Predictive Modeling for Rectal Bleeding Risk in Functional Constipation: Integrating Lifestyle Factors and Machine Learning for Targeted Prevention

Predictive Modeling for Rectal Bleeding Risk in Functional Constipation: Integrating Lifestyle Factors and Machine Learning for Targeted Prevention | 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 Predictive Modeling for Rectal Bleeding Risk in Functional Constipation: Integrating Lifestyle Factors and Machine Learning for Targeted Prevention Joyeta Ghosh, Jyoti Taneja, Ravi Kant This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5476421/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 Rectal bleeding is a prevalent but often underreported health concern in young adults, where functional constipation and lifestyle factors can play a pivotal role. This study investigates the influence of contemporary lifestyle factors—including dietary patterns, fibre intake, physical activity, and BMI—on rectal bleeding risk in young adults with functional constipation. Using a descriptive observational study design, data were collected from 875 college-aged individuals in India to analyse lifestyle and clinical factors associated with rectal bleeding. A variety of machine learning models were tested to develop an accurate predictive model for bleeding risk assessment. Findings revealed significant correlations between dietary habits and rectal bleeding; individuals consuming less than 50g of boiled vegetables or oatmeal daily experienced bleeding at a rate of 43.92% (p 25g daily) was linked to a 44.81% bleeding rate. BMI also significantly impacted bleeding risk (p = 0.008), with higher incidence among overweight/obese participants. The KNeighbors Classifier was identified as the most effective predictive model, achieving 98.86% accuracy with an ROC area of 0.994, where symptomatic factors outweighed lifestyle factors in predicting bleeding risk. This machine learning model offers a promising tool for early risk identification, supporting lifestyle interventions, particularly in fibre intake and weight management, to reduce bleeding risk in this population. Nutrition & Dietetics Artificial Intelligence and Machine Learning Women's studies Rectal bleeding functional constipation lifestyle factors machine learning prediction dietary habits young adults Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 1. Introduction Rectal bleeding, despite being a significant health indicator, is often neglected by young adults due to social stigma and lack of awareness. This issue may range from benign conditions such as anal fissures or haemorrhoids to severe pathologies, including colorectal cancer, especially if unaddressed[ 1 ]. Global studies report that 15–20% of adults will experience rectal bleeding at some point; however, delayed medical consultation is common due to embarrassment or a misconception that these symptoms are not serious [ 2 ], [ 3 ]. In young adults, rectal bleeding is commonly linked to functional constipation, a disorder that disrupts normal bowel function and can lead to chronic complications if untreated. Functional constipation, affecting around 16% of adults worldwide, is frequently driven by the demands and behaviours associated with modern lifestyles[ 4 ]. With the rise of highly processed foods, inadequate dietary fibre, limited physical activity, disrupted sleep, and elevated stress levels, modern lifestyles have been increasingly implicated in gastrointestinal health issues[ 5 ]. Research demonstrates that these lifestyle factors collectively impair digestive health, making individuals more prone to constipation and its associated complications, including rectal bleeding. For instance, individuals with low daily fibre intake (below 25 grams) are three times more likely to experience constipation and subsequent bleeding episodes compared to those who meet dietary fibre recommendations [ 6 ]. Consistent hydration (2–3 liters per day), good sleep hygiene, and regular physical activity are fundamental for maintaining a healthy gastrointestinal tract, but adherence to these practices can be challenging amidst busy, sedentary lifestyles [ 7 ]. To address the multifaceted nature of constipation and its complications, a more individualized approach is essential. This is where artificial intelligence (AI) and machine learning (ML) present new possibilities. Machine learning, a subset of AI, is proving invaluable in health research for building predictive models that consider unique behavioural, dietary, and physiological data[ 8 ]. With the potential to integrate multiple factors—such as dietary habits, hydration levels, physical activity, and stress patterns—machine learning models can forecast individual risk profiles for conditions like rectal bleeding in ways that traditional approaches cannot[ 9 ]. Through this technology, individuals at high risk for rectal bleeding can receive specific dietary and lifestyle recommendations based on their personal risk factors, making prevention both effective and tailored [ 10 ]. In fact, studies have shown that personalized, AI-driven health recommendations can increase adherence rates by as much as 42% over standard guidelines, suggesting that such tools could be transformative in preventive healthcare [ 11 ]. An ML-based predictive model for rectal bleeding risk could revolutionize gastrointestinal healthcare by identifying risk factors early on and facilitating preventive action before symptoms escalate. This study, therefore, aims to harness AI to fill a critical gap in preventive healthcare, specifically for young adults experiencing rectal bleeding due to functional constipation. By analysing key lifestyle and dietary factors through advanced ML algorithms, this study not only seeks to identify high-risk individuals but also to contribute actionable insights to support healthier digestive patterns in the broader population. The objectives of this study include the development and validation of a robust ML model to predict rectal bleeding risk based on a wide array of lifestyle factors. This research will: (1) assess the contribution of individual lifestyle variables such as dietary patterns, hydration, sleep quality, and BMI, (2) build a predictive model that processes these parameters to forecast bleeding risk with high accuracy, (3) perform feature importance analysis to inform lifestyle adjustments that could mitigate risk, and (4) validate the model's predictive performance using real-world data. By providing an accessible, personalized risk assessment tool, this study aims to empower young adults to take proactive steps toward digestive health improvement, potentially reducing the incidence of rectal bleeding and the related healthcare burden. The study’s findings may also support the broader public health goal of promoting preventive care in gastrointestinal health by demonstrating the value of lifestyle modifications in managing functional constipation and associated complications. 2. Materials and Methods 2.i. Data Source 2.i.a. Sample Size Calculation Sample size was calculated by taking the previous prevalence of self reported constipation was 24.8% [ 12 ] and using formula n = 4pq/L2 (where, p = prevalence of malnutrition, q = 100 − p, L = 15% of p) [ 13 ]. It came out to be 539. During the study period, 875 participants agreed to participate in the study based up on their availability, willing to participate, and according to exclusion criteria. 2.i.b. Study Design This observational descriptive study included 875 college girls from Kolkata, West Bengal, India, selected randomly through social media platforms (LinkedIn, WhatsApp, and Facebook). Participants were aged between 18 to 25 years. While the initial traditional evaluation of this study has been published elsewhere, the present study builds upon it by applying machine learning (ML) models and incorporating the Bristol Stool Chart and ROME-III criteria. This research is part of a larger project focused on adults, with institutional ethical clearance obtained from the All India Institute of Hygiene and Public Health, Kolkata, India [ 14 ]. The study included undergraduate and postgraduate students from their first to fifth year who voluntarily participated and provided informed consent upon turning 18. Exclusion criteria were: (1) individuals with chronic cardiovascular, hematologic, or digestive disorders, and (2) those with significant lesions in other organs. Data collection was conducted from February 2022 to October 2024 using a standardized, pre-tested online questionnaire. The collected data were entered into a Microsoft Excel worksheet and thoroughly reviewed for errors before analysis. 2.i.c. Selection of Predictors College-bound students often experience a challenging transition period that affects both their physical and emotional well-being. During this time, students frequently encounter stressful situations, or "stressful life events," which impact their emotions in various ways [ 15 ]. These include academic pressure, relationship issues, arguments with close friends, romantic breakups, and separation from family [ 16 ]. A particularly worrying trend is students' tendency to ignore serious health symptoms, especially rectal bleeding, often delaying medical attention until the condition becomes severe. Constipation is also prevalent among this population, with many students experiencing infrequent bowel movements, straining, and abdominal discomfort. The study examined 18 key variables affecting functional constipation (FC) in young adults, based on published studies of FC in young people and college-bound students [ 17 ], [ 18 ]. These included factors like bowel movement frequency, presence of rectal bleeding or tearing, stool consistency, dietary habits (including fruit and vegetable intake), water consumption, exercise frequency, sleep patterns, and BMI. Of particular concern is students' reluctance to seek medical help when experiencing rectal bleeding, potentially allowing underlying conditions to worsen. One ROME-III criterion ("Manual maneuvers on > 25% of defecations") was excluded from analysis due to uniform negative responses across all participants, leaving 21 attributes for final analysis of constipation patterns in this population ( Table 1 ) . Table 1 Explanation of Questionnaires used as a tool S. No. Questions Attributes used in dataset Answer 1 Age Age Age in number 2 BMI status of the participants as per the measurements? BMI (0 = Normal BMI,1 = Malnutrition) 3 What type of food habit participants has? Food Habit (0 = Vegetarian,1 = Non vegetarian) 4 How much water participant took daily? Daily Water Intake (0 = > 2 litr,1 = < 2 litr) 5 What is the frequency of too small bowel movement? Too-small bowel movement frequency 1 = Mild to Moderate; 0 = Absent. 6 Did the individual have tear or bleeding in the rectal area during or after a bowel movement? Crying or tearing in the rectal cavity during or after a bowel movement (0 = No,1 = Yes) 7 Did the participant feel any abdominal pain or discomfort? Abdominal pain and discomfort (0 = Absent,1 = Mild to Moderate) 8 What type of stool the participants have according to Bristol's Stool consistency Scale? Bristol's Stool consistency Scale (0 = Type 1,1 = Type2,2 = Type 3,3 = Type4,4 = Type 5,5 = Type 6,6 = Type 7) 9 What is the frequency of exercise per week? Frequency of exercise (0 = No exercise,1 = 1to 2 days per week,2 = 3to 4 days per week,3 = every day) 10 Does the participant do physical exercise without work? Do you exercise? (0 = No,1 = Yes) 11 What are the daily sleeping hours of the participants? Daily sleeping hours (0 = > 6 hours per day,1 = < 6 hours per day) 12 What are the frequencies of fruit consumption? Frequency of fruit consumption (0 = daily,1 = Once/ week ,2 = Less than three times/ week,3 = rarely) 13 How frequently do you eat green leafy vegetables? Consumption frequency of leafy green vegetables (insoluble fibre) (0 = every day, 1 = once per week, 2 = less than three times per week, and 3 = seldom) 14 Daily nuts/dried fruits/seeds consumption > 25 gm Consumption of insoluble fibre rich food > 25gm/day (0 = No,1 = Yes) 15 Daily boiled vegetables/oatmeal consumption > 50 gm Consumption of soluble fibre rich food > 50gm/day (0 = No,1 = Yes) 16 Daily whole grain consumption > 25 gm Consumption of soluble fibre rich food > 25 gm/day (0 = No,1 = Yes) ROME III Criteria 17 Restricting on more than 25% of feces Limiting more than 25% of bowel movements (0 = Absent,1 = Present) 18 Incomplete evacuation is perceived in more than 25% of defecations In more than 25% of cases, there is a sense of incomplete evacuation (0 = Absent,1 = Present) 19 Over 25% of defecations result in lumpy or hard stool. More than 25% of bowel movements result in a lumpy or hard stool. (0 = Absent,1 = Present) 20 Sensation of anarectal obstruction/blockage on > 25% of defecations Sensation of anarectal obstruction/blockage on > 25% of defecations (0 = Absent,1 = Present) 21 Less than 3 defecation per week Less than 3 defecation per week (0 = Absent,1 = Present) 2.i.d. Statistical Analysis and Disease Prediction System The research technique or step is shown in Fig. 1 . The full research methodology is outlined in the order and detail that follows. It gives the working flowchart a clear comprehension. The association between two qualitative data was calculated by Pearson’s Chi-square test and ‘P’ value was determined. All the statistical analysis was performed by SPSS software (Statistical Package for Social Sciences version 20.0). ‘P’ value is equal to or less than 0.05 was considered as statistically significant. 2.ii. Model Construction and Evaluation 2.ii.a Data Pre-processing Raw data collected from young adults with functional constipation often contains inherent noise, inconsistencies, and incompleteness that can significantly impact the analysis and final predictions. Data preprocessing is therefore crucial for ensuring reliable machine learning outcomes. The preprocessing steps include handling missing values, dimension reduction, attribute selection, and cleaning of noisy and inconsistent data related to lifestyle factors and bleeding incidents. 