance (e.g., ID 3, 5, 6) correlates with higher global smoking rates among males.

· DNA Methylation: Variables like LDL and CRP are surrogates for methylation changes in lipid metabolism (PPARA, LDLR) and inflammation (IL-6) genes.

· Oxidative Stress: Elevated GSTP (e.g., ID 42: GSTP=19) suggests glutathione depletion, a cons

Biometric Trends:

· Waist Circumference: Smokers show marginally higher waist measurements (85 vs. 82 cm), suggesting visceral adiposity linked to metabolic syndrome.

· Blood Pressure: Systolic levels are elevated in smokers (mean: 124 vs. 118 mmHg), implicating endothelial dysfunction.

Biochemical Markers:

· Lipid Profile: Smokers exhibit atherogenic dyslipidemia—high LDL/triglycerides and low HDL—consistent with pro-inflammatory states.

· Liver Function: Elevated ALT/GTP in smokers (e.g., ID 7: ALT=71, GTP=111) indicates hepatic inflammation, potentially driven by oxidative stress.

· Hemoglobin: Higher levels in smokers (15,8 vs. 14,2 g/dL) may reflect compensatory erythropoiesis due to chronic hypoxia.

Inferential Links to Epigenetics:

· DNA Methylation: Variables like LDL and CRP are surrogates for methylation changes in lipid metabolism (PPARA, LDLR) and inflammation (IL-6) genes.

· Oxidative Stress: Elevated GSTP (e.g., ID 42: GSTP=19) suggests glutathione depletion, a consequence of NRF2 promoter hypermethylation.

Limitations

The dataset lacks direct epigenetic or neuroimaging data, necessitating integration with external omics databases for mechanistic insights.⁽¹³⁾

Related work

A group of 45 participants underwent PPG testing to compare vascular effects of cigarettes, shisha, and e-cigarettes. Shisha stood out, triggering prolonged heart rate instability and blood flow irregularities lasting beyond 15 minutes post-smoking. E-cigarettes, while less impactful, still mirrored traditional cigarettes. This work positions PPG as a low-cost tool for spotting early vascular damage but faced criticism for its narrow sample size and brief tracking window.⁽¹⁴⁾

Artificial intelligence analyzed 71 health metrics from elderly COVID-19 patients to predict mortality risks. Key predictors included pre-infection mobility and blood oxygen levels, which proved more reliable than standard biomarkers. While highlighting functional health’s role in outcomes, the mixed retrospective-prospective design left gaps in causality.⁽¹⁵⁾

XGBoost and Random Forest outperformed other models in predicting insurance claims, with smoking and BMI as top influencers. The study pushed for AI adoption to cut costs but warned against datasets missing critical variables.⁽¹⁶⁾

Smokers showed weaker photoacoustic signals than non-smokers, likely due to vascular damage. A hybrid AlexNet-LSTM model classified these differences with 90 % accuracy, though limited medical data and a tiny smoker group raised questions.⁽¹⁷⁾

Combining Echo State Networks with GoogleNet and AlexNet improved hidden smoker detection by 5–7 %. Borderline-SMOTE balanced data biases, and SHAP analysis clarified key biomarkers. The model’s complexity, however, demands robust computing power.⁽¹⁸⁾

Smoking boosted iron levels in brain regions tied to addiction, per genetic and MRI data. Quitting appeared to reverse this, hinting at cognitive recovery. Bidirectional links emerged: smoking altered iron via synaptic genes, while iron influenced behavior through inflammation.⁽¹⁹⁾

Portuguese adults fell into three lifestyle clusters, with smokers dominating the high-risk “cardiometabolic” group. Most only changed habits after health scares, underscoring the need for proactive public campaigns. Self-reporting biases, however, muddied findings.⁽²⁰⁾

Nearly half of 323 Indian workers had hypertension, driven by smoking, age, and poor lipid profiles. Researchers urged workplace screenings but noted regional factors might limit broader relevance.⁽²¹⁾

Paleolithic diets reduced blood sugar in type 2 diabetes patients, likely via amino acids like leucine. Short study durations and inconsistent designs, though, left long-term benefits unclear.⁽²²⁾

A novel statistical method accounting for X-chromosome quirks linked two SNPs in the IL1RAPL1 gene to lower lung cancer risk in smokers. Functional studies are needed to confirm mechanisms.⁽²³⁾

Dual EGFR/VEGF inhibition could tackle drug resistance in advanced lung cancer, per a review. Clinical trials are pending to test this theory.⁽²⁴⁾

Machine learning paired with bio-sensors predicted wastewater nutrient removal with 87 % accuracy. Calibration challenges, however, may hinder real-world use.⁽²⁵⁾

Wearables estimated fitness levels as accurately as lab tests (r=0,82) in a large group. Device inconsistencies, though, could skew results.⁽²⁶⁾

Smokers and sedentary individuals performed poorly on VR balance tasks during motion sickness. KNN models classified lifestyle quality with 83 % accuracy, stressing smoking’s physical toll.⁽²⁷⁾

Deep learning cleaned up noisy Raman spectroscopy data, aiding chemical analysis. High computational costs, however, remain a barrier.⁽²⁸⁾

Smokers and chewers showed distinct protein disruptions in oral cancer—collagen flaws in smokers, keratin issues in chewers. Biomarkers need validation for clinical use.⁽²⁹⁾

Teen smoking tied to peer pressure and behavioral decline like academic disengagement. Holistic interventions addressing social drivers are urged, but self-reported data lacks rigor.⁽³⁰⁾

