"Exploring the Relationship Between Depression and the Five-Factor Personality Model: A Comparative Study Using Three Decision Tree Algorithms"

"Exploring the Relationship Between Depression and the Five-Factor Personality Model: A Comparative Study Using Three Decision Tree Algorithms" | 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 "Exploring the Relationship Between Depression and the Five-Factor Personality Model: A Comparative Study Using Three Decision Tree Algorithms" Maedeh Habibi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7722213/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Background Depression is one of the most prevalent and recurrent mental health disorders in recent years, particularly among university students, where it can significantly impact academic performance. This study aimed to explore the relationship between personality traits and depression using data mining techniques. Materials and Methods A cross-sectional study was conducted among 1,243 students at Isfahan University of Medical Sciences. Participants completed the PHQ-9 (for depression assessment), the NEO-60 (for personality traits), and a demographic questionnaire. Three widely used decision tree algorithms—CART, CHAID, and C5.0—were applied to predict depression levels. Results All three algorithms identified neuroticism as the most influential personality trait associated with depression (average rank = 87.4), followed by agreeableness, extraversion, and conscientiousness. Among the models, C5.0 demonstrated superior predictive performance (Sensitivity = 100%, Specificity = 96.8%, Accuracy = 97.5%) compared to CHAID and CART. Conclusion Decision tree algorithms offer effective tools for identifying depression based on personality traits. Neuroticism emerged as the strongest predictor, suggesting that targeted mental health interventions for students with high neuroticism scores may help reduce depression prevalence. data mining decision tree machine learning classification depression personality traits Figures Figure 1 Figure 2 Introduction Depression is the most common mental health condition in the general population [1]. It is increasingly viewed as a chronic illness, as individuals with depression often experience high rates of symptom recurrence and sustained functional impairment [2]. While all types of depression share core features—such as sadness, emptiness, or irritability accompanied by somatic and cognitive changes—their duration, timing, and presumed etiology may differ [3]. The overall prevalence of depression varies across studies, ranging from 12.9% to 27.2% in different countries [1, 4]. In the United States, the prevalence has increased from 8.7% to 11.3% among adolescents and from 8.8% to 9.6% among young adults in recent years[5]. Meta-analyses have shown that depressive symptoms are more common among university students compared to the general population [4, 6-8], with rates reaching up to 57% among medical students [9]. In Iran, a meta-analysis reported a 19.46% prevalence in the general population using the General Health Questionnaire[10], and 33% among university students[11]. Given the high prevalence and consequences of depression, screening programs are essential. Personality traits may predispose individuals to depressive disorders[12]. There is substantial evidence linking personality and psychopathology[13]. Personality traits reflect underlying biological differences that influence behavior and psychological responses to stress[14, 15]. They also shape individuals’ perceptions of their health conditions [16]. The Five-Factor Model (FFM) organizes personality into five broad dimensions: neuroticism, extraversion, agreeableness, conscientiousness, and openness[15]. In an Iranian study, higher neuroticism scores were associated with increased psychological distress and depression, while higher extraversion and agreeableness scores were linked to lower depression levels[17]. A review found that depression and dementia are associated with high neuroticism and low agreeableness, conscientiousness, openness, and extraversion[18]. A cross-sectional study in Norway confirmed a direct relationship between depression and neuroticism [19]. A prospective study identified high neuroticism and low conscientiousness as risk factors for chronic depression[20]. Another study showed significantly higher neuroticism and lower extraversion in depressed individuals compared to non-depressed ones[21]. Taiwanese researchers found that depressive symptoms were predicted by high neuroticism and low agreeableness, extraversion, and conscientiousness[22]. Mental health problems are a major global concern, and identifying contributing factors is essential. University students face stressors not only from daily life but also from academic demands and campus-related pressures. Their developmental stage, adjustment to new environments, and academic expectations make them particularly vulnerable[8]. Since personality traits may serve as prognostic indicators of mental health, identifying them as predictors of psychological problems is crucial for developing prevention and treatment strategies. To examine the relationship between depression and personality traits, this study employs decision tree algorithms—a data mining method known for its simplicity and interpretability[23]. Unlike traditional methods such as regression, decision trees do not require assumptions like linearity between predictors and outcomes. They are particularly useful in exploratory data mining, where prior knowledge of variable relationships is limited[24]. Classical statistical methods often fall short in capturing complex patterns between depression and personality traits. Therefore, newer approaches like decision trees, which offer fewer restrictive assumptions and strong predictive capabilities, are well-suited for analyzing large datasets[25, 26]. This study aims to investigate the relationship between depression and personality traits using decision tree algorithms (CART, CHAID, and C5.0), and to identify the most influential trait in predicting depression among university students. Method and Materials Study Design This cross-sectional study utilized data collected in 2018 from the RaSaD project (Ravand Salamati Daneshjooyan – Health Status Trend in Medical Students). RaSaD is a longitudinal study that investigates changes in lifestyle, social identity, physical health, and mental health among students at Isfahan University of Medical Sciences (IUMS) throughout their academic life. The project includes all students entering IUMS between 2018 and 2022. Data collection involved three questionnaires: the Neuroticism-Extraversion-Openness-60 (NEO-60), the Patient Health Questionnaire-9 (PHQ-9), and a demographic questionnaire. Inclusion criteria required students to have completed all three questionnaires in 2018. After explaining the study objectives and obtaining informed consent, eligible students were enrolled. Those who declined participation or did not complete the questionnaires were excluded. To streamline data collection and reduce costs, the questionnaires were made available electronically via the university’s website. Questionnaires NEO-60 Questionnaire Personality traits were assessed using the NEO-60, a 60-item self-report version of the 240-item NEO Personality Inventory-Revised (NEO-PI-R), which measures five domains: neuroticism, extraversion, openness to experience, agreeableness, and conscientiousness [27]. Each domain includes 12 items rated on a 5-point Likert scale (0 = strongly disagree to 4 = strongly agree). Scores for each domain range from 0 to 48, with 28 items reverse-scored. Studies have demonstrated good internal consistency for the NEO-60 subscales[28]. Joshanloo et al examined the structure of the NEO-60 in Iranian populations and confirmed its alignment with the five-factor personality model[29]. Afshar et al reported a Cronbach’s alpha of 0.86 for the questionnaire[30]. PHQ-9 Questionnaire Depression was measured using the PHQ-9, a self-report tool based on the nine DSM-IV criteria for major depressive episodes. It assesses symptoms experienced during the two weeks prior to completion. Each item is scored from 0 (not at all) to 3 (nearly every day), yielding a total score between 0 and 27 [31]. Dadfar validated the Persian version of PHQ-9 in Iranian populations, reporting a Cronbach’s alpha of 0.88 and test-retest reliability of 0.79 [32]. Park et al reported an alpha coefficient of 0.90 in a similar study[33]. Demographic Questionnaire A self-designed demographic questionnaire was designed specifically for this study and used to collect participants’ background information, including gender, age, marital status, ethnicity, field of study, academic semester, family size, employment status, residency, parental education and occupation, and socioeconomic indicators such as income, home/car ownership, insurance coverage, and travel history. An English version of questionnaire has been uploaded as a supplementary file (See Supplementary File 1). For this study, only marital status, education level, age, and gender were analyzed. Statistical Analysis Descriptive statistics were computed using chi-square and independent sample t-tests. Three classification algorithms—CART, CHAID, and C5.0—were applied to predict depression (dependent variable) using personality traits and demographic variables (independent variables) (Park et al., 2010). Depression scores were dichotomized into “depressed” and “not depressed” using a cut-off score of 12, determined via Receiver Operating Characteristic (ROC) analysis [34]. Model performance was evaluated using sensitivity, specificity, area under the curve (AUC), and kappa statistics. All analyses were conducted using IBM SPSS Statistics 21 and IBM SPSS Modeler 18, with a significance level of 0.05. Classification Algorithms CART The Classification and Regression Tree (CART) algorithm handles both numerical and categorical variables. It selects branches to minimize impurity, measured by the Gini index [23, 24]. Key formulas include impurity i(t)i(t) and best division Δi(s,t)\Delta i(s,t), which quantify the quality of splits[35]. CHAID The Chi-square Automatic Interaction Detector (CHAID) algorithm uses chi-square tests to split data and builds non-binary trees. It is suitable for large datasets and involves converting continuous predictors to categorical variables, merging categories based on p-values, and selecting split variables with the lowest adjusted p-values [36, 37]. C5.0 C5.0 is an advanced version of C4.5, offering faster performance and reduced memory usage. It builds smaller, more accurate trees using the information gain ratio [38, 39]. In this study, 80% of the data (964 cases) were used for training and 20% (241 cases) for testing. Predictor importance was ranked using algorithm-specific indices. Since each algorithm evaluates relevance differently, we averaged the results across all models for final interpretation. Results A total of 1,243 students from Isfahan University of Medical Sciences (IUMS) were approached to participate in the study. The average age of participants was 22.77 ± 5.29 years. Among them, 70.4% were female, 81.2% were single, and 38.5% were postgraduate students. Based on scores from the Patient Health Questionnaire-9 [ 32 ], 998 participants (80.3%) were classified as not depressed, while 245 (19.7%) were categorized as depressed. Depressed individuals were younger than their non-depressed counterparts. Significant differences were also observed between the two groups in terms of sex, marital status, and educational level (see Table 1 ). Regarding personality traits measured by the NEO-60 questionnaire[ 27 , 29 ], agreeableness, conscientiousness, and extraversion scores were significantly higher in the non-depressed group