2.ii.b Missing Value Computation The dataset was initially processed using Weka (Data Mining Tools, Version 3.8.3). Upon loading, missing values were identified in various lifestyle and symptom parameters. These missing values were handled using the Replace Missing Values filter under the unsupervised filter attribute. For numerical data points (such as frequency of bleeding incidents), the mean value was used as a replacement. For nominal values (such as lifestyle categories), the mode was employed as the replacement value. 2.ii.c Outlier Detection and Removal Given the sensitive nature of rectal bleeding prediction, outlier detection and removal was crucial. The process followed these steps: Utilized Weka's Inter Quartile Range filter to identify extreme values and outliers Divided the dataset into three quartiles (Q1, Q2, Q3) Calculated the Interquartile Range (IQR) using: IQR = Q3 – Q1 Determined boundaries using: Lower boundary (B min ) = Q1–1.5 * IQR Upper boundary (B max ) = Q3 + 1.5 * IQR To address any resulting class imbalance after outlier removal, the Synthetic Minority Oversampling Technique (SMOTE) was applied to maintain balanced representation of bleeding and non-bleeding cases. 2.ii.d Machine Learning Model Implementation Ten prediction models were implemented to analyze the relationship between lifestyle factors and rectal bleeding:1. Random Forest, 2. Logistic Regression, 3. KNeighbors Classifier,4. MLP Classifier, 5. Support Vector Machines, 6. Perceptron,7. Linear SVC,8. Stochastic Gradient Descent,9. Gaussian NB,10. Decision Tree The dataset (N = 875) was split into: Training set (70%): 612 samples Test set (30%): 263 samples Model validation employed a repeated nested cross-validation approach to prevent overfitting as explained in Table 2 . Table 2 Model validation employed a repeated nested cross-validation approach to prevent overfitting Steps Activity Conducted Stage 1 : Hyperparameter Optimization Implemented 10-fold cross-validation Optimized model complexity parameters Adjusted learning parameters based on validation data Stage 2 : Performance Evaluation Applied optimized parameters from Stage 1 Evaluated models using: Accuracy Sensitivity Precision AUC (Area Under Curve) Assessed predictor contributions to determine the relative importance of different lifestyle factors in predicting rectal bleeding Table 3 Distribution of the lifestyle, food habit and nutritional status of the respondents and its association with Rectal Bleeding or Tearing During and After Bowel Movements Parameters Participants (%) Rectal Bleeding or Tearing During and After Bowel Movements (%) Chi-square test (p value) N = 875 Yes No Food habit : Vegetarian 15(100) 1(6.66) 14(93.34) 0.27 (p-0.59) Non-vegetarian 860(100) 94(10.93) 766(89.07) Nutritional Status (BMI) Normal 180(100) 10(5.55) 170(94.46) 6.82 (p-0.008) Underweight 02(100) 00(0.00) 02(100) Overweight / Obesity 693(100) 85(12.26) 608(87.74) Daily water intake : 2 L 233(100) 29(12.44) 204(87.56) Frequency of green leafy vegetable consumption : Daily 28(100) 00(0.00) 28(100) 5.85 (p-0.01) Once per week 126(100) 10(7.93) 116(92.07) < 3times per week 701(100) 85(12.12) 616(87.88) Very rarely 20(100) 00(0.00) 20(100) Frequency of fruit consumption : Daily 28(100) 00(0.00) 28(100) 4.83 (p-0.02) Once per week 126(100) 10(7.93) 116(92.07) < 3times per week 710(100) 85(11.97) 625(88.03) Very rarely 11(100) 00(0.00) 11(100) Daily sleeping pattern : ≤ 6 hours 444(100) 47(10.58) 397(89.42) 0.220 (p-0.37) 7–8 hours 431(100) 48(11.14) 383(88.86) Daily nuts/dried fruits/seeds consumption > 25 gm Yes 659(100) 01(0.15) 658(99.85) 0.06 (p-0.79) No 216(100) 94(43.51) 122(56.49) Daily boiled vegetables/oatmeal consumption > 50 gm Yes 661(100) 01(0.15) 660(99.85) 320.02 (p-0.00) No 214(100) 94(43.92) 120(56.08) Daily whole grain consumption > 25 gm Yes 663(100) 00(0.00) 663(100) - No 212(100) 95(44.81) 117(55.19) Presence of Constipation Yes 214(100) 95(44.39) 119(55.61) _- No 661(100) 00(00) 661(100) Table 4 Application of different classification model and their performance in predicting rectal bleeding or tearing during and after bowel movements Classification model applied Correctly classified Instances (%) Incorrectly classified instances (%) Kappa Statistics Root Mean Squared Error Relative Absolute Error True Positive Rate False Positive Rate Precision F-Measures ROC Area Logistic Regression 97.14 2.86 0.856 0.169 0.000163 0.895 0.019 0.85 0.872 0.938 SVC 89.14 10.86 0 0.33 0.00062 0 0 0 0 0.5 KNeighbors Classifier 98.86 1.14 0.944 0.107 0.000065 1.00 0.013 0.905 0.95 0.994 GaussianNB 93.14 6.86 0.723 0.262 0.000392 1.00 0.077 0.613 0.76 0.962 Perceptron 82.86 17.14 0.477 0.414 0.00098 1.00 0.192 0.388 0.559 0.904 LinearSVC 97.14 2.86 0.868 0.169 0.000163 1.00 0.032 0.792 0.884 0.984 SGD Classifier 70.29 29.71 0.303 0.545 0.001698 1.00 0.333 0.268 0.422 0.833 MLP Classifier 97.14 2.86 0.856 0.169 0.000163 0.895 0.019 0.85 0.872 0.938 3. Results This descriptive observational study examined the nutritional, clinical, and other contributing factors to functional constipation in college going youth of India in addition to determining the normal bowel pattern. The study examined the distribution of lifestyle, food habits, and nutritional status among 875 respondents, with particular emphasis on dietary fiber types and their association with rectal bleeding or tearing during and after bowel movements (Table 3 ). The findings revealed striking differences between soluble and insoluble fiber consumption patterns. For soluble fiber sources, participants lacking adequate intake of boiled vegetables/oatmeal (> 50g daily) showed significantly higher bleeding rates (43.92%, p 25g) experienced notably higher bleeding incidents (44.81%). Regarding insoluble fiber sources, insufficient consumption of nuts/dried fruits/seeds (> 25g daily) was associated with higher bleeding rates (43.51%), while irregular consumption of green leafy vegetables (< 3 times per week) showed 12.12% bleeding incidents (p = 0.01), and similar patterns were observed with irregular fruit consumption (11.97%, p = 0.02). Additional significant associations included BMI status (p = 0.008), with overweight/obese individuals showing higher bleeding incidents (12.26%) compared to normal weight (5.55%). The presence of constipation emerged as a critical factor, with 44.39% of constipated individuals experiencing bleeding. Other lifestyle factors such as vegetarian versus non-vegetarian status (p = 0.59), daily water intake (p = 0.36), and sleeping patterns (p = 0.37) showed no significant associations. The results strongly indicate that inadequate intake of both soluble and insoluble fiber sources, along with constipation and higher BMI, are significant risk factors for rectal bleeding or tearing during and after bowel movements. Figure 2 presents the distribution patterns of age (A), BMI (B), and daily water intake (C) in relation to the occurrence of rectal bleeding or tearing during and after bowel movements among the targeted respondents. The correlation matrix (Fig. 4 ) provides crucial insights into the relationships between rectal bleeding/tearing and various lifestyle and constipation-related factors among young adults with functional constipation. Most significantly, the matrix reveals strong positive correlations (0.75-1.00, shown in dark red) between rectal bleeding/tearing and other constipation symptoms, including presence of constipation, Bristol's Stool consistency Scale, abdominal pain, straining during defecation, and sensation of incomplete evacuation. This interconnection suggests that rectal bleeding/tearing often occurs as part of a symptom cluster in functional constipation, rather than as an isolated symptom. Modern lifestyle factors show noteworthy patterns: dietary habits (whole grain, green leafy vegetables, and boiled vegetables/oatmeal consumption) demonstrate moderate positive correlations with each other (0.29–0.95), while physical characteristics (height, weight, BMI) and basic lifestyle factors (water intake, exercise frequency, sleeping patterns) show weak to moderate correlations (0.05–0.18) with bleeding/tearing symptoms. This comprehensive correlation analysis is particularly valuable for understanding how modern lifestyle factors contribute to rectal bleeding/tearing in young adults with functional constipation, potentially enabling better prediction and prevention strategies through lifestyle modifications. The strong symptom correlations also validate the focus on rectal bleeding/tearing as a significant indicator of functional constipation severity in young adults. 3.i. Training Model and its performance analysis Based on the comprehensive analysis of machine learning classifiers for predicting rectal bleeding or tearing during and after bowel movements, the KNeighbors Classifier demonstrated superior performance with 98.86% accuracy, significantly outperforming other models (Table 4 ). This model's excellence is evidenced by its high Kappa statistic (0.944), minimal root mean squared error (0.107), perfect true positive rate (1.00), and impressive ROC area (0.994). While Decision Tree, Random Forest, and XGBoost were initially considered, they were excluded from the final analysis due to their tendencies toward overfitting with this particular medical dataset. Three models tied for second place - Logistic Regression, LinearSVC, and MLP Classifier - each achieving 97.14% accuracy, demonstrating strong but slightly lower performance than KNeighbors. The KNeighbors Classifier's supremacy can be attributed to its ability to effectively handle medical diagnostic data through its instance-based learning approach, which is particularly advantageous when dealing with symptom-based classifications. Its robust performance across all metrics, especially its low false positive rate (0.013) and high precision (0.905), makes it particularly suitable for medical applications where minimizing misdiagnosis is crucial. The remaining models showed decreasing effectiveness: GaussianNB (93.14%), SVC (89.14%), Perceptron (82.86%), and SGD Classifier (70.29%), with their lower performance possibly due to their inability to effectively capture the complex relationships in this specific medical diagnostic context (Figs. 3 & 9 ). 3.ii. Feature Importance Analysis for Predicting Rectal Bleeding Using Multiple ML Models: Based on the feature importance visualizations (Figures shown Fig. 5 – 8 ), the analysis reveals varying rankings of predictors for rectal bleeding/tearing during and after bowel movements across different machine learning models. In the Logistic Regression analysis (Fig. 5 ), 'Pain and discomfort in abdomen', 'Straining on > 25% of defecations', and 'Sensation of incomplete evacuation' emerged as the top three predictors, showing the highest positive coefficient magnitudes. The Linear SVC model (Fig. 6 ) similarly identified 'Pain and discomfort in abdomen' and 'Straining' as crucial predictors, but also emphasized the importance of green leafy vegetable consumption. The MLP Classifier (Fig. 7 ) presented a different perspective, highlighting 'Sensation of incomplete evacuation', 'Sensation of anorectal obstruction/blockage', and 'Pain and discomfort in abdomen' as the most significant features, all with relative importance scores above 9. The Perceptron model (Fig. 8 ) aligned with these findings, showing strong feature importance for 'Sensation of incomplete evacuation', 'Pain and discomfort', and 'Lumpy or hard stool'. Notably, lifestyle factors such as dietary habits (vegetables, whole grains) and physical characteristics (BMI, height) consistently showed lower importance across all models, suggesting that symptomatic factors are more reliable predictors of rectal bleeding/tearing than lifestyle factors in young adults with functional constipation. 4. Discussion The study of 875 participants revealed significant associations between dietary habits and rectal bleeding/tearing during bowel movements. Notably, BMI status showed a significant correlation (p = 0.008), with overweight/obese individuals (12.26%) experiencing more symptoms compared to those with normal weight (5.55%). The consumption patterns of fiber-rich foods showed striking relationships: participants consuming daily boiled vegetables/oatmeal > 50g had significantly lower incidence (0.15%) compared to non-consumers (43.92%, p < 0.001). Our comprehensive analysis of 875 participants yielded significant insights into the relationships between dietary patterns, lifestyle factors, and rectal bleeding in young adults with functional constipation. The findings both support existing literature and provide novel perspectives on prediction and prevention strategies [ 3 ], [ 13 ], [ 14 ], [ 19 ]. The study revealed robust associations between dietary habits and rectal bleeding symptoms. Participants with higher BMI showed significantly increased prevalence of rectal bleeding (12.26% in overweight/obese vs. 5.55% in normal weight, p = 0.008), suggesting weight management may be an important preventive measure [ 20 ], [ 21 ]. Fiber consumption emerged as a critical protective factor, with dramatic differences between high and low consumers. Participants consuming > 50g daily of fibre-rich foods (boiled vegetables/oatmeal) showed minimal bleeding incidence (0.15%) compared to non-consumers (43.92%, p < 0.001). This finding reinforces current clinical guidelines recommending 25g daily fibre for women and 38g for men for haemorrhoid prevention and management [ 22 ], [ 23 ]. The protective effect of whole grain consumption was particularly striking, with complete absence of bleeding symptoms among regular consumers versus 44.81% incidence in non-consumers. These supports implementing whole grain dietary interventions as a first-line preventive strategy [ 6 ], [ 10 ]. This novel study is the first attempt ever taken and our machine learning approach using the KNeighbors Classifier achieved exceptional accuracy (98.86%) in predicting rectal bleeding risk, surpassing previously existing prediction models. The strong performance (ROC area 0.994) suggests potential clinical utility for early risk assessment and prevention. Key predictive features aligned with established clinical indicators are abdominal pain and discomfort, straining during defecation and presence of constipation (44.39% bleeding incidence vs. 0% in non-constipated). The model's high accuracy supports its potential integration into clinical decision support tools, particularly for identifying high-risk patients who may benefit from early intervention with conservative measures such as dietary modification and office-based procedures. The future research studies might focus on the interaction between dietary interventions and traditional treatments like rubber band ligation or sclerotherapy. The role of specific fibre types in symptom prevention might be explored in future studies and also the potential for machine learning models to guide personalized treatment selection is indeed an area worth investigating. The findings from this study suggests a structured approach to rectal bleeding prevention and management. Early dietary intervention focusing on whole grain and fibre-rich foods must be added to the diet patterns. Regular BMI monitoring and weight management counselling is highly recommended for the low risk as well as high risk groups. Implementation of risk prediction tools to identify patients requiring more precise intervention. Integration of lifestyle modifications with standard treatment protocols should be categorized. The predictive performance of our model, combined with clear dietary associations, provides an evidence-based framework for preventive care in this population. 