Interpretable Machine Learning Models for Identifying Premenstrual Syndrome and Related Factors in Young Adult Women

Interpretable Machine Learning Models for Identifying Premenstrual Syndrome and Related Factors in Young Adult Women | 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 Interpretable Machine Learning Models for Identifying Premenstrual Syndrome and Related Factors in Young Adult Women Xiaohe Lin, Xiangyu Zhao, Yue Zeng, Lina Guo, Hongqvn Liu, Cui Mao, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7522395/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Premenstrual syndrome (PMS) is a public health problem with widespread impact, influenced by the multiple factors. Young adult women, as a high-risk group for PMS, can benefit from early identification of key factors related to PMS. This study aimed to construct a machine learning model for identifying PMS among young adult women and explore the complex relationships between associated factors and PMS. Method A secondary analysis was performed using cross-sectional data from 3447 young adult women. Using a score of 6 points on the Premenstrual Syndrome Scale (PSS) as the cutoff, all participants were divided into the PMS group and the non-PMS group. The dataset was randomized into a training set and a validation set in 75% and 25% proportions. Five machine learning algorithms were used to develop models and the output of performed-best model was interpreted using SHapley Additiveex Planations (SHAP). Results There were 1474 women in PMS group and 1973 women in non-PMS group. Among five machine learning models, the random forest model performed best, with an AUC of 0.782. Neuroticism was most strongly associated with PMS, followed by mindfulness, history of dysmenorrhea, emotional abuse, and use of analgesic. Conclusion The results suggested that the random forest model was an effective tool for identifying PMS among young adult women, and neuroticism could serve as a crucial predictive indicator. Furthermore, interventions such as mindfulness training, dysmenorrhea management, and addressing early trauma may hold significant potential in preventing and managing PMS. Premenstrual Syndrome Machine Learning Young Adult Women Groups Figures Figure 1 Figure 2 Figure 3 Highlights • The result revealed machine learning techniques, particularly random forest, in the ability to process complex datasets and the potential of identifying PMS. • Based on the random forest model, neuroticism exhibited the highest predictive capacity for PMS among young women. • Interventions such as mindfulness training, dysmenorrhea management, and addressing early trauma may hold significant potential in preventing and managing PMS. Introduction Many women may periodically undergo a series of physical, psychological or behavioral changes during the luteal phase of the menstrual cycle, such as anxiety, irritability, hypersomnia, difficulty concentration and so on, which is known as premenstrual syndrome (PMS) (Liguori et al., 2023 ; Ma & Song, 2023 ). The American College of Obstetricians and Gynecologists (ACOG) defined PMS as a clinical condition (Geta et al., 2020 ), with severity affecting normal daily functioning, work, school performance, interpersonal relationships, or cause significant distress (O'Brien et al., 2011 ). The literature reported that approximately 80% of women experienced at least one emotional or physical symptom in the days leading up to their menstrual period (Wittchen et al., 2002 ). As a public health problem with widespread impact, PMS necessitates further attention. The prevalence of PMS varies in different countries due to differences in cultural backgrounds and social environments. A meta-analysis reported that the pooled global prevalence of PMS was 47.8%, with lowest being 12% in France (A et al., 2014). The prevalence of PMS in women of childbearing age was reported as 21.1% in China (Qiao et al., 2012 ), 43% in India (Dutta & Sharma, 2021 ), 52.2% in Turkey (Erbil & Yucesoy, 2023 ). Although the peak presentation of PMS occurs in 20s (Acikgoz et al., 2017 ), many women state they experienced premenstrual symptoms as early as adolescence (Robinson & Swindle, 2000 ). Young adult women, in the transitional phase from adolescence to adulthood, are at high risk of suffering from premenstrual disorders. Considering the negative effects of PMS on mental health and professional productivity (Liguori et al., 2023 ; Smith, 2008 ), it is crucial to identify the key factors associated with PMS at an early stage. Although the etiology of PMS has not been fully elucidated, based on previous research, it is the result of the combined effects of multiple factors, including physiological, psychological, lifestyle, and social aspects. The cyclic hormonal fluctuations during the menstrual cycle are widely recognized as an important factor influencing PMS (Le et al., 2020 ). However, increasing researchers have also noticed the significant associations between demographic and menstrual characteristics with PMS, as these factors are more intuitive and easier to self-observation by individuals. For instance, a meta-analysis reported exercise was negatively associated with risk of PMS (Yang et al., 2024 ). Obesity was a modifiable risk factor for PMS, with significant link between increasing body mass index (BMI) and increasing the severity of the emotional and psycho-behavioral symptoms (Mostafa et al., 2023 ). Smoking and alcohol consumption have also been found to be associated with an increased risk for PMS (Choi & Hamidovic, 2020 ; del Mar Fernandez et al., 2018 ). Among menstrual factors, the cycle regularity, flow during the menstrual cycle, duration of the cycle, the severity of dysmenorrhea, and analgesic use all possessed closely correlations with PMS (Ababneh et al., 2023 ; Mann & Pradeep, 2023 ). Moreover, the effects of psychological factors on PMS have received increasing interest, such as personality, emotional and cognitive factors. The literature reported that certain personality traits, like neuroticism, were risk factors for PMS, with more severe PMS symptoms observed in individuals with stronger neuroticism tendency (Singh et al., 2016 ). Emotional regulation was commonly conceptualized as the process by which individuals influence the generation, experience, and expression of their own emotions, primarily encompassing two core strategies: cognitive reappraisal and expressive suppression (Antuña-Camblor et al., 2024 ). Maladaptive emotional regulation might appeared to have a role in the underlying of premenstrual disorder (Azoulay et al., 2020 ). Mindfulness, defined as an ability to allow people to achieve an open and receptive state of awareness, has been gaining increasing attention (Bishop et al., 2004 ). Previous studies have reported the powerful impact of mindfulness on emotional and behavioral outcomes, including premenstrual symptoms and impairments during the luteal phase (Huang et al., 2019 ; Nayman et al., 2023 ). Mindfulness-based cognitive therapy has also been applied to women with PMS symptoms (Mazaheri Asadi et al., 2022 ), providing a foundation for further exploring the complex relationship between mindfulness and PMS in this study. It is well known that early life trauma was an important etiology of the development of symptoms of psychopathology (DeCou et al., 2023 ). Several studies have illustrated that women who have experienced childhood trauma had an increased risk of developing PMS and were likely to endure more diverse symptoms with a greater degree of severity (Azoulay et al., 2020 ; Gumussoy et al., 2021 ). To date, numerous studies have investigated the factors associated with PMS predominantly utilizing traditional regression analysis (Ababneh et al., 2023 ; Babapour et al., 2023 ; Liu et al., 2023 ). Although this method has provided valuable insights into understanding PMS, it comes with stringent data requirements and limited model complexity, making it challenging to assess the relative importance of various factors. Machine learning, a pivotal technology within the realm of artificial intelligence, is witnessing a growing prominence of its significance. Machine learning is defined as a technology that automatically learns from data and identifies patterns to develop training models and enable accurate predictions and classifications on new data (Domingos, 2012 ). Unlike traditional regression analysis, machine learning excels at handling high-dimensional data and constructing complex models by leveraging the nonlinear relationships among data, thereby achieving greater generalization ability (Lee et al., 2018 ). In the last few years, machine learning has been widely applied in various fields of medicine, such as neurology and psychiatry, demonstrating significant potential in disease prediction (Martin et al., 2023 ; Pigoni et al., 2024 ). Taken together, this study conducted a secondary analysis of data from young adult women, including demographic, menstrual characteristics, and socio-psychological factors, and aimed to construct a machine learning model for identifying PMS and explore the complex relationships between these factors with PMS. Noteworthy, to enhance the reliability and accuracy of the model, five machine learning algorithms were conducted. SHapley Additiveex Planations (SHAP) was used to interpret the output of the best-performed model. The findings of this study may provide valuable insights into understanding PMS and associated factors among young adult women and have the potential to sever as a reference in developing targeted interventions for PMS. Materials and methods Participants A second analysis was performed using data from young adult women across nine universities located in China. The survey was conducted by online questionnaire and recruited female students in their first to forth year. Those with a history of pregnancy, miscarriage, taking medicine (like oral contraceptives, psychotropic or other hormonal drugs) in the past three months, and mental disorders, gynecological and endocrine disorders were excluded. A total of 3848 participants completed the questionnaire. After removing incomplete questionnaires and those with less than 5 minutes of response time or irregular responses, 3447 young women were included in this analysis. Informed consent was obtained from all participants and the study was approved by the Research Ethics Committee of the affiliated institution. Measures Demographic and Menstrual Characteristics General demographic information included age, BMI, family economy, diet, smoking, drinking alcohol and exercise. Menstrual characteristics included age of menarche, menstrual regularity, days of menstruation, menstrual volume, history of dysmenorrhea and use of analgesic. Premenstrual Syndrome Premenstrual Syndrome Scale (PSS) was used to assess the prevalence of premenstrual syndrome among nursing college students in this study (Bancroft, 1993 ). This scale evaluated physical and emotional abnormalities in the 14 days before menstruation, consisting of 12 symptoms (i.e., irritability, depressed mood, anxiety, bloating and diarrhea, difficulty concentration, hypersomnia, tension, fidget, migraine, insomnia, swelling of hands or feet, nervousness). This scale was a 4-point scale, with each item scoring from 0 to 3 (0 = no symptoms, 1 = mild symptoms, 2 = symptoms that affect life, study and work, but can tolerate, 3 = symptoms that seriously affect life, study and work, and need treatment). The total score of the scale was the sum of all items, ranging from 0 to 36. In this study, participants with total score over 6 points were divided into PMS group, and the rest were non-PMS group. The Cronbach’s α of the total scale in this study was 0.902. Personality Trait-Neuroticism Neuroticism dimension of the 44-Item Big Five Inventory (BFI) was used to evaluate the level of neurotic personality (Soto & John, 2009 ). This dimension consisted of 8 items and each item was rated on a 5-point Likert scale from 1 (strongly disagree) to 5 (strongly agree). The higher score indicated greater neuroticism personality. The Cronbach’s α coefficient of this sub-dimension in current study was 0.709. Emotion Regulation Strategy The use of emotion regulation strategies was measured using Emotion Regulation questionnaire (ERQ) revised by Wang et al. (Wang et al., 2007 ). This questionnaire consisted of 10 items including 2 dimensions of cognitive reappraisal (items 1, 3, 5, 7, 8, and 10) and expressive suppression (items 2, 4, 6, and 9). Each item was rated on a Likert 7-point scoring (1 = strongly disagree and 7 = strongly agree), with higher score of each dimension indicating more frequent use of this emotion regulation strategy. In the present study, the Cronbach’s α coefficients for two dimensions were 0.925 and 0.813 respectively. Mindfulness Mindfulness was assessed by the five items version of Mindful Awareness Attention Scale (MASS-5) (Caycho-Rodríguez et al., 2021 ). Each item was rated on a 6-point Likert scale from 1 (never) to 6 (always), with higher score indicating higher level of mindfulness. This scale has shown good reliability and validity in Chinese populations, and the Cronbach’s α in this study was 0.858. Childhood Trauma Childhood Trauma Questionnaire-Short Form (CTQ-SF) was used to measure traumatic experiences before the age of 16(Spinhoven et al., 2014 ). In this study, the Chinese version translated by Zhao et al. was used (Zhao et al., 2005 ), which was a 28-item questionnaire, including physical abuse, emotional abuse, sexual abuse, physical neglect, and emotional neglect. Each item was rated on a 5-point scale from 1 (never) to 5 (always). The Cronbach’s α coefficients were between 0.663 and 0.931 in the study. Statistic analysis All analyses were used SPSS (version 26.0) and R (version 4.4.1) and a two-sided test was conducted with a significance level of P < 0.05. All variables were presented by descriptive statistics, with categorical variables by frequency (N) and percentage (%) and continuous variables by mean (M) and standard deviation (SD). Mann-whitney U tests and Chi-square tests were used to compare the differences of PMS group and non-PMS group in predictive variables. The dataset was randomized into a training set and a validation set in 75% and 25% proportions. A comparative analysis was conducted to evaluate the randomness and validity of the partition. Before the machine learning models construction, the correlation coefficients of all variables were calculated to exclude the predictive variables that highly correlated with PMS (correlation coefficient more than 0.8) and the near-zero-variance variables were also be excluded. In feature selection stage, Boruta algorithm was used to determine the significant predictive variables in a classification model. The algorithm is an extension of the idea introduced by to determine relevance by comparing the relevance of the real features to that of the random probes (Handhika et al., 2023). R Software was employed to perform five machine learning algorithms, namely logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multilayer perceptron (MLP), to construct models for predicting the premenstrual syndrome in young adult women. Each model underwent five repetitions of 5-fold cross-validation, followed by parameter tuning, in order to optimize the model parameters and enhance its generalization ability. Moreover, to compare the predictive performance of models, five metrics were evaluated, such as accuracy, specificity, sensitivity, F1 score, and the area under the receiver operating characteristic curve (AUC). Finally, SHapley Additiveex Planations (SHAP) was used to elucidate the output of the best-performing model. SHAP assigns each feature a SHAP value based on its contribution to the prediction. If the SHAP value was positive, the model tended to predict that the participant was divided into PMS group; conversely, if the value was negative, the model tended to predict that the participant was divided into non-PMS group. These values can be readily comprehended and visualized, which facilitates both global and local explanations of the model (Lundberg & Lee, 2017 ). Results Sample characteristics A total of 3447 young adult women were included in data analysis. The average age of participants was 19.48 years (SD = 1.15). Most of the women experienced dysmenorrhea (86.8%), with 32.6% occurring frequently. However, only 24.5% of women had ever used analgesic. The average PMS score for all participants was 6.65 (SD = 1.15). According to the PSS criteria, there were 1474 women in PMS group and 1973 women in non-PMS group. More basic information are presented in Table 1 . Table 1 Descriptive and comparative analyses among nursing students ( N = 3447) Variable Total Sample ( N = 3447) M ± SD/n(%) PMS Group (N = 1474) M ± SD/n(%) Non-PMS Group (N = 1973) M ± SD/n(%) χ 2 / z Demographic Age (years) 19.48 ± 1.15 19.42 ± 1.14 19.56 ± 1.15 3.371** BMI 20.47 ± 2.68 20.53 ± 2.70 20.39 ± 2.65 1.412 Family economy 3.997 Insufficient 515(14.9) 238 (16.1) 277 (14.0) Sufficient for essentials 2318(67.2) 966 (65.5) 1352 (68.5) More than sufficient 614(17.8) 270 (18.3) 344 (17.4) Diet 36.415*** Irregular 324(9.4) 173 (11.7) 151 (7.7) Basic regular 2639(76.6) 1144 (77.6) 1495 (75.8) Regular 484(14.0) 157 (10.7) 327 (16.6) Exercise 2.331 Never 361(10.5) 163 (11.1) 198 (10.0) Occasionally 2923(84.8) 1249 (84.7) 1674 (84.8) Frequently 163(4.7) 62 (4.2) 101 (5.1) Smoking 6.870** No 3396(98.8) 1443 (97.9) 1953 (99.0) Yes 51(1.5) 31 (2.1) 20 (1.0) Alcohol consumption 11.655** No 3001(87.1) 1250 (84.8) 1751 (88.7) Yes 446(12.9) 224 (15.2) 222 (11.3) Menstrual Characteristics Age of menarche (years) 5.739 16 38(1.1) 17 (1.2) 21 (1.1) Menstrual regularity 16.870*** Irregular 739(21.4) 350 (23.7) 389 (19.7) Basic regular 2290(66.4) 978 (66.4) 1312 (66.5) Regular 418(12.1) 146 (9.9) 272 (13.8) Days of menstruation 4.237 ≤ 3 295(8.6) 129 (8.8) 166 (8.4) 4 ~ 7 3002(87.1) 1269 (86.1) 1733 (87.8) ≥ 8 150(4.4) 76 (5.2) 74 (3.8) Menstrual volume 17.689*** Small 326(9.5) 141 (9.6) 185 (9.4) Medium 2853(82.8) 1186 (80.5) 1667 (84.5) Large 268(7.8) 147 (10.0) 121 (6.1) History of dysmenorrhea 207.002*** Never 455(13.2) 102 (6.9) 353 (17.9) Occasionally 1868(54.2) 714 (48.4) 1154 (58.5) Frequently 1124(32.6) 658 (44.6) 466 (23.6) Use of analgesic 109.487*** Never 2600(75.4) 984 (66.8) 1616 (81.9) Occasionally 611(17.7) 339 (23.0) 272 (13.8) Frequently 236(6.8) 151 (10.2) 85 (4.3) Socio-psychological Factors Neuroticism 2.69 ± 0.69 2.97 ± 0.64 2.47 ± 0.64 21.724*** Emotion regulation Cognitive reappraisal 28.00 ± 7.00 27.62 ± 6.16 28.28 ± 7.56 4.907** Expressive suppression 14.56 ± 4.60 15.43 ± 4.20 13.91 ± 4.77 9.629*** Mindfulness 21.15 ± 4.61 15.91 ± 4.28 22.38 ± 4.48 18.305*** Childhood trauma Emotional abuse 6.85 ± 2.77 7.56 ± 3.14 6.32 ± 2.31 13.841*** Physical abuse 5.74 ± 2.31 6.02 ± 2.68 5.27 ± 1.96 6.997*** Sexual abuse 5.64 ± 2.12 5.88 ± 2.43 5.46 ± 1.84 7.097*** Emotional neglect 9.82 ± 4.92 10.63 ± 4.93 9.22 ± 4.82 9.844*** Physical neglect 7.91 ± 3.30 8.53 ± 3.58 7.45 ± 2.98 9.143*** Note. *<0.05 **<0.01***<0.001 Feature selection, model construction, and performance comparison All participants were randomly divided into a training set of 2584 participants and a validation of 800 participants set at a ratio of 75% and 25%. The results of comparative analysis showed that there was no statistical difference in sample characteristics between the two sets. The details are showed in Table S1 . Before the feature selection, smoking and sexual abuse were excluded from the dataset due to the variances being close to zero. The Boruta algorithm was selected for feature selection. Of the 20 independent variables, 11 variables had significant effects on PMS, followed by neuroticism, mindfulness, history of dysmenorrhea, emotional abuse, expressive suppression, use of analgesic, physical neglect, emotional neglect, physical abuse, cognitive reappraise, and menstrual volume (See Figure S1 for details). Then, five machine learning models were constructed, including logistic regression, random forest, XGBoost, SVM, and MLP, with the above 11 features as independent variables and the presence or absence of PMS as dependent variables. The performance of each model was summarized in Table 2 and the receiver operating characteristic (ROC) curves of training set and validation set were showed in Fig. 1 (a) and 1(b). According a comprehensive comparison, the random forest model performed best, with an AUC of 0.782, accuracy of 0.717, specificity of 0.733, sensitivity of 0.696, and an F1 score of 0.678 in validation set. Table 2 Model performance in identifying PMS in the training and validation set. AUC Accuracy Specificity Sensitivity F1 Score Training Set RF 0.834 0.756 0.766 0.743 0.723 XGBoost 0.789 0.712 0.657 0.786 0.700 SVM 0.788 0.726 0.705 0.753 0.701 MLP 0.785 0.717 0.684 0.763 0.698 Logistic 0.785 0.720 0.692 0.758 0.699 Validation Set RF 0.782 0.717 0.733 0.696 0.678 XGBoost 0.778 0.705 0.662 0.762 0.688 SVM 0.780 0.718 0.715 0.724 0.687 MLP 0.781 0.716 0.704 0.732 0.688 Logistic 0.781 0.721 0.711 0.734 0.692 Abbreviations. RF random forest, XGBoost extreme gradient boosting, SVM support vector machine, MLP multilayer perceptron, Logistic logistic regression. Importance of features To gain insight into the contribution of each feature to the results, SHAP was used to interpret the output of the random forest model. Figure 2 shows SHAP summary plots, describing the absolute value of SHAP mean of each feature, with the top five being neuroticism, mindfulness, history of dysmenorrhea, emotional abuse, and use of analgesic. Furthermore, the positive and negative contribution of each feature to PMS were visualized in Fig. 3 , with the x-axis representing the value of the feature and the y-axis representing the SHAP value. As seen in Fig. 3 (a), participants who have frequent dysmenorrhea or use analgesic are at greater risk of developing PMS. In Fig. 3 (b), as neuroticism scores increased, the SHAP values increased and stabilized at a positive value above 3 points. Conversely, the relationship between mindfulness and SHAP values showed a negative correlation and remained stable for mindfulness larger than 24. For emotional abuse, the SHAP values show a increasing then slightly decreasing trend, but basically stable at positive. Discussion This study explored the status of PMS among young adult women in China and developed machine learning-based models for identifying PMS. According to the comprehensive comparison of model performance, random forest exhibited the best performance. Then, SHAP was employed to explain the output of random forest and identify the key features associated with PMS, providing a powerful reference for accurate identification and intervention of PMS. A total of 3447 young women were included in the secondary analysis. Of them, 42.8% were found to suffer PMS, which was relatively consistent with results from Korean college students (Kim & Park, 2020 ), but lower than those from high school students (64.6%) (Takeda et al., 2010 ) and higher with women of reproductive age (24.1%) (Qiao et al., 2012 ). The main reason behind these differences can be explained by the use of different measurement tools encompassing different symptoms. However, these findings also illustrate a relative higher prevalence of PMS in young adult women. Close interaction between hypothalamic-pituitary-ovarian (HPO) axis hormones is fundamental for a regular menstrual cycle (Naz et al., 2022 ). Young adult women are in the transition phase from adolescence to adulthood, and their HPO axis may not be fully mature, accompanied with immaturity in ovarian responses and FSH secretion (Sun et al., 2018 ), which is prone to menstrual abnormalities, such as PMS. Additionally, young adult women may experience multiple pressures from academia, social life, and the workplace. These stressors could affect the normal activity of the hypothalamic-pituitary-adrenal (HPA) axis (Oyola & Handa, 2017 ), raising cortisol concentrations (Juruena, 2014 ), which disrupts the typical cyclical pattern of hormonal fluctuations, leading to PMS ultimately (Alshdaifat et al., 2022 ; Maity et al., 2022 ). Therefore, it is necessary to pay attention to PMS in young adult women and provide them with efficient diagnosis and effective intervention. In this study, five machine learning models were employed, including logistic regression, random forest, XGBoost, SVM, and MLP. The results of model performance reported that the AUC values of five models were all greater than 0.75 on both training and validation sets, suggesting good prediction of performance. Among them, the random forest model performed better, with an AUC of 0.782, accuracy of 0.717, specificity of 0.733, sensitivity of 0.696, and an F1 score of 0.678. These findings demonstrate machine learning, and random forest model in particular, in the ability to process complex datasets and the potential of disease identification, showing great promise for practical application in clinical settings (Dutta et al., 2024 ; Wang et al., 2023 ). Additionally, to further investigate the relative importance of associated features for PMS among young adult women and their interactions, SHAP was used to interpret the output of the random forest model. The results revealed that neuroticism exhibited the highest predictive capacity for PMS among young women. Specifically, with the increase of neuroticism scores, the likelihood of young women with PMS was higher and showed a stable trend, reflecting the negative relationship between neuroticism and PMS, which is consistent with previous studies (Yilmaz, 2024 ). Neuroticism, as a stable disposition to negative affect (Ormel et al., 2013 ), has been found to be directly associated with premenstrual psychological and behavioral symptoms. For example, Hamidovic et al. found a significant relationship between neuroticism, premenstrual difficulty in concentrating and low interest (Hamidovic et al., 2022 ). Huang et al. found females with high-neuroticism scores may experience more negative emotions during the midlate luteal phase (Huang et al., 2015 ). Alternatively, one plausible explanation lies in the relationship between neuroticism and sex hormones. High-neuroticism individuals are characterized by emotional instability and heightened sensitivity, a trait that may amplify their responsiveness to hormonal fluctuations during the menstrual cycle, thereby increasing the susceptibility to PMS (Wu et al., 2014 ). These findings suggest that neuroticism can serve as an important identifier for PMS among young adult women. Early identification and intervention for high-neuroticism individuals can help effectively prevent the symptoms of PMS and alleviate the various adverse effects. The results also showed that higher mindfulness was associated with a lower likelihood of experiencing PMS. On the one hand, mindfulness enables individuals to deeply understand their thoughts and feelings, accept their emotional and physical experiences, thereby reducing their excessive focus and sensitivity towards symptoms (Asadi et al., 2022 ). On the other hand, it assists individuals in accurately identifying stressful situations, consciously regulating their responses to these experiences, and subsequently decreasing the activation of their somatic and psychological symptom response systems (Panahi & Faramarzi, 2016 ). Mindfulness-based therapy has been utilized as a non-pharmacological treatment for patients with PMS in previous studies, effectively alleviating their symptoms (Mazaheri Asadi et al., 2022 ). This findings support previous viewpoints and provide additional theoretical support for them. Additionally, this study reveled the notable association between childhood trauma and PMS, consistent with previous findings (Saglam et al., 2024 ). A common explanation for the underlying mechanism is the impact of early abuse on the HPA axis (Taylor-Cavelier et al., 2021 ). Specifically, the homeostatic balance of the HPA axis may be disrupted by excessive cortisol release induced by childhood trauma, thereby influencing the occurrence and progression of PMS (Suzuki et al., 2014 ). It is noteworthy that emotional abuse exerted a greater impact in this study compared to other forms of childhood maltreatment, which underscores the necessity of conducting additional investigations into the relationship between emotional abuse and PMS (Bertone-Johnson et al., 2014 ). Among the menstrual factors, the history of dysmenorrhea and use of analgesic showed significant associations with PMS. Specifically, women who experienced dysmenorrhea and use analgesic frequently were more likely to suffer from PMS. This relationship might be the resultant outcome of the combined actions of physiological and psychological factors (Babapour et al., 2023 ). Previous research has indicated that primary dysmenorrhea appeared to be the result of augmented prostanoid secretion (Jihong et al., 2011 ). Frequent occurrences of dysmenorrhea may potentially signify an underlying hormonal disequilibrium, and females experiencing dysmenorrhea are more predisposed to display negative emotion and maladaptive coping strategies (Li & Li, 2011 ), thereby contributing to the development of PMS. Analgesic, commonly non-steroidal anti-inflammatory drugs (NSAIDs), were considered the first-line treatment for primary dysmenorrhea, offering efficient pain relief to most women (Oladosu et al., 2018 ). In agreement with our findings, a study on Jordanian females also reported a significant correlation between analgesic use and PMS (Ababneh et al., 2023 ). Taken together, in view of the currently high incidence of dysmenorrhea (Bettendorf et al., 2008 ), further research is needed regarding how to implement effective self-management strategies and conduct rational analgesic use. Strength and limitations In this study, machine learning was innovatively introduced to identify PMS among young adult women, enhancing the accuracy and reliability of prediction, and five machine learning algorithms were used to ensure the robustness of the results. Additionally, SHAP was employed to explain the importance and interrelationships of various features on PMS, providing theoretical support for early identification and the establishment of personalized preventive measures. However, this study inevitably has certain constraints. Firstly, the cross-sectional design adopted in this study is unable to infer the causal logical relationships between variables. Secondly, the subjects of this study are only limited to young adult women in China. Studies on PMS among women of diverse ages, occupations, and cultural backgrounds could contribute to the expansion of our understanding of PMS and provide a generalized support for well being of female population. Thirdly, the data collected through self-reporting may lead to potential response biases. Objective measures could be considered in future studies, such as using wearable detection devices to record daily activities or sleep quality. Finally, PMS is a complex phenomenon affected by social, physiological, and psychological factors. Further studies should explore additional variables to gain a more comprehensive understanding of the underlying mechanism of PMS. Conclusion This study employed machine learning to identifying the high-risk gruop PMS among young adult women, showing great potential for the application of machine learning in disease identification. Additionally, the study explored the complex relationships between demographic, menstrual characteristics, and socio-psychological factors and PMS, revealing that neuroticism plays a great role in the development of PMS. Interventions such as mindfulness training, dysmenorrhea management, and addressing early trauma may hold significant potential in preventing and managing PMS. To sum up, these findings offer valuable evidence for early identification of PMS and serving as a reference in formulating targeted intervention programs among young adult women. Declarations Ethics Declarations Ethics approval This study was approved by the institutional review board of the School of Nursing and Rehabilitation, Shandong University (2020-R-202). Consent to participate All participants gave informed consent. Conflict of interest statement The authors have no conflicts of interest to disclose. Funding No funding was received to assist with the preparation of this manuscript. Author Contribution XHL: Investigation, Formal analysis, Methodology, Writing-original draft; XYZ: Methodology, Formal analysis, Software, Writing – review and editing; YZ: Investigation, Formal analysis; LNG: Investigation, Visualization; HQL: Investigation; CM: Validation, Supervision, Resources, Writing – review and editing; PL: Conceptualization, Project administration, Supervision, Resources, Writing – review and editing. Acknowledgments We acknowledge all participants for their voluntarily participation. Data Availability The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions. References A D-M, K, S., A, D., Sattar K (2014) Epidemiology of Premenstrual Syndrome (PMS)-A Systematic Review and Meta-Analysis Study. J Clin Diagn research: JCDR 8(2):106–109. https://doi.org/10.7860/jcdr/2014/8024.4021 Ababneh MA, Alkhalil M, Rababah A (2023) The prevalence, risk factors and lifestyle patterns of Jordanian females with premenstrual syndrome: a cross-sectional study. Future Sci Oa 9(9) Article Fso889. https://doi.org/10.2144/fsoa-2023-0056 Acikgoz A, Dayi A, Binbay T (2017) Prevalence of premenstrual syndrome and its relationship to depressive symptoms in first-year university students. Saudi Med J 38(11):1125–1131. https://doi.org/10.15537/smj.2017.11.20526 Alshdaifat E, Absy N, Sindiani A, AlOsta N, Hijazi H, Amarin Z, Alnazly E (2022) Premenstrual Syndrome and Its Association with Perceived Stress: The Experience of Medical Students in Jordan. Int J Womens Health 14:777–785. https://doi.org/10.2147/ijwh.S361964 Antuña-Camblor C, Gómez-Salas FJ, Burgos-Julián FA, González-Vázquez A, Juarros-Basterretxea J, Rodríguez-Díaz FJ (2024) Emotional Regulation as a Transdiagnostic Process of Emotional Disorders in Therapy: A Systematic Review and Meta-Analysis. Clin Psychol Psychother 31(3):e2997. https://doi.org/https://doi.org/10.1002/cpp.2997 Asadi DM, Tajrishi KZ, Gharaei B (2022) Mindfulness Training Intervention With the Persian Version of the Mindfulness Training Mobile App for Premenstrual Syndrome: A Randomized Controlled Trial. Front Psychiatry 13:922360. https://doi.org/10.3389/fpsyt.2022.922360 Azoulay M, Reuveni I, Dan R, Goelman G, Segman R, Kalla C, Bonne O, Canetti L (2020) Childhood Trauma and Premenstrual Symptoms: The Role of Emotion Regulation. Child Abuse Negl 108. https://doi.org/10.1016/j.chiabu.2020.104637 