compared to the depressed group (p < .001). Conversely, neuroticism scores were significantly higher in the depressed group (p .05; see Table 1 ). Table 1 Comparison of Demographic Characteristics and Personality Traits Between Depressed and Non-Depressed Groups : Data are presented as mean ± SD or N (%) Variable Non-Depressed (n = 998) Depressed (n = 245) p-value Age (years) 23.12 ± 5.11 21.34 ± 5.67 < .001 Sex (Female) 670 (67.1%) 207 (84.5%) < .001 Marital Status (Single) 785 (78.6%) 225 (91.8%) < .001 Education (Postgrad) 412 (41.3%) 66 (26.9%) < .001 Agreeableness 36.45 ± 6.12 31.78 ± 5.94 < .001 Conscientiousness 34.89 ± 6.45 29.56 ± 6.02 < .001 Extraversion 32.14 ± 5.87 27.03 ± 5.66 < .001 Neuroticism 28.67 ± 6.21 36.92 ± 6.88 .05 The performance of decision tree algorithms is highly dependent on the nature and quality of the training data. A confusion matrix is a structured table that enables visualization of an algorithm’s classification performance. In this matrix, each column represents the predicted class, while each row corresponds to the actual class. As shown in Table 2 , the C5.0 classifier misclassified six instances that were actually depressed as non-depressed. However, no misclassification occurred in the opposite direction—none of the non-depressed individuals were incorrectly classified as depressed. Out of the 241 instances randomly assigned to the test sample, 235 were correctly classified by the C5.0 algorithm, indicating high accuracy. Performance details of the other classifiers (CART and CHAID) are also presented in Table 2 and visualized in Fig. 1 . Table 2 Confusion Matrix for Test Sample : Each column represents predicted class; each row represents actual class Classifier Actual Class Predicted: No Depression Predicted: Depression C5.0 No 182 0 Yes 6 53 CART No 169 13 Yes 34 25 CHAID No 173 9 Yes 37 22 As shown in Table 3 , the C5.0 classifier achieved the highest overall accuracy at 97.51%, outperforming both CART (80.49%) and CHAID (80.91%). These results indicate that C5.0 is the most effective algorithm for predicting depression in this dataset. In addition to accuracy, C5.0 demonstrated superior performance across all evaluation metrics, including positive predictive value (PPV), negative predictive value (NPV), sensitivity, specificity, area under the curve (AUC), and kappa statistic (KS). These metrics are detailed in Table 3 . When comparing CART and CHAID, CART showed higher PPV, specificity, AUC, and kappa statistic, whereas CHAID performed better in terms of NPV, sensitivity, and overall accuracy. These findings suggest that while both CART and CHAID have strengths in specific areas, C5.0 offers the most balanced and robust performance across all criteria. Therefore, based on the comparative analysis presented in Table 3 , C5.0 emerges as the most suitable choice for classifying depression using personality and demographic variables. Table 3 Performance Metrics of Classification Algorithms : All values are percentages unless otherwise indicated Classifier PPV (%) NPV (%) Sensitivity (%) Specificity (%) AUC Kappa Statistic Accuracy (%) C5.0 89.83 100.00 100.00 96.80 0.970 0.885 97.51 CART 42.37 92.85 65.78 83.25 0.735 0.360 80.49 CHAID 37.28 95.05 70.96 82.38 0.622 0.342 80.91 One of the primary objectives of this analysis was to assess the individual importance of each predictor variable in relation to depression. Table 4 and Fig. 2 present the relative importance scores derived from the three classification algorithms (CART, CHAID, and C5.0), along with their averaged values. As shown in Table 4 , neuroticism emerged as the most influential predictor, with the highest average importance score (87.43). This finding suggests that neuroticism plays a dominant role in predicting depression among university students. Following neuroticism, the variables were ranked in descending order of importance as: agreeableness, extraversion, conscientiousness, sex, educational level, age, marital status, and openness. These results highlight the central role of personality traits—particularly neuroticism—in shaping mental health outcomes, and reinforce the value of incorporating psychological dimensions into predictive models for depression. Table 4 Predictor Importance Based on CHAID, CART, and C5.0 Algorithms : Average rank reflects combined importance across all three methods Variable Chi-square (CHAID) Gini (CART) Information Gain Ratio (C5.0) Average Rank Neuroticism 262.035 0.062 0.205 87.43 Agreeableness 89.256 0.022 0.053 29.77 Conscientiousness 77.848 0.025 0.078 25.98 Extraversion 48.872 0.018 0.062 28.31 Sex 18.591 0.007 0.020 6.20 Educational Level 18.265 0.010 0.033 6.10 Age 14.442 0.001 0.056 4.83 Marital Status 9.983 0.004 0.014 3.33 Openness 1.712 0.0001 0.002 0.57 Based on average rank derived from C5.0, CHAID, and CART algorithms in predicting depression This figure illustrates the relative importance of each predictor variable in classifying depression, as calculated by averaging the importance scores from three decision tree algorithms. Neuroticism stands out as the most influential factor, followed by agreeableness, extraversion, and conscientiousness. Demographic variables such as sex, educational level, age, and marital status show moderate importance, while openness has minimal predictive value. Discussion The findings of this study demonstrate that decision tree algorithms are reliable data mining tools for identifying students who are potentially at risk of depression. Among the three algorithms evaluated, C5.0 outperformed CHAID and CART in terms of accuracy and overall performance. Using decision tree techniques, neuroticism emerged as the most influential personality trait associated with depression, followed by agreeableness, extraversion, conscientiousness, sex, educational level, age, marital status, and openness. Data mining is increasingly recognized as a powerful technique for analyzing large datasets and building predictive models, particularly in health and medical sciences. Its applications span various domains, and it is considered one of the top ten scientific fields influencing technological advancement. Wherever data exists, data mining holds significance. Our findings align with previous research in medical sciences that applied decision tree algorithms. For example, Islami et al found that C5.0 had the highest accuracy compared to CHAID, CART, and QUEST in predicting knowledge levels about exercise during pregnancy[ 40 ]. Similarly, Momenyan et al reported that C5.0 outperformed other decision tree algorithms and logistic regression in predicting breast cancer survival[ 41 ]. Ladanza et al applied neural networks, support vector machines, and C5.0 to predict chronic obstructive pulmonary disease, with C5.0 yielding superior results[ 42 ]. Delen et al compared artificial neural networks, C5.0, and logistic regression for breast cancer survivability prediction and concluded that C5.0 was the most accurate model[ 43 ]. The superior performance of C5.0 can be attributed to its advanced features, such as boosting, which enhances accuracy[ 44 ]. C5.0 also builds smaller trees than its predecessors (e.g., C4.5) and demonstrates lower error rates on unseen data [ 39 ]. It is faster and more memory-efficient, making it ideal for large-scale studies with categorical response variables and no assumptions of linearity. Given the high accuracy of decision trees in disease prediction, they can be effectively used for early diagnosis of common conditions such as depression. Liu et al conducted a meta-analysis of 30 cohort studies involving 25,124 students and identified key biological, psychological, and environmental predictors of depression [ 8 ]. Neuroticism had the highest odds ratio, indicating a 25% increased risk of depression among students with high neuroticism. Gender was also a significant predictor, ranked fourth with an odds ratio of 1.11[ 8 ]. Our study similarly found significant associations between depression, neuroticism, and gender. Neuroticism encompasses traits such as low mood, stress sensitivity, irritability, and poor emotional regulation [ 45 ]. Consistent with our findings, Navrady et al reported strong associations between neuroticism and major depressive disorder in two population-based cohorts[ 46 ]. Speed et al used Mendelian Randomization to establish a causal relationship between neuroticism and depression, based on GWAS data from the Eysenck Personality Questionnaire and the Psychiatric Genomics Consortium. Their results confirmed neuroticism as a causal risk factor for depression[ 47 ], echoing our findings derived from decision tree analysis in a cross-sectional study. Our results also support previous research on the relationship between depression and extraversion. Extraversion is characterized by sociability, liveliness, and cheerfulness [ 48 ]. Chioqueta and Stiles found that depressive symptoms were positively predicted by neuroticism and negatively predicted by extraversion[ 48 ]. Extraversion is considered an independent dimension of positive affectivity [ 49 , 50 ]. Watson et al demonstrated that extraversion negatively correlates with depression and anhedonia, particularly through communal extraversion and positive emotions[ 51 ]. Jylhä and Isometsä (2006) found that neuroticism was strongly associated with depressive and anxiety symptoms, while introversion was moderately associated with depression in the general population[ 52 ]. Other studies have similarly reported negative associations between extraversion and depression[ 52 , 53 ]. Agreeableness includes traits such as trust, honesty, altruism, adaptability, humility, and compassion. Our findings are consistent with Pearman et al, who found that agreeableness predicted levels of sadness[ 54 ]. However, our results differ from those of Takahashi et al, who found no significant relationship between agreeableness and depression[ 55 ]. In our study, agreeableness was the second most influential predictor of depression. Conscientiousness reflects traits such as achievement orientation, responsibility, dependability, and orderliness[ 56 ]. Weber et al found that depressed patients had significantly lower levels of conscientiousness compared to controls[ 57 ]. Takahashi et al also reported lower conscientiousness scores among treatment-resistant depressed individuals[ 55 ], consistent with our findings. Their study further suggested that low openness contributes to depression, whereas agreeableness had no effect. These discrepancies may stem from differences in study populations and measurement tools. Takahashi’s study focused on treatment-resistant depression and used the 17-item Hamilton Depression Rating Scale, while our study examined general depression using the PHQ-9. Conclusion This study demonstrated that among the Big Five personality traits, neuroticism has the strongest association with depression in university students. Individuals with high levels of neuroticism were significantly more likely to experience depressive symptoms. Additionally, the C5.0 decision tree algorithm exhibited the highest classification accuracy compared to CART and CHAID, confirming its effectiveness in predicting depression. These findings suggest that decision tree algorithms, particularly C5.0, can be reliably used for early identification of students at risk for depression. Early detection of personality traits associated with depression may enable timely interventions and preventive strategies to support student mental health. Limitations Despite its contributions, the present research is subject to certain limitations. One of the main challenges was the large volume of questionnaires used, which may have led to participant fatigue and reduced engagement. Additionally, due to the sensitivity of some questions and participants’ reluctance to respond, many items were