5. Limitation of the study In the current study, models developed for specific demographic groups lack effectiveness across diverse age groups or ethnic backgrounds, emphasizing the need for broader cross-population validation. Most existing models rely on retrospective data, and only a few are designed to predict the onset or progression of rectal bleeding in real-time, an area requiring further development. Additionally, the small sample size remains a concern. While our findings demonstrate strong predictive power, several limitations warrant consideration like the unexpected lack of association between water intake and bleeding symptoms (p = 0.36) contrasts with previous research and may require further investigation. The study's focus on young adults may limit generalizability to other age groups and lastly longitudinal studies are needed to validate the long-term predictive value of our model. 6. Conclusion This study provides compelling evidence regarding the intricate relationships between dietary habits, lifestyle factors, and rectal bleeding/tearing in young adults with functional constipation. The findings demonstrate that inadequate fiber intake, particularly from both soluble (boiled vegetables, whole grains) and insoluble sources (nuts, dried fruits, green leafy vegetables), significantly increases the risk of rectal bleeding. The development of a highly accurate KNeighbors Classifier (98.86% accuracy) represents a significant advancement in predicting rectal bleeding risk, potentially offering clinicians a valuable diagnostic tool. The strong correlations identified between rectal bleeding and other constipation symptoms, coupled with the clear impact of BMI status and dietary patterns, underscore the importance of a holistic approach to prevention and treatment. Furthermore, the feature importance analysis highlighting symptomatic predictors over lifestyle factors provides crucial insights for clinical assessment priorities. These findings have important implications for preventive healthcare strategies among young adults, suggesting that targeted interventions focusing on fiber-rich diet modification and weight management could substantially reduce the incidence of rectal bleeding in this population. Future research should focus on validating these predictive models in diverse populations and investigating the long-term effectiveness of preventive dietary interventions based on these findings. Declarations Acknowledgements The authors thankfully acknowledge all the participants in this study. Joyeta Ghosh gratefully acknowledge Amity university Kolkata for providing the infrastructure support. Ravi Kant thankfully acknowledges the School of Clinical & Experimental Sciences at Faculty of Medicine, University of Southampton for computational resources and IT support. Jyoti Taneja thankfully acknowledge Council of Scientific and Industrial Research (CSIR) India for the research support. Funding Sources The study was not funded by any source of funding. Conflict of Interest There are no conflicts of interest Authors’ Contribution Joyeta Ghosh : Conceptualization, Methodology, Data generation, Data analysis, Data Curation, Writing Original Draft, Reviewing and editing the final draft. Jyoti Taneja: Conceptualization, Writing Original Draft, Reviewing and editing the final draft Ravi Kant : Conceptualization, Methodology, Writing-reviewing-editing original draft, Supervision Data Availability The data presented in this study are available on request from the corresponding author Ethics Statement The present study has been started after getting approval from institutional ethics committee of All India Institute of Hygiene and Public Health, Kolkata and is part of an established project which has also been published (Ghosh et al 2020). Informed Consent Statement Consent has been obtained from each participant before their involvement in this study. References Sabry AO, Sood T ‘Rectal Bleeding’, in StatPearls , Treasure Island (FL): StatPearls Publishing, 2024. Accessed: Nov. 08, 2024. [Online]. Available: http://www.ncbi.nlm.nih.gov/books/NBK563143/ Crosland A, Jones R (1995) ‘Rectal bleeding: prevalence and consultation behaviour’, BMJ , vol. 311, no. 7003, pp. 486–488, Aug. 10.1136/bmj.311.7003.486 Sabry AO, Sood T ‘Rectal Bleeding’, in StatPearls , Treasure Island (FL): StatPearls Publishing, 2024. Accessed: Nov. 08, 2024. [Online]. Available: http://www.ncbi.nlm.nih.gov/books/NBK563143/ Tran DL, Sintusek P (2023) ‘Functional constipation in children: What physicians should know’, World J. Gastroenterol. , vol. 29, no. 8, p. 1261, Feb. 10.3748/wjg.v29.i8.1261 Clemente-Suárez VJ, Beltrán-Velasco AI, Redondo-Flórez L, Martín-Rodríguez A, Tornero-Aguilera JF (2023) ‘Global Impacts of Western Diet and Its Effects on Metabolism and Health: A Narrative Review’, Nutrients , vol. 15, no. 12, p. 2749, Jun. 10.3390/nu15122749 Markland AD, Palsson O, Goode PS, Burgio KL, Busby-Whitehead J, Whitehead WE (May 2013) Association of low dietary intake of fiber and liquids with constipation: evidence from the National Health and Nutrition Examination Survey. Am J Gastroenterol 108(5):796–803. 10.1038/ajg.2013.73 Briguglio M et al (Jan. 2020) Healthy Eating, Physical Activity, and Sleep Hygiene (HEPAS) as the Winning Triad for Sustaining Physical and Mental Health in Patients at Risk for or with Neuropsychiatric Disorders: Considerations for Clinical Practice. Neuropsychiatr Dis Treat 16:55. 10.2147/NDT.S229206 Alowais SA et al (Sep. 2023) Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ 23:689. 10.1186/s12909-023-04698-z Sarraju A, Ward A, Chung S, Li J, Scheinker D, Rodríguez F (2021) ‘Machine learning approaches improve risk stratification for secondary cardiovascular disease prevention in multiethnic patients’, Open Heart , vol. 8, no. 2, p. e001802, Oct. 10.1136/openhrt-2021-001802 Ghosh J, Sanyal P (2024) ‘Development and Performance Analysis of Machine Learning Methods for Predicting the Occurrence of Constipation and its Risk Factors Among College-aged Girls’, Curr. Res. Nutr. Food Sci. J. , vol. 12, no. 3, Sep. Accessed: Nov. 08, 2024. [Online]. Available: https://www.foodandnutritionjournal.org/volume12number3/development-and-performance-analysis-of-machine-learning-methods-for-predicting-the-occurrence-of-constipation-and-its-risk-factors-among-college-aged-girls/ Shakil S, Ghosh J, Singh K, Chaudhury SR (Aug. 2024) Comparative analysis of nutritional status among institutionalised and community-dwelling elderly women and its association with mental health status and cognitive function. J Fam Med Prim Care 13(8):3078. 10.4103/jfmpc.jfmpc_1932_23 Rajput M, Saini SK (2014) Prevalence of constipation among the general population: a community-based survey from India. Gastroenterol Nurs Off J Soc Gastroenterol Nurses Assoc 37(6):425–429. 10.1097/SGA.0000000000000074 Ghosh J, Singh K, Roy Choudhury S, Koner S, Basu N (2022) ‘Impact of Diet and Nutrition on Memory T Cell Development, Maintenance and Function in the Context of Healthy Immune System’, Acta Sci. Nutr. Health , Jul. 10.31080/ASNH.2022.06.1108 Choudhury SR, Ghosh J, Koner S, Singh K, Basu N (2022) ‘Media Influence on Dietary Practices Among Young Adults of Kolkata’, Acta Sci. Nutr. Health , pp. 09–15, Oct. 10.31080/ASNH.2022.06.1123 Steinhoff A et al (Jun. 2023) Early Adolescent Predictors of Young Adults’ Distress and Adaptive Coping During the COVID-19 Pandemic: Findings From a Longitudinal Cohort Study. J Early Adolesc 44(9):1250. 10.1177/02724316231181660 Khullar TH, Kirmayer MH, Dirks MA (Jul. 2021) Relationship dissolution in the friendships of emerging adults: How, when, and why? J Soc Pers Relatsh 38(11):3243. 10.1177/02654075211026015 Machado NC, Dias JT, Weber TK, Gamarra ACQ, de Carvalho M (2023) ‘Overweight/obesity Prevalence and Clinical Features in Children’s Functional Constipation: Descriptive Analysis in a Single Tertiary Center’, J. Transl. Gastroenterol. , vol. 1, no. 2, pp. 67–73, Dec. 10.14218/JTG.2023.00029 Zhang Y, Lin Q, An X, Tan X, Yang L (2022) ‘Factors Associated with Functional Constipation among Students of a Chinese University: A Cross-Sectional Study’, Nutrients , vol. 14, no. 21, p. 4590, Nov. 10.3390/nu14214590 Gholizadeh E, Keshteli AH, Esmaillzadeh A, Feizi A, Adibi P (2021) ‘The Relationship between Functional Constipation and Major Dietary Patterns in Iranian Adults: Findings from the Large Cross-Sectional Population-Based SEPAHAN Study’, Prev. Nutr. Food Sci. , vol. 26, no. 2, pp. 146–156, Jun. 10.3746/pnf.2021.26.2.146 Seo JY et al (Jun. 2023) The risk of colorectal cancer according to obesity status at four-year intervals: a nationwide population-based cohort study. Sci Rep 13:8928. 10.1038/s41598-023-36111-6 Juszczyk K et al (Aug. 2020) High body mass index is associated with an increased overall survival in rectal cancer. J Gastrointest Oncol 11(4):626. 10.21037/jgo-20-48 Alonso-Coello P et al (Jan. 2006) Fiber for the treatment of hemorrhoids complications: a systematic review and meta-analysis. Am J Gastroenterol 101(1):181–188. 10.1111/j.1572-0241.2005.00359.x Brown S et al (Mar. 2022) Guidelines, guidelines and more guidelines for haemorrhoid treatment: A review to sort the wheat from the chaff. Colorectal Dis 24(6):764. 10.1111/codi.16078 Additional Declarations The authors declare no competing interests. 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-5476421","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":379494316,"identity":"1e493ecc-36f3-4b6e-907a-e2126946662e","order_by":0,"name":"Joyeta Ghosh","email":"","orcid":"","institution":"Department of Dietetics and Applied Nutrition, Amity Institute of Applied Sciences (AIAS), Amity University - Kolkata Campus, Major Arterial Road, Action Area II, Kadampukur Village, Rajarhat, Newtown, Kolkata, West Bengal 700135, India.","correspondingAuthor":false,"prefix":"","firstName":"Joyeta","middleName":"","lastName":"Ghosh","suffix":""},{"id":379495246,"identity":"8767ff92-0275-425e-bc80-a0b33c237705","order_by":1,"name":"Jyoti Taneja","email":"","orcid":"","institution":"2Department of Zoology, Daulat Ram College, University of Delhi, Delhi-110007 India","correspondingAuthor":false,"prefix":"","firstName":"Jyoti","middleName":"","lastName":"Taneja","suffix":""},{"id":379495247,"identity":"aeeaa2a6-173b-49e7-8283-203e3aeacbad","order_by":2,"name":"Ravi Kant","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYBAC+wYeAyBlgyTEQ0CLwQGeBAaGhDQGBjYStBwAajlMkhbexs+FP87b88s3H3vAUGPHYHDmAH4t9g38zNIzEm4nzmxjSzdgOJbMYHC2Ab8WOwZ+BmmehNsJBsd4zCQY2A4wGJwn4DBjBt7m3zwJ5+whWv4RocWwgecY0JYDjBtAWhjbDhB2mMFhnjRrnrRkoF/S0iQS+5J5JAl53+B4j/FtHhs7e37mw8ckPnyzk+M7k0DAZczInATCsTIKRsEoGAWjgBgAAApxPDe03hYrAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0007-6348-4638","institution":"Molecular Microbiology, School of Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton SO16 6YD, England","correspondingAuthor":true,"prefix":"","firstName":"Ravi","middleName":"","lastName":"Kant","suffix":""}],"badges":[],"createdAt":"2024-11-18 13:25:35","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-5476421/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5476421/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":69362137,"identity":"c6892404-8a0e-446b-bf66-c44e6608558e","added_by":"auto","created_at":"2024-11-19 14:27:50","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":228748,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003ePredictive Modeling Workflow for Rectal Bleeding Risk in Functional Constipation: Data Processing, Feature Selection, and Model Evaluation\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/3302ee8a4af7dbec20e7e740.jpeg"},{"id":69362564,"identity":"f006fa27-c72b-405e-b6e6-72f928d01361","added_by":"auto","created_at":"2024-11-19 14:35:50","extension":"jpeg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":165464,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eDistribution of age (A), BMI (B) and daily water intake (C) pattern according to their rectal bleeding or tearing during and after bowel movements among targeted respondents (N=875)\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/48a3ae9360b2385eab3a8e94.jpeg"},{"id":69362140,"identity":"b4649acf-cfcf-4fe3-8db4-9ca0e89da213","added_by":"auto","created_at":"2024-11-19 14:27:50","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":76834,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eBoxplot Distribution of Accuracy Scores Across Tested Machine Learning Models for Prediction\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/9233d608ef9e7a90d23735b1.png"},{"id":69362144,"identity":"b012291b-f052-49fb-b21a-1c608c09fee9","added_by":"auto","created_at":"2024-11-19 14:27:51","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":488830,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eGenerated Heatmap Illustrating Correlation Strengths Between Lifestyle, Clinical, and Dietary Factors Associated with Rectal Bleeding Incidence\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/ef22f4a9c2d485acd15be89c.png"},{"id":69362141,"identity":"ab36327d-8284-40ab-9a46-711518421a5b","added_by":"auto","created_at":"2024-11-19 14:27:50","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":162850,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eLogistic Regression Feature Coefficients Demonstrating Impact of Key Attributes on Rectal Bleeding Prediction\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/14cf6446e444b0637ed6ef18.png"},{"id":69362563,"identity":"d8fe8831-3618-41f5-a69b-ea65d1cddc1c","added_by":"auto","created_at":"2024-11-19 14:35:50","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":67157,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eFeature Importance Scores from MLP Classifiers Identifying Key Contributors to Bleeding Risk Prediction\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/a134f9cc2f52e00743100ffb.png"},{"id":69362138,"identity":"03a52208-a38f-4948-8758-a2131fb89616","added_by":"auto","created_at":"2024-11-19 14:27:50","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":109277,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eIdentification of Key Features Using Linear SVC Classifier for Predicting Rectal Bleeding in Study Participants\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image7.