Machine Learning Identification of Nutrient Intake Variations across Age Groups in Metabolic Syndrome and Healthy Populations
"> Figure 1
<p>Participant selection and exclusion criteria flowchart. This schematic depicts the process of creating dataset 4 from four attribute-filtered datasets, consolidated into a table via sequence number (seqn), followed by the removal of duplicates, pregnant women, missing, and unreasonable data entries. Unreasonable data are defined as values exceeding five times the standard deviation above the attribute mean. Exclusions also include neither the metabolic syndrome nor the optimal cardiometabolic health population and minors, resulting in 5838 records, comprising 4721 MetS subjects and 1117 with OCH. Dataset 2 encompasses 2532 participants aged ≤44 years post-SMOTE processing. Dataset 3 includes 6910 participants aged ≥45 years, also post-SMOTE. Dataset 1 is derived from dataset 4, featuring 9442 entries post-SMOTE processing.</p> "> Figure 2
<p>Original dataset (dataset 4) analysis. (<b>A</b>) A histogram analyzes the distribution of different age groups, along with the prevalence of OCH versus metabolic syndrome within these groups. (<b>B</b>) The age distribution of subjects with MetS. (<b>C</b>) Examination of the risk ratios of selected social factors (including sex, age, education level, race/ethnicity, and income PIR) to MetS in dataset 4. In the sex row, females are defined as 0, and males are defined as 1. In the age row, all ages 18 and older are included, those aged 44 and under are defined as 0 and those aged 45 and over are defined as 1. In the education level row, education is incremental; specifically, ‘<HS grad’ is defined as 0, ‘HS grad’ is defined as 1, ‘Some college/AA degree’ is defined as 2, and ‘College grad’ is defined as 3. Income, PIR was divided into two groups by their mean (2.47), where less than 2.47 was defined as 0 and greater than or equal to 2.47 was defined as 1. In the race/ethnicity column, we refer to the definitions in the NHANES dataset to place the following: ‘Mexican American’ is defined as 0, ‘Other Hispanic’ as 1, ‘Non-Hispanic White’ as 2, ‘Non-Hispanic Black’ as 3, and ‘Other Race’ as 4. The income PIR column contains the salary level of everyone in the dataset. A coefficient >1 suggests a positive correlation with metabolic syndrome risk, while <1 indicates a negative correlation. The diamond symbol represents the multivariable-adjusted hazard ratio, with width denoting the 95% CI.</p> "> Figure 3