left unanswered. This resulted in a considerable amount of missing data in several variables. As a consequence, valuable information—particularly regarding students’ socioeconomic status—could not be fully utilized in the analysis. Recommendations Future research could explore alternative personality models such as the Myers-Briggs Type Indicator (MBTI) and incorporate additional risk factors, including socioeconomic indicators and academic discipline. Moreover, it is recommended to evaluate other data mining classification techniques, such as artificial neural networks and Bayesian algorithms, to further enhance predictive performance and model robustness. Abbreviations PHQ-9 Patient Health Questionnaire-9 NEO-60 NEO Five-Factor Inventory – 60-item version CART Classification and Regression Trees CHAID Chi-squared Automatic Interaction Detection C5.0 An advanced decision tree algorithm (successor to C4.5) FFM Five-Factor Model DSM-5 Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition GHQ General Health Questionnaire RaSaD Ravand Salamati Daneshjooyan IUMS Isfahan University of Medical Sciences NEO-PI-R NEO Personality Inventory-Revised DSM-IV Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition ROC Receiver Operating Characteristic AUC Area Under the Curve SPSS Statistical Package for the Social Sciences PPV Positive Predictive Value NPV Negative Predictive Value KS Kappa Statistic QUEST Quick, Unbiased, Efficient Statistical Tree GWAS Genome-Wide Association Study MBTI Myers-Briggs Type Indicator Declarations Ethics approval and consent to participate This study was conducted in accordance with the ethical principles of the Declaration of Helsinki, last revised in 2013 (World Medical Association, 2013). Ethics approval was obtained from Isfahan University of Medical Sciences (Ethics ID: IR.MUI.RESEARCH.REC.1398.701. Written informed consent to participate was obtained from all participants after they were fully informed about the study objectives and confidentiality protocols. only those who provided written informed consent were included. Consent for publication : Not applicable Competing Interests: The author declares that there are no competing interests. Funding : The author declares that no funding was received for this study. Author Contribution The author confirms sole responsibility for the conception, design, data collection, analysis, interpretation, and writing of this manuscript. Acknowledgements: The author would like to thank Isfahan University of Medical Sciences for their support and guidance during the course of this research. Data Availability The data that support the findings of this study are not publicly available due to institutional restrictions but are available from the corresponding author on reasonable request. References Lim GY, et al. Prevalence of Depression in the Community from 30 Countries between 1994 and 2014. Sci Rep. 2018;8(1):2861. Aghakhani N, et al. Prevalence of depression among students of urmia university of medical sciences (iran). Iran J Psychiatry Behav Sci. 2011;5(2):131–5. Diagnostic. and statistical manual of mental disorders: DSM-5™, 5th ed , in Diagnostic and statistical manual of mental disorders: DSM-5™, 5th ed. 2013, American Psychiatric Publishing, Inc.: Arlington, VA, US. p. xliv, 947-xliv, 947. Rotenstein LS, et al. Prevalence of Depression, Depressive Symptoms, and Suicidal Ideation Among Medical Students: A Systematic Review and Meta-Analysis. JAMA. 2016;316(21):2214–36. Mojtabai R, Olfson M, Han B. National trends in the prevalence and treatment of depression in adolescents and young adults. Pediatrics. 2016;138(6):e20161878. Mikolajczyk RT, et al. Prevalence of depressive symptoms in university students from Germany, Denmark, Poland and Bulgaria. Soc Psychiatry Psychiatr Epidemiol. 2008;43(2):105–12. Ibrahim AK, et al. A systematic review of studies of depression prevalence in university students. J Psychiatr Res. 2013;47(3):391–400. Liu Y, et al. Predictors of depressive symptoms in college students: A systematic review and meta-analysis of cohort studies. J Affect Disord. 2019;244:196–208. Akbari V, Hajian A, Damirchi P. Prevalence of Emotional Disorders Among Students of University of Medical Sciences; Iran. Open Psychol J. 2014;7:29–32. Mohamadi M, et al. A meta-analysis of studies related prevalence of depression in Iran. J Res Health. 2017;7(1):581–93. Sarokhani D et al. Prevalence of Depression among University Students: A Systematic Review and Meta-Analysis Study. Depress Res Treat, 2013. 2013: p. 373857. Duggan C, et al. Theories of general personality and mental disorder. Br J Psychiatry. 2003;182(Suppl44):s19–23. Watson D, Gamez W, Simms LJ. Basic dimensions of temperament and their relation to anxiety and depression: A symptom-based perspective. J Res Pers. 2005;39(1):46–66. Newbury-Birch D, Kamali F. Psychological stress, anxiety, depression, job satisfaction, and personality characteristics in preregistration house officers. Postgrad Med J. 2001;77(904):109–11. Terracciano A, Costa PT Jr. Smoking and the Five-Factor Model of personality. Addiction. 2004;99(4):472–81. Jerram KL, Coleman PG. The big five personality traits and reporting of health problems and health behaviour in old age. Br J Health Psychol. 1999;4(2):181–92. Nouri F, et al. How five-factor personality traits affect psychological distress and depression? Results from a large population-based study. Psychol Stud. 2019;64(1):59–69. Sadeq NA, Molinari V. Personality and its relationship to depression and cognition in older adults: implications for practice. Clin Gerontologist. 2018;41(5):385–98. Grav S, et al. The relationship among neuroticism, extraversion, and depression in the HUNT Study: in relation to age and gender. Issues Ment Health Nurs. 2012;33(11):777–85. Weiss A, et al. The personality domains and styles of the five-factor model are related to incident depression in Medicare recipients aged 65 to 100. Am J Geriatric Psychiatry. 2009;17(7):591–601. BESHARAT GR, Z. KHANJANI, and, BABAPOUR J. Comparison of five big personality factors in depressive disorder patients and obsessive–compulsive disorders with normal individuals. 2013. Chien L-L, Ko H-C, Wu JY-W. The five-factor model of personality and depressive symptoms: One-year follow-up. Pers Indiv Differ. 2007;43(5):1013–23. Madadipouya K. A survey on data mining algorithms and techniques in medicine. JOIV: Int J Inf Visualization. 2017;1(3):61–71. Chaurasia V, Pal S. Early prediction of heart diseases using data mining techniques. Caribb J Sci Technol. 2013;1(1):208–17. Frank E, et al. Using model trees for classification. Mach Learn. 1998;32(1):63–76. Kiers HA, et al. Data analysis, classification, and related methods. Springer Science & Business Media; 2012. Chapman B, Duberstein P, Lyness JM. Personality traits, education, and health-related quality of life among older adult primary care patients. Journals Gerontol Ser B: Psychol Sci Social Sci. 2007;62(6):P343–52. Eysenck HJ. A reply to Costa and McCrae. P or A and C—the role of theory. Pers Indiv Differ. 1992;13(8):867–8. Joshanloo M, et al. Construct validity of NEO-personality inventory-revised in Iran. Iran J Psychiatry Clin Psychol. 2010;16(3):220–30. Afshar H, et al. Association of personality traits with psychological factors of depression, anxiety, and psychological distress: a community based study. Int J Body Mind Cult. 2015;2(2):105–14. Lotrakul M, Sumrithe S, Saipanish R. Reliability and validity of the Thai version of the PHQ-9. BMC Psychiatry. 2008;8(1):46. Dadfar M, Kalibatseva Z, Lester D. Reliability and validity of the Farsi version of the Patient Health Questionnaire-9 (PHQ-9) with Iranian psychiatric outpatients. Trends psychiatry Psychother. 2018;40(2):144–51. Park S-J, Choi H-RCJ-H, Kim K-W. Jin-Pyo Hong., Reliability and validity of the Korean version of the Patient Health Questionnaire-9 (PHQ-9). Korean Academy of Anxiety Disorders, 2010. 6(2): pp. 119–124. van Steenbergen-Weijenburg KM, et al. Validation of the PHQ-9 as a screening instrument for depression in diabetes patients in specialized outpatient clinics. BMC Health Serv Res. 2010;10(1):235. Prather JC et al. Medical data mining: knowledge discovery in a clinical data warehouse . in Proceedings of the AMIA annual fall symposium . 1997. Kass GV. An exploratory technique for investigating large quantities of categorical data. J Roy Stat Soc: Ser C (Appl Stat). 1980;29(2):119–27. Tang T-I, et al. A comparative study of medical data classification methods based on decision tree and system reconstruction analysis. Industrial Eng Manage Syst. 2005;4(1):102–8. Pang S-l, Gong J-z. C5. 0 classification algorithm and application on individual credit evaluation of banks. Syst Engineering-Theory Pract Online. 2009;29(12):94–104. Pandya R, Pandya J. C5. 0 algorithm to improved decision tree with feature selection and reduced error pruning. International Journal of Computer Applications, 2015. 117(16). Islamı F, Bagherı F, Mohammadı F. Surveying the knowledge of pregnant women towards sport activities during pregnancy using data mining algorithms. Turkish J Sport Exerc. 2016;18(1):8–16. Momenyan S et al. Survival prediction of patients with breast cancer: comparisons of decision tree and logistic regression analysis. International Journal of Cancer Management, 2018. 11(7). Iadanza E, et al. An automatic system supporting clinical decision for chronic obstructive pulmonary disease. Health Technol. 2020;10(2):487–98. Delen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med. 2005;34(2):113–27. Patidar PT. Handling Missing Value in Decision Tree Algorithm. Int J Comput Appl. 2013;70(13):31–6. Huang C, et al. Characterization of genetic loci that affect susceptibility to inflammatory bowel diseases in African Americans. Gastroenterology. 2015;149(6):1575–86. Navrady LB, et al. Intelligence and neuroticism in relation to depression and psychological distress: Evidence from two large population cohorts. Eur Psychiatry. 2017;43:58–65. Speed D, et al. Investigating the causal relationship between neuroticism and depression via Mendelian randomization. Acta psychiatrica Scandinavica. 2019;139(4):395. Chioqueta AP, Stiles TC. Personality traits and the development of depression, hopelessness, and suicide ideation. Pers Indiv Differ. 2005;38(6):1283–91. Watson D, Clark LA, Tellegen A. Development and validation of brief measures of positive and negative affect: the PANAS scales. J Personal Soc Psychol. 1988;54(6):1063. Watson D, Tellegen A. Toward a consensual structure of mood. Psychol Bull. 1985;98(2):219. Watson D, et al. Extraversion and psychopathology: A multilevel hierarchical review. J Res Pers. 2019;81:1–10. Jylhä P, Isometsä E. The relationship of neuroticism and extraversion to symptoms of anxiety and depression in the general population. Depress Anxiety. 2006;23(5):281–9. Saklofske D, Kelly I, Janzen B. Neuroticism, depression, and depression proneness. Pers Indiv Differ. 1995;18(1):27–31. Pearman A, Andreoletti C, Isaacowitz DM. Sadness prediction and response: Effects of age and agreeableness. Aging Ment Health. 2010;14(3):355–63. Takahashi M, et al. Low openness on the revised NEO personality inventory as a risk factor for treatment-resistant depression. PLoS ONE. 2013;8(9):e71964. Koorevaar A, et al. Big Five personality and depression diagnosis, severity and age of onset in older adults. J Affect Disord. 2013;151(1):178–85. Weber K, et al. Personality traits are associated with acute major depression across the age spectrum. Aging Ment Health. 