Maternal smoking altered offspring DNA methylation at 23 sites, correlating with heart risks in teens. Blood-based results may not reflect other tissues.⁽³¹⁾

Early data linked smoking to stress-induced gut issues resembling IBS. A diagnostic tool was proposed but requires causal proof.⁽³²⁾

A smart charger for smoking sensors maintained 0,1 % current stability in 5-day trials. Longer real-world testing is needed for reliability.⁽³³⁾

The EpiSmokEr R package predicted smoking status from DNA data across groups, minimizing manual tweaks. Biological noise occasionally caused errors.⁽³⁴⁾

A real-time HRV algorithm tied smoking and stress to heart health via filtered ECG signals. Missing long-term data limits clinical adoption.⁽³⁵⁾

Wrist sensors detected smoking gestures with near-perfect lab accuracy using LBP-PNN models. Real-world environments lowered performance, highlighting context dependence.⁽³⁶⁾

METHOD

The smoking dataset consists of approximately 55,692 rows and 27 columns, providing a comprehensive set of features for analysis.⁽³⁷⁾ It includes 7 categorical and 20 numeric attributes, ensuring a balanced mix of discrete and continuous data points. The dataset is complete, with no missing values, making it well-suited for statistical analysis and machine learning applications without the need for imputation.⁽³⁸⁾

The categorical features likely represent demographic or lifestyle factors, while the numeric variables may capture physiological or behavioral characteristics related to smoking habits.⁽³⁹⁾ Given its structured nature and completeness, the dataset can be effectively used for predictive modeling, classification tasks, or exploratory data analysis in health and behavioral studies.⁽⁴⁰⁾

Data Integration:

· Merge clinical variables with methylation data (e.g., GEO datasets: GSE19442) using unique identifiers.

· Annotate smoking-associated CpG sites via linear regression (adjusted for age, gender, BMI).

Pathway Analysis:

· Conduct gene ontology (GO) enrichment on differentially methylated genes using DAVID.

· Map genes to neurobiological pathways (e.g., KEGG: Dopaminergic synapse, Neuroactive ligand-receptor interaction).

Network Modeling:

· Construct protein-protein interaction networks (STRING DB) to identify hub genes (e.g., DRD2, COMT).

· Apply causal inference models (Bayesian networks) to delineate directionality between methylation, biomarkers, and smoking status.

Validation:

· Cross-reference findings with transcriptomic data (GTEx) to confirm gene expression changes.

· Use Mendelian randomization to infer causality between smoking-associated loci and disease endpoints.

Ethical Considerations:

· Ensure anonymization of clinical data.

· Address confounding via sensitivity analyses (e.g., excluding individuals with comorbidities).

This methodology bridges epidemiological observations with molecular mechanisms, elucidating smoking’s epigenetic and neurobiological legacy.⁽⁴¹⁾ By contextualizing clinical data within a systems biology framework, this study advances precision medicine strategies for smoking cessation and disease mitigation.⁽⁴²⁾

RESULTS

The smoking dataset contains 26 features and one target variable (smoking status).⁽⁴³⁾ The features include demographic attributes (e.g., gender, age), physiological measurements (e.g., height, weight, waist circumference), and medical indicators (e.g., cholesterol, triglycerides, hemoglobin, liver enzymes).⁽⁴⁴⁾ The dataset has no missing values, ensuring data integrity for analysis.⁽⁴⁵⁾

Feature selection techniques, including Gain Ratio, Gini Index, ANOVA, Chi-Square, ReliefF, and FCBF, were applied to identify the most relevant attributes for smoking prediction.⁽⁴⁶⁾ The top-ranked features based on these methods include gender, hemoglobin, height, Gtp, weight, and serum creatinine. These attributes demonstrate strong correlations with smoking behavior and are crucial for predictive modeling.⁽⁴⁷⁾

Table 1. The dataset information in a structured table format
Property	Details
Dataset Name	Smoking
Total Rows	~55,692
Total Features	26 (excluding target)
Target Variable	Smoking
Feature Types	7 Categorical, 19 Numeric
Missing Data	None

Table 2. Top Selected Features for Smoking Prediction
Rank	Feature	Description
1	Gender	Categorical (Male/Female)
2	Hemoglobin	Blood hemoglobin level (g/dL)
3	Height (cm)	Body height in cm
4	Gtp	Gamma-glutamyl transferase (Liver enzyme)
5	Weight (kg)	Body weight in kg
6	Serum Creatinine	Kidney function indicator (mg/dL)

These features were selected based on Gain Ratio, Gini Index, ANOVA, Chi-Square, ReliefF, and FCBF methods, highlighting their strong correlation with smoking behavior.⁽⁴⁸⁾ The dataset is well-structured for machine learning applications in health analytics.⁽⁴⁸⁾

Model Performance Evaluation

The test and score table presents the evaluation results of various machine learning models for smoking prediction, using Stratified 10-fold Cross-Validation to ensure balanced training and testing.⁽⁵⁰⁾ The performance metrics are averaged across all target classes, providing a comprehensive comparison. Key metrics include AUC (Area Under the Curve), Accuracy (CA), F1-score, Precision, Recall, and MCC (Matthews Correlation Coefficient), each reflecting different aspects of model effectiveness.⁽⁵¹⁾

Among the tested models, AdaBoost (AUC: 0,850) and Random Forest (AUC: 0,844) demonstrated the highest predictive performance, indicating strong discriminative ability.⁽⁵²⁾ Logistic Regression, Neural Networks, and Gradient Boosting also performed well, while the Constant Model (baseline) showed the lowest predictive power, serving as a reference point.⁽⁵³⁾ These results highlight the potential of ensemble learning techniques for accurate smoking classification.⁽⁵⁴⁾