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/d3508c824afcdbb6aa157d0c.png"},{"id":69362142,"identity":"c2aa8239-aaef-43aa-babd-7688a203c1a7","added_by":"auto","created_at":"2024-11-19 14:27:50","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":113472,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003ePerceptron Classifier Feature Importance for Predicting Key Factors of Rectal Bleeding\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image8.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/45e148487873ff8b017e624d.png"},{"id":69362145,"identity":"878d6053-7014-445f-8887-65486e7b4b2a","added_by":"auto","created_at":"2024-11-19 14:27:51","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":212243,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003eEvaluation of Performance Across Prediction Models: Accuracy, Sensitivity, and Specificity Estimates\u003c/em\u003e\u003c/p\u003e","description":"","filename":"image9.png","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/a84fbc7ac82ebbea06d6acca.png"},{"id":69363804,"identity":"1d060ec6-8742-40b7-9aaa-c6af34c44dec","added_by":"auto","created_at":"2024-11-19 14:43:52","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2385730,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5476421/v1/c418e801-6b7e-412e-9bd8-4d1216c7f437.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003ePredictive Modeling for Rectal Bleeding Risk in Functional Constipation: Integrating Lifestyle Factors and Machine Learning for Targeted Prevention\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eRectal bleeding, despite being a significant health indicator, is often neglected by young adults due to social stigma and lack of awareness. This issue may range from benign conditions such as anal fissures or haemorrhoids to severe pathologies, including colorectal cancer, especially if unaddressed[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Global studies report that 15\u0026ndash;20% of adults will experience rectal bleeding at some point; however, delayed medical consultation is common due to embarrassment or a misconception that these symptoms are not serious [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e], [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. In young adults, rectal bleeding is commonly linked to functional constipation, a disorder that disrupts normal bowel function and can lead to chronic complications if untreated. Functional constipation, affecting around 16% of adults worldwide, is frequently driven by the demands and behaviours associated with modern lifestyles[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWith the rise of highly processed foods, inadequate dietary fibre, limited physical activity, disrupted sleep, and elevated stress levels, modern lifestyles have been increasingly implicated in gastrointestinal health issues[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Research demonstrates that these lifestyle factors collectively impair digestive health, making individuals more prone to constipation and its associated complications, including rectal bleeding. For instance, individuals with low daily fibre intake (below 25 grams) are three times more likely to experience constipation and subsequent bleeding episodes compared to those who meet dietary fibre recommendations [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Consistent hydration (2\u0026ndash;3 liters per day), good sleep hygiene, and regular physical activity are fundamental for maintaining a healthy gastrointestinal tract, but adherence to these practices can be challenging amidst busy, sedentary lifestyles [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eTo address the multifaceted nature of constipation and its complications, a more individualized approach is essential. This is where artificial intelligence (AI) and machine learning (ML) present new possibilities. Machine learning, a subset of AI, is proving invaluable in health research for building predictive models that consider unique behavioural, dietary, and physiological data[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. With the potential to integrate multiple factors\u0026mdash;such as dietary habits, hydration levels, physical activity, and stress patterns\u0026mdash;machine learning models can forecast individual risk profiles for conditions like rectal bleeding in ways that traditional approaches cannot[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Through this technology, individuals at high risk for rectal bleeding can receive specific dietary and lifestyle recommendations based on their personal risk factors, making prevention both effective and tailored [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. In fact, studies have shown that personalized, AI-driven health recommendations can increase adherence rates by as much as 42% over standard guidelines, suggesting that such tools could be transformative in preventive healthcare [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAn ML-based predictive model for rectal bleeding risk could revolutionize gastrointestinal healthcare by identifying risk factors early on and facilitating preventive action before symptoms escalate. This study, therefore, aims to harness AI to fill a critical gap in preventive healthcare, specifically for young adults experiencing rectal bleeding due to functional constipation. By analysing key lifestyle and dietary factors through advanced ML algorithms, this study not only seeks to identify high-risk individuals but also to contribute actionable insights to support healthier digestive patterns in the broader population.\u003c/p\u003e \u003cp\u003eThe objectives of this study include the development and validation of a robust ML model to predict rectal bleeding risk based on a wide array of lifestyle factors. This research will: (1) assess the contribution of individual lifestyle variables such as dietary patterns, hydration, sleep quality, and BMI, (2) build a predictive model that processes these parameters to forecast bleeding risk with high accuracy, (3) perform feature importance analysis to inform lifestyle adjustments that could mitigate risk, and (4) validate the model's predictive performance using real-world data. By providing an accessible, personalized risk assessment tool, this study aims to empower young adults to take proactive steps toward digestive health improvement, potentially reducing the incidence of rectal bleeding and the related healthcare burden. The study\u0026rsquo;s findings may also support the broader public health goal of promoting preventive care in gastrointestinal health by demonstrating the value of lifestyle modifications in managing functional constipation and associated complications.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003ch3\u003e2.i. Data Source\u003c/h3\u003e\n\u003ch3\u003e2.i.a. Sample Size Calculation\u003c/h3\u003e\n\u003cp\u003eSample size was calculated by taking the previous prevalence of self reported constipation was 24.8% [\u003cspan class=\"CitationRef\"\u003e12\u003c/span\u003e] and using formula n\u0026thinsp;=\u0026thinsp;4pq/L2 (where, p\u0026thinsp;=\u0026thinsp;prevalence of malnutrition, q\u0026thinsp;=\u0026thinsp;100\u0026thinsp;\u0026minus;\u0026thinsp;p, L\u0026thinsp;=\u0026thinsp;15% of p) [\u003cspan class=\"CitationRef\"\u003e13\u003c/span\u003e]. It came out to be 539. During the study period, 875 participants agreed to participate in the study based up on their availability, willing to participate, and according to exclusion criteria.\u003c/p\u003e\n\u003ch3\u003e2.i.b. Study Design\u003c/h3\u003e\n\u003cp\u003eThis observational descriptive study included 875 college girls from Kolkata, West Bengal, India, selected randomly through social media platforms (LinkedIn, WhatsApp, and Facebook). Participants were aged between 18 to 25 years. While the initial traditional evaluation of this study has been published elsewhere, the present study builds upon it by applying machine learning (ML) models and incorporating the Bristol Stool Chart and ROME-III criteria. This research is part of a larger project focused on adults, with institutional ethical clearance obtained from the All India Institute of Hygiene and Public Health, Kolkata, India [\u003cspan class=\"CitationRef\"\u003e14\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eThe study included undergraduate and postgraduate students from their first to fifth year who voluntarily participated and provided informed consent upon turning 18. Exclusion criteria were: (1) individuals with chronic cardiovascular, hematologic, or digestive disorders, and (2) those with significant lesions in other organs. Data collection was conducted from February 2022 to October 2024 using a standardized, pre-tested online questionnaire. The collected data were entered into a Microsoft Excel worksheet and thoroughly reviewed for errors before analysis.\u003c/p\u003e\n\u003ch3\u003e2.i.c. Selection of Predictors\u003c/h3\u003e\n\u003cp\u003eCollege-bound students often experience a challenging transition period that affects both their physical and emotional well-being. During this time, students frequently encounter stressful situations, or \"stressful life events,\" which impact their emotions in various ways [\u003cspan class=\"CitationRef\"\u003e15\u003c/span\u003e]. These include academic pressure, relationship issues, arguments with close friends, romantic breakups, and separation from family [\u003cspan class=\"CitationRef\"\u003e16\u003c/span\u003e]. A particularly worrying trend is students' tendency to ignore serious health symptoms, especially rectal bleeding, often delaying medical attention until the condition becomes severe. Constipation is also prevalent among this population, with many students experiencing infrequent bowel movements, straining, and abdominal discomfort. The study examined 18 key variables affecting functional constipation (FC) in young adults, based on published studies of FC in young people and college-bound students [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e], [\u003cspan class=\"CitationRef\"\u003e18\u003c/span\u003e]. These included factors like bowel movement frequency, presence of rectal bleeding or tearing, stool consistency, dietary habits (including fruit and vegetable intake), water consumption, exercise frequency, sleep patterns, and BMI. Of particular concern is students' reluctance to seek medical help when experiencing rectal bleeding, potentially allowing underlying conditions to worsen. One ROME-III criterion (\"Manual maneuvers on \u0026gt;\u0026thinsp;25% of defecations\") was excluded from analysis due to uniform negative responses across all participants, leaving 21 attributes for final analysis of constipation patterns in this population \u003cstrong\u003e(\u003c/strong\u003eTable\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e\u003cstrong\u003e)\u003c/strong\u003e.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab1\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eExplanation of Questionnaires used as a tool\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eS. No.\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eQuestions\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAttributes used in dataset\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAnswer\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAge\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAge\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAge in number\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBMI status of the participants as per the measurements?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBMI\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Normal BMI,1\u0026thinsp;=\u0026thinsp;Malnutrition)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eWhat type of food habit participants has?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eFood Habit\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Vegetarian,1\u0026thinsp;=\u0026thinsp;Non vegetarian)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHow much water participant took daily?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily Water Intake\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;\u0026gt;\u0026thinsp;2 litr,1\u0026thinsp;=\u0026thinsp;\u0026lt;\u0026thinsp;2 litr)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e5\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eWhat is the frequency of too small bowel movement?