2012;16(4):472–80. Additional Declarations No competing interests reported. Supplementary Files SupplementaryFile1DemographicQuestionnaireDesignedforthestudy.docx Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 17 Dec, 2025 Reviews received at journal 09 Dec, 2025 Reviews received at journal 28 Nov, 2025 Reviewers agreed at journal 19 Nov, 2025 Reviewers agreed at journal 18 Nov, 2025 Reviewers invited by journal 11 Nov, 2025 Editor assigned by journal 04 Nov, 2025 Editor invited by journal 12 Oct, 2025 Submission checks completed at journal 07 Oct, 2025 First submitted to journal 07 Oct, 2025 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-7722213","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":547824719,"identity":"c87685b0-46c5-49b8-a905-c8aec7290476","order_by":0,"name":"Maedeh Habibi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABJUlEQVRIie3PMUvDQBTA8QsH53L1NjmJmK/wSiA2oPSrXAg4dXB0KFgRMrV0NfgRXAKBqtuFg7o0ZD2xgy7dxIogERQ0GcQhKboJ5j8e78e7h1BT0x8MJELcGEgEmCK5zPvbrHgWB/XE/U6ScDi1NwcFgXrS/SKIIkwJ9iJZbq8nzrVK9NPl3NpZayWSUmLE2bm3vANksQ1ZTWb7vhvOFu2rk3UheWcLO/oh5p8fa4dnoprInmO2AmVEioIESoij06ggAm6rCWSPL+Z7oLolEQRT+zSN85VE94hpBMoriSSYAxtNVm/RC9sdBcovbkmOh1PgujXpCOC1t0Dm3+vXQO1dsFQ9v+X9o/E4jW/yw12LmdWkIl5O8p+OFzH5m+mmpqamf9AHTyxvfndVJiIAAAAASUVORK5CYII=","orcid":"","institution":"Isfahan University of Medical Sciences","correspondingAuthor":true,"prefix":"","firstName":"Maedeh","middleName":"","lastName":"Habibi","suffix":""}],"badges":[],"createdAt":"2025-09-26 13:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7722213/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7722213/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96556288,"identity":"4a763b69-4b6c-465e-8c40-e81955b989c3","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85997,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedManuscriptcleanV5.docx","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/fc3e06c93ed48b9a0426dcee.docx"},{"id":96556291,"identity":"bc98cdf5-896d-47af-a959-8fb9470791c7","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3460,"visible":true,"origin":"","legend":"","description":"","filename":"4588996640ad4031baef97d25a6199d7.json","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/a186804bb8bea0c4cec5c47d.json"},{"id":96556294,"identity":"f89b3471-32ec-4842-98ad-33388795cdbc","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16273,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFile1DemographicQuestionnaireDesignedforthestudy.docx","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/893538c38192ba798e9c3a70.docx"},{"id":96556292,"identity":"5296e292-ed5a-43a8-9f12-fd34ef07fbc2","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":111233,"visible":true,"origin":"","legend":"","description":"","filename":"4588996640ad4031baef97d25a6199d71enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/fa0d5bdfd129e7a1e5f652c7.xml"},{"id":96556296,"identity":"7a3d3d12-80cc-4e9a-80cd-0d2e70c11bfd","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"xml","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109540,"visible":true,"origin":"","legend":"","description":"","filename":"4588996640ad4031baef97d25a6199d71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/6c05f424f09638d86fdd0cb6.xml"},{"id":96604897,"identity":"6b10e9dd-dc8d-4d12-897c-56ef3d246781","added_by":"auto","created_at":"2025-11-24 09:15:48","extension":"html","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119282,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/88dcda232992070d8a16b1d9.html"},{"id":96556289,"identity":"32877ce7-2692-4a4b-a982-9ab998d0e488","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":77917,"visible":true,"origin":"","legend":"\u003cp\u003eefficiency of different models\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/dae51588f93f050d8cba2bda.png"},{"id":96556287,"identity":"8f056285-696e-465e-8328-b2e269b128cc","added_by":"auto","created_at":"2025-11-23 11:45:51","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":43326,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of Predictor Importance\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/ff3eb459356bd5d0efbf6ad1.png"},{"id":96708451,"identity":"998f9d30-7e1b-47cb-95d6-cc28bc2f9c62","added_by":"auto","created_at":"2025-11-25 10:02:23","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1045614,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/7c281d83-4700-4ab5-9644-fff551a9bc30.pdf"},{"id":96605299,"identity":"209039bd-4e55-46de-8c11-78605565f2fc","added_by":"auto","created_at":"2025-11-24 09:22:10","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":16273,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFile1DemographicQuestionnaireDesignedforthestudy.docx","url":"https://assets-eu.researchsquare.com/files/rs-7722213/v1/7d681468435a550e51bb2280.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"\"Exploring the Relationship Between Depression and the Five-Factor Personality Model: A Comparative Study Using Three Decision Tree Algorithms\"","fulltext":[{"header":"Introduction","content":"\u003cp\u003eDepression is the most common mental health condition in the general population [1]. It is increasingly viewed as a chronic illness, as individuals with depression often experience high rates of symptom recurrence and sustained functional impairment [2]. While all types of depression share core features—such as sadness, emptiness, or irritability accompanied by somatic and cognitive changes—their duration, timing, and presumed etiology may differ [3].\u003c/p\u003e\n\u003cp\u003eThe overall prevalence of depression varies across studies, ranging from 12.9% to 27.2% in different countries [1, 4]. In the United States, the prevalence has increased from 8.7% to 11.3% among adolescents and from 8.8% to 9.6% among young adults in recent years[5]. Meta-analyses have shown that depressive symptoms are more common among university students compared to the general population [4, 6-8], with rates reaching up to 57% among medical students [9]. In Iran, a meta-analysis reported a 19.46% prevalence in the general population using the General Health Questionnaire[10], and 33% among university students[11]. Given the high prevalence and consequences of depression, screening programs are essential.\u003c/p\u003e\n\u003cp\u003ePersonality traits may predispose individuals to depressive disorders[12]. There is substantial evidence linking personality and psychopathology[13]. Personality traits reflect underlying biological differences that influence behavior and psychological responses to stress[14, 15]. They also shape individuals’ perceptions of their health conditions [16]. The Five-Factor Model (FFM) organizes personality into five broad dimensions: neuroticism, extraversion, agreeableness, conscientiousness, and openness[15].\u003c/p\u003e\n\u003cp\u003eIn an Iranian study, higher neuroticism scores were associated with increased psychological distress and depression, while higher extraversion and agreeableness scores were linked to lower depression levels[17]. A review found that depression and dementia are associated with high neuroticism and low agreeableness, conscientiousness, openness, and extraversion[18]. A cross-sectional study in Norway confirmed a direct relationship between depression and neuroticism [19]. A prospective study identified high neuroticism and low conscientiousness as risk factors for chronic depression[20]. Another study showed significantly higher neuroticism and lower extraversion in depressed individuals compared to non-depressed ones[21]. Taiwanese researchers found that depressive symptoms were predicted by high neuroticism and low agreeableness, extraversion, and conscientiousness[22].\u003c/p\u003e\n\u003cp\u003eMental health problems are a major global concern, and identifying contributing factors is essential. University students face stressors not only from daily life but also from academic demands and campus-related pressures. Their developmental stage, adjustment to new environments, and academic expectations make them particularly vulnerable[8]. Since personality traits may serve as prognostic indicators of mental health, identifying them as predictors of psychological problems is crucial for developing prevention and treatment strategies.\u003c/p\u003e\n\u003cp\u003eTo examine the relationship between depression and personality traits, this study employs decision tree algorithms—a data mining method known for its simplicity and interpretability[23]. Unlike traditional methods such as regression, decision trees do not require assumptions like linearity between predictors and outcomes. They are particularly useful in exploratory data mining, where prior knowledge of variable relationships is limited[24]. Classical statistical methods often fall short in capturing complex patterns between depression and personality traits. Therefore, newer approaches like decision trees, which offer fewer restrictive assumptions and strong predictive capabilities, are well-suited for analyzing large datasets[25, 26].\u003c/p\u003e\n\u003cp\u003eThis study aims to investigate the relationship between depression and personality traits using decision tree algorithms (CART, CHAID, and C5.0), and to identify the most influential trait in predicting depression among university students.\u003c/p\u003e"},{"header":"Method and Materials ","content":"\u003cp\u003e\u003cstrong\u003eStudy Design\u003c/strong\u003e This cross-sectional study utilized data collected in 2018 from the RaSaD project (Ravand Salamati Daneshjooyan – Health Status Trend in Medical Students). RaSaD is a longitudinal study that investigates changes in lifestyle, social identity, physical health, and mental health among students at Isfahan University of Medical Sciences (IUMS) throughout their academic life. The project includes all students entering IUMS between 2018 and 2022.\u003c/p\u003e\n\u003cp\u003eData collection involved three questionnaires: the Neuroticism-Extraversion-Openness-60 (NEO-60), the Patient Health Questionnaire-9 (PHQ-9), and a demographic questionnaire. Inclusion criteria required students to have completed all three questionnaires in 2018. After explaining the study objectives and obtaining informed consent, eligible students were enrolled. Those who declined participation or did not complete the questionnaires were excluded. To streamline data collection and reduce costs, the questionnaires were made available electronically via the university’s website.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eQuestionnaires\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eNEO-60 Questionnaire\u003c/strong\u003e Personality traits were assessed using the NEO-60, a 60-item self-report version of the 240-item NEO Personality Inventory-Revised (NEO-PI-R), which measures five domains: neuroticism, extraversion, openness to experience, agreeableness, and conscientiousness [27]. Each domain includes 12 items rated on a 5-point Likert scale (0 = strongly disagree to 4 = strongly agree). Scores for each domain range from 0 to 48, with 28 items reverse-scored. Studies have demonstrated good internal consistency for the NEO-60 subscales[28]. Joshanloo et al examined the structure of the NEO-60 in Iranian populations and confirmed its alignment with the five-factor personality model[29]. Afshar et al reported a Cronbach’s alpha of 0.86 for the questionnaire[30].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePHQ-9 Questionnaire\u003c/strong\u003e Depression was measured using the PHQ-9, a self-report tool based on the nine DSM-IV criteria for major depressive episodes. It assesses symptoms experienced during the two weeks prior to completion. Each item is scored from 0 (not at all) to 3 (nearly every day), yielding a total score between 0 and 27 [31]. Dadfar validated the Persian version of PHQ-9 in Iranian populations, reporting a Cronbach’s alpha of 0.88 and test-retest reliability of 0.79 [32]. Park et al reported an alpha coefficient of 0.90 in a similar study[33].