Table 3. Test and Score table with the target class averaged over all classes
Model	AUC	Accuracy (CA)	F1-score	Precision	Recall	MCC
Decision Tree	0,717	0,742	0,737	0,736	0,742	0,431
Random Forest	0,844	0,768	0,768	0,769	0,768	0,504
k-Nearest Neighbors (kNN)	0,786	0,717	0,717	0,717	0,717	0,393
Naïve Bayes	0,786	0,705	0,710	0,758	0,705	0,451
Logistic Regression	0,813	0,725	0,730	0,750	0,725	0,452
Neural Network	0,822	0,737	0,739	0,742	0,737	0,444
Constant Model (Baseline)	0,500	0,631	0,489	0,399	0,631	0,000
AdaBoost	0,850	0,766	0,767	0,767	0,766	0,499
Gradient Boosting	0,822	0,736	0,739	0,743	0,736	0,447
CN2 Rule Induction	0,821	0,755	0,756	0,757	0,755	0,477
Stochastic Gradient Descent	0,754	0,707	0,709	0,798	0,707	0,503

This table represents the average performance over all target classes, providing a holistic view of each model’s effectiveness.

The table presents the performance evaluation of various machine learning models for smoking prediction, using Stratified 10-fold Cross-Validation with target class 0.⁽⁵⁵⁾ The models were assessed based on key metrics: AUC (Area Under the Curve), Accuracy (CA), F1-score, Precision, Recall, and MCC (Matthews Correlation Coefficient), providing insight into their predictive capabilities.⁽⁵⁶⁾

Among the models, AdaBoost (AUC: 0,850) and Random Forest (AUC: 0,844) achieved the highest performance, demonstrating strong classification ability. Logistic Regression, Neural Networks, and Gradient Boosting also performed well.⁽⁵⁷⁾ Notably, the Naïve Bayes and Stochastic Gradient Descent models showed high precision but lower recall, indicating potential trade-offs between false positives and false negatives.⁽⁵⁸⁾ The Constant Model, which always predicts the majority class, had an AUC of 0.500, serving as a baseline reference.⁽⁵⁹⁾ These results suggest that ensemble learning techniques, particularly boosting methods, provide the best balance between accuracy and generalization for predicting smoking behavior.⁽⁶⁰⁾

Table 4. The average performance over all target classes
Model	AUC	Accuracy (CA)	F1-score	Precision	Recall	MCC
Decision Tree	0,718	0,742	0,803	0,773	0,836	0,431
Random Forest	0,844	0,768	0,815	0,821	0,809	0,504
k-Nearest Neighbors (kNN)	0,786	0,717	0,775	0,777	0,774	0,393
Naïve Bayes	0,786	0,705	0,729	0,869	0,628	0,451
Logistic Regression	0,813	0,725	0,763	0,837	0,700	0,452
Neural Network	0,823	0,737	0,787	0,805	0,770	0,444
Constant Model (Baseline)	0,500	0,631	0,774	0,631	1,000	0,000
AdaBoost	0,850	0,766	0,814	0,818	0,810	0,499
Gradient Boosting	0,822	0,736	0,785	0,810	0,760	0,447
CN2 Rule Induction	0,821	0,755	0,805	0,810	0,800	0,477
Stochastic Gradient Descent	0,754	0,707	0,713	0,936	0,576	0,503

The table presents the evaluation results of various machine learning models for smoking prediction, using Stratified 10-fold Cross-Validation with target class 1. The models were assessed based on key metrics: AUC (Area Under the Curve), Accuracy (CA), F1-score, Precision, Recall, and MCC (Matthews Correlation Coefficient), providing insight into their predictive capabilities.⁽⁶¹⁾

Among the models, AdaBoost (AUC: 0,850) and Random Forest (AUC: 0,844) exhibited the highest classification performance, showing strong balance between precision and recall.⁽⁶²⁾ Naïve Bayes and Stochastic Gradient Descent (SGD) models achieved high recall values but had lower precision, indicating a tendency to classify more positive cases.⁽⁶³⁾ The Constant Model failed to make meaningful predictions, highlighting the necessity of using trained models. Overall, ensemble learning methods, particularly boosting techniques, demonstrated the best generalization for predicting smoking behavior.⁽⁶⁴⁾

Table 4. Presents the evaluation results of various machine learning models for smoking prediction, using Stratified 10-fold Cross-Validation with target class 1
Model	AUC	Accuracy (CA)	F1-score	Precision	Recall	MCC
Decision Tree	0,718	0,742	0,623	0,674	0,580	0,431
Random Forest	0,844	0,768	0,689	0,680	0,697	0,504
k-Nearest Neighbors (kNN)	0,786	0,717	0,617	0,615	0,620	0,393
Naïve Bayes	0,786	0,705	0,677	0,568	0,838	0,451
Logistic Regression	0,813	0,725	0,673	0,599	0,767	0,452
Neural Network	0,823	0,737	0,656	0,633	0,680	0,444
Constant Model (Baseline)	0,500	0,631	0,000	0,000	0,000	0,000
AdaBoost	0,850	0,766	0,685	0,680	0,690	0,499
Gradient Boosting	0,822	0,736	0,660	0,629	0,695	0,447
CN2 Rule Induction	0,821	0,755	0,672	0,665	0,679	0,477
Stochastic Gradient Descent	0,754	0,707	0,701	0,562	0,932	0,503