Babapour F, Elyasi F, Shahhosseini Z, Tabaghdehi MH (2023) The prevalence of moderate-severe premenstrual syndrome and premenstrual dysphoric disorder and the related factors in high school students: A cross-sectional study. Neuropsychopharmacol Rep 43(2):249–254. https://doi.org/10.1002/npr2.12338 Bancroft J (1993) The premenstrual syndrome–a reappraisal of the concept and the evidence. Psychol Med Suppl 24:1–47. https://doi.org/10.1017/s0264180100001272 Bertone-Johnson ER, Whitcomb BW, Missmer SA, Manson JE, Hankinson SE, Rich-Edwards JW (2014) Early Life Emotional, Physical, and Sexual Abuse and the Development of Premenstrual Syndrome: A Longitudinal Study. J Womens Health 23(9):729–739. https://doi.org/10.1089/jwh.2013.4674 Bettendorf B, Shay S, Tu F (2008) Dysmenorrhea: contemporary perspectives. Obstet Gynecol Surv 63(9):597–603. https://doi.org/10.1097/OGX.0b013e31817f15ff Bishop SR, Lau M, Shapiro S, Carlson L, Anderson ND, Carmody J, Segal ZV, Abbey S, Speca M, Velting D, Devins G (2004) Mindfulness: A Proposed Operational Definition. Clin Psychol Sci Pract 11(3):230–241. https://doi.org/https://doi.org/10.1093/clipsy.bph077 Caycho-Rodríguez T, Tomás JM, Ventura-León J, Esteban C, Guadalupe RFO, Reyes-Bossio LA, García M, Cadena CH, Cabrera-Orosco I (2021) Factorial validity and invariance analysis of the five items version of Mindful Awareness Attention Scale in older adults. Aging Ment Health 25(4):756–765. https://doi.org/10.1080/13607863.2020.1716685 Choi SH, Hamidovic A (2020) Association Between Smoking and Premenstrual Syndrome: A Meta-Analysis. Front Psychiatry 11., Article 575526. https://doi.org/10.3389/fpsyt.2020.575526 DeCou CR, Lynch SM, Weber S, Richner D, Mozafari A, Huggins H, Perschon B (2023) On the Association Between Trauma-Related Shame and Symptoms of Psychopathology: A Meta-Analysis. Trauma Violence Abuse 24(3):1193–1201 Article 15248380211053617. https://doi.org/10.1177/15248380211053617 del Mar Fernandez M, Saulyte J, Inskip HM, Takkouche B (2018) Premenstrual syndrome and alcohol consumption: a systematic review and meta-analysis. Bmj Open 8(3) Article e019490. https://doi.org/10.1136/bmjopen-2017-019490 Domingos P (2012) A few useful things to know about machine learning. Commun ACM 55(10):78–87. https://doi.org/10.1145/2347736.2347755 Dutta A, Sharma A (2021) Prevalence of premenstrual syndrome and premenstrual dysphoric disorder in India: A systematic review and meta-analysis. Health Promotion Perspect 11(2):161–170. https://doi.org/10.34172/hpp.2021.20 Dutta RR, Mukherjee I, Chakraborty C (2024) Obesity disease risk prediction using machine learning. Int J Data Sci Analytics. https://doi.org/10.1007/s41060-023-00491-9 Erbil N, Yucesoy H (2023) Premenstrual syndrome prevalence in Turkey: a systematic review and meta-analysis. Psychol Health Med 28(5):1347–1357. https://doi.org/10.1080/13548506.2021.2013509 Geta TG, Woldeamanuel GG, Dassa TT (2020) Prevalence and associated factors of premenstrual syndrome among women of the reproductive age group in Ethiopia: Systematic review and meta-analysis. PLoS ONE 15(11) Article e0241702. https://doi.org/10.1371/journal.pone.0241702 Gumussoy S, Donmez S, Keskin G (2021) Investigation of the Relationship between Premenstrual Syndrome, and Childhood Trauma and Mental State in Adolescents with Premenstrual Syndrome. J Pediatr Nursing-Nursing Care Child Families 61:E65–E71. https://doi.org/10.1016/j.pedn.2021.04.022 Hamidovic A, Dang N, Khalil D, Sun J, Girardi P (2022) Association between Neuroticism and Premenstrual Affective/Psychological Symptomatology. Psychiatry Int 3(1):52–64. https://doi.org/10.3390/psychiatryint3010005 Handhika T, Murni, Fahreza RM (2023) Boruta algorithm: An alternative feature selection method in credit scoring model. AIP Conference Proceedings , 2431 (1). https://doi.org/10.1063/5.0114178 Huang C-C, Chen Y, Cheung S, Greene L, Lu S (2019) Resilience, emotional problems, and behavioural problems of adolescents in China: Roles of mindfulness and life skills. Health Soc Care Commun 27(5):1158–1166. https://doi.org/10.1111/hsc.12753 Huang Y, Zhou R, Cui H, Wu M, Wang Q, Zhao Y, Liu Y (2015) Variations in resting frontal alpha asymmetry between high- and low-neuroticism females across the menstrual cycle. Psychophysiology 52(2):182–191. https://doi.org/10.1111/psyp.12301 Jihong Y, Ying C, Jiazhen HU (2011) Relationship between PGF2alpha and primary dysmenorrhea in female middle school students. China Public Health , 27 (8), 1042–1043. https://d.wanfangdata.com.cn/periodical/Ch9QZXJpb2RpY2FsQ0hJTmV3UzIwMjUwMTA0MTcwMjI2Eg96Z2dnd3MyMDExMDgwNDgaCHRzc2NiMzJl Juruena MF (2014) Early-life stress and HPA axis trigger recurrent adulthood depression. Epilepsy Behav 38:148–159. https://doi.org/10.1016/j.yebeh.2013.10.020 Kim Y-J, Park Y-J (2020) Menstrual Cycle Characteristics and Premenstrual Syndrome Prevalence Based on the Daily Record of Severity of Problems in Korean Adult Women. J Korean Acad Nurs 50(1):147–157. https://doi.org/10.4040/jkan.2020.50.1.147 Le J, Thomas N, Gurvich C (2020) Cognition, The Menstrual Cycle, and Premenstrual Disorders: A Review. Brain Sci 10(4). Article 198. https://doi.org/10.3390/brainsci10040198 Lee Y, Ragguett R-M, Mansur RB, Boutilier JJ, Rosenblat JD, Trevizol A, Brietzke E, Lin K, Pan Z, Subramaniapillai M, Chan TCY, Fus D, Park C, Musial N, Zuckerman H, Chen VC-H, Ho R, Rong C, McIntyre RS (2018) Applications of machine learning algorithms to predict therapeutic outcomes in depression: A meta-analysis and systematic review. J Affect Disord 241:519–532. https://doi.org/10.1016/j.jad.2018.08.073 Li S, Li J (2011) Analysis of the emotion and anxiety status of female military students with dysmenorrhea. Chin J Pain Med 17(2):104–106. https://doi.org/10.3969/j.issn.1006-9852.2011.02.007 Liguori F, Saraiello E, Calella P (2023) Premenstrual Syndrome and Premenstrual Dysphoric Disorder's Impact on Quality of Life, and the Role of Physical Activity. Medicina-Lithuania , 59 (11), Article 2044. https://doi.org/10.3390/medicina59112044 Liu X, Liu Z-Z, Yang Y, Jia C-X (2023) Prevalence and Associated Factors of Premenstrual Syndrome in Chinese Adolescent Girls. Child Psychiatry Hum Dev. https://doi.org/10.1007/s10578-023-01624-8 Lundberg SM, Lee S-I (2017) A Unified Approach to Interpreting Model Predictions. Neural Information Processing Systems Ma S, Song SJ (2023) Oral contraceptives containing drospirenone for premenstrual syndrome. Cochrane Database Syst Rev 6(6):Cd006586. https://doi.org/10.1002/14651858.CD006586.pub5 Maity S, Wray J, Coffin T, Nath R, Nauhria S, Sah R, Waechter R, Ramdass P, Nauhria S (2022) Academic and Social Impact of Menstrual Disturbances in Female Medical Students: A Systematic Review and Meta-Analysis. Front Med (Lausanne) 9:821908. https://doi.org/10.3389/fmed.2022.821908 Mann P, Pradeep TS (2023) Premenstrual Syndrome, Anxiety, and Depression Among Menstruating Rural Adolescent Girls: A Community-Based Cross-Sectional Study. Cureus J Med Sci 15(12) Article e50385. https://doi.org/10.7759/cureus.50385 Martin SA, Townend FJ, Barkhof F, Cole JH (2023) Interpretable machine learning for dementia: A systematic review. Alzheimers Dement 19(5):2135–2149. https://doi.org/10.1002/alz.12948 Mazaheri Asadi D, Tajrishi Z, K., Gharaei B (2022) Mindfulness Training Intervention With the Persian Version of the Mindfulness Training Mobile App for Premenstrual Syndrome: A Randomized Controlled Trial. Front Psychiatry 13:922360. https://doi.org/10.3389/fpsyt.2022.922360 Mostafa HE-S, Alkurdi AA, Sanousi M, Aljuhani F, Abdullah M, Aljohani BS, Aljohani WK (2023) Correlation between premenstrual syndrome and body mass index among reproductive females. Med Sci 27(133). https://doi.org/10.54905/disssi/v27i133/e123ms2926 Nayman S, Konstantinow DT, Schricker IF, Reinhard I, Kuehner C (2023) Associations of premenstrual symptoms with daily rumination and perceived stress and the moderating effects of mindfulness facets on symptom cyclicity in premenstrual syndrome. Archives Womens Mental Health 26(2):167–176. https://doi.org/10.1007/s00737-023-01304-5 Naz MSG, Farahmand M, Dashti S, Tehrani FR (2022) Factors Affecting Menstrual Cycle Developmental Trajectory in Adolescents: A Narrative Review. Int J Endocrinol Metabolism 20(1) Article e120438. https://doi.org/10.5812/ijem.120438 O'Brien PM, Bäckström T, Brown C, Dennerstein L, Endicott J, Epperson CN, Eriksson E, Freeman E, Halbreich U, Ismail KM, Panay N, Pearlstein T, Rapkin A, Reid R, Schmidt P, Steiner M, Studd J, Yonkers K (2011) Towards a consensus on diagnostic criteria, measurement and trial design of the premenstrual disorders: the ISPMD Montreal consensus. Arch Womens Ment Health 14(1):13–21. https://doi.org/10.1007/s00737-010-0201-3 Oladosu FA, Tu FF, Hellman KM (2018) Nonsteroidal antiinflammatory drug resistance in dysmenorrhea: epidemiology, causes, and treatment. Am J Obstet Gynecol 218(4):390–400. https://doi.org/10.1016/j.ajog.2017.08.108 Ormel J, Bastiaansen A, Riese H, Bos EH, Servaas M, Ellenbogen M, Rosmalen JG, Aleman A (2013) The biological and psychological basis of neuroticism: current status and future directions. Neurosci Biobehav Rev 37(1):59–72. https://doi.org/10.1016/j.neubiorev.2012.09.004 Oyola MG, Handa RJ (2017) Hypothalamic-pituitary-adrenal and hypothalamic-pituitary-gonadal axes: sex differences in regulation of stress responsivity. Stress 20(5):476–494. https://doi.org/10.1080/10253890.2017.1369523 Panahi F, Faramarzi M (2016) The Effects of Mindfulness-Based Cognitive Therapy on Depression and Anxiety in Women with Premenstrual Syndrome. Depress Res Treat , 2016 , 9816481. https://doi.org/10.1155/2016/9816481 Pigoni A, Delvecchio G, Turtulici N, Madonna D, Pietrini P, Cecchetti L, Brambilla P (2024) Machine learning and the prediction of suicide in psychiatric populations: a systematic review. Translational Psychiatry 14(1). Article 140. https://doi.org/10.1038/s41398-024-02852-9 Qiao M, Zhang H, Liu H, Luo S, Wang T, Zhang J, Ji L (2012) Prevalence of premenstrual syndrome and premenstrual dysphoric disorder in a population-based sample in China. Eur J Obstet Gynecol Reprod Biol 162(1):83–86. https://doi.org/10.1016/j.ejogrb.2012.01.017 Robinson RL, Swindle RW (2000) Premenstrual symptom severity: impact on social functioning and treatment-seeking behaviors. J Womens Health Gend Based Med 9(7):757–768. https://doi.org/10.1089/15246090050147736 Saglam HY, Gursoy E, Karakus A (2024) Impact of childhood trauma history on premenstrual syndrome in women of reproductive age: A cross-sectional study. J Eval Clin Pract. https://doi.org/10.1111/jep.14172 Singh C, Jain J, Singh K, Jain MP, Chaudhary A (2016) A Study of Premenstrual Dysphoric Disorder Prevalence, Phenomenology and Personality Factors in College Going Students. Indian J Health Wellbeing 7:962–965 Smith DR (2008) Menstrual disorders and their adverse symptoms at work: An emerging occupational health issue in the nursing profession. Nurs Health Sci 10(3):222–228. https://doi.org/10.1111/j.1442-2018.2008.00391.x Soto CJ, John OP (2009) Ten facet scales for the Big Five Inventory: Convergence with NEO PI-R facets, self-peer agreement, and discriminant validity. J Res Pers 43(1):84–90. https://doi.org/10.1016/j.jrp.2008.10.002 Spinhoven P, Penninx BW, Hickendorff M, van Hemert AM, Bernstein DP, Elzinga BM (2014) Childhood Trauma Questionnaire: factor structure, measurement invariance, and validity across emotional disorders. Psychol Assess 26(3):717–729. https://doi.org/10.1037/pas0000002 Sun BZ, Kangarloo T, Adams JM, Sluss PM, Welt CK, Chandler DW, Zava DT, McGrath JA, Umbach DM, Hall JE, Shaw ND (2018) Healthy Post-Menarchal Adolescent Girls Demonstrate Multi-Level Reproductive Axis Immaturity. J Clin Endocrinol Metabolism 104(2):613–623. https://doi.org/10.1210/jc.2018-00595 Suzuki A, Poon L, Papadopoulos AS, Kumari V, Cleare AJ (2014) Long term effects of childhood trauma on cortisol stress reactivity in adulthood and relationship to the occurrence of depression. Psychoneuroendocrinology 50:289–299. https://doi.org/10.1016/j.psyneuen.2014.09.007 Takeda T, Koga S, Yaegashi N (2010) Prevalence of premenstrual syndrome and premenstrual dysphoric disorder in Japanese high school students. Archives Womens Mental Health 13(6):535–537. https://doi.org/10.1007/s00737-010-0181-3 Taylor-Cavelier SJ, Micol VJ, Roberts AG, Geiss EG, Lopez-Duran N (2021) DHEA Moderates the Impact of Childhood Trauma on the HPA Axis in Adolescence. Neuropsychobiology 80(4):299–312. https://doi.org/10.1159/000511629 Wang K, Zhao J, Hu J, Liang D, Luo Y (2023) Predicting unmet activities of daily living needs among the oldest old with disabilities in China: a machine learning approach. Front Public Health 11. https://doi.org/10.3389/fpubh.2023.1257818 Wang L, lIU H, Li Z, Du W (2007) Reliability and Validity of Emotion Regulation Questionnaire Chinese Revised Version. Chine J Health Psychol 15(6):503–505. https://doi.org/10.3969/j.issn.1005-1252.2007.06.034 Wittchen HU, Becker E, Lieb R, Krause P (2002) Prevalence, incidence and stability of premenstrual dysphoric disorder in the community. Psychol Med 32(1):119–132. https://doi.org/10.1017/s0033291701004925 Wu M, Zhou R, Huang Y, Wang Q, Zhao Y, Liu Y (2014) Effects of Menstrual Cycle and Neuroticism on Emotional Responses of Healthy Women. Acta Physiol Sinica 158–68. https://doi.org/10.3724/sp.J.1041.2014.00058 Yang H, Ma Y, Wang Y, Fu C, Liu W, Li W (2024) Association between physical activity and risk of premenstrual syndrome among female college students: a systematic review and meta-analysis. Bmc Womens Health 24(1). Article 307. https://doi.org/10.1186/s12905-024-03147-3 Yilmaz FA (2024) The relationship between premenstrual syndrome and personality traits in university students. Rev Assoc Med Bras 70(7) Article e20231679. https://doi.org/10.1590/1806-9282.20231679 Zhao X, Zhang Y, Li L, Zhou Y, Li H, Yang S (2005) Reliability and validity of the Chinese version of childhood trauma questionnaire. Chin J Clin Rehabilitation 9(20):105–107. https://doi.org/10.3321/j.issn:1673-8225.2005.20.052 Additional Declarations No competing interests reported. Supplementary Files SupportingInformation.docx Cite Share Download PDF Status: Posted Version 1 posted 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-7522395","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":515806654,"identity":"f4a23049-44a5-4a0c-92a2-425a1e08288e","order_by":0,"name":"Xiaohe Lin","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Xiaohe","middleName":"","lastName":"Lin","suffix":""},{"id":515806655,"identity":"a7da420b-186b-4ff4-af97-78c77bd00314","order_by":1,"name":"Xiangyu Zhao","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Xiangyu","middleName":"","lastName":"Zhao","suffix":""},{"id":515806656,"identity":"5348078a-09d8-4e02-89f9-068e29ed53ac","order_by":2,"name":"Yue Zeng","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Yue","middleName":"","lastName":"Zeng","suffix":""},{"id":515806657,"identity":"0fa473f3-4efa-4943-8fc0-01872a0ed9b0","order_by":3,"name":"Lina Guo","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Lina","middleName":"","lastName":"Guo","suffix":""},{"id":515806658,"identity":"c5cfe9d1-5c20-4a35-9d5b-4c3d50d9d37c","order_by":4,"name":"Hongqvn Liu","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Hongqvn","middleName":"","lastName":"Liu","suffix":""},{"id":515806659,"identity":"67d46dc1-c0e6-4cd1-813a-21e7e03ea063","order_by":5,"name":"Cui Mao","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Cui","middleName":"","lastName":"Mao","suffix":""},{"id":515806660,"identity":"d8ac6ec1-e804-42a2-9617-2205c3398147","order_by":6,"name":"Ping Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIie3QsQrCMBCA4ZNCu0Rdz0Gf4SCQVnyZdGkXEUEQB9FAwbWvogjOQsCp4tqxo2MfQMSI4lgzCuaHGw7ugxAAl+sX88xUhIMuAL1XGyIp4j1lTZ5JWMTboy0Jg7a+yim29hd9QFiMYhWcj41kmHWSSBJ6okzmCEUaKzaRjYQ0E2SIL0omsLXRsUJGVoTxvDDkbkd4ZQgSjA1RFmSYMWE+GQnLZBbJU8o3bNxMwm7B6/q2Wue53pX1ctTPg+LLwwB8/GzSjN94/yJe/e3I5XK5/rwH96k95N+CZ3gAAAAASUVORK5CYII=","orcid":"","institution":"Shandong University","correspondingAuthor":true,"prefix":"","firstName":"Ping","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-09-03 03:53:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7522395/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7522395/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91837643,"identity":"a16f9c68-f4d2-4b32-9e22-16c282051e45","added_by":"auto","created_at":"2025-09-22 09:40:59","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":561111,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/afe9acf653509bde92c4685f.docx"},{"id":91835563,"identity":"99cab09b-d1b8-4248-b8f2-c45d78f7841d","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8320,"visible":true,"origin":"","legend":"","description":"","filename":"1d8d93da84b542b88448f3369a78c2fc.json","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/2989cd6b76b4a8d35f566600.json"},{"id":91837644,"identity":"a422f409-7bb9-4dd5-be98-09cb2388b6cf","added_by":"auto","created_at":"2025-09-22 09:40:59","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52595,"visible":true,"origin":"","legend":"","description":"","filename":"SupportingInformation.docx","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/78426bb851e0898789627bac.docx"},{"id":91838717,"identity":"7e3f8d91-f6de-4c9d-8dc4-c7a03ddceae0","added_by":"auto","created_at":"2025-09-22 09:48:59","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":177882,"visible":true,"origin":"","legend":"","description":"","filename":"1d8d93da84b542b88448f3369a78c2fc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/77bcfb824481e34590cb0dd4.xml"},{"id":91841774,"identity":"9559a814-e29f-4a11-a357-05954cf68734","added_by":"auto","created_at":"2025-09-22 09:56:59","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27155,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/212672000652455060788cbd.png"},{"id":91835570,"identity":"8d2c32ac-da2c-4fc0-b397-191f20e36388","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24288,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/2895c6e6d1fb6d60a77ae916.png"},{"id":91835578,"identity":"c2cd60a6-359a-47c9-bec7-2da3f10132ef","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":46892,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/67f6a0b6a0013ce1297d0063.png"},{"id":91835579,"identity":"f0c9bb88-2bd6-4df1-b716-196206330c4e","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"xml","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":178178,"visible":true,"origin":"","legend":"","description":"","filename":"1d8d93da84b542b88448f3369a78c2fc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/9513b7ff0aeac188e7a2b3bc.xml"},{"id":91835577,"identity":"601f25ea-8491-45cc-9fba-d305640c4e6c","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"html","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":184177,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/58963227b4baa25e5da31599.html"},{"id":91837647,"identity":"c3eaa81b-db7b-4d37-9518-fb46f627899f","added_by":"auto","created_at":"2025-09-22 09:40:59","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":116119,"visible":true,"origin":"","legend":"\u003cp\u003eROC curves of five machine learning models in the training (a) and validation set (b).