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDemographic Questionnaire\u003c/strong\u003e A self-designed demographic questionnaire\u0026nbsp;was designed specifically for this study and used to collect participants’ background information, including gender, age, marital status, ethnicity, field of study, academic semester, family size, employment status, residency, parental education and occupation, and socioeconomic indicators such as income, home/car ownership, insurance coverage, and travel history. An English version of questionnaire has been uploaded as a supplementary file (See Supplementary File 1). For this study, only marital status, education level, age, and gender were analyzed.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStatistical Analysis\u003c/strong\u003e Descriptive statistics were computed using chi-square and independent sample t-tests. Three classification algorithms—CART, CHAID, and C5.0—were applied to predict depression (dependent variable) using personality traits and demographic variables (independent variables) (Park et al., 2010). Depression scores were dichotomized into “depressed” and “not depressed” using a cut-off score of 12, determined via Receiver Operating Characteristic (ROC) analysis [34].\u003c/p\u003e\n\u003cp\u003eModel performance was evaluated using sensitivity, specificity, area under the curve (AUC), and kappa statistics. All analyses were conducted using IBM SPSS Statistics 21 and IBM SPSS Modeler 18, with a significance level of 0.05.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClassification Algorithms\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCART\u003c/strong\u003e The Classification and Regression Tree (CART) algorithm handles both numerical and categorical variables. It selects branches to minimize impurity, measured by the Gini index [23, 24]. Key formulas include impurity i(t)i(t) and best division Δi(s,t)\\Delta i(s,t), which quantify the quality of splits[35].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCHAID\u003c/strong\u003e The Chi-square Automatic Interaction Detector (CHAID) algorithm uses chi-square tests to split data and builds non-binary trees. It is suitable for large datasets and involves converting continuous predictors to categorical variables, merging categories based on p-values, and selecting split variables with the lowest adjusted p-values [36, 37].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eC5.0\u003c/strong\u003e C5.0 is an advanced version of C4.5, offering faster performance and reduced memory usage. It builds smaller, more accurate trees using the information gain ratio [38, 39].\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn this study, 80% of the data (964 cases) were used for training and 20% (241 cases) for testing. Predictor importance was ranked using algorithm-specific indices. Since each algorithm evaluates relevance differently, we averaged the results across all models for final interpretation.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eA total of 1,243 students from Isfahan University of Medical Sciences (IUMS) were approached to participate in the study. The average age of participants was 22.77\u0026thinsp;\u0026plusmn;\u0026thinsp;5.29 years. Among them, 70.4% were female, 81.2% were single, and 38.5% were postgraduate students.\u003c/p\u003e\n\u003cp\u003eBased on scores from the Patient Health Questionnaire-9 [\u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e], 998 participants (80.3%) were classified as not depressed, while 245 (19.7%) were categorized as depressed. Depressed individuals were younger than their non-depressed counterparts. Significant differences were also observed between the two groups in terms of sex, marital status, and educational level (see Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003eRegarding personality traits measured by the NEO-60 questionnaire[\u003cspan class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e], agreeableness, conscientiousness, and extraversion scores were significantly higher in the non-depressed group compared to the depressed group (p\u0026thinsp;\u0026lt;\u0026thinsp;.001). Conversely, neuroticism scores were significantly higher in the depressed group (p\u0026thinsp;\u0026lt;\u0026thinsp;.001). No significant difference was found in openness between the two groups (p\u0026thinsp;\u0026gt;\u0026thinsp;.05; see Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab1\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003e\u003cstrong\u003eComparison of Demographic Characteristics and Personality Traits Between Depressed and Non-Depressed Groups\u003c/strong\u003e: \u003cem\u003eData are presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD or N (%)\u003c/em\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eVariable\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eNon-Depressed (n\u0026thinsp;=\u0026thinsp;998)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eDepressed (n\u0026thinsp;=\u0026thinsp;245)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003ep-value\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\u003eAge (years)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e23.12\u0026thinsp;\u0026plusmn;\u0026thinsp;5.11\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e21.34\u0026thinsp;\u0026plusmn;\u0026thinsp;5.67\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSex (Female)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e670 (67.1%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e207 (84.5%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMarital Status (Single)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e785 (78.6%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e225 (91.8%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eEducation (Postgrad)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e412 (41.3%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e66 (26.9%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAgreeableness\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e36.45\u0026thinsp;\u0026plusmn;\u0026thinsp;6.12\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e31.78\u0026thinsp;\u0026plusmn;\u0026thinsp;5.94\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eConscientiousness\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e34.89\u0026thinsp;\u0026plusmn;\u0026thinsp;6.45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e29.56\u0026thinsp;\u0026plusmn;\u0026thinsp;6.02\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eExtraversion\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e32.14\u0026thinsp;\u0026plusmn;\u0026thinsp;5.87\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e27.03\u0026thinsp;\u0026plusmn;\u0026thinsp;5.66\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNeuroticism\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e28.67\u0026thinsp;\u0026plusmn;\u0026thinsp;6.21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e36.92\u0026thinsp;\u0026plusmn;\u0026thinsp;6.88\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOpenness\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e30.12\u0026thinsp;\u0026plusmn;\u0026thinsp;5.98\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e29.87\u0026thinsp;\u0026plusmn;\u0026thinsp;6.04\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026gt;\u0026thinsp;.05\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\u003eThe performance of decision tree algorithms is highly dependent on the nature and quality of the training data. A confusion matrix is a structured table that enables visualization of an algorithm\u0026rsquo;s classification performance. In this matrix, each column represents the predicted class, while each row corresponds to the actual class.\u003c/p\u003e\n\u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e, the C5.0 classifier misclassified six instances that were actually depressed as non-depressed. However, no misclassification occurred in the opposite direction\u0026mdash;none of the non-depressed individuals were incorrectly classified as depressed. Out of the 241 instances randomly assigned to the test sample, 235 were correctly classified by the C5.0 algorithm, indicating high accuracy.\u003c/p\u003e\n\u003cp\u003ePerformance details of the other classifiers (CART and CHAID) are also presented in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e and visualized in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab2\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003e\u003cstrong\u003eConfusion Matrix for Test Sample\u003c/strong\u003e: \u003cem\u003eEach column represents predicted class; each row represents actual class\u003c/em\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eClassifier\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eActual Class\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003ePredicted: No Depression\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003ePredicted: Depression\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eC5.0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e182\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e53\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eCART\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e169\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e13\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e34\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e25\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eCHAID\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e173\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\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e37\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\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e, the C5.0 classifier achieved the highest overall accuracy at 97.51%, outperforming both CART (80.49%) and CHAID (80.91%). These results indicate that C5.0 is the most effective algorithm for predicting depression in this dataset.\u003c/p\u003e\n\u003cp\u003eIn addition to accuracy, C5.0 demonstrated superior performance across all evaluation metrics, including positive predictive value (PPV), negative predictive value (NPV), sensitivity, specificity, area under the curve (AUC), and kappa statistic (KS). These metrics are detailed in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003eWhen comparing CART and CHAID, CART showed higher PPV, specificity, AUC, and kappa statistic, whereas CHAID performed better in terms of NPV, sensitivity, and overall accuracy. These findings suggest that while both CART and CHAID have strengths in specific areas, C5.0 offers the most balanced and robust performance across all criteria.\u003c/p\u003e\n\u003cp\u003eTherefore, based on the comparative analysis presented in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e, C5.0 emerges as the most suitable choice for classifying depression using personality and demographic variables.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab3\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003e\u003cstrong\u003ePerformance Metrics of Classification Algorithms\u003c/strong\u003e: \u003cem\u003eAll values are percentages unless otherwise indicated\u003c/em\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eClassifier\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003ePPV (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eNPV (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSensitivity (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSpecificity (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAUC\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eKappa Statistic\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAccuracy (%)\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\u003eC5.0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e89.83\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e100.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e100.