DISCUSSION

The findings of this study provide compelling evidence that smoking induces systemic biological changes through epigenetic modifications and neurobiological dysregulation.⁽⁶⁵⁾ The dataset analysis revealed significant associations between smoking status and key physiological markers, particularly in lipid metabolism, liver function, and oxidative stress.⁽⁶⁶⁾ Smokers exhibited elevated triglycerides, LDL cholesterol, and liver enzyme levels (ALT and GTP), suggesting that smoking contributes to chronic inflammation and metabolic disruptions.⁽⁶⁷⁾ These observations align with existing literature indicating that smoking accelerates atherogenesis and hepatic stress through oxidative damage and inflammatory cascades.⁽⁶⁸⁾

One of the critical aspects explored in this study is the bidirectional relationship between neurobiology and epigenetics in addiction.⁽⁶⁹⁾ Smoking’s impact on dopaminergic pathways and stress regulation mechanisms supports the hypothesis that nicotine dependence is reinforced through both immediate neurotransmitter effects and long-term epigenetic modifications.⁽⁷⁰⁾ Notably, methylation alterations in genes such as BDNF and MAOA—which regulate neuronal plasticity and stress response—potentially contribute to addiction persistence by altering neural reward pathways.⁽⁷¹⁾ This aligns with findings in neurobiology that indicate chronic nicotine exposure induces synaptic remodeling in addiction-related brain regions.⁽⁷²⁾

From a machine learning perspective, feature selection techniques identified gender, hemoglobin, height, GTP, weight, and serum creatinine as the most relevant predictors of smoking status.⁽⁷³⁾ The presence of gender as a top feature suggests inherent behavioral or physiological differences in smoking patterns between males and females. Hemoglobin levels, likely elevated due to smoking-induced hypoxia, also emerged as a strong indicator.⁽⁷⁴⁾ Similarly, elevated GTP levels further reinforce the connection between smoking and liver dysfunction, a well-documented consequence of chronic exposure to tobacco toxins.⁽⁷⁵⁾

The model evaluation demonstrated that ensemble learning methods, particularly AdaBoost and Random Forest, outperformed traditional classification techniques, highlighting their robustness in predicting smoking status.⁽⁷⁶⁾ The superior AUC scores of these models suggest that integrating multiple weak classifiers allows for better identification of complex relationships between smoking and physiological parameters.⁽⁷⁷⁾ However, certain models, such as Stochastic Gradient Descent (SGD) and Naïve Bayes, exhibited imbalanced performance, with high precision but lower recall, indicating challenges in capturing true positive cases effectively.⁽⁷⁸⁾

Despite the robustness of the dataset, certain limitations must be acknowledged. The study lacks direct epigenetic profiling, meaning that inferred methylation changes rely on known associations rather than direct experimental validation. Additionally, the dataset is observational, limiting causal inferences regarding smoking’s impact on physiological markers.⁽⁷⁸⁾ Future research should integrate DNA methylation data, transcriptomic profiles, and neuroimaging studies to establish a more definitive causal framework linking smoking, epigenetic modifications, and disease progression.⁽⁸⁰⁾

CONCLUSION

This study provides a comprehensive analysis of smoking’s physiological and epigenetic consequences using a large dataset of 55,692 individuals and 27 health metrics. The results reinforce the well-established link between smoking and metabolic disturbances, oxidative stress, and liver dysfunction, while also offering novel insights into smoking-induced epigenetic alterations that may perpetuate addiction and disease.

The findings demonstrate that smoking’s impact extends beyond direct chemical exposure, influencing gene expression and neurobiological pathways in a bidirectional manner. This supports the hypothesis that epigenetic modifications, particularly in stress-regulating and reward-related genes, contribute to addiction persistence. The identification of key biomarkers such as GTP, hemoglobin, and triglycerides offers potential avenues for early detection and intervention strategies aimed at mitigating smoking-related health risks.

From a computational standpoint, the study highlights the effectiveness of machine learning techniques in smoking prediction, with AdaBoost and Random Forest outperforming other models. This underscores the value of ensemble learning in health analytics and suggests that AI-driven approaches could enhance personalized smoking cessation programs by identifying high-risk individuals based on physiological signatures.

Future work should focus on validating these findings using direct epigenetic sequencing and functional neuroimaging to map the precise molecular pathways influenced by smoking. Additionally, incorporating longitudinal studies would help clarify the temporal progression of smoking-induced epigenetic changes and their reversibility upon cessation. Ultimately, these insights contribute to the broader field of precision medicine, where targeted interventions can be designed to counteract the biological legacy of smoking and improve public health outcomes.

REFERENCES

1.  Al-Oqily I, Alzboon M, Al-Shemery H, Alsarhan A. Towards autonomic overlay self-load balancing. In: 2013 10th International Multi-Conference on Systems, Signals and Devices, SSD 2013. Ieee; 2013. p. 1–6. 

2.  SalemAlzboon, Mowafaq and Arif, Suki and Mahmuddin, M and Dakkak O. Peer to Peer Resource Discovery Mechanisms in Grid Computing : A Critical Review. In: The 4th International Conference on Internet Applications, Protocols and Services (NETAPPS2015). 2015. p. 48–54. 

3.  Alzboon MS, Sintok UUM, Sintok UUM, Arif S. Towards Self-Organizing Infrastructure : A New Architecture for Autonomic Green Cloud Data Centers. ARPN J Eng Appl Sci. 2015;1–7. 

4.  Mowafaq Salem Alzboon M. Mahmuddin ASCA. Challenges and Mitigation Techniques of Grid Resource Management System. In: National Workshop on FUTURE INTERNET RESEARCH (FIRES2016). 2016. p. 1–6.