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAbbreviations. \u003c/strong\u003e\u003cem\u003eRF\u003c/em\u003e random forest, \u003cem\u003eXGBoost\u003c/em\u003e\u003cstrong\u003e \u003c/strong\u003eextreme gradient boosting,\u003cem\u003e SVM\u003c/em\u003e support vector machine, \u003cem\u003eMLP\u003c/em\u003e multilayer perceptron, \u003cem\u003eLogistic\u003c/em\u003e logistic regression.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/db3b6bd3fa9c65ec9eec0e25.png"},{"id":91835565,"identity":"88e001e6-220e-4611-90ab-274b7db640f3","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":65090,"visible":true,"origin":"","legend":"\u003cp\u003eAbsolute value sorting of SHAP mean of each feature.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAbbreviations.\u003c/strong\u003e\u003cem\u003eDysmenorrhea\u003c/em\u003ehistory of dysmenorrhea, \u003cem\u003eEA\u003c/em\u003e emotional abuse, \u003cem\u003eAnalgesic\u003c/em\u003e use of analgesic, \u003cem\u003eES\u003c/em\u003e expressive suppression, \u003cem\u003eEN\u003c/em\u003e emotional neglect, \u003cem\u003eCR\u003c/em\u003ecognitive reappraisal, \u003cem\u003ePN\u003c/em\u003e physical neglect, \u003cem\u003eVolume\u003c/em\u003e menstrual volume, \u003cem\u003ePA \u003c/em\u003ephysical abuse.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/ab036211556efca8adec3ea4.png"},{"id":91835568,"identity":"9ec6442a-2138-419f-aa2b-510b5755ace4","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":216407,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP dependence plots of categorical (a) and continuous variables (b) to PMS.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAbbreviations.\u003c/strong\u003e\u003cem\u003eDysmenorrhea\u003c/em\u003ehistory of dysmenorrhea, \u003cem\u003eAnalgesic\u003c/em\u003e use of analgesic, \u003cem\u003eVolume\u003c/em\u003emenstrual volume, \u003cem\u003eEA\u003c/em\u003e emotional abuse, \u003cem\u003eES\u003c/em\u003e expressive suppression, \u003cem\u003eEN\u003c/em\u003eemotional neglect, \u003cem\u003eCR\u003c/em\u003e cognitive reappraisal, \u003cem\u003ePN\u003c/em\u003e physical neglect, \u003cem\u003ePA \u003c/em\u003ephysical abuse.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/103fd48a8982bba67e193b9b.png"},{"id":96912974,"identity":"e19cf090-f6d8-4a48-a122-ea6473925dfa","added_by":"auto","created_at":"2025-11-27 13:46:36","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1391527,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/856d1df7-cc5e-46e7-8ae7-86d4ab039801.pdf"},{"id":91835562,"identity":"ff030eb4-c6b9-40f3-9114-55da36b4f18e","added_by":"auto","created_at":"2025-09-22 09:32:59","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":52595,"visible":true,"origin":"","legend":"","description":"","filename":"SupportingInformation.docx","url":"https://assets-eu.researchsquare.com/files/rs-7522395/v1/173e0eead0af3d08ac7a1ec4.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Interpretable Machine Learning Models for Identifying Premenstrual Syndrome and Related Factors in Young Adult Women","fulltext":[{"header":"Highlights","content":"\u003cp\u003e\u0026bull; The result revealed machine learning techniques, particularly random forest, in the ability to process complex datasets and the potential of identifying PMS.\u003c/p\u003e\u003cp\u003e\u0026bull; Based on the random forest model, neuroticism exhibited the highest predictive capacity for PMS among young women.\u003c/p\u003e\u003cp\u003e\u0026bull; Interventions such as mindfulness training, dysmenorrhea management, and addressing early trauma may hold significant potential in preventing and managing PMS.\u003c/p\u003e"},{"header":"Introduction","content":"\u003cp\u003eMany women may periodically undergo a series of physical, psychological or behavioral changes during the luteal phase of the menstrual cycle, such as anxiety, irritability, hypersomnia, difficulty concentration and so on, which is known as premenstrual syndrome (PMS) (Liguori et al., \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Ma \u0026amp; Song, \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). The American College of Obstetricians and Gynecologists (ACOG) defined PMS as a clinical condition (Geta et al., \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), with severity affecting normal daily functioning, work, school performance, interpersonal relationships, or cause significant distress (O'Brien et al., \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2011\u003c/span\u003e). The literature reported that approximately 80% of women experienced at least one emotional or physical symptom in the days leading up to their menstrual period (Wittchen et al., \u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e2002\u003c/span\u003e). As a public health problem with widespread impact, PMS necessitates further attention.\u003c/p\u003e\u003cp\u003eThe prevalence of PMS varies in different countries due to differences in cultural backgrounds and social environments. A meta-analysis reported that the pooled global prevalence of PMS was 47.8%, with lowest being 12% in France (A et al., 2014). The prevalence of PMS in women of childbearing age was reported as 21.1% in China (Qiao et al., \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2012\u003c/span\u003e), 43% in India (Dutta \u0026amp; Sharma, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2021\u003c/span\u003e), 52.2% in Turkey (Erbil \u0026amp; Yucesoy, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Although the peak presentation of PMS occurs in 20s (Acikgoz et al., \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2017\u003c/span\u003e), many women state they experienced premenstrual symptoms as early as adolescence (Robinson \u0026amp; Swindle, \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e2000\u003c/span\u003e). Young adult women, in the transitional phase from adolescence to adulthood, are at high risk of suffering from premenstrual disorders. Considering the negative effects of PMS on mental health and professional productivity (Liguori et al., \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Smith, \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e2008\u003c/span\u003e), it is crucial to identify the key factors associated with PMS at an early stage.\u003c/p\u003e\u003cp\u003eAlthough the etiology of PMS has not been fully elucidated, based on previous research, it is the result of the combined effects of multiple factors, including physiological, psychological, lifestyle, and social aspects. The cyclic hormonal fluctuations during the menstrual cycle are widely recognized as an important factor influencing PMS (Le et al., \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). However, increasing researchers have also noticed the significant associations between demographic and menstrual characteristics with PMS, as these factors are more intuitive and easier to self-observation by individuals. For instance, a meta-analysis reported exercise was negatively associated with risk of PMS (Yang et al., \u003cspan citationid=\"CR65\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Obesity was a modifiable risk factor for PMS, with significant link between increasing body mass index (BMI) and increasing the severity of the emotional and psycho-behavioral symptoms (Mostafa et al., \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Smoking and alcohol consumption have also been found to be associated with an increased risk for PMS (Choi \u0026amp; Hamidovic, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; del Mar Fernandez et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). Among menstrual factors, the cycle regularity, flow during the menstrual cycle, duration of the cycle, the severity of dysmenorrhea, and analgesic use all possessed closely correlations with PMS (Ababneh et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Mann \u0026amp; Pradeep, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Moreover, the effects of psychological factors on PMS have received increasing interest, such as personality, emotional and cognitive factors. The literature reported that certain personality traits, like neuroticism, were risk factors for PMS, with more severe PMS symptoms observed in individuals with stronger neuroticism tendency (Singh et al., \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). Emotional regulation was commonly conceptualized as the process by which individuals influence the generation, experience, and expression of their own emotions, primarily encompassing two core strategies: cognitive reappraisal and expressive suppression (Antu\u0026ntilde;a-Camblor et al., \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Maladaptive emotional regulation might appeared to have a role in the underlying of premenstrual disorder (Azoulay et al., \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). Mindfulness, defined as an ability to allow people to achieve an open and receptive state of awareness, has been gaining increasing attention (Bishop et al., \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2004\u003c/span\u003e). Previous studies have reported the powerful impact of mindfulness on emotional and behavioral outcomes, including premenstrual symptoms and impairments during the luteal phase (Huang et al., \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Nayman et al., \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Mindfulness-based cognitive therapy has also been applied to women with PMS symptoms (Mazaheri Asadi et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2022\u003c/span\u003e), providing a foundation for further exploring the complex relationship between mindfulness and PMS in this study. It is well known that early life trauma was an important etiology of the development of symptoms of psychopathology (DeCou et al., \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Several studies have illustrated that women who have experienced childhood trauma had an increased risk of developing PMS and were likely to endure more diverse symptoms with a greater degree of severity (Azoulay et al., \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Gumussoy et al., \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eTo date, numerous studies have investigated the factors associated with PMS predominantly utilizing traditional regression analysis (Ababneh et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Babapour et al., \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Liu et al., \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Although this method has provided valuable insights into understanding PMS, it comes with stringent data requirements and limited model complexity, making it challenging to assess the relative importance of various factors. Machine learning, a pivotal technology within the realm of artificial intelligence, is witnessing a growing prominence of its significance. Machine learning is defined as a technology that automatically learns from data and identifies patterns to develop training models and enable accurate predictions and classifications on new data (Domingos, \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2012\u003c/span\u003e). Unlike traditional regression analysis, machine learning excels at handling high-dimensional data and constructing complex models by leveraging the nonlinear relationships among data, thereby achieving greater generalization ability (Lee et al., \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). In the last few years, machine learning has been widely applied in various fields of medicine, such as neurology and psychiatry, demonstrating significant potential in disease prediction (Martin et al., \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Pigoni et al., \u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e2024\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eTaken together, this study conducted a secondary analysis of data from young adult women, including demographic, menstrual characteristics, and socio-psychological factors, and aimed to construct a machine learning model for identifying PMS and explore the complex relationships between these factors with PMS. Noteworthy, to enhance the reliability and accuracy of the model, five machine learning algorithms were conducted. SHapley Additiveex Planations (SHAP) was used to interpret the output of the best-performed model. The findings of this study may provide valuable insights into understanding PMS and associated factors among young adult women and have the potential to sever as a reference in developing targeted interventions for PMS.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eParticipants\u003c/h2\u003e\u003cp\u003eA second analysis was performed using data from young adult women across nine universities located in China. The survey was conducted by online questionnaire and recruited female students in their first to forth year. Those with a history of pregnancy, miscarriage, taking medicine (like oral contraceptives, psychotropic or other hormonal drugs) in the past three months, and mental disorders, gynecological and endocrine disorders were excluded. A total of 3848 participants completed the questionnaire. After removing incomplete questionnaires and those with less than 5 minutes of response time or irregular responses, 3447 young women were included in this analysis. Informed consent was obtained from all participants and the study was approved by the Research Ethics Committee of the affiliated institution.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eMeasures\u003c/h3\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003eDemographic and Menstrual Characteristics\u003c/h2\u003e\u003cp\u003eGeneral demographic information included age, BMI, family economy, diet, smoking, drinking alcohol and exercise. Menstrual characteristics included age of menarche, menstrual regularity, days of menstruation, menstrual volume, history of dysmenorrhea and use of analgesic.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003ePremenstrual Syndrome\u003c/h3\u003e\n\u003cp\u003ePremenstrual Syndrome Scale (PSS) was used to assess the prevalence of premenstrual syndrome among nursing college students in this study (Bancroft, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e1993\u003c/span\u003e). This scale evaluated physical and emotional abnormalities in the 14 days before menstruation, consisting of 12 symptoms (i.e., irritability, depressed mood, anxiety, bloating and diarrhea, difficulty concentration, hypersomnia, tension, fidget, migraine, insomnia, swelling of hands or feet, nervousness). This scale was a 4-point scale, with each item scoring from 0 to 3 (0\u0026thinsp;=\u0026thinsp;no symptoms, 1\u0026thinsp;=\u0026thinsp;mild symptoms, 2\u0026thinsp;=\u0026thinsp;symptoms that affect life, study and work, but can tolerate, 3\u0026thinsp;=\u0026thinsp;symptoms that seriously affect life, study and work, and need treatment). The total score of the scale was the sum of all items, ranging from 0 to 36. In this study, participants with total score over 6 points were divided into PMS group, and the rest were non-PMS group. The Cronbach\u0026rsquo;s α of the total scale in this study was 0.902.