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e96.80\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.970\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.885\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e97.51\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCART\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e42.37\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e92.85\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e65.78\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e83.25\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.735\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.360\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e80.49\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCHAID\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e37.28\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e95.05\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e70.96\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e82.38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.622\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.342\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e80.91\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\u003eOne of the primary objectives of this analysis was to assess the individual importance of each predictor variable in relation to depression. Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e present the relative importance scores derived from the three classification algorithms (CART, CHAID, and C5.0), along with their averaged values.\u003c/p\u003e\n\u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e, neuroticism emerged as the most influential predictor, with the highest average importance score (87.43). This finding suggests that neuroticism plays a dominant role in predicting depression among university students. Following neuroticism, the variables were ranked in descending order of importance as: agreeableness, extraversion, conscientiousness, sex, educational level, age, marital status, and openness.\u003c/p\u003e\n\u003cp\u003eThese results highlight the central role of personality traits\u0026mdash;particularly neuroticism\u0026mdash;in shaping mental health outcomes, and reinforce the value of incorporating psychological dimensions into predictive models for depression.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab4\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003e\u003cstrong\u003ePredictor Importance Based on CHAID, CART, and C5.0 Algorithms\u003c/strong\u003e: \u003cem\u003eAverage rank reflects combined importance across all three methods\u003c/em\u003e\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eVariable\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eChi-square (CHAID)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eGini (CART)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eInformation Gain Ratio (C5.0)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAverage Rank\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\u003eNeuroticism\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e262.035\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.062\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.205\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e87.43\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAgreeableness\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e89.256\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.022\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.053\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e29.77\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eConscientiousness\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e77.848\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.025\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.078\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e25.98\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eExtraversion\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e48.872\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.018\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.062\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e28.31\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSex\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e18.591\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.007\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.020\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e6.20\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eEducational Level\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e18.265\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.010\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.033\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e6.10\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAge\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e14.442\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.056\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e4.83\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMarital Status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e9.983\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.004\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.014\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e3.33\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOpenness\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1.712\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.0001\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.002\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.57\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\u0026nbsp;\u003c/p\u003e\n\u003ch3\u003eBased on average rank derived from C5.0, CHAID, and CART algorithms in predicting depression\u003c/h3\u003e\n\u003cp\u003eThis figure illustrates the relative importance of each predictor variable in classifying depression, as calculated by averaging the importance scores from three decision tree algorithms. Neuroticism stands out as the most influential factor, followed by agreeableness, extraversion, and conscientiousness. Demographic variables such as sex, educational level, age, and marital status show moderate importance, while openness has minimal predictive value.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe findings of this study demonstrate that decision tree algorithms are reliable data mining tools for identifying students who are potentially at risk of depression. Among the three algorithms evaluated, C5.0 outperformed CHAID and CART in terms of accuracy and overall performance. Using decision tree techniques, neuroticism emerged as the most influential personality trait associated with depression, followed by agreeableness, extraversion, conscientiousness, sex, educational level, age, marital status, and openness.\u003c/p\u003e\u003cp\u003eData mining is increasingly recognized as a powerful technique for analyzing large datasets and building predictive models, particularly in health and medical sciences. Its applications span various domains, and it is considered one of the top ten scientific fields influencing technological advancement. Wherever data exists, data mining holds significance.\u003c/p\u003e\u003cp\u003eOur findings align with previous research in medical sciences that applied decision tree algorithms. For example, Islami et al found that C5.0 had the highest accuracy compared to CHAID, CART, and QUEST in predicting knowledge levels about exercise during pregnancy[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. Similarly, Momenyan et al reported that C5.0 outperformed other decision tree algorithms and logistic regression in predicting breast cancer survival[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]. Ladanza et al applied neural networks, support vector machines, and C5.0 to predict chronic obstructive pulmonary disease, with C5.0 yielding superior results[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. Delen et al compared artificial neural networks, C5.0, and logistic regression for breast cancer survivability prediction and concluded that C5.0 was the most accurate model[\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe superior performance of C5.0 can be attributed to its advanced features, such as boosting, which enhances accuracy[\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]. C5.0 also builds smaller trees than its predecessors (e.g., C4.5) and demonstrates lower error rates on unseen data [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. It is faster and more memory-efficient, making it ideal for large-scale studies with categorical response variables and no assumptions of linearity.\u003c/p\u003e\u003cp\u003eGiven the high accuracy of decision trees in disease prediction, they can be effectively used for early diagnosis of common conditions such as depression. Liu et al conducted a meta-analysis of 30 cohort studies involving 25,124 students and identified key biological, psychological, and environmental predictors of depression [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Neuroticism had the highest odds ratio, indicating a 25% increased risk of depression among students with high neuroticism. Gender was also a significant predictor, ranked fourth with an odds ratio of 1.11[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Our study similarly found significant associations between depression, neuroticism, and gender.\u003c/p\u003e\u003cp\u003eNeuroticism encompasses traits such as low mood, stress sensitivity, irritability, and poor emotional regulation [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]. Consistent with our findings, Navrady et al reported strong associations between neuroticism and major depressive disorder in two population-based cohorts[\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]. Speed et al used Mendelian Randomization to establish a causal relationship between neuroticism and depression, based on GWAS data from the Eysenck Personality Questionnaire and the Psychiatric Genomics Consortium. Their results confirmed neuroticism as a causal risk factor for depression[\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e], echoing our findings derived from decision tree analysis in a cross-sectional study.\u003c/p\u003e\u003cp\u003eOur results also support previous research on the relationship between depression and extraversion. Extraversion is characterized by sociability, liveliness, and cheerfulness [\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]. Chioqueta and Stiles found that depressive symptoms were positively predicted by neuroticism and negatively predicted by extraversion[\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]. Extraversion is considered an independent dimension of positive affectivity [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e]. Watson et al demonstrated that extraversion negatively correlates with depression and anhedonia, particularly through communal extraversion and positive emotions[\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e]. Jylh\u0026auml; and Isomets\u0026auml; (2006) found that neuroticism was strongly associated with depressive and anxiety symptoms, while introversion was moderately associated with depression in the general population[\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e]. Other studies have similarly reported negative associations between extraversion and depression[\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e, \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAgreeableness includes traits such as trust, honesty, altruism, adaptability, humility, and compassion. Our findings are consistent with Pearman et al, who found that agreeableness predicted levels of sadness[\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e]. However, our results differ from those of Takahashi et al, who found no significant relationship between agreeableness and depression[\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e]. In our study, agreeableness was the second most influential predictor of depression.