5.  Alzboon MS, Arif AS, Mahmuddin M. Towards self-resource discovery and selection models in grid computing. ARPN J Eng Appl Sci. 2016;11(10):6269–74.

6.  Arif S, Alzboon MS, Mahmuddin M. Distributed quadtree overlay for resource discovery in shared computing infrastructure. Adv Sci Lett. 2017;23(6):5397–401.

7.  Mahmuddin M, Alzboon MS, Arif S. Dynamic network topology for resource discovery in shared computing infrastructure. Adv Sci Lett. 2017;23(6):5402–5.

8.  Alzboon MS, Alomari S, Al-Batah MS, Alomari SA, Banikhalaf M. The characteristics of the green internet of things and big data in building safer, smarter, and sustainable cities Vehicle Detection and Tracking for Aerial Surveillance Videos View project Evaluation of Knowledge Quality in the E-Learning System View pr [Internet]. Vol. 6, Article in International Journal of Engineering and Technology. 2017. p. 83–92. Available from: https://www.researchgate.net/publication/333808921

9.  Banikhalaf M, Alomari SA, Alzboon MS. An advanced emergency warning message scheme based on vehicles speed and traffic densities. Int J Adv Comput Sci Appl. 2019;10(5):201–5.

10. Alomari, Alzboon, Zaqaibeh, Al-Batah, Saleh Ali, Mowafaq Salem, Belal MS. An Effective Self-Adaptive Policy for Optimal Video Quality over Heterogeneous Mobile Devices and Network Discovery Services. Appl Math Inf Sci [Internet]. 2019 May;13(3):489–505. Available from: http://www.naturalspublishing.com/Article.asp?ArtcID=19739

11. Shawawreh S, Alomari SA, Alzboon MS, Al Salaimeh S. Evaluation of knowledge quality in the E -learning system. Int J Eng Res Technol. 2019;12(4):548–53.

12. Al-Batah M, Zaqaibeh B, Alomari SA, Alzboon MS. Gene Microarray Cancer classification using correlation based feature selection algorithm and rules classifiers. Int J online Biomed Eng. 2019;15(8):62–73.

13. Alzboon MS. Internet of things between reality or a wishing - list : a survey. Int J Eng \& Technol. 2019;7(June):956–61.

14. Qananwah Q, Khader A, Al-Hashem M, Mumani A, Dagamseh A. Investigating the impact of smoking habits through photoplethysmography analysis. Physiol Meas. 2024 Jan;45(1):15003.

15. Fedecostante M, Sabbatinelli J, Dell’Aquila G, Salvi F, Bonfigli AR, Volpato S, et al. Prediction of COVID-19 in-hospital mortality in older patients using artificial intelligence: a multicenter study. Front Aging. 2024 Oct;5.

16. Alam A, Prybutok VR. Use of responsible artificial intelligence to predict health insurance claims in the USA using machine learning algorithms. Explor Digit Heal Technol. 2024;30–45.

17. Chua HL, Huong A. Deep Learning and Photoacoustic Technology for Microcirculation Classification: Comparison Between Smoking and Nonsmoking Groups. Glob Clin Eng J. 2024;6(3):37–45.

18. Ammar M, Javaid N, Alrajeh N, Shafiq M, Aslam M. A Novel Blending Approach for Smoking Status Prediction in Hidden Smokers to Reduce Cardiovascular Disease Risk. IEEE Access. 2024;

19. Trofimova O, Iuliani I, Bergmann S. Bidirectional genetic and phenotypic links between smoking and striatal iron content involving dopaminergic and inflammatory pathways. medRxiv. 2024;

20. Teixeira A, Páscoa R, Martins C, Rodrigues PP. Finding Groups in the Portuguese Population Through Lifestyle: A Cross-Sectional Study. Stud Health Technol Inform. 2024;316:1659–63.

21. Goyal P, Goyal GK, Yadav K, Bhatt A, Nassa K, Raushan SK, et al. Attributes of hypertension among industrial workers in Northern India - An alarming signal. J Fam Med Prim Care. 2024;13(1):330–5.

22. Flores-Hernández MN, Martínez-Coria H, López-Valdés HE, Arteaga-Silva M, Arrieta-Cruz I, Gutiérrez-Juárez R. Efficacy of a High-Protein Diet to Lower Glycemic Levels in Type 2 Diabetes Mellitus: A Systematic Review. Vol. 25, International Journal of Molecular Sciences. 2024.

23. Jantzen R, Camilleri-Broët S, Ezer N, Broët P. A Statistical Testing Strategy Accounting for Random and Nonrandom (Skewed) X-Chromosome Inactivation Identifies Lung Cancer Susceptibility Loci among Smokers. Hum Hered. 2024 Jun;89(1):71–83.

24. Wang Q, Zeng A, Zhu M, Song L. Dual inhibition of EGFR‑VEGF: An effective approach to the treatment of advanced non‑small cell lung cancer with EGFR mutation (Review). Int J Oncol. 2023;

25. Emaminejad SA, Sparks J, Cusick RD. Integrating Bio-Electrochemical Sensors and Machine Learning to Predict the Efficacy of Biological Nutrient Removal Processes at Water Resource Recovery Facilities. Environ Sci Technol. 2023;57(46):18372–81.

26. Khudhur Zaal I, Faisal Mohammad Y. Review “Smoker/Non-Smoker Classification of People Using a Speech Signal.” Int Res J Innov Eng Technol. 2023;07(05):99–107.