\u003c/p\u003e\n\u003ch3\u003ePersonality Trait-Neuroticism\u003c/h3\u003e\n\u003cp\u003eNeuroticism dimension of the 44-Item Big Five Inventory (BFI) was used to evaluate the level of neurotic personality (Soto \u0026amp; John, \u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e2009\u003c/span\u003e). This dimension consisted of 8 items and each item was rated on a 5-point Likert scale from 1 (strongly disagree) to 5 (strongly agree). The higher score indicated greater neuroticism personality. The Cronbach\u0026rsquo;s α coefficient of this sub-dimension in current study was 0.709.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eEmotion Regulation Strategy\u003c/h2\u003e\u003cp\u003eThe use of emotion regulation strategies was measured using Emotion Regulation questionnaire (ERQ) revised by Wang et al. (Wang et al., \u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). This questionnaire consisted of 10 items including 2 dimensions of cognitive reappraisal (items 1, 3, 5, 7, 8, and 10) and expressive suppression (items 2, 4, 6, and 9). Each item was rated on a Likert 7-point scoring (1\u0026thinsp;=\u0026thinsp;strongly disagree and 7\u0026thinsp;=\u0026thinsp;strongly agree), with higher score of each dimension indicating more frequent use of this emotion regulation strategy. In the present study, the Cronbach\u0026rsquo;s α coefficients for two dimensions were 0.925 and 0.813 respectively.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eMindfulness\u003c/h3\u003e\n\u003cp\u003eMindfulness was assessed by the five items version of Mindful Awareness Attention Scale (MASS-5) (Caycho-Rodr\u0026iacute;guez et al., \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Each item was rated on a 6-point Likert scale from 1 (never) to 6 (always), with higher score indicating higher level of mindfulness. This scale has shown good reliability and validity in Chinese populations, and the Cronbach\u0026rsquo;s α in this study was 0.858.\u003c/p\u003e\n\u003ch3\u003eChildhood Trauma\u003c/h3\u003e\n\u003cp\u003eChildhood Trauma Questionnaire-Short Form (CTQ-SF) was used to measure traumatic experiences before the age of 16(Spinhoven et al., \u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e2014\u003c/span\u003e). In this study, the Chinese version translated by Zhao et al. was used (Zhao et al., \u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e2005\u003c/span\u003e), which was a 28-item questionnaire, including physical abuse, emotional abuse, sexual abuse, physical neglect, and emotional neglect. Each item was rated on a 5-point scale from 1 (never) to 5 (always). The Cronbach\u0026rsquo;s α coefficients were between 0.663 and 0.931 in the study.\u003c/p\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eStatistic analysis\u003c/h2\u003e\u003cp\u003eAll analyses were used SPSS (version 26.0) and R (version 4.4.1) and a two-sided test was conducted with a significance level of \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\u003cp\u003eAll variables were presented by descriptive statistics, with categorical variables by frequency (N) and percentage (%) and continuous variables by mean (M) and standard deviation (SD). Mann-whitney U tests and Chi-square tests were used to compare the differences of PMS group and non-PMS group in predictive variables. The dataset was randomized into a training set and a validation set in 75% and 25% proportions. A comparative analysis was conducted to evaluate the randomness and validity of the partition.\u003c/p\u003e\u003cp\u003eBefore the machine learning models construction, the correlation coefficients of all variables were calculated to exclude the predictive variables that highly correlated with PMS (correlation coefficient more than 0.8) and the near-zero-variance variables were also be excluded. In feature selection stage, Boruta algorithm was used to determine the significant predictive variables in a classification model. The algorithm is an extension of the idea introduced by to determine relevance by comparing the relevance of the real features to that of the random probes (Handhika et al., 2023). R Software was employed to perform five machine learning algorithms, namely logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multilayer perceptron (MLP), to construct models for predicting the premenstrual syndrome in young adult women. Each model underwent five repetitions of 5-fold cross-validation, followed by parameter tuning, in order to optimize the model parameters and enhance its generalization ability. Moreover, to compare the predictive performance of models, five metrics were evaluated, such as accuracy, specificity, sensitivity, F1 score, and the area under the receiver operating characteristic curve (AUC). Finally, SHapley Additiveex Planations (SHAP) was used to elucidate the output of the best-performing model. SHAP assigns each feature a SHAP value based on its contribution to the prediction. If the SHAP value was positive, the model tended to predict that the participant was divided into PMS group; conversely, if the value was negative, the model tended to predict that the participant was divided into non-PMS group. These values can be readily comprehended and visualized, which facilitates both global and local explanations of the model (Lundberg \u0026amp; Lee, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2017\u003c/span\u003e).\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003eSample characteristics\u003c/h2\u003e\u003cp\u003eA total of 3447 young adult women were included in data analysis. The average age of participants was 19.48 years (SD\u0026thinsp;=\u0026thinsp;1.15). Most of the women experienced dysmenorrhea (86.8%), with 32.6% occurring frequently. However, only 24.5% of women had ever used analgesic. The average PMS score for all participants was 6.65 (SD\u0026thinsp;=\u0026thinsp;1.15). According to the PSS criteria, there were 1474 women in PMS group and 1973 women in non-PMS group. More basic information are presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDescriptive and comparative analyses among nursing students (\u003cem\u003eN\u003c/em\u003e\u0026thinsp;=\u0026thinsp;3447)\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVariable\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTotal Sample\u003c/p\u003e\u003cp\u003e(\u003cem\u003eN\u003c/em\u003e\u0026thinsp;=\u0026thinsp;3447)\u003c/p\u003e\u003cp\u003eM\u0026thinsp;\u0026plusmn;\u0026thinsp;SD/n(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePMS Group\u003c/p\u003e\u003cp\u003e(N\u0026thinsp;=\u0026thinsp;1474)\u003c/p\u003e\u003cp\u003eM\u0026thinsp;\u0026plusmn;\u0026thinsp;SD/n(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNon-PMS Group\u003c/p\u003e\u003cp\u003e(N\u0026thinsp;=\u0026thinsp;1973)\u003c/p\u003e\u003cp\u003eM\u0026thinsp;\u0026plusmn;\u0026thinsp;SD/n(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u003cem\u003eχ\u003c/em\u003e\u003csup\u003e\u003cem\u003e2\u003c/em\u003e\u003c/sup\u003e/\u003cem\u003ez\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDemographic\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge (years)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e19.48\u0026thinsp;\u0026plusmn;\u0026thinsp;1.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19.42\u0026thinsp;\u0026plusmn;\u0026thinsp;1.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e19.56\u0026thinsp;\u0026plusmn;\u0026thinsp;1.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.371**\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBMI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e20.47\u0026thinsp;\u0026plusmn;\u0026thinsp;2.68\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e20.53\u0026thinsp;\u0026plusmn;\u0026thinsp;2.70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e20.39\u0026thinsp;\u0026plusmn;\u0026thinsp;2.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.412\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFamily economy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.997\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInsufficient\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e515(14.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e238 (16.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e277 (14.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSufficient for essentials\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2318(67.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e966 (65.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1352 (68.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMore than sufficient\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e614(17.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e270 (18.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e344 (17.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDiet\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e36.415***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIrregular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e324(9.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e173 (11.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e151 (7.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBasic regular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2639(76.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1144 (77.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1495 (75.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e484(14.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e157 (10.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e327 (16.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExercise\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2.331\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e361(10.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e163 (11.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e198 (10.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOccasionally\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2923(84.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1249 (84.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1674 (84.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrequently\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e163(4.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e62 (4.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e101 (5.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmoking\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e6.870**\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3396(98.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1443 (97.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1953 (99.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e51(1.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31 (2.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e20 (1.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAlcohol consumption\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e11.655**\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3001(87.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1250 (84.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1751 (88.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e446(12.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e224 (15.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e222 (11.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMenstrual Characteristics\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge of menarche (years)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e5.739\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026lt;13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e980(28.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e450 (30.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e530 (26.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e13\u0026thinsp;~\u0026thinsp;16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2429(70.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1007 (68.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1422 (72.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026gt;16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e38(1.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e17 (1.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e21 (1.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMenstrual regularity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e16.870***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIrregular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e739(21.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e350 (23.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e389 (19.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBasic regular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2290(66.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e978 (66.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1312 (66.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e418(12.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e146 (9.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e272 (13.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDays of menstruation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e4.237\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026le;\u0026thinsp;3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e295(8.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e129 (8.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e166 (8.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e4\u0026thinsp;~\u0026thinsp;7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3002(87.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1269 (86.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1733 (87.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026ge;\u0026thinsp;8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e150(4.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e76 (5.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e74 (3.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMenstrual volume\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e17.689***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmall\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e326(9.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e141 (9.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e185 (9.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMedium\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2853(82.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1186 (80.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1667 (84.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLarge\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e268(7.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e147 (10.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e121 (6.1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHistory of dysmenorrhea\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e207.002***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e455(13.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e102 (6.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e353 (17.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOccasionally\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1868(54.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e714 (48.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1154 (58.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrequently\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1124(32.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e658 (44.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e466 (23.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUse of analgesic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e109.487***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNever\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2600(75.4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e984 (66.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1616 (81.9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOccasionally\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e611(17.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e339 (23.0)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e272 (13.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrequently\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e236(6.8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e151 (10.2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e85 (4.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSocio-psychological Factors\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNeuroticism\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.69\u0026thinsp;\u0026plusmn;\u0026thinsp;0.69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2.97\u0026thinsp;\u0026plusmn;\u0026thinsp;0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e21.724***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEmotion regulation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCognitive reappraisal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e28.00\u0026thinsp;\u0026plusmn;\u0026thinsp;7.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e27.62\u0026thinsp;\u0026plusmn;\u0026thinsp;6.16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e28.28\u0026thinsp;\u0026plusmn;\u0026thinsp;7.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e4.907**\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExpressive suppression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e14.56\u0026thinsp;\u0026plusmn;\u0026thinsp;4.