<p>Model selection analysis. (<b>A</b>) Compares the accuracy of four models using dataset 1’s validation set. (<b>B</b>) Assesses the sensitivity and specificity of these models. (<b>C</b>) Shows the precision–recall curve. (<b>D</b>) Illustrates the ROC curve for model evaluation using dataset 1’s validation set.</p> "> Figure 4
<p>Dietary factors: feature importance and <span class="html-italic">p</span>-value distribution. (<b>A</b>) The top 10 feature importance in the XGBoost model for age ≤44. (<b>B</b>) The top 10 feature importance in the XGBoost model for age ≥45. (<b>C</b>) The <span class="html-italic">p</span>-value distribution from two-sided Wald tests, with the Y-axis showing the negative logarithm of each exposure’s <span class="html-italic">p</span>-value. The dotted red line indicates the <span class="html-italic">p</span>-value threshold of 0.01. Significant nutrients negatively associated with metabolic syndrome (HR < 1) are highlighted in green, and those with a positive association (HR > 1) are in red.</p> "> Figure 5
<p>Significant nutritional elements by age group. The white horizontal line represents the average value. (<b>A</b>) Cholesterol as a possible metabolic syndrome-promoting nutrient in patients aged ≤44. (<b>B</b>) Theobromine as a possible metabolic syndrome-inhibiting nutrient in patients aged ≤44. (<b>C</b>) Carbohydrates as possible metabolic syndrome-promoting nutrients in patients aged ≥45. (<b>D</b>) Caffeine as a possible metabolic syndrome-inhibiting nutrient in patients aged ≥45.</p> "> Figure A1
<p>Approach overview. This figure outlines the sequential execution steps of our methodology. Step 1 involves data processing, detailing the handling of temporary dataset 1. In Step 2, we assess four models against five evaluation metrics to determine the most suitable model for selection. Step 3 focuses on feature selection within the dataset, applying feature importance and manual examination to construct a new model. This model undergoes further analysis for feature importance and the impact of feature adjustments.</p> "> Figure A2
<p>Age group dataset comparison. (<b>A</b>,<b>B</b>) Precision–recall and ROC curves for age group ≤44. (<b>C</b>,<b>D</b>) Precision–recall and ROC curves for age group ≥45.</p> "> Figure A3
<p>Model performance comparison across different datasets. It evaluates the effectiveness of models trained with various datasets: “All Age All Nutrition” utilizes a dataset with all nutritional indicators across all ages, “Some Age All Nutrition” uses a dataset with all nutritional indicators for specific age groups, “Some Age Some Nutrition” involves a dataset with selected nutritional indicators for specific ages, and “All Age Some Nutrition” employs a dataset with selected nutritional indicators across all ages. (<b>A</b>) A comparison of four models trained with different datasets for age ≤44. (<b>B</b>) An analysis of the sensitivity and specificity of models in (<b>A</b>). (<b>C</b>) A comparison of four models for age ≥45 trained with different datasets. (<b>D</b>) An evaluation of the sensitivity and specificity of models in (<b>C</b>).