27. K JBS, Jayasudha BSK, Sudha PN, Sudha P, S R, Rachana S, et al. Machine Learning Techniques for Cardiovascular Risk Score -Prediction. 2021 IEEE Mysore Sub Sect Int Conf. 2021;

28. Xie Y, Li F, Wu Y, Yang S, Wang Y. HearSmoking: Smoking Detection in Driving Environment via Acoustic Sensing on Smartphones. IEEE Trans Mob Comput. 2022;21(8):2847–60.

29. Bhat FA, Mohan S V., Patil S, Advani J, Bhat MY, Patel K, et al. Proteomic Alterations Associated with Oral Cancer Patients with Tobacco Using Habits. Omi A J Integr Biol. 2021;25(4):255–68.

30. Ashari A, Pratama Madaseta S, Rio Agus Santoso AP. IMPACT OF CIGARETTE AGAINST ADOLESCENT BEHAVIOR VIEWED FROM THE HOLISTIC ASPECT (BIO-PSYCHO-SOCIO-SPIRITUAL-CULTURAL). IJLLE (International J Law Leg Ethics). 2020;1(2):80–4.

31. Rauschert S, Rauschert S, Melton PE, Melton PE, Burdge GC, Burdge GC, et al. Maternal Smoking During Pregnancy Induces Persistent Epigenetic Changes Into Adolescence, Independent of Postnatal Smoke Exposure and Is Associated With Cardiometabolic Risk. Front Genet. 2019;

32. Balmuș I-M, Balmus I-M, Ciobîcă A, Ciobica A, Cojocariu R, Cojocariu R, et al. Correlative Studies on the Biorelevance of Smoking in Gastrointestinal Irritable Bowel Syndrome-like Symptoms. E-Health Bioeng Conf. 2019;

33. Imtiaz MH, Imtiaz MH, Senyurek V, Senyurek VY, Belsare P, Belsare P, et al. Development of a Smart IoT Charger for Wearable Cigarette Smoking Monitor. SoutheastCon. 2019;

34. Bollepalli S, Bollepalli S, Korhonen T, Korhonen T, Kaprio J, Kaprio J, et al. EpiSmokEr: a robust classifier to determine smoking status from DNA methylation data. Epigenomics. 2019;

35. Divyabharathi O, Sundar A, Mukherjee C, Deepika S. Analysis of Human Physiological Parameters Using Real-Time HRV Estimation from Acquired ECG Signals. In: 2019 International Conference on Data Science and Communication, IconDSC 2019. 2019.

36. Benouis M, Abo-Tabik M, Benn Y, Salmon O, Barret-Chapman A, Costen N. Behavioural smoking identification via hand-movement dynamics. In: Proceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019. 2019. p. 1734–9. 

37. Al Tal S, Al Salaimeh S, Ali Alomari S, Alqaraleh M. The modern hosting computing systems for small and medium businesses. Acad Entrep J. 2019;25(4):1–7.

38. Alomari SA, Alzboon MS, Al-Batah MS, Zaqaibeh B. A novel adaptive schema to facilitates playback switching technique for video delivery in dense LTE cellular heterogeneous network environments. Int J Electr Comput Eng [Internet]. 2020 Oct;10(5):5347. Available from: http://ijece.iaescore.com/index.php/IJECE/article/view/16563

39. Alomari SA, Salaimeh S Al, Jarrah E Al, Alzboon MS. Enhanced logistics information service systems performance: using theoretical model and cybernetics’ principles. WSEAS Trans Bus Econ [Internet]. 2020 Apr;17:278–87. Available from: https://wseas.com/journals/bae/2020/a585107-896.pdf

40. Alzboon MS, Mahmuddin M, Arif S. Resource discovery mechanisms in shared computing infrastructure: A survey. In: Advances in Intelligent Systems and Computing. 2020. p. 545–56.

41. Alomari SA, Alqaraleh M, Aljarrah E, Alzboon MS. Toward achieving self-resource discovery in distributed systems based on distributed quadtree. J Theor Appl Inf Technol. 2020;98(20):3088–99.

42. Alzboon MS, Aljarrah E, Alqaraleh M, Alomari SA. Nodexl Tool for Social Network Analysis. Turkish J Comput Math Educ. 2021;12(14):202–16.

43. Alzboon M. Semantic Text Analysis on Social Networks and Data Processing: Review and Future Directions. Inf Sci Lett. 2022;11(5):1371–84.

44. Alqaraleh M, Salem Alzboon M, Subhi Al-Batah M. Real-Time UAV Recognition Through Advanced Machine Learning for Enhanced Military Surveillance. Gamification Augment Real [Internet]. 2025 Jan 1;3:63. Available from: https://gr.ageditor.ar/index.php/gr/article/view/63

45. Alzboon MS. Survey on Patient Health Monitoring System Based on Internet of Things. Inf Sci Lett. 2022;11(4):1183–90.

46. Alzboon MS, Al-Batah M, Alqaraleh M, Abuashour A, Bader AF. A Comparative Study of Machine Learning Techniques for Early Prediction of Diabetes. In: 2023 IEEE 10th International Conference on Communications and Networking, ComNet 2023 - Proceedings. 2023. p. 1–12.

47. Alzboon MS, Al-Batah M, Alqaraleh M, Abuashour A, Bader AF. A Comparative Study of Machine Learning Techniques for Early Prediction of Prostate Cancer. In: 2023 IEEE 10th International Conference on Communications and Networking, ComNet 2023 - Proceedings. 2023. p. 1–12.

48. Putri AK, Alzboon MS. Doctor Adam Talib’s Public Relations Strategy in Improving the Quality of Patient Service. Sinergi Int J Commun Sci. 2023;1(1):42–54.