\u003c/p\u003e\u003cp\u003eConscientiousness reflects traits such as achievement orientation, responsibility, dependability, and orderliness[\u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e]. Weber et al found that depressed patients had significantly lower levels of conscientiousness compared to controls[\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]. Takahashi et al also reported lower conscientiousness scores among treatment-resistant depressed individuals[\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e], consistent with our findings. Their study further suggested that low openness contributes to depression, whereas agreeableness had no effect. These discrepancies may stem from differences in study populations and measurement tools. Takahashi\u0026rsquo;s study focused on treatment-resistant depression and used the 17-item Hamilton Depression Rating Scale, while our study examined general depression using the PHQ-9.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study demonstrated that among the Big Five personality traits, neuroticism has the strongest association with depression in university students. Individuals with high levels of neuroticism were significantly more likely to experience depressive symptoms. Additionally, the C5.0 decision tree algorithm exhibited the highest classification accuracy compared to CART and CHAID, confirming its effectiveness in predicting depression.\u003c/p\u003e\u003cp\u003eThese findings suggest that decision tree algorithms, particularly C5.0, can be reliably used for early identification of students at risk for depression. Early detection of personality traits associated with depression may enable timely interventions and preventive strategies to support student mental health.\u003c/p\u003e"},{"header":"Limitations","content":"\u003cp\u003eDespite its contributions, the present research is subject to certain limitations. One of the main challenges was the large volume of questionnaires used, which may have led to participant fatigue and reduced engagement. Additionally, due to the sensitivity of some questions and participants\u0026rsquo; reluctance to respond, many items were left unanswered. This resulted in a considerable amount of missing data in several variables. As a consequence, valuable information\u0026mdash;particularly regarding students\u0026rsquo; socioeconomic status\u0026mdash;could not be fully utilized in the analysis.\u003c/p\u003e"},{"header":"Recommendations","content":"\u003cp\u003eFuture research could explore alternative personality models such as the Myers-Briggs Type Indicator (MBTI) and incorporate additional risk factors, including socioeconomic indicators and academic discipline. Moreover, it is recommended to evaluate other data mining classification techniques, such as artificial neural networks and Bayesian algorithms, to further enhance predictive performance and model robustness.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePHQ-9\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ePatient Health Questionnaire-9\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eNEO-60\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eNEO Five-Factor Inventory \u0026ndash; 60-item version\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCART\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eClassification and Regression Trees\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eCHAID\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eChi-squared Automatic Interaction Detection\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eC5.0\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eAn advanced decision tree algorithm (successor to C4.5)\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eFFM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eFive-Factor Model\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eDSM-5\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eDiagnostic and Statistical Manual of Mental Disorders, Fifth Edition\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eGHQ\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eGeneral Health Questionnaire\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eRaSaD\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eRavand Salamati Daneshjooyan\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eIUMS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eIsfahan University of Medical Sciences\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eNEO-PI-R\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eNEO Personality Inventory-Revised\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eDSM-IV\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eDiagnostic and Statistical Manual of Mental Disorders, Fourth Edition\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eROC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eReceiver Operating Characteristic\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAUC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eArea Under the Curve\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eSPSS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eStatistical Package for the Social Sciences\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePPV\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ePositive Predictive Value\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eNPV\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eNegative Predictive Value\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eKS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eKappa Statistic\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eQUEST\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eQuick, Unbiased, Efficient Statistical Tree\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eGWAS\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eGenome-Wide Association Study\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eMBTI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eMyers-Briggs Type Indicator\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\u003e This study was conducted in accordance with the ethical principles of the Declaration of Helsinki, last revised in 2013 (World Medical Association, 2013). Ethics approval was obtained from Isfahan University of Medical Sciences (Ethics ID: IR.MUI.RESEARCH.REC.1398.701. Written informed consent to participate was obtained from all participants after they were fully informed about the study objectives and confidentiality protocols. only those who provided written informed consent were included.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConsent for publication :\u003c/strong\u003e\u003cp\u003eNot applicable\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003ch2\u003eCompeting Interests:\u003c/h2\u003e\u003cp\u003eThe author declares that there are no competing interests.\u003c/p\u003e\u003c/p\u003e\u003ch2\u003eFunding :\u003c/h2\u003e\u003cp\u003eThe author declares that no funding was received for this study.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eThe author confirms sole responsibility for the conception, design, data collection, analysis, interpretation, and writing of this manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgements:\u003c/h2\u003e\u003cp\u003eThe author would like to thank Isfahan University of Medical Sciences for their support and guidance during the course of this research.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe data that support the findings of this study are not publicly available due to institutional restrictions but are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eLim GY, et al. Prevalence of Depression in the Community from 30 Countries between 1994 and 2014. Sci Rep. 2018;8(1):2861.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAghakhani N, et al. Prevalence of depression among students of urmia university of medical sciences (iran). Iran J Psychiatry Behav Sci. 2011;5(2):131\u0026ndash;5.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDiagnostic. \u003cem\u003eand statistical manual of mental disorders: DSM-5\u0026trade;, 5th ed\u003c/em\u003e, in \u003cem\u003eDiagnostic and statistical manual of mental disorders: DSM-5\u0026trade;, 5th ed.\u003c/em\u003e 2013, American Psychiatric Publishing, Inc.: Arlington, VA, US. p. xliv, 947-xliv, 947.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRotenstein LS, et al. Prevalence of Depression, Depressive Symptoms, and Suicidal Ideation Among Medical Students: A Systematic Review and Meta-Analysis. JAMA. 2016;316(21):2214\u0026ndash;36.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMojtabai R, Olfson M, Han B. National trends in the prevalence and treatment of depression in adolescents and young adults. Pediatrics. 2016;138(6):e20161878.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMikolajczyk RT, et al. Prevalence of depressive symptoms in university students from Germany, Denmark, Poland and Bulgaria. Soc Psychiatry Psychiatr Epidemiol. 2008;43(2):105\u0026ndash;12.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIbrahim AK, et al. A systematic review of studies of depression prevalence in university students. J Psychiatr Res. 2013;47(3):391\u0026ndash;400.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu Y, et al. Predictors of depressive symptoms in college students: A systematic review and meta-analysis of cohort studies. J Affect Disord. 2019;244:196\u0026ndash;208.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAkbari V, Hajian A, Damirchi P. Prevalence of Emotional Disorders Among Students of University of Medical Sciences; Iran. Open Psychol J. 2014;7:29\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMohamadi M, et al. A meta-analysis of studies related prevalence of depression in Iran. J Res Health. 2017;7(1):581\u0026ndash;93.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSarokhani D et al. \u003cem\u003ePrevalence of Depression among University Students: A Systematic Review and Meta-Analysis Study.\u003c/em\u003e Depress Res Treat, 2013. 2013: p. 373857.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDuggan C, et al. Theories of general personality and mental disorder. Br J Psychiatry. 2003;182(Suppl44):s19\u0026ndash;23.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWatson D, Gamez W, Simms LJ. Basic dimensions of temperament and their relation to anxiety and depression: A symptom-based perspective. J Res Pers. 2005;39(1):46\u0026ndash;66.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNewbury-Birch D, Kamali F. Psychological stress, anxiety, depression, job satisfaction, and personality characteristics in preregistration house officers. Postgrad Med J. 2001;77(904):109\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTerracciano A, Costa PT Jr. Smoking and the Five-Factor Model of personality. Addiction. 2004;99(4):472\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJerram KL, Coleman PG. The big five personality traits and reporting of health problems and health behaviour in old age. Br J Health Psychol. 1999;4(2):181\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNouri F, et al. How five-factor personality traits affect psychological distress and depression? Results from a large population-based study. Psychol Stud. 2019;64(1):59\u0026ndash;69.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSadeq NA, Molinari V. Personality and its relationship to depression and cognition in older adults: implications for practice. Clin Gerontologist. 2018;41(5):385\u0026ndash;98.