</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. Data Collection and Processing
- Waist circumference: >88 cm for women or >102 cm for men.
- Triglycerides: >150 mg/dL.
- HDL-C: <50 mg/dL for women or <40 mg/dL for men.
- Blood pressure: systolic BP ≥ 130 mm Hg or diastolic BP ≥ 85 mmHg.
- Fasting plasma glucose: ≥100 mg/dL.
- Adiposity: BMI < 25 kg/m2 AND waist circumference < 88 cm for women or <102 cm for men.
- Blood glucose: fasting plasma glucose < 100 mg/dL and HbA1c < 5.7%.
- Blood lipids: total cholesterol to HDL ratio < 3.5:1.
- Blood pressure: systolic BP < 120 mmHg, diastolic BP < 80 mmHg.
2.2. Model Selection
2.3. Model Evaluation
2.4. Feature Verification and Screening
2.5. Risk Ratio Analysis
2.6. Final Model Construction
3. Results
3.1. The Impact of Age on the Prevalence of MetS
3.2. Evaluating Machine Learning Techniques for Predicting MetS Risk in Individuals
3.3. Investigating the Impact of Nutritional Intake on MetS
3.4. Feature Importance Analysis in MetS Risk Prediction
3.5. Nutritional Intake and Its Association with MetS
3.6. Model Optimization for Predictive Analysis across Age Groups
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A
Characteristics | Optimal Cardiometabolic Health | Metabolic Syndrome |
---|---|---|
N | 1117 | 4721 |
Sex (men%) | 26.41% | 47.11% |
Age | 30.79 ± 12.79 | 55.67 ± 16.58 |
Weight (kg) | 59.36 ± 8.8 | 90.35 ± 20.9 |
Height (cm) | 166.07 ± 8.89 | 166.76 ± 10.26 |
Upper Arm Length | 35.62 ± 2.34 | 37.67 ± 2.82 |
Arm Circumference | 27.29 ± 2.67 | 35.31 ± 4.79 |
Waist Circumference | 77.2 ± 6.23 | 108.56 ± 13.82 |
Systolic (first reading) | 105.41 ± 7.51 | 132.92 ± 18.74 |
Diastolic (first reading) | 62.91 ± 7.87 | 72.86 ± 12.51 |
Systolic (second reading) | 105.09 ± 7.44 | 131.56 ± 18.24 |
Diastolic (second reading) | 62.93 ± 8.12 | 72.13 ± 12.71 |
Systolic (third reading) | 104.76 ± 7.5 | 130.53 ± 18.1 |
Diastolic (third reading) | 62.91 ± 8.56 | 71.75 ± 13.03 |
Direct HDL-Cholesterol (mg/dL) | 64.1 ± 13.39 | 46.03 ± 13.17 |
Fasting Glucose (mg/dL) | 89.68 ± 6.13 | 117.64 ± 28.93 |
Triglycerides (mg/dL) | 69.38 ± 31.38 | 177.68 ± 98.02 |
Glycohemoglobin (%) | 5.14 ± 0.28 | 5.98 ± 0.92 |
Total Cholesterol (mg/dL) | 169.2 ± 30.79 | 197.39 ± 42.86 |
BMI | 21.45 ± 2.04 | 32.36 ± 6.32 |