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e15.43\u0026thinsp;\u0026plusmn;\u0026thinsp;4.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e13.91\u0026thinsp;\u0026plusmn;\u0026thinsp;4.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e9.629***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMindfulness\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e21.15\u0026thinsp;\u0026plusmn;\u0026thinsp;4.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e15.91\u0026thinsp;\u0026plusmn;\u0026thinsp;4.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e22.38\u0026thinsp;\u0026plusmn;\u0026thinsp;4.48\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e18.305***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eChildhood trauma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEmotional abuse\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e6.85\u0026thinsp;\u0026plusmn;\u0026thinsp;2.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e7.56\u0026thinsp;\u0026plusmn;\u0026thinsp;3.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e6.32\u0026thinsp;\u0026plusmn;\u0026thinsp;2.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e13.841***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePhysical abuse\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5.74\u0026thinsp;\u0026plusmn;\u0026thinsp;2.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e6.02\u0026thinsp;\u0026plusmn;\u0026thinsp;2.68\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e5.27\u0026thinsp;\u0026plusmn;\u0026thinsp;1.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e6.997***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSexual abuse\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5.64\u0026thinsp;\u0026plusmn;\u0026thinsp;2.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5.88\u0026thinsp;\u0026plusmn;\u0026thinsp;2.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e5.46\u0026thinsp;\u0026plusmn;\u0026thinsp;1.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e7.097***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEmotional neglect\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e9.82\u0026thinsp;\u0026plusmn;\u0026thinsp;4.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e10.63\u0026thinsp;\u0026plusmn;\u0026thinsp;4.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e9.22\u0026thinsp;\u0026plusmn;\u0026thinsp;4.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e9.844***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePhysical neglect\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e7.91\u0026thinsp;\u0026plusmn;\u0026thinsp;3.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e8.53\u0026thinsp;\u0026plusmn;\u0026thinsp;3.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e7.45\u0026thinsp;\u0026plusmn;\u0026thinsp;2.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e9.143***\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003e\u003cb\u003eNote.\u003c/b\u003e *\u0026lt;0.05 **\u0026lt;0.01***\u0026lt;0.001\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003eFeature selection, model construction, and performance comparison\u003c/h2\u003e\u003cp\u003eAll participants were randomly divided into a training set of 2584 participants and a validation of 800 participants set at a ratio of 75% and 25%. The results of comparative analysis showed that there was no statistical difference in sample characteristics between the two sets. The details are showed in Table \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e. Before the feature selection, smoking and sexual abuse were excluded from the dataset due to the variances being close to zero.\u003c/p\u003e\u003cp\u003eThe Boruta algorithm was selected for feature selection. Of the 20 independent variables, 11 variables had significant effects on PMS, followed by neuroticism, mindfulness, history of dysmenorrhea, emotional abuse, expressive suppression, use of analgesic, physical neglect, emotional neglect, physical abuse, cognitive reappraise, and menstrual volume (See Figure \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e for details). Then, five machine learning models were constructed, including logistic regression, random forest, XGBoost, SVM, and MLP, with the above 11 features as independent variables and the presence or absence of PMS as dependent variables. The performance of each model was summarized in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and the receiver operating characteristic (ROC) curves of training set and validation set were showed in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e(a) and 1(b). According a comprehensive comparison, the random forest model performed best, with an AUC of 0.782, accuracy of 0.717, specificity of 0.733, sensitivity of 0.696, and an F1 score of 0.678 in validation set.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eModel performance in identifying PMS in the training and validation set.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAUC\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eF1 Score\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraining Set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRF\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.834\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.756\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.766\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.743\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.723\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.789\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.712\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.657\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.786\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.700\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSVM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.788\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.726\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.705\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.753\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.701\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMLP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.785\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.717\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.684\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.763\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.698\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.785\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.720\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.692\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.758\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.699\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eValidation Set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRF\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.782\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.717\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.733\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.696\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.678\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.778\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.705\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.662\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.762\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.688\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSVM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.780\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.718\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.715\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.724\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.687\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMLP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.781\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.716\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.704\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.732\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.688\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.781\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.721\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.711\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.734\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.692\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"6\"\u003e\u003cb\u003eAbbreviations.\u003c/b\u003e \u003cem\u003eRF\u003c/em\u003e random forest, \u003cem\u003eXGBoost\u003c/em\u003e extreme gradient boosting, \u003cem\u003eSVM\u003c/em\u003e support vector machine, \u003cem\u003eMLP\u003c/em\u003e multilayer perceptron, \u003cem\u003eLogistic\u003c/em\u003e logistic regression.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003eImportance of features\u003c/h2\u003e\u003cp\u003eTo gain insight into the contribution of each feature to the results, SHAP was used to interpret the output of the random forest model. Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e shows SHAP summary plots, describing the absolute value of SHAP mean of each feature, with the top five being neuroticism, mindfulness, history of dysmenorrhea, emotional abuse, and use of analgesic. Furthermore, the positive and negative contribution of each feature to PMS were visualized in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, with the x-axis representing the value of the feature and the y-axis representing the SHAP value. As seen in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e(a), participants who have frequent dysmenorrhea or use analgesic are at greater risk of developing PMS. In Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e(b), as neuroticism scores increased, the SHAP values increased and stabilized at a positive value above 3 points. Conversely, the relationship between mindfulness and SHAP values showed a negative correlation and remained stable for mindfulness larger than 24. For emotional abuse, the SHAP values show a increasing then slightly decreasing trend, but basically stable at positive.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis study explored the status of PMS among young adult women in China and developed machine learning-based models for identifying PMS. According to the comprehensive comparison of model performance, random forest exhibited the best performance. Then, SHAP was employed to explain the output of random forest and identify the key features associated with PMS, providing a powerful reference for accurate identification and intervention of PMS.\u003c/p\u003e\u003cp\u003eA total of 3447 young women were included in the secondary analysis. Of them, 42.8% were found to suffer PMS, which was relatively consistent with results from Korean college students (Kim \u0026amp; Park, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), but lower than those from high school students (64.6%) (Takeda et al., \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e2010\u003c/span\u003e) and higher with women of reproductive age (24.1%) (Qiao et al., \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2012\u003c/span\u003e). The main reason behind these differences can be explained by the use of different measurement tools encompassing different symptoms. However, these findings also illustrate a relative higher prevalence of PMS in young adult women. Close interaction between hypothalamic-pituitary-ovarian (HPO) axis hormones is fundamental for a regular menstrual cycle (Naz et al., \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). Young adult women are in the transition phase from adolescence to adulthood, and their HPO axis may not be fully mature, accompanied with immaturity in ovarian responses and FSH secretion (Sun et al., \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e2018\u003c/span\u003e), which is prone to menstrual abnormalities, such as PMS. Additionally, young adult women may experience multiple pressures from academia, social life, and the workplace. These stressors could affect the normal activity of the hypothalamic-pituitary-adrenal (HPA) axis (Oyola \u0026amp; Handa, \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e2017\u003c/span\u003e), raising cortisol concentrations (Juruena, \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2014\u003c/span\u003e), which disrupts the typical cyclical pattern of hormonal fluctuations, leading to PMS ultimately (Alshdaifat et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Maity et al., \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). Therefore, it is necessary to pay attention to PMS in young adult women and provide them with efficient diagnosis and effective intervention.\u003c/p\u003e\u003cp\u003eIn this study, five machine learning models were employed, including logistic regression, random forest, XGBoost, SVM, and MLP. The results of model performance reported that the AUC values of five models were all greater than 0.75 on both training and validation sets, suggesting good prediction of performance. Among them, the random forest model performed better, with an AUC of 0.782, accuracy of 0.717, specificity of 0.733, sensitivity of 0.696, and an F1 score of 0.678. These findings demonstrate machine learning, and random forest model in particular, in the ability to process complex datasets and the potential of disease identification, showing great promise for practical application in clinical settings (Dutta et al., \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Wang et al., \u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eAdditionally, to further investigate the relative importance of associated features for PMS among young adult women and their interactions, SHAP was used to interpret the output of the random forest model. The results revealed that neuroticism exhibited the highest predictive capacity for PMS among young women. Specifically, with the increase of neuroticism scores, the likelihood of young women with PMS was higher and showed a stable trend, reflecting the negative relationship between neuroticism and PMS, which is consistent with previous studies (Yilmaz, \u003cspan citationid=\"CR66\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Neuroticism, as a stable disposition to negative affect (Ormel et al., \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e2013\u003c/span\u003e), has been found to be directly associated with premenstrual psychological and behavioral symptoms. For example, Hamidovic et al. found a significant relationship between neuroticism, premenstrual difficulty in concentrating and low interest (Hamidovic et al., \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). Huang et al. found females with high-neuroticism scores may experience more negative emotions during the midlate luteal phase (Huang et al., \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2015\u003c/span\u003e). Alternatively, one plausible explanation lies in the relationship between neuroticism and sex hormones. High-neuroticism individuals are characterized by emotional instability and heightened sensitivity, a trait that may amplify their responsiveness to hormonal fluctuations during the menstrual cycle, thereby increasing the susceptibility to PMS (Wu et al., \u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e2014\u003c/span\u003e). These findings suggest that neuroticism can serve as an important identifier for PMS among young adult women. Early identification and intervention for high-neuroticism individuals can help effectively prevent the symptoms of PMS and alleviate the various adverse effects.