49. Alzboon MS, Al-Batah MS, Alqaraleh M, Abuashour A, Bader AFH. Early Diagnosis of Diabetes: A Comparison of Machine Learning Methods. Int J online Biomed Eng. 2023;19(15):144–65.

50. Al-Batah MS, Alzboon MS, Alazaidah R. Intelligent Heart Disease Prediction System with Applications in Jordanian Hospitals. Int J Adv Comput Sci Appl. 2023;14(9):508–17.

51. Alzboon MS, Qawasmeh S, Alqaraleh M, Abuashour A, Bader AF, Al-Batah M. Machine Learning Classification Algorithms for Accurate Breast Cancer Diagnosis. In: 2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023. 2023.

52. Alzboon MS, Al-Batah MS. Prostate Cancer Detection and Analysis using Advanced Machine Learning. Int J Adv Comput Sci Appl. 2023;14(8):388–96.

53. Alzboon MS, Qawasmeh S, Alqaraleh M, Abuashour A, Bader AF, Al-Batah M. Pushing the Envelope: Investigating the Potential and Limitations of ChatGPT and Artificial Intelligence in Advancing Computer Science Research. In: 2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023. 2023.

54. Alzboon MS, Bader AF, Abuashour A, Alqaraleh MK, Zaqaibeh B, Al-Batah M. The Two Sides of AI in Cybersecurity: Opportunities and Challenges. In: Proceedings of 2023 2nd International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2023. 2023.

55. Al-Shanableh N, Alzyoud M, Al-Husban RY, Alshanableh NM, Al-Oun A, Al-Batah MS, et al. Advanced ensemble machine learning techniques for optimizing diabetes mellitus prognostication: A detailed examination of hospital data. Data Metadata. 2024;3:363.

56. Al-Batah MS, Salem Alzboon M, Solayman Migdadi H, Alkhasawneh M, Alqaraleh M. Advanced Landslide Detection Using Machine Learning and Remote Sensing Data. Data Metadata [Internet]. 2024 Oct 7;1. Available from: https://dm.ageditor.ar/index.php/dm/article/view/419/782

57. Muhyeeddin A, Mowafaq SA, Al-Batah MS, Mutaz AW. Advancing Medical Image Analysis: The Role of Adaptive Optimization Techniques in Enhancing COVID-19 Detection, Lung Infection, and Tumor Segmentation. LatIA [Internet]. 2024 Sep 29;2(74):74. Available from: https://latia.ageditor.uy/index.php/latia/article/view/74

58. Mowafaq SA, Alqaraleh M, Al-Batah MS. AI in the Sky: Developing Real-Time UAV Recognition Systems to Enhance Military Security. Data Metadata. 2024;3:417.

59. Alzboon MS, Alqaraleh M, Wahed MA, Alourani A, Bader AF, Al-Batah M. AI-Driven UAV Distinction: Leveraging Advanced Machine Learning. In: 2024 7th International Conference on Internet Applications, Protocols, and Services (NETAPPS) [Internet]. IEEE; 2024. p. 1–7. Available from: http://dx.doi.org/10.1109/netapps63333.2024.10823488

60. Wahed MA, Alzboon MS, Alqaraleh M, Ayman J, Al-Batah M, Bader AF. Automating Web Data Collection: Challenges, Solutions, and Python-Based Strategies for Effective Web Scraping. In: 2024 7th International Conference on Internet Applications, Protocols, and Services, NETAPPS 2024 [Internet]. IEEE; 2024. p. 1–6. Available from: http://dx.doi.org/10.1109/netapps63333.2024.10823528

61. Al-Batah M, Salem Alzboon M, Alqaraleh M, Ahmad Alzaghoul F. Comparative Analysis of Advanced Data Mining Methods for Enhancing Medical Diagnosis and Prognosis. Data Metadata. 2024;3:465.

62. Alzboon MS, Subhi Al-Batah M, Alqaraleh M, Alzboon F, Alzboon L. Phishing Website Detection Using Machine Learning. Gamification Augment Real [Internet]. 2025 Jan 16;3:81. Available from: http://dx.doi.org/10.56294/gr202581

63. Abuashour A, Salem Alzboon M, Kamel Alqaraleh M, Abuashour A. Comparative Study of Classification Mechanisms of Machine Learning on Multiple Data Mining Tool Kits. Am J Biomed Sci Res 2024 [Internet]. 2024;22(1):1. Available from: www.biomedgrid.com

64. Wahed MA, Alzboon MS, Alqaraleh M, Halasa A, Al-Batah M, Bader AF. Comprehensive Assessment of Cybersecurity Measures: Evaluating Incident Response, AI Integration, and Emerging Threats. In: 2024 7th International Conference on Internet Applications, Protocols, and Services (NETAPPS) [Internet]. IEEE; 2024. p. 1–8. Available from: http://dx.doi.org/10.1109/netapps63333.2024.10823603

65. Alqaraleh M. Enhanced Resource Discovery Algorithm for Efficient Grid Computing. In: Proceedings of the 3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024. 2024. p. 925–31.

66. Wahed MA, Alzboon MS, Alqaraleh M, Al-Batah M, Bader AF, Wahed SA. Enhancing Diagnostic Precision in Pediatric Urology: Machine Learning Models for Automated Grading of Vesicoureteral Reflux. In: 2024 7th International Conference on Internet Applications, Protocols, and Services (NETAPPS) [Internet]. IEEE; 2024. p. 1–7. Available from: http://dx.doi.org/10.1109/netapps63333.2024.10823509

67. Al-Batah MS, Alzboon MS, Alzyoud M, Al-Shanableh N. Enhancing Image Cryptography Performance with Block Left Rotation Operations. Appl Comput Intell Soft Comput. 2024;2024(1):3641927.