Energy (kcal) | 2007.28 ± 766.01 | 1896.51 ± 721 |
Protein (gm) | 76.93 ± 32.44 | 74.67 ± 30.9 |
Carbohydrate (gm) | 250.6 ± 101.1 | 232.49 ± 94.69 |
Total fat (gm) | 74.96 ± 35.03 | 72.86 ± 33.92 |
Total saturated fatty acids (gm) | 24.45 ± 12.78 | 23.59 ± 11.97 |
Total monounsaturated fatty acids (gm) | 27.01 ± 13.55 | 26.27 ± 12.98 |
Total polyunsaturated fatty acids (gm) | 16.78 ± 8.62 | 16.27 ± 8.7 |
Cholesterol (mg) | 255.63 ± 165.17 | 278.21 ± 174.62 |
Dietary fiber (gm) | 15.67 ± 8.13 | 15.6 ± 8.02 |
Vitamin B1 (mg) | 1.55 ± 0.71 | 1.47 ± 0.64 |
Vitamin B2 (mg) | 1.96 ± 0.93 | 1.89 ± 0.86 |
Niacin (mg) | 23.73 ± 10.76 | 22.18 ± 10.02 |
Vitamin B6 (mg) | 1.9 ± 1 | 1.8 ± 0.91 |
Total folate (mcg) | 388.58 ± 192.74 | 360.68 ± 174.72 |
Vitamin B12 (mcg) | 4.5 ± 3.07 | 4.39 ± 3.06 |
Vitamin C (mg) | 83.33 ± 70.11 | 75.41 ± 65.03 |
Calcium (mg) | 901.1 ± 467.3 | 828.81 ± 428.32 |
Phosphorus (mg) | 1272.32 ± 515.23 | 1221.58 ± 495 |
Magnesium (mg) | 273.16 ± 115.77 | 263.04 ± 107.17 |
Iron (mg) | 14.29 ± 6.93 | 13.71 ± 6.54 |
Zinc (mg) | 10.64 ± 5.29 | 10.4 ± 5.15 |
Copper (mg) | 1.19 ± 0.55 | 1.11 ± 0.48 |
Sodium (mg) | 3315.06 ± 1430.18 | 3158.27 ± 1365.69 |
Potassium (mg) | 2426.03 ± 982.38 | 2440.12 ± 949.01 |
Selenium (mcg) | 105.75 ± 47.19 | 103.21 ± 44.84 |
Caffeine (mg) | 110.87 ± 132.83 | 145.71 ± 149.88 |
Theobromine (mg) | 33.7 ± 52.28 | 28.08 ± 46.79 |
Alcohol (gm) | 6.94 ± 15.77 | 5.28 ± 13.97 |
Butanoic (gm) | 0.52 ± 0.42 | 0.45 ± 0.37 |
Hexanoic (gm) | 0.29 ± 0.24 | 0.26 ± 0.22 |
Octanoic (gm) | 0.24 ± 0.19 | 0.21 ± 0.17 |
Decanoic (gm) | 0.44 ± 0.33 | 0.4 ± 0.3 |
Dodecanoic (gm) | 0.72 ± 0.72 | 0.67 ± 0.69 |
Tetradecanoic (gm) | 2.08 ± 1.42 | 1.92 ± 1.31 |
Hexadecanoic (gm) | 13.27 ± 6.72 | 12.95 ± 6.35 |
Octadecanoic (gm) | 6.06 ± 3.25 | 5.94 ± 3.08 |
Hexadecenoic (gm) | 1.09 ± 0.68 | 1.09 ± 0.64 |
Octadecenoic (gm) | 25.14 ± 12.75 | 24.44 ± 12.15 |
Eicosenoic (gm) | 0.25 ± 0.17 | 0.25 ± 0.17 |
Docosenoic (gm) | 0.02 ± 0.04 | 0.02 ± 0.05 |
Octadecadienoic (gm) | 14.82 ± 7.71 | 14.35 ± 7.8 |
Octadecatrienoic (gm) | 1.51 ± 0.87 | 1.49 ± 0.87 |
Octadecatetraenoic (gm) | 0.01 ± 0.02 | 0.01 ± 0.02 |
Eicosatetraenoic (gm) | 0.13 ± 0.09 | 0.14 ± 0.1 |
Eicosapentaenoic (gm) | 0.03 ± 0.06 | 0.03 ± 0.06 |
Docosapentaenoic (gm) | 0.02 ± 0.02 | 0.02 ± 0.02 |
Docosahexaenoic (gm) | 0.06 ± 0.1 | 0.06 ± 0.09 |
Total sugars (gm) | 110.24 ± 61.83 | 102.55 ± 58.97 |
Vitamin E as alpha-tocopherol (mg) | 7.52 ± 4.41 | 6.9 ± 3.99 |
Retinol (mcg) | 384.31 ± 274.36 | 369.12 ± 270.51 |
Vitamin A, RAE (mcg) | 565.87 ± 362 | 535.65 ± 347.02 |
Alpha-carotene (mcg) | 372.35 ± 628.52 | 338.48 ± 589.78 |
Beta-carotene (mcg) | 1952.63 ± 2435.91 | 1786.77 ± 2199.68 |