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eToo-small bowel movement frequency\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u0026thinsp;=\u0026thinsp;Mild to Moderate; 0\u0026thinsp;=\u0026thinsp;Absent.\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDid the individual have tear or bleeding in the rectal area during or after a bowel movement?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCrying or tearing in the rectal cavity during or after a bowel movement\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;No,1\u0026thinsp;=\u0026thinsp;Yes)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDid the participant feel any abdominal pain or discomfort?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAbdominal pain and discomfort\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Absent,1\u0026thinsp;=\u0026thinsp;Mild to Moderate)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e8\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eWhat type of stool the participants have according to Bristol's Stool consistency Scale?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBristol's Stool consistency Scale\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Type 1,1\u0026thinsp;=\u0026thinsp;Type2,2\u0026thinsp;=\u0026thinsp;Type 3,3\u0026thinsp;=\u0026thinsp;Type4,4\u0026thinsp;=\u0026thinsp;Type 5,5\u0026thinsp;=\u0026thinsp;Type 6,6\u0026thinsp;=\u0026thinsp;Type 7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e9\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eWhat is the frequency of exercise per week?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eFrequency of exercise\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;No exercise,1\u0026thinsp;=\u0026thinsp;1to 2 days per week,2\u0026thinsp;=\u0026thinsp;3to 4 days per week,3\u0026thinsp;=\u0026thinsp;every day)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e10\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDoes the participant do physical exercise without work?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDo you exercise?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;No,1\u0026thinsp;=\u0026thinsp;Yes)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e11\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eWhat are the daily sleeping hours of the participants?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily sleeping hours\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;\u0026gt;\u0026thinsp;6 hours per day,1\u0026thinsp;=\u0026thinsp;\u0026lt;\u0026thinsp;6 hours per day)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e12\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eWhat are the frequencies of fruit consumption?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eFrequency of fruit consumption\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;daily,1\u0026thinsp;=\u0026thinsp;Once/ week ,2\u0026thinsp;=\u0026thinsp;Less than three times/ week,3\u0026thinsp;=\u0026thinsp;rarely)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e13\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHow frequently do you eat green leafy vegetables?\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eConsumption frequency of leafy green vegetables (insoluble fibre)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;every day, 1\u0026thinsp;=\u0026thinsp;once per week, 2\u0026thinsp;=\u0026thinsp;less than three times per week, and 3\u0026thinsp;=\u0026thinsp;seldom)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily nuts/dried fruits/seeds consumption\u0026thinsp;\u0026gt;\u0026thinsp;25 gm\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eConsumption of insoluble fibre rich food\u0026thinsp;\u0026gt;\u0026thinsp;25gm/day\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;No,1\u0026thinsp;=\u0026thinsp;Yes)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily boiled vegetables/oatmeal consumption\u0026thinsp;\u0026gt;\u0026thinsp;50 gm\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eConsumption of soluble fibre rich food\u0026thinsp;\u0026gt;\u0026thinsp;50gm/day\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;No,1\u0026thinsp;=\u0026thinsp;Yes)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e16\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily whole grain consumption\u0026thinsp;\u0026gt;\u0026thinsp;25 gm\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eConsumption of soluble fibre rich food\u0026thinsp;\u0026gt;\u0026thinsp;25 gm/day\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;No,1\u0026thinsp;=\u0026thinsp;Yes)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"4\" align=\"left\"\u003e\n\u003cp\u003eROME III Criteria\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e17\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRestricting on more than 25% of feces\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLimiting more than 25% of bowel movements\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Absent,1\u0026thinsp;=\u0026thinsp;Present)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e18\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eIncomplete evacuation is perceived in more than 25% of defecations\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eIn more than 25% of cases, there is a sense of incomplete evacuation\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Absent,1\u0026thinsp;=\u0026thinsp;Present)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e19\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOver 25% of defecations result in lumpy or hard stool.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMore than 25% of bowel movements result in a lumpy or hard stool.\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Absent,1\u0026thinsp;=\u0026thinsp;Present)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e20\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSensation of anarectal obstruction/blockage on \u0026gt;\u0026thinsp;25% of defecations\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSensation of anarectal obstruction/blockage on \u0026gt;\u0026thinsp;25% of defecations\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Absent,1\u0026thinsp;=\u0026thinsp;Present)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLess than 3 defecation per week\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLess than 3 defecation per week\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e(0\u0026thinsp;=\u0026thinsp;Absent,1\u0026thinsp;=\u0026thinsp;Present)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003ch3\u003e2.i.d. Statistical Analysis and Disease Prediction System\u003c/h3\u003e\n\u003cp\u003eThe research technique or step is shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e. The full research methodology is outlined in the order and detail that follows. It gives the working flowchart a clear comprehension.\u003c/p\u003e\n\u003cp\u003eThe association between two qualitative data was calculated by Pearson\u0026rsquo;s Chi-square test and \u0026lsquo;P\u0026rsquo; value was determined. All the statistical analysis was performed by SPSS software (Statistical Package for Social Sciences version 20.0). \u0026lsquo;P\u0026rsquo; value is equal to or less than 0.05 was considered as statistically significant.\u003c/p\u003e\n\u003ch3\u003e2.ii. Model Construction and Evaluation\u003c/h3\u003e\n\u003ch3\u003e2.ii.a Data Pre-processing\u003c/h3\u003e\n\u003cp\u003eRaw data collected from young adults with functional constipation often contains inherent noise, inconsistencies, and incompleteness that can significantly impact the analysis and final predictions. Data preprocessing is therefore crucial for ensuring reliable machine learning outcomes. The preprocessing steps include handling missing values, dimension reduction, attribute selection, and cleaning of noisy and inconsistent data related to lifestyle factors and bleeding incidents.\u003c/p\u003e\n\u003ch3\u003e2.ii.b Missing Value Computation\u003c/h3\u003e\n\u003cp\u003eThe dataset was initially processed using Weka (Data Mining Tools, Version 3.8.3). Upon loading, missing values were identified in various lifestyle and symptom parameters. These missing values were handled using the Replace Missing Values filter under the unsupervised filter attribute. For numerical data points (such as frequency of bleeding incidents), the mean value was used as a replacement. For nominal values (such as lifestyle categories), the mode was employed as the replacement value.\u003c/p\u003e\n\u003ch3\u003e2.ii.c Outlier Detection and Removal\u003c/h3\u003e\n\u003cp\u003eGiven the sensitive nature of rectal bleeding prediction, outlier detection and removal was crucial. The process followed these steps:\u003c/p\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cp\u003eUtilized Weka's Inter Quartile Range filter to identify extreme values and outliers\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eDivided the dataset into three quartiles (Q1, Q2, Q3)\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eCalculated the Interquartile Range (IQR) using: IQR\u0026thinsp;=\u0026thinsp;Q3 \u0026ndash; Q1\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eDetermined boundaries using:\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ol\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eLower boundary (B\u003csub\u003emin\u003c/sub\u003e)\u0026thinsp;=\u0026thinsp;Q1\u0026ndash;1.5 * IQR\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eUpper boundary (B\u003csub\u003emax\u003c/sub\u003e)\u0026thinsp;=\u0026thinsp;Q3\u0026thinsp;+\u0026thinsp;1.5 * IQR\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eTo address any resulting class imbalance after outlier removal, the Synthetic Minority Oversampling Technique (SMOTE) was applied to maintain balanced representation of bleeding and non-bleeding cases.\u003c/p\u003e\n\u003ch3\u003e2.ii.d Machine Learning Model Implementation\u003c/h3\u003e\n\u003cp\u003eTen prediction models were implemented to analyze the relationship between lifestyle factors and rectal bleeding:1. Random Forest, 2. Logistic Regression, 3. KNeighbors Classifier,4. MLP Classifier, 5. Support Vector Machines, 6. Perceptron,7. Linear SVC,8. Stochastic Gradient Descent,9. Gaussian NB,10. Decision Tree\u003c/p\u003e\n\u003cp\u003eThe dataset (N\u0026thinsp;=\u0026thinsp;875) was split into:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cp\u003eTraining set (70%): 612 samples\u003c/p\u003e\n\u003c/li\u003e\n\u003cli\u003e\n\u003cp\u003eTest set (30%): 263 samples\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eModel validation employed a repeated nested cross-validation approach to prevent overfitting as explained in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab2\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eModel validation employed a repeated nested cross-validation approach to prevent overfitting\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSteps\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eActivity Conducted\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eStage 1\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eHyperparameter Optimization\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eImplemented 10-fold cross-validation\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOptimized model complexity parameters\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAdjusted learning parameters based on validation data\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eStage 2\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePerformance Evaluation\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eApplied optimized parameters from Stage 1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eEvaluated models using:\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAccuracy\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSensitivity\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePrecision\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAUC (Area Under Curve)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAssessed predictor contributions to determine the relative importance of different lifestyle factors in predicting rectal bleeding\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003ctable id=\"Tab3\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eDistribution of the lifestyle, food habit and nutritional status of the respondents and its association with Rectal Bleeding or Tearing During and After Bowel Movements\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eParameters\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eParticipants (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eRectal Bleeding or Tearing During and After Bowel Movements (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eChi-square test\u003c/p\u003e\n\u003cp\u003e(p value)\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eN\u0026thinsp;=\u0026thinsp;875\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eFood habit\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eVegetarian\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e15(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1(6.66)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e14(93.34)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e0.27\u003c/p\u003e\n\u003cp\u003e(p-0.59)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNon-vegetarian\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e860(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e94(10.93)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e766(89.07)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eNutritional Status (BMI)\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNormal\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e180(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e10(5.55)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e170(94.46)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003e6.82\u003c/p\u003e\n\u003cp\u003e(p-0.008)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eUnderweight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e02(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e02(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOverweight / Obesity\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e693(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e85(12.26)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e608(87.74)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eDaily water intake\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;2 L\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e642(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e66(10.28)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e576(89.72)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e0.82\u003c/p\u003e\n\u003cp\u003e(p-0.36)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026gt;\u0026thinsp;2 L\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e233(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e29(12.44)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e204(87.56)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eFrequency of green leafy vegetable consumption\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e28(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e28(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" align=\"left\"\u003e\n\u003cp\u003e5.85\u003c/p\u003e\n\u003cp\u003e(p-0.01)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOnce per week\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e126(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e10(7.93)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e116(92.07)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;3times per week\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e701(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e85(12.12)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e616(87.88)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eVery rarely\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e20(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e20(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eFrequency of fruit consumption\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDaily\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e28(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e28(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" align=\"left\"\u003e\n\u003cp\u003e4.83\u003c/p\u003e\n\u003cp\u003e(p-0.02)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOnce per week\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e126(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e10(7.93)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e116(92.07)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;3times per week\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e710(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e85(11.97)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e625(88.03)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eVery rarely\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e11(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e11(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eDaily sleeping pattern\u003c/strong\u003e:\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026le;\u0026thinsp;6 hours\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e444(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e47(10.58)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e397(89.42)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e0.220\u003c/p\u003e\n\u003cp\u003e(p-0.37)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e7\u0026ndash;8 hours\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e431(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e48(11.14)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e383(88.86)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eDaily nuts/dried fruits/seeds consumption\u0026thinsp;\u0026gt;\u0026thinsp;25 gm\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e659(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e01(0.15)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e658(99.85)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e0.06\u003c/p\u003e\n\u003cp\u003e(p-0.79)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e216(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e94(43.51)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e122(56.49)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eDaily boiled vegetables/oatmeal consumption\u0026thinsp;\u0026gt;\u0026thinsp;50 gm\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e661(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e01(0.15)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e660(99.85)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e320.02\u003c/p\u003e\n\u003cp\u003e(p-0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e214(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e94(43.92)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e120(56.08)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eDaily whole grain consumption\u0026thinsp;\u0026gt;\u0026thinsp;25 gm\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e663(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(0.00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e663(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e212(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e95(44.81)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e117(55.19)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"5\" align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003ePresence of Constipation\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e214(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e95(44.39)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e119(55.61)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003e_-\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e661(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e00(00)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e661(100)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab4\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eApplication of different classification model and their performance in predicting rectal bleeding or tearing during and after bowel movements\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eClassification model applied\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eCorrectly classified Instances\u003c/p\u003e\n\u003cp\u003e(%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eIncorrectly classified instances\u003c/p\u003e\n\u003cp\u003e(%)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eKappa Statistics\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eRoot Mean Squared Error\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eRelative Absolute Error\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eTrue Positive Rate\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eFalse Positive Rate\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003ePrecision\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eF-Measures\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eROC Area\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLogistic Regression\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e97.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.856\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.169\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.000163\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.895\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.019\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.85\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.872\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.938\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSVC\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e89.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e10.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.33\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.00062\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.5\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eKNeighbors\u003c/p\u003e\n\u003cp\u003eClassifier\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e98.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.944\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.107\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.000065\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.013\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.905\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.95\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.994\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eGaussianNB\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e93.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e6.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.723\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.262\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.000392\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.077\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.613\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.76\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.962\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePerceptron\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e82.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e17.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.477\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.414\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.00098\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.192\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.388\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.559\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.904\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eLinearSVC\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e97.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.868\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.169\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.000163\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.032\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.792\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.884\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.984\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSGD Classifier\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e70.29\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e29.71\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.303\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.545\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.001698\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.00\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.333\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.268\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.422\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.833\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMLP Classifier\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e97.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.856\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.169\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.000163\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.895\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.019\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.85\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.872\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.938\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e"},{"header":"3. Results","content":"\u003cp\u003eThis descriptive observational study examined the nutritional, clinical, and other contributing factors to functional constipation in college going youth of India in addition to determining the normal bowel pattern. The study examined the distribution of lifestyle, food habits, and nutritional status among 875 respondents, with particular emphasis on dietary fiber types and their association with rectal bleeding or tearing during and after bowel movements (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The findings revealed striking differences between soluble and insoluble fiber consumption patterns. For soluble fiber sources, participants lacking adequate intake of boiled vegetables/oatmeal (\u0026gt;\u0026thinsp;50g daily) showed significantly higher bleeding rates (43.92%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and those without regular whole grain consumption (\u0026gt;\u0026thinsp;25g) experienced notably higher bleeding incidents (44.81%). Regarding insoluble fiber sources, insufficient consumption of nuts/dried fruits/seeds (\u0026gt;\u0026thinsp;25g daily) was associated with higher bleeding rates (43.51%), while irregular consumption of green leafy vegetables (\u0026lt;\u0026thinsp;3 times per week) showed 12.12% bleeding incidents (p\u0026thinsp;=\u0026thinsp;0.01), and similar patterns were observed with irregular fruit consumption (11.97%, p\u0026thinsp;=\u0026thinsp;0.02). Additional significant associations included BMI status (p\u0026thinsp;=\u0026thinsp;0.008), with overweight/obese individuals showing higher bleeding incidents (12.26%) compared to normal weight (5.55%). The presence of constipation emerged as a critical factor, with 44.39% of constipated individuals experiencing bleeding. Other lifestyle factors such as vegetarian versus non-vegetarian status (p\u0026thinsp;=\u0026thinsp;0.59), daily water intake (p\u0026thinsp;=\u0026thinsp;0.36), and sleeping patterns (p\u0026thinsp;=\u0026thinsp;0.37) showed no significant associations. The results strongly indicate that inadequate intake of both soluble and insoluble fiber sources, along with constipation and higher BMI, are significant risk factors for rectal bleeding or tearing during and after bowel movements. Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presents the distribution patterns of age (A), BMI (B), and daily water intake (C) in relation to the occurrence of rectal bleeding or tearing during and after bowel movements among the targeted respondents.\u003c/p\u003e \u003cp\u003eThe correlation matrix (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e) provides crucial insights into the relationships between rectal bleeding/tearing and various lifestyle and constipation-related factors among young adults with functional constipation. Most significantly, the matrix reveals strong positive correlations (0.75-1.00, shown in dark red) between rectal bleeding/tearing and other constipation symptoms, including presence of constipation, Bristol's Stool consistency Scale, abdominal pain, straining during defecation, and sensation of incomplete evacuation. This interconnection suggests that rectal bleeding/tearing often occurs as part of a symptom cluster in functional constipation, rather than as an isolated symptom. Modern lifestyle factors show noteworthy patterns: dietary habits (whole grain, green leafy vegetables, and boiled vegetables/oatmeal consumption) demonstrate moderate positive correlations with each other (0.29\u0026ndash;0.95), while physical characteristics (height, weight, BMI) and basic lifestyle factors (water intake, exercise frequency, sleeping patterns) show weak to moderate correlations (0.05\u0026ndash;0.18) with bleeding/tearing symptoms. This comprehensive correlation analysis is particularly valuable for understanding how modern lifestyle factors contribute to rectal bleeding/tearing in young adults with functional constipation, potentially enabling better prediction and prevention strategies through lifestyle modifications. The strong symptom correlations also validate the focus on rectal bleeding/tearing as a significant indicator of functional constipation severity in young adults.\u003c/p\u003e\n\u003ch3\u003e3.i. Training Model and its performance analysis\u003c/h3\u003e\n\u003cp\u003eBased on the comprehensive analysis of machine learning classifiers for predicting rectal bleeding or tearing during and after bowel movements, the KNeighbors Classifier demonstrated superior performance with 98.86% accuracy, significantly outperforming other models (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). This model's excellence is evidenced by its high Kappa statistic (0.944), minimal root mean squared error (0.107), perfect true positive rate (1.00), and impressive ROC area (0.994). While Decision Tree, Random Forest, and XGBoost were initially considered, they were excluded from the final analysis due to their tendencies toward overfitting with this particular medical dataset. Three models tied for second place - Logistic Regression, LinearSVC, and MLP Classifier - each achieving 97.14% accuracy, demonstrating strong but slightly lower performance than KNeighbors. The KNeighbors Classifier's supremacy can be attributed to its ability to effectively handle medical diagnostic data through its instance-based learning approach, which is particularly advantageous when dealing with symptom-based classifications. Its robust performance across all metrics, especially its low false positive rate (0.013) and high precision (0.905), makes it particularly suitable for medical applications where minimizing misdiagnosis is crucial. The remaining models showed decreasing effectiveness: GaussianNB (93.14%), SVC (89.14%), Perceptron (82.86%), and SGD Classifier (70.29%), with their lower performance possibly due to their inability to effectively capture the complex relationships in this specific medical diagnostic context (Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e \u0026amp; \u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e9\u003c/span\u003e).\u003c/p\u003e\n\u003ch3\u003e3.ii. Feature Importance Analysis for Predicting Rectal Bleeding Using Multiple ML Models:\u003c/h3\u003e\n\u003cp\u003eBased on the feature importance visualizations (Figures shown Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e), the analysis reveals varying rankings of predictors for rectal bleeding/tearing during and after bowel movements across different machine learning models. In the Logistic Regression analysis (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e), 'Pain and discomfort in abdomen', 'Straining on \u0026gt;\u0026thinsp;25% of defecations', and 'Sensation of incomplete evacuation' emerged as the top three predictors, showing the highest positive coefficient magnitudes. The Linear SVC model (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e) similarly identified 'Pain and discomfort in abdomen' and 'Straining' as crucial predictors, but also emphasized the importance of green leafy vegetable consumption. The MLP Classifier (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e) presented a different perspective, highlighting 'Sensation of incomplete evacuation', 'Sensation of anorectal obstruction/blockage', and 'Pain and discomfort in abdomen' as the most significant features, all with relative importance scores above 9. The Perceptron model (Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e) aligned with these findings, showing strong feature importance for 'Sensation of incomplete evacuation', 'Pain and discomfort', and 'Lumpy or hard stool'. Notably, lifestyle factors such as dietary habits (vegetables, whole grains) and physical characteristics (BMI, height) consistently showed lower importance across all models, suggesting that symptomatic factors are more reliable predictors of rectal bleeding/tearing than lifestyle factors in young adults with functional constipation.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"4. Discussion","content":"\u003cp\u003e The study of 875 participants revealed significant associations between dietary habits and rectal bleeding/tearing during bowel movements. Notably, BMI status showed a significant correlation (p\u0026thinsp;=\u0026thinsp;0.008), with overweight/obese individuals (12.26%) experiencing more symptoms compared to those with normal weight (5.55%). The consumption patterns of fiber-rich foods showed striking relationships: participants consuming daily boiled vegetables/oatmeal\u0026thinsp;\u0026gt;\u0026thinsp;50g had significantly lower incidence (0.15%) compared to non-consumers (43.92%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e \u003cp\u003eOur comprehensive analysis of 875 participants yielded significant insights into the relationships between dietary patterns, lifestyle factors, and rectal bleeding in young adults with functional constipation. The findings both support existing literature and provide novel perspectives on prediction and prevention strategies [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e], [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e], [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. The study revealed robust associations between dietary habits and rectal bleeding symptoms. Participants with higher BMI showed significantly increased prevalence of rectal bleeding (12.26% in overweight/obese vs. 5.55% in normal weight, p\u0026thinsp;=\u0026thinsp;0.008), suggesting weight management may be an important preventive measure [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e], [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Fiber consumption emerged as a critical protective factor, with dramatic differences between high and low consumers. Participants consuming\u0026thinsp;\u0026gt;\u0026thinsp;50g daily of fibre-rich foods (boiled vegetables/oatmeal) showed minimal bleeding incidence (0.15%) compared to non-consumers (43.92%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). This finding reinforces current clinical guidelines recommending 25g daily fibre for women and 38g for men for haemorrhoid prevention and management [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e], [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. The protective effect of whole grain consumption was particularly striking, with complete absence of bleeding symptoms among regular consumers versus 44.81% incidence in non-consumers. These supports implementing whole grain dietary interventions as a first-line preventive strategy [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e], [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThis novel study is the first attempt ever taken and our machine learning approach using the KNeighbors Classifier achieved exceptional accuracy (98.86%) in predicting rectal bleeding risk, surpassing previously existing prediction models. The strong performance (ROC area 0.994) suggests potential clinical utility for early risk assessment and prevention.\u003c/p\u003e \u003cp\u003eKey predictive features aligned with established clinical indicators are abdominal pain and discomfort, straining during defecation and presence of constipation (44.39% bleeding incidence vs. 0% in non-constipated).\u003c/p\u003e \u003cp\u003eThe model's high accuracy supports its potential integration into clinical decision support tools, particularly for identifying high-risk patients who may benefit from early intervention with conservative measures such as dietary modification and office-based procedures.\u003c/p\u003e \u003cp\u003eThe future research studies might focus on the interaction between dietary interventions and traditional treatments like rubber band ligation or sclerotherapy. The role of specific fibre types in symptom prevention might be explored in future studies and also the potential for machine learning models to guide personalized treatment selection is indeed an area worth investigating.\u003c/p\u003e \u003cp\u003eThe findings from this study suggests a structured approach to rectal bleeding prevention and management. Early dietary intervention focusing on whole grain and fibre-rich foods must be added to the diet patterns. Regular BMI monitoring and weight management counselling is highly recommended for the low risk as well as high risk groups. Implementation of risk prediction tools to identify patients requiring more precise intervention. Integration of lifestyle modifications with standard treatment protocols should be categorized.\u003c/p\u003e \u003cp\u003eThe predictive performance of our model, combined with clear dietary associations, provides an evidence-based framework for preventive care in this population.\u003c/p\u003e"},{"header":"5. Limitation of the study","content":"\u003cp\u003eIn the current study, models developed for specific demographic groups lack effectiveness across diverse age groups or ethnic backgrounds, emphasizing the need for broader cross-population validation. Most existing models rely on retrospective data, and only a few are designed to predict the onset or progression of rectal bleeding in real-time, an area requiring further development. Additionally, the small sample size remains a concern. While our findings demonstrate strong predictive power, several limitations warrant consideration like the unexpected lack of association between water intake and bleeding symptoms (p\u0026thinsp;=\u0026thinsp;0.36) contrasts with previous research and may require further investigation. The study's focus on young adults may limit generalizability to other age groups and lastly longitudinal studies are needed to validate the long-term predictive value of our model.\u003c/p\u003e"},{"header":"6. Conclusion","content":"\u003cp\u003eThis study provides compelling evidence regarding the intricate relationships between dietary habits, lifestyle factors, and rectal bleeding/tearing in young adults with functional constipation. The findings demonstrate that inadequate fiber intake, particularly from both soluble (boiled vegetables, whole grains) and insoluble sources (nuts, dried fruits, green leafy vegetables), significantly increases the risk of rectal bleeding. The development of a highly accurate KNeighbors Classifier (98.86% accuracy) represents a significant advancement in predicting rectal bleeding risk, potentially offering clinicians a valuable diagnostic tool. The strong correlations identified between rectal bleeding and other constipation symptoms, coupled with the clear impact of BMI status and dietary patterns, underscore the importance of a holistic approach to prevention and treatment. Furthermore, the feature importance analysis highlighting symptomatic predictors over lifestyle factors provides crucial insights for clinical assessment priorities. These findings have important implications for preventive healthcare strategies among young adults, suggesting that targeted interventions focusing on fiber-rich diet modification and weight management could substantially reduce the incidence of rectal bleeding in this population. Future research should focus on validating these predictive models in diverse populations and investigating the long-term effectiveness of preventive dietary interventions based on these findings.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe authors thankfully acknowledge all the participants in this study. Joyeta Ghosh gratefully acknowledge Amity university Kolkata for providing the infrastructure support.\u0026nbsp;Ravi Kant thankfully acknowledges the School of Clinical \u0026amp; Experimental Sciences at Faculty of Medicine, University of Southampton for computational resources and IT support. Jyoti Taneja thankfully acknowledge Council of Scientific and Industrial Research (CSIR) India for the research support.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding Sources\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was not funded by any source of funding.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of Interest \u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThere are no conflicts of interest\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026rsquo; Contribution\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eJoyeta Ghosh\u003c/strong\u003e: Conceptualization, Methodology, Data generation, Data analysis, Data Curation, Writing Original Draft, Reviewing and editing the final draft.