68. Alqaraleh M. Enhancing Internet-based Resource Discovery: The Efficacy of Distributed Quadtree Overlay. In: Proceedings of the 3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024. 2024. p. 1619–28.

69. Alqaraleh M, Salem Alzboon M, Mohammad SA-B. Optimizing Resource Discovery in Grid Computing: A Hierarchical and Weighted Approach with Behavioral Modeling. LatIA [Internet]. 2025 Jan 1;3:97. Available from: https://latia.ageditor.uy/index.php/latia/article/view/97

70. Alqaraleh M, Alzboon MS, Al-Batah MS, Wahed MA, Abuashour A, Alsmadi FH. Harnessing Machine Learning for Quantifying Vesicoureteral Reflux: A Promising Approach for Objective Assessment. Int J online Biomed Eng. 2024;20(11):123–45.

71. Alqaraleh M, Alzboon MS, Al-Batah MS. Skywatch: Advanced Machine Learning Techniques for Distinguishing UAVs from Birds in Airspace Security. Int J Adv Comput Sci Appl [Internet]. 2024;15(11). Available from: http://dx.doi.org/10.14569/IJACSA.2024.01511104

72. Abdel Wahed M, Al-Batah M, Salem Alzboon M, Fuad Bader A, Alqaraleh M. Technological Innovations in Autonomous Vehicles: A Focus on Sensor Fusion and Environmental Perception [Internet]. 2024 7th International Conference on Internet Applications, Protocols, and Services (NETAPPS). IEEE; 2024 Nov. Available from: http://dx.doi.org/10.1109/netapps63333.2024.10823624

73. lzboon MS, Al-Shorman HM, Alka’awneh SMN, Saatchi SG, Alqaraleh MKS, Samara EIM, et al. The Role of Perceived Trust in Embracing Artificial Intelligence Technologies: Insights from Jordan’s SME Sector. In: Studies in Computational Intelligence [Internet]. Springer Nature Switzerland; 2024. p. 1–15. Available from: http://dx.doi.org/10.1007/978-3-031-74220-0_1

74. Salem Alzboon M, Subhi Al-Batah M, Alqaraleh M, Alzboon F, Alzboon L. Guardians of the Web: Harnessing Machine Learning to Combat Phishing Attacks. Gamification Augment Real [Internet]. 2025 Jan;3:91. Available from: http://dx.doi.org/10.56294/gr202591

75. Wahed MA, Alqaraleh M, Alzboon MS, Subhi Al-Batah M. AI Rx: Revolutionizing Healthcare Through Intelligence, Innovation, and Ethics. Semin Med Writ Educ [Internet]. 2025 Jan 1;4:35. Available from: https://mw.ageditor.ar/index.php/mw/article/view/35

76. Wahed MA, Alqaraleh M, Alzboon MS, Al-Batah MS. Application of Artificial Intelligence for Diagnosing Tumors in the Female Reproductive System: A Systematic Review. Multidiscip. 2025;3:54.

77. Abdel Wahed M, Alqaraleh M, Salem Alzboon M, Subhi Al-Batah M. Application of Artificial Intelligence for Diagnosing Tumors in the Female Reproductive System: A Systematic Review. Multidiscip [Internet]. 2025 Jan 1;3:54. Available from: https://multidisciplinar.ageditor.uy/index.php/multidisciplinar/article/view/54

78. Alqaraleh M, Al-Batah M, Salem Alzboon M, Alzaghoul E. Automated quantification of vesicoureteral reflux using machine learning with advancing diagnostic precision. Data Metadata. 2025;4:460.

79. Wahed MA, Alqaraleh M, Salem Alzboon M, Subhi Al-Batah M. Evaluating AI and Machine Learning Models in Breast Cancer Detection: A Review of Convolutional Neural Networks (CNN) and Global Research Trends. LatIA [Internet]. 2025 Jan 1;3:117. Available from: https://latia.ageditor.uy/index.php/latia/article/view/117

80. Alqaraleh M, Salem Alzboon M, Subhi Al-Batah M, Solayman Migdadi H. From Complexity to Clarity: Improving Microarray Classification with Correlation-Based Feature Selection. LatIA [Internet]. 2025 Jan 1;3:84. Available from: https://latia.ageditor.uy/index.php/latia/article/view/84

FINANCING

This work is supported from Jadara University under grant number [Jadara-SR-Full2023], and Zarqa University.

CONFLICT OF INTEREST

The authors declare that the research was conducted without any commercial or financial relationships that could be construed as a potential conflict of interest.

AUTHORSHIP CONTRIBUTION

Conceptualization: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon, Muhyeeddin Alqaraleh.

Data curation: Faisal Alzboon, Lujin Alzboon, Mohammad Nayef Alamoush

Formal analysis: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon, Muhyeeddin Alqaraleh.

Research: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon.

Methodology: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon.

Project management: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon.

Resources: Muhyeeddin Alqaraleh, Mohammad Subhi Al-Batah.

Software: Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah.

Supervision: Mohammad Subhi Al-Batah.

Validation: Mowafaq Salem Alzboon, Muhyeeddin Alqaraleh.

Display: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon.

Drafting - original draft: Faisal Alzboon, Lujin Alzboon, Mohammad Nayef Alamoush

Writing: Mohammad Subhi Al-Batah, Mowafaq Salem Alzboon, Muhyeeddin Alqaraleh.