Beta-cryptoxanthin (mcg) | 83.65 ± 130.46 | 88.74 ± 135.4 |
Lycopene (mcg) | 5408.43 ± 6878.02 | 4747.59 ± 6305.36 |
Lutein + zeaxanthin (mcg) | 1289.21 ± 1675.67 | 1242.74 ± 1651.25 |
Folic acid (mcg) | 190.04 ± 143.47 | 166.34 ± 129.35 |
Food folate (mcg) | 198.39 ± 105.13 | 194.45 ± 96.09 |
Folate, DFE (mcg) | 521.51 ± 282.57 | 477.06 ± 255.61 |
Vitamin K (mcg) | 95.55 ± 90.27 | 89.91 ± 89.54 |
Characteristics | Optimal Cardiometabolic Health | Metabolic Syndrome |
---|---|---|
N | 1266 | 1266 |
Sex (men %) | 25.28% | 50.87% |
Age | 26.74 ± 7.38 | 33.58 ± 7.64 |
Weight (kg) | 59.15 ± 8.46 | 97.81 ± 22.55 |
Height (cm) | 166.03 ± 8.56 | 168.95 ± 10.11 |
Energy (kcal) | 2007.24 ± 749.26 | 2134.5 ± 789.76 |
Protein (gm) | 76.67 ± 31.71 | 82.12 ± 34.3 |
Carbohydrate (gm) | 252.19 ± 98.24 | 265.16 ± 105.83 |
Cholesterol (mg) | 252.33 ± 157.77 | 295.16 ± 184.82 |
Dietary fiber (gm) | 15.47 ± 7.72 | 15.55 ± 8.46 |
Vitamin B1 (mg) | 1.56 ± 0.7 | 1.56 ± 0.71 |
Vitamin B2 (mg) | 1.92 ± 0.92 | 1.91 ± 0.95 |
Vitamin B12 (mcg) | 4.41 ± 2.94 | 4.58 ± 3.17 |
Vitamin C (mg) | 84.03 ± 68.84 | 73.25 ± 67.78 |
Caffeine (mg) | 95.4 ± 113.28 | 128.48 ± 143.28 |
Theobromine (mg) | 32.94 ± 48.9 | 28.27 ± 48.29 |
Alcohol (gm) | 6.47 ± 14.88 | 6.15 ± 15.45 |
Docosenoic (gm) | 0.02 ± 0.04 | 0.03 ± 0.05 |
Octadecatetraenoic (gm) | 0.01 ± 0.02 | 0.01 ± 0.02 |
Eicosatetraenoic (gm) | 0.13 ± 0.09 | 0.15 ± 0.1 |
Docosahexaenoic (gm) | 0.06 ± 0.1 | 0.05 ± 0.09 |
Total sugars (gm) | 110.14 ± 58.69 | 120.73 ± 69.27 |
Vitamin E as alpha-tocopherol (mg) | 7.41 ± 4.23 | 7.26 ± 4.27 |
Retinol (mcg) | 374.91 ± 261.69 | 356.94 ± 264.47 |
Alpha-carotene (mcg) | 361.25 ± 584.17 | 294.8 ± 594.05 |
Beta-cryptoxanthin (mcg) | 84.42 ± 125.49 | 75.86 ± 130 |
Lycopene (mcg) | 5559.89 ± 6875.51 | 5446.79 ± 6597.58 |
Lutein + zeaxanthin (mcg) | 1193.56 ± 1474.42 | 1048.66 ± 1335.73 |
Characteristics | Optimal Cardiometabolic Health | Metabolic Syndrome |
---|---|---|
N | 3455 | 3455 |
Sex (men %) | 23.27% | 45.73% |
Age | 55.25 ± 8.09 | 63.77 ± 10.49 |
Weight (kg) | 59.24 ± 6.82 | 87.62 ± 19.57 |
Height (cm) | 165.01 ± 6.8 | 165.96 ± 10.19 |
Energy (kcal) | 1790.95 ± 531.69 | 1809.31 ± 673.49 |
Protein (gm) | 70.19 ± 23.02 | 71.94 ± 29.09 |
Carbohydrate (gm) | 213.48 ± 64.91 | 220.52 ± 87.27 |
Cholesterol (mg) | 249.82 ± 135.42 | 272 ± 170.34 |
Dietary fiber (gm) | 15.28 ± 6.52 | 15.62 ± 7.86 |
Vitamin B1 (mg) | 1.39 ± 0.51 | 1.44 ± 0.61 |
Vitamin B2 (mg) | 1.99 ± 0.64 | 1.88 ± 0.83 |
Vitamin B12 (mcg) | 4.42 ± 2.53 | 4.32 ± 3.01 |
Vitamin C (mg) | 77.33 ± 52.86 | 76.2 ± 63.99 |
Caffeine (mg) | 195.51 ± 138.81 | 152.03 ± 151.77 |