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eJyoti Taneja:\u003c/strong\u003e Conceptualization, Writing Original Draft, Reviewing and editing the final draft\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRavi Kant\u003c/strong\u003e: Conceptualization, Methodology, Writing-reviewing-editing original draft, Supervision\u003c/p\u003e\n\u003ch2\u003e\u003cstrong\u003eData Availability \u0026nbsp;\u0026nbsp;\u003c/strong\u003e\u003c/h2\u003e\n\u003cp\u003eThe data presented in this study are available on request from the corresponding author\u003c/p\u003e\n\u003ch2\u003e\u003cstrong\u003eEthics Statement\u0026nbsp;\u003c/strong\u003e\u003c/h2\u003e\n\u003cp\u003eThe present study has been started after getting approval from institutional ethics committee of All India Institute of Hygiene and Public Health, Kolkata and is part of an established project which has also been published (Ghosh et al 2020).\u003c/p\u003e\n\u003ch2\u003e\u003cstrong\u003eInformed Consent Statement\u0026nbsp;\u003c/strong\u003e\u003c/h2\u003e\n\u003cp\u003eConsent has been obtained from each participant before their involvement in this study.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSabry AO, Sood T \u0026lsquo;Rectal Bleeding\u0026rsquo;, in \u003cem\u003eStatPearls\u003c/em\u003e, Treasure Island (FL): StatPearls Publishing, 2024. Accessed: Nov. 08, 2024. [Online]. Available: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.ncbi.nlm.nih.gov/books/NBK563143/\u003c/span\u003e\u003cspan address=\"http://www.ncbi.nlm.nih.gov/books/NBK563143/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCrosland A, Jones R (1995) \u0026lsquo;Rectal bleeding: prevalence and consultation behaviour\u0026rsquo;, \u003cem\u003eBMJ\u003c/em\u003e, vol. 311, no. 7003, pp. 486\u0026ndash;488, Aug. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1136/bmj.311.7003.486\u003c/span\u003e\u003cspan address=\"10.1136/bmj.311.7003.486\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSabry AO, Sood T \u0026lsquo;Rectal Bleeding\u0026rsquo;, in \u003cem\u003eStatPearls\u003c/em\u003e, Treasure Island (FL): StatPearls Publishing, 2024. Accessed: Nov. 08, 2024. [Online]. Available: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.ncbi.nlm.nih.gov/books/NBK563143/\u003c/span\u003e\u003cspan address=\"http://www.ncbi.nlm.nih.gov/books/NBK563143/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTran DL, Sintusek P (2023) \u0026lsquo;Functional constipation in children: What physicians should know\u0026rsquo;, \u003cem\u003eWorld J. Gastroenterol.\u003c/em\u003e, vol. 29, no. 8, p. 1261, Feb. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3748/wjg.v29.i8.1261\u003c/span\u003e\u003cspan address=\"10.3748/wjg.v29.i8.1261\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eClemente-Su\u0026aacute;rez VJ, Beltr\u0026aacute;n-Velasco AI, Redondo-Fl\u0026oacute;rez L, Mart\u0026iacute;n-Rodr\u0026iacute;guez A, Tornero-Aguilera JF (2023) \u0026lsquo;Global Impacts of Western Diet and Its Effects on Metabolism and Health: A Narrative Review\u0026rsquo;, \u003cem\u003eNutrients\u003c/em\u003e, vol. 15, no. 12, p. 2749, Jun. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/nu15122749\u003c/span\u003e\u003cspan address=\"10.3390/nu15122749\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMarkland AD, Palsson O, Goode PS, Burgio KL, Busby-Whitehead J, Whitehead WE (May 2013) Association of low dietary intake of fiber and liquids with constipation: evidence from the National Health and Nutrition Examination Survey. Am J Gastroenterol 108(5):796\u0026ndash;803. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/ajg.2013.73\u003c/span\u003e\u003cspan address=\"10.1038/ajg.2013.73\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBriguglio M et al (Jan. 2020) Healthy Eating, Physical Activity, and Sleep Hygiene (HEPAS) as the Winning Triad for Sustaining Physical and Mental Health in Patients at Risk for or with Neuropsychiatric Disorders: Considerations for Clinical Practice. Neuropsychiatr Dis Treat 16:55. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2147/NDT.S229206\u003c/span\u003e\u003cspan address=\"10.2147/NDT.S229206\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlowais SA et al (Sep. 2023) Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ 23:689. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12909-023-04698-z\u003c/span\u003e\u003cspan address=\"10.1186/s12909-023-04698-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSarraju A, Ward A, Chung S, Li J, Scheinker D, Rodr\u0026iacute;guez F (2021) \u0026lsquo;Machine learning approaches improve risk stratification for secondary cardiovascular disease prevention in multiethnic patients\u0026rsquo;, \u003cem\u003eOpen Heart\u003c/em\u003e, vol. 8, no. 2, p. e001802, Oct. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1136/openhrt-2021-001802\u003c/span\u003e\u003cspan address=\"10.1136/openhrt-2021-001802\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGhosh J, Sanyal P (2024) \u0026lsquo;Development and Performance Analysis of Machine Learning Methods for Predicting the Occurrence of Constipation and its Risk Factors Among College-aged Girls\u0026rsquo;, \u003cem\u003eCurr. Res. Nutr. Food Sci. J.\u003c/em\u003e, vol. 12, no. 3, Sep. Accessed: Nov. 08, 2024. [Online]. Available: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.foodandnutritionjournal.org/volume12number3/development-and-performance-analysis-of-machine-learning-methods-for-predicting-the-occurrence-of-constipation-and-its-risk-factors-among-college-aged-girls/\u003c/span\u003e\u003cspan address=\"https://www.foodandnutritionjournal.org/volume12number3/development-and-performance-analysis-of-machine-learning-methods-for-predicting-the-occurrence-of-constipation-and-its-risk-factors-among-college-aged-girls/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShakil S, Ghosh J, Singh K, Chaudhury SR (Aug. 2024) Comparative analysis of nutritional status among institutionalised and community-dwelling elderly women and its association with mental health status and cognitive function. J Fam Med Prim Care 13(8):3078. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4103/jfmpc.jfmpc_1932_23\u003c/span\u003e\u003cspan address=\"10.4103/jfmpc.jfmpc_1932_23\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRajput M, Saini SK (2014) Prevalence of constipation among the general population: a community-based survey from India. Gastroenterol Nurs Off J Soc Gastroenterol Nurses Assoc 37(6):425\u0026ndash;429. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/SGA.0000000000000074\u003c/span\u003e\u003cspan address=\"10.1097/SGA.0000000000000074\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGhosh J, Singh K, Roy Choudhury S, Koner S, Basu N (2022) \u0026lsquo;Impact of Diet and Nutrition on Memory T Cell Development, Maintenance and Function in the Context of Healthy Immune System\u0026rsquo;, \u003cem\u003eActa Sci. Nutr. Health\u003c/em\u003e, Jul. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.31080/ASNH.2022.06.1108\u003c/span\u003e\u003cspan address=\"10.31080/ASNH.2022.06.1108\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoudhury SR, Ghosh J, Koner S, Singh K, Basu N (2022) \u0026lsquo;Media Influence on Dietary Practices Among Young Adults of Kolkata\u0026rsquo;, \u003cem\u003eActa Sci. Nutr. Health\u003c/em\u003e, pp. 09\u0026ndash;15, Oct. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.31080/ASNH.2022.06.1123\u003c/span\u003e\u003cspan address=\"10.31080/ASNH.2022.06.1123\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSteinhoff A et al (Jun. 2023) Early Adolescent Predictors of Young Adults\u0026rsquo; Distress and Adaptive Coping During the COVID-19 Pandemic: Findings From a Longitudinal Cohort Study. J Early Adolesc 44(9):1250. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/02724316231181660\u003c/span\u003e\u003cspan address=\"10.1177/02724316231181660\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhullar TH, Kirmayer MH, Dirks MA (Jul. 2021) Relationship dissolution in the friendships of emerging adults: How, when, and why? J Soc Pers Relatsh 38(11):3243. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/02654075211026015\u003c/span\u003e\u003cspan address=\"10.1177/02654075211026015\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMachado NC, Dias JT, Weber TK, Gamarra ACQ, de Carvalho M (2023) \u0026lsquo;Overweight/obesity Prevalence and Clinical Features in Children\u0026rsquo;s Functional Constipation: Descriptive Analysis in a Single Tertiary Center\u0026rsquo;, \u003cem\u003eJ. Transl. Gastroenterol.\u003c/em\u003e, vol. 1, no. 2, pp. 67\u0026ndash;73, Dec. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.14218/JTG.2023.00029\u003c/span\u003e\u003cspan address=\"10.14218/JTG.2023.00029\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Y, Lin Q, An X, Tan X, Yang L (2022) \u0026lsquo;Factors Associated with Functional Constipation among Students of a Chinese University: A Cross-Sectional Study\u0026rsquo;, \u003cem\u003eNutrients\u003c/em\u003e, vol. 14, no. 21, p. 4590, Nov. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/nu14214590\u003c/span\u003e\u003cspan address=\"10.3390/nu14214590\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGholizadeh E, Keshteli AH, Esmaillzadeh A, Feizi A, Adibi P (2021) \u0026lsquo;The Relationship between Functional Constipation and Major Dietary Patterns in Iranian Adults: Findings from the Large Cross-Sectional Population-Based SEPAHAN Study\u0026rsquo;, \u003cem\u003ePrev. Nutr. Food Sci.\u003c/em\u003e, vol. 26, no. 2, pp. 146\u0026ndash;156, Jun. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3746/pnf.2021.26.2.146\u003c/span\u003e\u003cspan address=\"10.3746/pnf.2021.26.2.146\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSeo JY et al (Jun. 2023) The risk of colorectal cancer according to obesity status at four-year intervals: a nationwide population-based cohort study. Sci Rep 13:8928. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41598-023-36111-6\u003c/span\u003e\u003cspan address=\"10.1038/s41598-023-36111-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJuszczyk K et al (Aug. 2020) High body mass index is associated with an increased overall survival in rectal cancer. J Gastrointest Oncol 11(4):626. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21037/jgo-20-48\u003c/span\u003e\u003cspan address=\"10.21037/jgo-20-48\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlonso-Coello P et al (Jan. 2006) Fiber for the treatment of hemorrhoids complications: a systematic review and meta-analysis. Am J Gastroenterol 101(1):181\u0026ndash;188. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/j.1572-0241.2005.00359.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1572-0241.2005.00359.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBrown S et al (Mar. 2022) Guidelines, guidelines and more guidelines for haemorrhoid treatment: A review to sort the wheat from the chaff. Colorectal Dis 24(6):764. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/codi.16078\u003c/span\u003e\u003cspan address=\"10.1111/codi.16078\" 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":true,"hideJournal":true,"highlight":"","institution":"University of Southampton","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":"Rectal bleeding, functional constipation, lifestyle factors, machine learning prediction, dietary habits, young adults","lastPublishedDoi":"10.21203/rs.3.rs-5476421/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5476421/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRectal bleeding is a prevalent but often underreported health concern in young adults, where functional constipation and lifestyle factors can play a pivotal role. This study investigates the influence of contemporary lifestyle factors\u0026mdash;including dietary patterns, fibre intake, physical activity, and BMI\u0026mdash;on rectal bleeding risk in young adults with functional constipation. Using a descriptive observational study design, data were collected from 875 college-aged individuals in India to analyse lifestyle and clinical factors associated with rectal bleeding. A variety of machine learning models were tested to develop an accurate predictive model for bleeding risk assessment. Findings revealed significant correlations between dietary habits and rectal bleeding; individuals consuming less than 50g of boiled vegetables or oatmeal daily experienced bleeding at a rate of 43.92% (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), while low whole grain intake (\u0026gt;\u0026thinsp;25g daily) was linked to a 44.81% bleeding rate. BMI also significantly impacted bleeding risk (p\u0026thinsp;=\u0026thinsp;0.008), with higher incidence among overweight/obese participants. The KNeighbors Classifier was identified as the most effective predictive model, achieving 98.86% accuracy with an ROC area of 0.994, where symptomatic factors outweighed lifestyle factors in predicting bleeding risk. This machine learning model offers a promising tool for early risk identification, supporting lifestyle interventions, particularly in fibre intake and weight management, to reduce bleeding risk in this population.\u003c/p\u003e","manuscriptTitle":"Predictive Modeling for Rectal Bleeding Risk in Functional Constipation: Integrating Lifestyle Factors and Machine Learning for Targeted Prevention","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-19 14:27:45","doi":"10.21203/rs.3.rs-5476421/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":"d21983a6-0e9e-4485-8eb9-3fca54a197eb","owner":[],"postedDate":"November 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":40410979,"name":"Nutrition \u0026 Dietetics"},{"id":40410980,"name":"Artificial Intelligence and Machine Learning"},{"id":40410981,"name":"Women's studies"}],"tags":[],"updatedAt":"2024-11-19T14:27:46+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-19 14:27:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5476421","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5476421","identity":"rs-5476421","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}