\u003c/p\u003e\u003cp\u003eThe results also showed that higher mindfulness was associated with a lower likelihood of experiencing PMS. On the one hand, mindfulness enables individuals to deeply understand their thoughts and feelings, accept their emotional and physical experiences, thereby reducing their excessive focus and sensitivity towards symptoms (Asadi et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). On the other hand, it assists individuals in accurately identifying stressful situations, consciously regulating their responses to these experiences, and subsequently decreasing the activation of their somatic and psychological symptom response systems (Panahi \u0026amp; Faramarzi, \u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). Mindfulness-based therapy has been utilized as a non-pharmacological treatment for patients with PMS in previous studies, effectively alleviating their symptoms (Mazaheri Asadi et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). This findings support previous viewpoints and provide additional theoretical support for them. Additionally, this study reveled the notable association between childhood trauma and PMS, consistent with previous findings (Saglam et al., \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). A common explanation for the underlying mechanism is the impact of early abuse on the HPA axis (Taylor-Cavelier et al., \u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Specifically, the homeostatic balance of the HPA axis may be disrupted by excessive cortisol release induced by childhood trauma, thereby influencing the occurrence and progression of PMS (Suzuki et al., \u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e2014\u003c/span\u003e). It is noteworthy that emotional abuse exerted a greater impact in this study compared to other forms of childhood maltreatment, which underscores the necessity of conducting additional investigations into the relationship between emotional abuse and PMS (Bertone-Johnson et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2014\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eAmong the menstrual factors, the history of dysmenorrhea and use of analgesic showed significant associations with PMS. Specifically, women who experienced dysmenorrhea and use analgesic frequently were more likely to suffer from PMS. This relationship might be the resultant outcome of the combined actions of physiological and psychological factors (Babapour et al., \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Previous research has indicated that primary dysmenorrhea appeared to be the result of augmented prostanoid secretion (Jihong et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2011\u003c/span\u003e). Frequent occurrences of dysmenorrhea may potentially signify an underlying hormonal disequilibrium, and females experiencing dysmenorrhea are more predisposed to display negative emotion and maladaptive coping strategies (Li \u0026amp; Li, \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2011\u003c/span\u003e), thereby contributing to the development of PMS. Analgesic, commonly non-steroidal anti-inflammatory drugs (NSAIDs), were considered the first-line treatment for primary dysmenorrhea, offering efficient pain relief to most women (Oladosu et al., \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). In agreement with our findings, a study on Jordanian females also reported a significant correlation between analgesic use and PMS (Ababneh et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Taken together, in view of the currently high incidence of dysmenorrhea (Bettendorf et al., \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2008\u003c/span\u003e), further research is needed regarding how to implement effective self-management strategies and conduct rational analgesic use.\u003c/p\u003e\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003eStrength and limitations\u003c/h2\u003e\u003cp\u003eIn this study, machine learning was innovatively introduced to identify PMS among young adult women, enhancing the accuracy and reliability of prediction, and five machine learning algorithms were used to ensure the robustness of the results. Additionally, SHAP was employed to explain the importance and interrelationships of various features on PMS, providing theoretical support for early identification and the establishment of personalized preventive measures.\u003c/p\u003e\u003cp\u003eHowever, this study inevitably has certain constraints. Firstly, the cross-sectional design adopted in this study is unable to infer the causal logical relationships between variables. Secondly, the subjects of this study are only limited to young adult women in China. Studies on PMS among women of diverse ages, occupations, and cultural backgrounds could contribute to the expansion of our understanding of PMS and provide a generalized support for well being of female population. Thirdly, the data collected through self-reporting may lead to potential response biases. Objective measures could be considered in future studies, such as using wearable detection devices to record daily activities or sleep quality. Finally, PMS is a complex phenomenon affected by social, physiological, and psychological factors. Further studies should explore additional variables to gain a more comprehensive understanding of the underlying mechanism of PMS.\u003c/p\u003e\u003c/div\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study employed machine learning to identifying the high-risk gruop PMS among young adult women, showing great potential for the application of machine learning in disease identification. Additionally, the study explored the complex relationships between demographic, menstrual characteristics, and socio-psychological factors and PMS, revealing that neuroticism plays a great role in the development of PMS. Interventions such as mindfulness training, dysmenorrhea management, and addressing early trauma may hold significant potential in preventing and managing PMS. To sum up, these findings offer valuable evidence for early identification of PMS and serving as a reference in formulating targeted intervention programs among young adult women.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch3\u003eEthics Declarations\u003c/h3\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was approved by the institutional review board of the School of Nursing and Rehabilitation, Shandong University (2020-R-202).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll participants gave informed consent.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have no conflicts of interest to disclose.\u003c/p\u003e\n\u003ch3\u003eFunding\u003c/h3\u003e\n\u003cp\u003eNo funding was received to assist with the preparation of this manuscript.\u003c/p\u003e\n\u003ch3\u003eAuthor Contribution\u003c/h3\u003e\n\u003cp\u003eXHL: Investigation, Formal analysis, Methodology, Writing-original draft; XYZ: Methodology, Formal analysis, Software, Writing \u0026ndash; review and editing; YZ: Investigation, Formal analysis; LNG: Investigation, Visualization; HQL: Investigation; CM: Validation, Supervision, Resources, Writing \u0026ndash; review and editing; PL: Conceptualization, Project administration, Supervision, Resources, Writing \u0026ndash; review and editing.\u003c/p\u003e\n\u003ch3\u003eAcknowledgments\u003c/h3\u003e\n\u003cp\u003eWe acknowledge all participants for their voluntarily participation.\u003c/p\u003e\n\u003ch2\u003eData Availability\u003c/h2\u003e\n\u003cp\u003eThe data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eA D-M, K, S., A, D., Sattar K (2014) Epidemiology of Premenstrual Syndrome (PMS)-A Systematic Review and Meta-Analysis Study. J Clin Diagn research: JCDR 8(2):106\u0026ndash;109. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.7860/jcdr/2014/8024.4021\u003c/span\u003e\u003cspan address=\"10.7860/jcdr/2014/8024.4021\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAbabneh MA, Alkhalil M, Rababah A (2023) The prevalence, risk factors and lifestyle patterns of Jordanian females with premenstrual syndrome: a cross-sectional study. Future Sci Oa 9(9) Article Fso889. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2144/fsoa-2023-0056\u003c/span\u003e\u003cspan address=\"10.2144/fsoa-2023-0056\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAcikgoz A, Dayi A, Binbay T (2017) Prevalence of premenstrual syndrome and its relationship to depressive symptoms in first-year university students. Saudi Med J 38(11):1125\u0026ndash;1131. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.15537/smj.2017.11.20526\u003c/span\u003e\u003cspan address=\"10.15537/smj.2017.11.20526\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAlshdaifat E, Absy N, Sindiani A, AlOsta N, Hijazi H, Amarin Z, Alnazly E (2022) Premenstrual Syndrome and Its Association with Perceived Stress: The Experience of Medical Students in Jordan. Int J Womens Health 14:777\u0026ndash;785. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2147/ijwh.S361964\u003c/span\u003e\u003cspan address=\"10.2147/ijwh.S361964\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAntu\u0026ntilde;a-Camblor C, G\u0026oacute;mez-Salas FJ, Burgos-Juli\u0026aacute;n FA, Gonz\u0026aacute;lez-V\u0026aacute;zquez A, Juarros-Basterretxea J, Rodr\u0026iacute;guez-D\u0026iacute;az FJ (2024) Emotional Regulation as a Transdiagnostic Process of Emotional Disorders in Therapy: A Systematic Review and Meta-Analysis. Clin Psychol Psychother 31(3):e2997. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1002/cpp.2997\u003c/span\u003e\u003cspan address=\"10.1002/cpp.2997\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAsadi DM, Tajrishi KZ, Gharaei B (2022) Mindfulness Training Intervention With the Persian Version of the Mindfulness Training Mobile App for Premenstrual Syndrome: A Randomized Controlled Trial. Front Psychiatry 13:922360. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpsyt.2022.922360\u003c/span\u003e\u003cspan address=\"10.3389/fpsyt.2022.922360\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAzoulay M, Reuveni I, Dan R, Goelman G, Segman R, Kalla C, Bonne O, Canetti L (2020) Childhood Trauma and Premenstrual Symptoms: The Role of Emotion Regulation. Child Abuse Negl 108. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.chiabu.2020.104637\u003c/span\u003e\u003cspan address=\"10.1016/j.chiabu.2020.104637\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBabapour F, Elyasi F, Shahhosseini Z, Tabaghdehi MH (2023) The prevalence of moderate-severe premenstrual syndrome and premenstrual dysphoric disorder and the related factors in high school students: A cross-sectional study. Neuropsychopharmacol Rep 43(2):249\u0026ndash;254. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/npr2.12338\u003c/span\u003e\u003cspan address=\"10.1002/npr2.12338\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBancroft J (1993) The premenstrual syndrome\u0026ndash;a reappraisal of the concept and the evidence. Psychol Med Suppl 24:1\u0026ndash;47. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1017/s0264180100001272\u003c/span\u003e\u003cspan address=\"10.1017/s0264180100001272\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBertone-Johnson ER, Whitcomb BW, Missmer SA, Manson JE, Hankinson SE, Rich-Edwards JW (2014) Early Life Emotional, Physical, and Sexual Abuse and the Development of Premenstrual Syndrome: A Longitudinal Study. J Womens Health 23(9):729\u0026ndash;739. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1089/jwh.2013.4674\u003c/span\u003e\u003cspan address=\"10.1089/jwh.2013.4674\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBettendorf B, Shay S, Tu F (2008) Dysmenorrhea: contemporary perspectives. Obstet Gynecol Surv 63(9):597\u0026ndash;603. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/OGX.0b013e31817f15ff\u003c/span\u003e\u003cspan address=\"10.1097/OGX.0b013e31817f15ff\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBishop SR, Lau M, Shapiro S, Carlson L, Anderson ND, Carmody J, Segal ZV, Abbey S, Speca M, Velting D, Devins G (2004) Mindfulness: A Proposed Operational Definition. Clin Psychol Sci Pract 11(3):230\u0026ndash;241. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/https://doi.org/10.1093/clipsy.bph077\u003c/span\u003e\u003cspan address=\"10.1093/clipsy.bph077\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCaycho-Rodr\u0026iacute;guez T, Tom\u0026aacute;s JM, Ventura-Le\u0026oacute;n J, Esteban C, Guadalupe RFO, Reyes-Bossio LA, Garc\u0026iacute;a M, Cadena CH, Cabrera-Orosco I (2021) Factorial validity and invariance analysis of the five items version of Mindful Awareness Attention Scale in older adults. Aging Ment Health 25(4):756\u0026ndash;765. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/13607863.2020.1716685\u003c/span\u003e\u003cspan address=\"10.1080/13607863.2020.1716685\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChoi SH, Hamidovic A (2020) Association Between Smoking and Premenstrual Syndrome: A Meta-Analysis. Front Psychiatry 11., Article 575526. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpsyt.2020.575526\u003c/span\u003e\u003cspan address=\"10.3389/fpsyt.2020.575526\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDeCou CR, Lynch SM, Weber S, Richner D, Mozafari A, Huggins H, Perschon B (2023) On the Association Between Trauma-Related Shame and Symptoms of Psychopathology: A Meta-Analysis. Trauma Violence Abuse 24(3):1193\u0026ndash;1201 Article 15248380211053617. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/15248380211053617\u003c/span\u003e\u003cspan address=\"10.1177/15248380211053617\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003edel Mar Fernandez M, Saulyte J, Inskip HM, Takkouche B (2018) Premenstrual syndrome and alcohol consumption: a systematic review and meta-analysis. Bmj Open 8(3) Article e019490. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bmjopen-2017-019490\u003c/span\u003e\u003cspan address=\"10.1136/bmjopen-2017-019490\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDomingos P (2012) A few useful things to know about machine learning. Commun ACM 55(10):78\u0026ndash;87. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1145/2347736.2347755\u003c/span\u003e\u003cspan address=\"10.1145/2347736.2347755\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDutta A, Sharma A (2021) Prevalence of premenstrual syndrome and premenstrual dysphoric disorder in India: A systematic review and meta-analysis. Health Promotion Perspect 11(2):161\u0026ndash;170. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.34172/hpp.2021.20\u003c/span\u003e\u003cspan address=\"10.34172/hpp.2021.20\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDutta RR, Mukherjee I, Chakraborty C (2024) Obesity disease risk prediction using machine learning. Int J Data Sci Analytics. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s41060-023-00491-9\u003c/span\u003e\u003cspan address=\"10.1007/s41060-023-00491-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eErbil N, Yucesoy H (2023) Premenstrual syndrome prevalence in Turkey: a systematic review and meta-analysis. Psychol Health Med 28(5):1347\u0026ndash;1357. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/13548506.2021.2013509\u003c/span\u003e\u003cspan address=\"10.1080/13548506.2021.2013509\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGeta TG, Woldeamanuel GG, Dassa TT (2020) Prevalence and associated factors of premenstrual syndrome among women of the reproductive age group in Ethiopia: Systematic review and meta-analysis. PLoS ONE 15(11) Article e0241702. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pone.0241702\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0241702\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGumussoy S, Donmez S, Keskin G (2021) Investigation of the Relationship between Premenstrual Syndrome, and Childhood Trauma and Mental State in Adolescents with Premenstrual Syndrome. J Pediatr Nursing-Nursing Care Child Families 61:E65\u0026ndash;E71. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.pedn.2021.04.022\u003c/span\u003e\u003cspan address=\"10.1016/j.pedn.2021.04.022\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHamidovic A, Dang N, Khalil D, Sun J, Girardi P (2022) Association between Neuroticism and Premenstrual Affective/Psychological Symptomatology. Psychiatry Int 3(1):52\u0026ndash;64. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/psychiatryint3010005\u003c/span\u003e\u003cspan address=\"10.3390/psychiatryint3010005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHandhika T, Murni, Fahreza RM (2023) Boruta algorithm: An alternative feature selection method in credit scoring model. \u003cem\u003eAIP Conference Proceedings\u003c/em\u003e, \u003cem\u003e2431\u003c/em\u003e(1). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1063/5.0114178\u003c/span\u003e\u003cspan address=\"10.1063/5.0114178\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang C-C, Chen Y, Cheung S, Greene L, Lu S (2019) Resilience, emotional problems, and behavioural problems of adolescents in China: Roles of mindfulness and life skills. Health Soc Care Commun 27(5):1158\u0026ndash;1166. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/hsc.12753\u003c/span\u003e\u003cspan address=\"10.1111/hsc.12753\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang Y, Zhou R, Cui H, Wu M, Wang Q, Zhao Y, Liu Y (2015) Variations in resting frontal alpha asymmetry between high- and low-neuroticism females across the menstrual cycle. Psychophysiology 52(2):182\u0026ndash;191. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/psyp.12301\u003c/span\u003e\u003cspan address=\"10.1111/psyp.12301\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJihong Y, Ying C, Jiazhen HU (2011) Relationship between PGF2alpha and primary dysmenorrhea in female middle school students. \u003cem\u003eChina Public Health\u003c/em\u003e, \u003cem\u003e27\u003c/em\u003e(8), 1042\u0026ndash;1043. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://d.wanfangdata.com.cn/periodical/Ch9QZXJpb2RpY2FsQ0hJTmV3UzIwMjUwMTA0MTcwMjI2Eg96Z2dnd3MyMDExMDgwNDgaCHRzc2NiMzJl\u003c/span\u003e\u003cspan address=\"https://d.wanfangdata.com.cn/periodical/Ch9QZXJpb2RpY2FsQ0hJTmV3UzIwMjUwMTA0MTcwMjI2Eg96Z2dnd3MyMDExMDgwNDgaCHRzc2NiMzJl\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJuruena MF (2014) Early-life stress and HPA axis trigger recurrent adulthood depression. Epilepsy Behav 38:148\u0026ndash;159. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.yebeh.2013.10.020\u003c/span\u003e\u003cspan address=\"10.1016/j.yebeh.2013.10.020\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKim Y-J, Park Y-J (2020) Menstrual Cycle Characteristics and Premenstrual Syndrome Prevalence Based on the Daily Record of Severity of Problems in Korean Adult Women. J Korean Acad Nurs 50(1):147\u0026ndash;157. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.4040/jkan.2020.50.1.147\u003c/span\u003e\u003cspan address=\"10.4040/jkan.2020.50.1.147\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLe J, Thomas N, Gurvich C (2020) Cognition, The Menstrual Cycle, and Premenstrual Disorders: A Review. Brain Sci 10(4). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003eArticle 198. https://doi.org/10.3390/brainsci10040198\u003c/span\u003e\u003cspan address=\"Article 198. 10.3390/brainsci10040198\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLee Y, Ragguett R-M, Mansur RB, Boutilier JJ, Rosenblat JD, Trevizol A, Brietzke E, Lin K, Pan Z, Subramaniapillai M, Chan TCY, Fus D, Park C, Musial N, Zuckerman H, Chen VC-H, Ho R, Rong C, McIntyre RS (2018) Applications of machine learning algorithms to predict therapeutic outcomes in depression: A meta-analysis and systematic review. J Affect Disord 241:519\u0026ndash;532. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jad.2018.08.073\u003c/span\u003e\u003cspan address=\"10.1016/j.jad.2018.08.073\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi S, Li J (2011) Analysis of the emotion and anxiety status of female military students with dysmenorrhea. Chin J Pain Med 17(2):104\u0026ndash;106. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3969/j.issn.1006-9852.2011.02.007\u003c/span\u003e\u003cspan address=\"10.3969/j.issn.1006-9852.2011.02.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiguori F, Saraiello E, Calella P (2023) Premenstrual Syndrome and Premenstrual Dysphoric Disorder's Impact on Quality of Life, and the Role of Physical Activity. \u003cem\u003eMedicina-Lithuania\u003c/em\u003e, \u003cem\u003e59\u003c/em\u003e(11), Article 2044. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/medicina59112044\u003c/span\u003e\u003cspan address=\"10.3390/medicina59112044\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu X, Liu Z-Z, Yang Y, Jia C-X (2023) Prevalence and Associated Factors of Premenstrual Syndrome in Chinese Adolescent Girls. Child Psychiatry Hum Dev. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10578-023-01624-8\u003c/span\u003e\u003cspan address=\"10.1007/s10578-023-01624-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLundberg SM, Lee S-I (2017) A Unified Approach to Interpreting Model Predictions. Neural Information Processing Systems\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMa S, Song SJ (2023) Oral contraceptives containing drospirenone for premenstrual syndrome. Cochrane Database Syst Rev 6(6):Cd006586. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/14651858.CD006586.pub5\u003c/span\u003e\u003cspan address=\"10.1002/14651858.CD006586.pub5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMaity S, Wray J, Coffin T, Nath R, Nauhria S, Sah R, Waechter R, Ramdass P, Nauhria S (2022) Academic and Social Impact of Menstrual Disturbances in Female Medical Students: A Systematic Review and Meta-Analysis. Front Med (Lausanne) 9:821908. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fmed.2022.821908\u003c/span\u003e\u003cspan address=\"10.3389/fmed.2022.821908\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMann P, Pradeep TS (2023) Premenstrual Syndrome, Anxiety, and Depression Among Menstruating Rural Adolescent Girls: A Community-Based Cross-Sectional Study. Cureus J Med Sci 15(12) Article e50385. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.7759/cureus.50385\u003c/span\u003e\u003cspan address=\"10.7759/cureus.50385\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMartin SA, Townend FJ, Barkhof F, Cole JH (2023) Interpretable machine learning for dementia: A systematic review. Alzheimers Dement 19(5):2135\u0026ndash;2149. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/alz.12948\u003c/span\u003e\u003cspan address=\"10.1002/alz.12948\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMazaheri Asadi D, Tajrishi Z, K., Gharaei B (2022) Mindfulness Training Intervention With the Persian Version of the Mindfulness Training Mobile App for Premenstrual Syndrome: A Randomized Controlled Trial. Front Psychiatry 13:922360. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpsyt.2022.922360\u003c/span\u003e\u003cspan address=\"10.3389/fpsyt.2022.922360\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMostafa HE-S, Alkurdi AA, Sanousi M, Aljuhani F, Abdullah M, Aljohani BS, Aljohani WK (2023) Correlation between premenstrual syndrome and body mass index among reproductive females. Med Sci 27(133). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.54905/disssi/v27i133/e123ms2926\u003c/span\u003e\u003cspan address=\"10.54905/disssi/v27i133/e123ms2926\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNayman S, Konstantinow DT, Schricker IF, Reinhard I, Kuehner C (2023) Associations of premenstrual symptoms with daily rumination and perceived stress and the moderating effects of mindfulness facets on symptom cyclicity in premenstrual syndrome. Archives Womens Mental Health 26(2):167\u0026ndash;176. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00737-023-01304-5\u003c/span\u003e\u003cspan address=\"10.1007/s00737-023-01304-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNaz MSG, Farahmand M, Dashti S, Tehrani FR (2022) Factors Affecting Menstrual Cycle Developmental Trajectory in Adolescents: A Narrative Review. Int J Endocrinol Metabolism 20(1) Article e120438. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5812/ijem.120438\u003c/span\u003e\u003cspan address=\"10.5812/ijem.120438\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eO'Brien PM, B\u0026auml;ckstr\u0026ouml;m T, Brown C, Dennerstein L, Endicott J, Epperson CN, Eriksson E, Freeman E, Halbreich U, Ismail KM, Panay N, Pearlstein T, Rapkin A, Reid R, Schmidt P, Steiner M, Studd J, Yonkers K (2011) Towards a consensus on diagnostic criteria, measurement and trial design of the premenstrual disorders: the ISPMD Montreal consensus. Arch Womens Ment Health 14(1):13\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00737-010-0201-3\u003c/span\u003e\u003cspan address=\"10.1007/s00737-010-0201-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOladosu FA, Tu FF, Hellman KM (2018) Nonsteroidal antiinflammatory drug resistance in dysmenorrhea: epidemiology, causes, and treatment. Am J Obstet Gynecol 218(4):390\u0026ndash;400. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ajog.2017.08.108\u003c/span\u003e\u003cspan address=\"10.1016/j.ajog.2017.08.108\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOrmel J, Bastiaansen A, Riese H, Bos EH, Servaas M, Ellenbogen M, Rosmalen JG, Aleman A (2013) The biological and psychological basis of neuroticism: current status and future directions. Neurosci Biobehav Rev 37(1):59\u0026ndash;72. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.neubiorev.2012.09.004\u003c/span\u003e\u003cspan address=\"10.1016/j.neubiorev.2012.09.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOyola MG, Handa RJ (2017) Hypothalamic-pituitary-adrenal and hypothalamic-pituitary-gonadal axes: sex differences in regulation of stress responsivity. Stress 20(5):476\u0026ndash;494. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/10253890.2017.1369523\u003c/span\u003e\u003cspan address=\"10.1080/10253890.2017.1369523\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePanahi F, Faramarzi M (2016) The Effects of Mindfulness-Based Cognitive Therapy on Depression and Anxiety in Women with Premenstrual Syndrome. \u003cem\u003eDepress Res Treat\u003c/em\u003e, \u003cem\u003e2016\u003c/em\u003e, 9816481. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1155/2016/9816481\u003c/span\u003e\u003cspan address=\"10.1155/2016/9816481\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePigoni A, Delvecchio G, Turtulici N, Madonna D, Pietrini P, Cecchetti L, Brambilla P (2024) Machine learning and the prediction of suicide in psychiatric populations: a systematic review. Translational Psychiatry 14(1). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003eArticle 140. https://doi.org/10.1038/s41398-024-02852-9\u003c/span\u003e\u003cspan address=\"Article 140. 10.1038/s41398-024-02852-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eQiao M, Zhang H, Liu H, Luo S, Wang T, Zhang J, Ji L (2012) Prevalence of premenstrual syndrome and premenstrual dysphoric disorder in a population-based sample in China. Eur J Obstet Gynecol Reprod Biol 162(1):83\u0026ndash;86. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ejogrb.2012.01.017\u003c/span\u003e\u003cspan address=\"10.1016/j.ejogrb.2012.01.017\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRobinson RL, Swindle RW (2000) Premenstrual symptom severity: impact on social functioning and treatment-seeking behaviors. J Womens Health Gend Based Med 9(7):757\u0026ndash;768. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1089/15246090050147736\u003c/span\u003e\u003cspan address=\"10.1089/15246090050147736\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSaglam HY, Gursoy E, Karakus A (2024) Impact of childhood trauma history on premenstrual syndrome in women of reproductive age: A cross-sectional study. J Eval Clin Pract. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/jep.14172\u003c/span\u003e\u003cspan address=\"10.1111/jep.14172\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSingh C, Jain J, Singh K, Jain MP, Chaudhary A (2016) A Study of Premenstrual Dysphoric Disorder Prevalence, Phenomenology and Personality Factors in College Going Students. Indian J Health Wellbeing 7:962\u0026ndash;965\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSmith DR (2008) Menstrual disorders and their adverse symptoms at work: An emerging occupational health issue in the nursing profession. Nurs Health Sci 10(3):222\u0026ndash;228. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.1442-2018.2008.00391.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1442-2018.2008.00391.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSoto CJ, John OP (2009) Ten facet scales for the Big Five Inventory: Convergence with NEO PI-R facets, self-peer agreement, and discriminant validity. J Res Pers 43(1):84\u0026ndash;90. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jrp.2008.10.002\u003c/span\u003e\u003cspan address=\"10.1016/j.jrp.2008.10.002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSpinhoven P, Penninx BW, Hickendorff M, van Hemert AM, Bernstein DP, Elzinga BM (2014) Childhood Trauma Questionnaire: factor structure, measurement invariance, and validity across emotional disorders. Psychol Assess 26(3):717\u0026ndash;729. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1037/pas0000002\u003c/span\u003e\u003cspan address=\"10.1037/pas0000002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSun BZ, Kangarloo T, Adams JM, Sluss PM, Welt CK, Chandler DW, Zava DT, McGrath JA, Umbach DM, Hall JE, Shaw ND (2018) Healthy Post-Menarchal Adolescent Girls Demonstrate Multi-Level Reproductive Axis Immaturity. J Clin Endocrinol Metabolism 104(2):613\u0026ndash;623. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1210/jc.2018-00595\u003c/span\u003e\u003cspan address=\"10.1210/jc.2018-00595\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSuzuki A, Poon L, Papadopoulos AS, Kumari V, Cleare AJ (2014) Long term effects of childhood trauma on cortisol stress reactivity in adulthood and relationship to the occurrence of depression. Psychoneuroendocrinology 50:289\u0026ndash;299. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.psyneuen.2014.09.007\u003c/span\u003e\u003cspan address=\"10.1016/j.psyneuen.2014.09.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTakeda T, Koga S, Yaegashi N (2010) Prevalence of premenstrual syndrome and premenstrual dysphoric disorder in Japanese high school students. Archives Womens Mental Health 13(6):535\u0026ndash;537. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00737-010-0181-3\u003c/span\u003e\u003cspan address=\"10.1007/s00737-010-0181-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTaylor-Cavelier SJ, Micol VJ, Roberts AG, Geiss EG, Lopez-Duran N (2021) DHEA Moderates the Impact of Childhood Trauma on the HPA Axis in Adolescence. Neuropsychobiology 80(4):299\u0026ndash;312. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1159/000511629\u003c/span\u003e\u003cspan address=\"10.1159/000511629\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang K, Zhao J, Hu J, Liang D, Luo Y (2023) Predicting unmet activities of daily living needs among the oldest old with disabilities in China: a machine learning approach. Front Public Health 11. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3389/fpubh.2023.1257818\u003c/span\u003e\u003cspan address=\"10.3389/fpubh.2023.1257818\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang L, lIU H, Li Z, Du W (2007) Reliability and Validity of Emotion Regulation Questionnaire Chinese Revised Version. Chine J Health Psychol 15(6):503\u0026ndash;505. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3969/j.issn.1005-1252.2007.06.034\u003c/span\u003e\u003cspan address=\"10.3969/j.issn.1005-1252.2007.06.034\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWittchen HU, Becker E, Lieb R, Krause P (2002) Prevalence, incidence and stability of premenstrual dysphoric disorder in the community. Psychol Med 32(1):119\u0026ndash;132. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1017/s0033291701004925\u003c/span\u003e\u003cspan address=\"10.1017/s0033291701004925\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWu M, Zhou R, Huang Y, Wang Q, Zhao Y, Liu Y (2014) Effects of Menstrual Cycle and Neuroticism on Emotional Responses of Healthy Women. Acta Physiol Sinica 158\u0026ndash;68. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3724/sp.J.1041.2014.00058\u003c/span\u003e\u003cspan address=\"10.3724/sp.J.1041.2014.00058\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang H, Ma Y, Wang Y, Fu C, Liu W, Li W (2024) Association between physical activity and risk of premenstrual syndrome among female college students: a systematic review and meta-analysis. Bmc Womens Health 24(1). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003eArticle 307. https://doi.org/10.1186/s12905-024-03147-3\u003c/span\u003e\u003cspan address=\"Article 307. 10.1186/s12905-024-03147-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYilmaz FA (2024) The relationship between premenstrual syndrome and personality traits in university students. Rev Assoc Med Bras 70(7) Article e20231679. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1590/1806-9282.20231679\u003c/span\u003e\u003cspan address=\"10.1590/1806-9282.20231679\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhao X, Zhang Y, Li L, Zhou Y, Li H, Yang S (2005) Reliability and validity of the Chinese version of childhood trauma questionnaire. Chin J Clin Rehabilitation 9(20):105\u0026ndash;107. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3321/j.issn:1673-8225.2005.20.052\u003c/span\u003e\u003cspan address=\"10.3321/j.issn:1673-8225.2005.20.052\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Premenstrual Syndrome, Machine Learning, Young Adult, Women Groups","lastPublishedDoi":"10.21203/rs.3.rs-7522395/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7522395/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003ePremenstrual syndrome (PMS) is a public health problem with widespread impact, influenced by the multiple factors. Young adult women, as a high-risk group for PMS, can benefit from early identification of key factors related to PMS. This study aimed to construct a machine learning model for identifying PMS among young adult women and explore the complex relationships between associated factors and PMS.\u003c/p\u003e\u003ch2\u003eMethod\u003c/h2\u003e\u003cp\u003eA secondary analysis was performed using cross-sectional data from 3447 young adult women. Using a score of 6 points on the Premenstrual Syndrome Scale (PSS) as the cutoff, all participants were divided into the PMS group and the non-PMS group. The dataset was randomized into a training set and a validation set in 75% and 25% proportions. Five machine learning algorithms were used to develop models and the output of performed-best model was interpreted using SHapley Additiveex Planations (SHAP).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eThere were 1474 women in PMS group and 1973 women in non-PMS group. Among five machine learning models, the random forest model performed best, with an AUC of 0.782. Neuroticism was most strongly associated with PMS, followed by mindfulness, history of dysmenorrhea, emotional abuse, and use of analgesic.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eThe results suggested that the random forest model was an effective tool for identifying PMS among young adult women, and neuroticism could serve as a crucial predictive indicator. Furthermore, interventions such as mindfulness training, dysmenorrhea management, and addressing early trauma may hold significant potential in preventing and managing PMS.\u003c/p\u003e","manuscriptTitle":"Interpretable Machine Learning Models for Identifying Premenstrual Syndrome and Related Factors in Young Adult Women","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-22 09:32:54","doi":"10.21203/rs.3.rs-7522395/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6283e917-3bc1-4638-aa62-ba4f16f38e13","owner":[],"postedDate":"September 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-22T06:23:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-22 09:32:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7522395","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7522395","identity":"rs-7522395","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}