Theobromine (mg) | 37.65 ± 44.36 | 28.01 ± 46.23 |
Alcohol (gm) | 8.87 ± 13.21 | 4.96 ± 13.37 |
Docosenoic (gm) | 0.03 ± 0.04 | 0.02 ± 0.05 |
Octadecatetraenoic (gm) | 0.01 ± 0.02 | 0.01 ± 0.02 |
Eicosatetraenoic (gm) | 0.12 ± 0.07 | 0.14 ± 0.1 |
Docosahexaenoic (gm) | 0.06 ± 0.07 | 0.06 ± 0.1 |
Total sugars (gm) | 97.17 ± 42.73 | 95.89 ± 53.19 |
Vitamin E as alpha-tocopherol (mg) | 7.66 ± 3.77 | 6.77 ± 3.87 |
Retinol (mcg) | 406.66 ± 221.26 | 373.58 ± 272.59 |
Alpha-carotene (mcg) | 357.35 ± 518.84 | 354.49 ± 587.49 |
Beta-cryptoxanthin (mcg) | 84.73 ± 117.17 | 93.46 ± 137.05 |
Lycopene (mcg) | 3587.05 ± 5068.25 | 4491.39 ± 6176.02 |
Lutein + zeaxanthin (mcg) | 1487.48 ± 1595.76 | 1313.85 ± 1747.49 |
Key | Coefficient | Lower_95_CI | Upper_95_CI | p_Value | p_Value2 | −log p |
---|---|---|---|---|---|---|
Energy (kcal) | 2.09 | 1.45 | 3.01 | 6.80 × 10−5 | p < 0.005 | 4.1673 |
Protein (gm) | 1.87 | 1.25 | 2.79 | 0.00215 | p < 0.005 | 2.6668 |
Carbohydrate (gm) | 1.95 | 1.39 | 2.73 | 0.00012 | p < 0.005 | 3.9265 |
Cholesterol (mg) | 2.35 | 1.65 | 3.34 | 2.06 × 10−6 | p < 0.005 | 5.6871 |
Dietary fiber (gm) | 0.7 | 0.48 | 1.04 | 0.07509 | 0.075 | 1.1244 |
Vitamin C (mg) | 0.55 | 0.36 | 0.84 | 0.00599 | 0.006 | 2.2222 |
Caffeine (mg) | 0.97 | 0.66 | 1.42 | 0.86598 | 0.866 | 0.0625 |
Theobromine (mg) | 0.56 | 0.36 | 0.86 | 0.00796 | 0.008 | 2.0993 |
Alcohol (gm) | 0.67 | 0.44 | 1.01 | 0.05638 | 0.056 | 1.2488 |
Docosenoic (gm) | 1.35 | 0.73 | 2.51 | 0.34161 | 0.342 | 0.4665 |
Octadecatetraenoic (gm) | 0.86 | 0.55 | 1.33 | 0.49389 | 0.494 | 0.3064 |
Eicosatetraenoic (gm) | 2.5 | 1.82 | 3.44 | 1.95 × 10−8 | p < 0.005 | 7.7094 |
Docosahexaenoic (gm) | 0.58 | 0.36 | 0.94 | 0.02848 | 0.028 | 1.5455 |
Total sugars (gm) | 2.38 | 1.68 | 3.38 | 1.08 × 10−6 | p < 0.005 | 5.968 |
Vitamin E as alpha-tocopherol (mg) | 0.67 | 0.44 | 1.02 | 0.05996 | 0.06 | 1.2222 |
Retinol (mcg) | 0.77 | 0.52 | 1.14 | 0.18586 | 0.186 | 0.7308 |
Alpha-carotene (mcg) | 0.29 | 0.16 | 0.52 | 3.40 × 10−5 | p < 0.005 | 4.4688 |
Beta-cryptoxanthin (mcg) | 0.6 | 0.36 | 1.02 | 0.05985 | 0.06 | 1.2229 |
Lycopene (mcg) | 0.93 | 0.65 | 1.33 | 0.68583 | 0.686 | 0.1638 |
Lutein + zeaxanthin (mcg) | 0.22 | 0.11 | 0.42 | 7.64 × 10−6 | p < 0.005 | 5.117 |
Key | Coefficient | Lower_95_CI | Upper_95_CI | p_Value | p_Value2 | −log p |
---|---|---|---|---|---|---|
Energy (kcal) | 2.51 | 1.94 | 3.25 | 2.89 × 10−12 | p < 0.005 | 11.53899 |
Protein (gm) | 3.37 | 2.56 | 4.44 | 6.19 × 10−18 | p < 0.005 | 17.20796 |
Carbohydrate (gm) | 3.28 | 2.44 | 4.39 | 2.21 × 10−15 | p < 0.005 | 14.65522 |
Cholesterol (mg) | 2.23 | 1.76 | 2.83 | 3.38 × 10−11 | p < 0.005 | 10.47107 |