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGrav S, et al. The relationship among neuroticism, extraversion, and depression in the HUNT Study: in relation to age and gender. Issues Ment Health Nurs. 2012;33(11):777\u0026ndash;85.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWeiss A, et al. The personality domains and styles of the five-factor model are related to incident depression in Medicare recipients aged 65 to 100. Am J Geriatric Psychiatry. 2009;17(7):591\u0026ndash;601.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBESHARAT GR, Z. KHANJANI, and, BABAPOUR J. \u003cem\u003eComparison of five big personality factors in depressive disorder patients and obsessive\u0026ndash;compulsive disorders with normal individuals.\u003c/em\u003e 2013.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChien L-L, Ko H-C, Wu JY-W. The five-factor model of personality and depressive symptoms: One-year follow-up. Pers Indiv Differ. 2007;43(5):1013\u0026ndash;23.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMadadipouya K. A survey on data mining algorithms and techniques in medicine. JOIV: Int J Inf Visualization. 2017;1(3):61\u0026ndash;71.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChaurasia V, Pal S. Early prediction of heart diseases using data mining techniques. Caribb J Sci Technol. 2013;1(1):208\u0026ndash;17.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFrank E, et al. Using model trees for classification. Mach Learn. 1998;32(1):63\u0026ndash;76.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKiers HA, et al. Data analysis, classification, and related methods. Springer Science \u0026amp; Business Media; 2012.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChapman B, Duberstein P, Lyness JM. Personality traits, education, and health-related quality of life among older adult primary care patients. Journals Gerontol Ser B: Psychol Sci Social Sci. 2007;62(6):P343\u0026ndash;52.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEysenck HJ. A reply to Costa and McCrae. P or A and C\u0026mdash;the role of theory. Pers Indiv Differ. 1992;13(8):867\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJoshanloo M, et al. Construct validity of NEO-personality inventory-revised in Iran. Iran J Psychiatry Clin Psychol. 2010;16(3):220\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAfshar H, et al. Association of personality traits with psychological factors of depression, anxiety, and psychological distress: a community based study. Int J Body Mind Cult. 2015;2(2):105\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLotrakul M, Sumrithe S, Saipanish R. Reliability and validity of the Thai version of the PHQ-9. BMC Psychiatry. 2008;8(1):46.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDadfar M, Kalibatseva Z, Lester D. Reliability and validity of the Farsi version of the Patient Health Questionnaire-9 (PHQ-9) with Iranian psychiatric outpatients. Trends psychiatry Psychother. 2018;40(2):144\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePark S-J, Choi H-RCJ-H, Kim K-W. Jin-Pyo Hong., \u003cem\u003eReliability and validity of the Korean version of the Patient Health Questionnaire-9 (PHQ-9).\u003c/em\u003e Korean Academy of Anxiety Disorders, 2010. 6(2): pp. 119\u0026ndash;124.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003evan Steenbergen-Weijenburg KM, et al. Validation of the PHQ-9 as a screening instrument for depression in diabetes patients in specialized outpatient clinics. BMC Health Serv Res. 2010;10(1):235.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePrather JC et al. \u003cem\u003eMedical data mining: knowledge discovery in a clinical data warehouse\u003c/em\u003e. in \u003cem\u003eProceedings of the AMIA annual fall symposium\u003c/em\u003e. 1997.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKass GV. An exploratory technique for investigating large quantities of categorical data. J Roy Stat Soc: Ser C (Appl Stat). 1980;29(2):119\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTang T-I, et al. A comparative study of medical data classification methods based on decision tree and system reconstruction analysis. Industrial Eng Manage Syst. 2005;4(1):102\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePang S-l, Gong J-z. C5. 0 classification algorithm and application on individual credit evaluation of banks. Syst Engineering-Theory Pract Online. 2009;29(12):94\u0026ndash;104.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePandya R, Pandya J. \u003cem\u003eC5. 0 algorithm to improved decision tree with feature selection and reduced error pruning.\u003c/em\u003e International Journal of Computer Applications, 2015. 117(16).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIslamı F, Bagherı F, Mohammadı F. Surveying the knowledge of pregnant women towards sport activities during pregnancy using data mining algorithms. Turkish J Sport Exerc. 2016;18(1):8\u0026ndash;16.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMomenyan S et al. \u003cem\u003eSurvival prediction of patients with breast cancer: comparisons of decision tree and logistic regression analysis.\u003c/em\u003e International Journal of Cancer Management, 2018. 11(7).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIadanza E, et al. An automatic system supporting clinical decision for chronic obstructive pulmonary disease. Health Technol. 2020;10(2):487\u0026ndash;98.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDelen D, Walker G, Kadam A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med. 2005;34(2):113\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePatidar PT. Handling Missing Value in Decision Tree Algorithm. Int J Comput Appl. 2013;70(13):31\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang C, et al. Characterization of genetic loci that affect susceptibility to inflammatory bowel diseases in African Americans. Gastroenterology. 2015;149(6):1575\u0026ndash;86.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNavrady LB, et al. Intelligence and neuroticism in relation to depression and psychological distress: Evidence from two large population cohorts. Eur Psychiatry. 2017;43:58\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSpeed D, et al. Investigating the causal relationship between neuroticism and depression via Mendelian randomization. Acta psychiatrica Scandinavica. 2019;139(4):395.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChioqueta AP, Stiles TC. Personality traits and the development of depression, hopelessness, and suicide ideation. Pers Indiv Differ. 2005;38(6):1283\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWatson D, Clark LA, Tellegen A. Development and validation of brief measures of positive and negative affect: the PANAS scales. J Personal Soc Psychol. 1988;54(6):1063.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWatson D, Tellegen A. Toward a consensual structure of mood. Psychol Bull. 1985;98(2):219.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWatson D, et al. Extraversion and psychopathology: A multilevel hierarchical review. J Res Pers. 2019;81:1\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJylh\u0026auml; P, Isomets\u0026auml; E. The relationship of neuroticism and extraversion to symptoms of anxiety and depression in the general population. Depress Anxiety. 2006;23(5):281\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSaklofske D, Kelly I, Janzen B. Neuroticism, depression, and depression proneness. Pers Indiv Differ. 1995;18(1):27\u0026ndash;31.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePearman A, Andreoletti C, Isaacowitz DM. Sadness prediction and response: Effects of age and agreeableness. Aging Ment Health. 2010;14(3):355\u0026ndash;63.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTakahashi M, et al. Low openness on the revised NEO personality inventory as a risk factor for treatment-resistant depression. PLoS ONE. 2013;8(9):e71964.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKoorevaar A, et al. Big Five personality and depression diagnosis, severity and age of onset in older adults. J Affect Disord. 2013;151(1):178\u0026ndash;85.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWeber K, et al. Personality traits are associated with acute major depression across the age spectrum. Aging Ment Health. 2012;16(4):472\u0026ndash;80.\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":"data mining, decision tree, machine learning, classification, depression, personality traits","lastPublishedDoi":"10.21203/rs.3.rs-7722213/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7722213/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eBackground\u003c/b\u003e\u003c/p\u003e\u003cp\u003eDepression is one of the most prevalent and recurrent mental health disorders in recent years, particularly among university students, where it can significantly impact academic performance. This study aimed to explore the relationship between personality traits and depression using data mining techniques.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMaterials and Methods\u003c/b\u003e\u003c/p\u003e\u003cp\u003eA cross-sectional study was conducted among 1,243 students at Isfahan University of Medical Sciences. Participants completed the PHQ-9 (for depression assessment), the NEO-60 (for personality traits), and a demographic questionnaire. Three widely used decision tree algorithms\u0026mdash;CART, CHAID, and C5.0\u0026mdash;were applied to predict depression levels.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e\u003c/p\u003e\u003cp\u003eAll three algorithms identified neuroticism as the most influential personality trait associated with depression (average rank\u0026thinsp;=\u0026thinsp;87.4), followed by agreeableness, extraversion, and conscientiousness. Among the models, C5.0 demonstrated superior predictive performance (Sensitivity\u0026thinsp;=\u0026thinsp;100%, Specificity\u0026thinsp;=\u0026thinsp;96.8%, Accuracy\u0026thinsp;=\u0026thinsp;97.5%) compared to CHAID and CART.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e\u003c/p\u003e\u003cp\u003eDecision tree algorithms offer effective tools for identifying depression based on personality traits. Neuroticism emerged as the strongest predictor, suggesting that targeted mental health interventions for students with high neuroticism scores may help reduce depression prevalence.\u003c/p\u003e","manuscriptTitle":"\"Exploring the Relationship Between Depression and the Five-Factor Personality Model: A Comparative Study Using Three Decision Tree Algorithms\"","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-23 11:45:46","doi":"10.21203/rs.3.rs-7722213/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-17T15:09:18+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-09T13:53:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-28T06:36:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"189381612687253864609798940418761688383","date":"2025-11-20T02:26:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"144955131921810351314033993131298088658","date":"2025-11-18T14:17:25+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-11T17:34:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-04T06:06:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-12T09:11:29+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-07T09:57:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2025-10-07T09:53:37+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":"0e8380b8-0658-4802-9d80-95220d091c30","owner":[],"postedDate":"November 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-03-17T10:25:54+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-23 11:45:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7722213","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7722213","identity":"rs-7722213","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}