Dietary fiber (gm) | 1.71 | 1.33 | 2.19 | 2.28 × 10−5 | p < 0.005 | 4.642278 |
Vitamin C (mg) | 1.11 | 0.84 | 1.47 | 0.476642 | 0.477 | 0.321807 |
Caffeine (mg) | 0.3 | 0.24 | 0.38 | 3.22 × 10−22 | p < 0.005 | 21.49154 |
Theobromine (mg) | 0.53 | 0.39 | 0.71 | 2.47 × 10−5 | p < 0.005 | 4.607976 |
Alcohol (gm) | 0.29 | 0.2 | 0.41 | 3.58 × 10−12 | p < 0.005 | 11.44574 |
Docosenoic (gm) | 0.43 | 0.27 | 0.7 | 0.000572 | p < 0.005 | 3.242502 |
Octadecatetraenoic (gm) | 1.63 | 1.19 | 2.22 | 0.002036 | p < 0.005 | 2.691272 |
Eicosatetraenoic (gm) | 3.32 | 2.61 | 4.22 | 1.04 × 10−22 | p < 0.005 | 21.98281 |
Docosahexaenoic (gm) | 1.29 | 0.95 | 1.76 | 0.098474 | 0.098 | 1.006681 |
Total sugars (gm) | 1.25 | 0.95 | 1.65 | 0.116162 | 0.116 | 0.934938 |
Vitamin E as alpha-tocopherol (mg) | 0.41 | 0.31 | 0.55 | 3.03 × 10−9 | p < 0.005 | 8.519156 |
Retinol (mcg) | 0.25 | 0.18 | 0.35 | 9.27 × 10−16 | p < 0.005 | 15.03288 |
Alpha-carotene (mcg) | 1.5 | 1.1 | 2.05 | 0.010036 | 0.01 | 1.998431 |
Beta-cryptoxanthin (mcg) | 1.11 | 0.84 | 1.47 | 0.455166 | 0.455 | 0.34183 |
Lycopene (mcg) | 2.42 | 1.94 | 3.01 | 5.61 × 10−15 | p < 0.005 | 14.25066 |
Lutein + zeaxanthin (mcg) | 0.74 | 0.54 | 1.03 | 0.075194 | 0.075 | 1.123818 |
Key | Importance |
---|---|
Weight | 1653 |
Height | 1241 |
Age | 630 |
Retinol | 529 |
Beta-cryptoxanthin | 447 |
Caffeine | 419 |
Vitamin C | 405 |
Dietary fiber | 389 |
Total sugars | 385 |
Alpha-carotene | 373 |
Docosahexaenoic | 342 |
Lycopene | 342 |
Lutein + zeaxanthin | 335 |
Eicosatetraenoic | 327 |
Vitamin E (alpha-tocopherol) | 318 |
Theobromine | 315 |
Cholesterol | 312 |
Docosenoic | 275 |
Carbohydrate | 266 |
Protein | 252 |
Energy | 219 |
Alcohol | 203 |
Octadecatetraenoic | 192 |
Sex | 104 |
Key | Importance |
Weight | 932 |
Height | 775 |
Age | 510 |
Caffeine | 415 |
Lycopene | 379 |
Retinol | 354 |
Alcohol | 325 |
Theobromine | 298 |
Docosenoic | 287 |
Docosahexaenoic | 281 |
Vitamin C | 270 |
Alpha-carotene | 268 |
Total sugars | 261 |
Carbohydrate | 258 |
Dietary fiber | 255 |
Eicosatetraenoic | 240 |
Vitamin E (alpha-tocopherol) | 239 |
Octadecatetraenoic | 231 |
Protein | 223 |
Cholesterol | 212 |
Beta-cryptoxanthin | 199 |
Lutein + zeaxanthin | 193 |
Energy | 152 |
Sex | 50 |
References
- Alberti, K.G.M.; Zimmet, P.; Shaw, J. The Metabolic Syndrome—A New Worldwide Definition. Lancet 2005, 366, 1059–1062. [Google Scholar] [CrossRef]
- Desroches, S.; Lamarche, B. The Evolving Definitions and Increasing Prevalence of the Metabolic Syndrome. Appl. Physiol. Nutr. Metab. 2007, 32, 23–32. [Google Scholar] [CrossRef] [PubMed]
- Ford, E.S.; Giles, W.H.; Mokdad, A.H. Increasing Prevalence of the Metabolic Syndrome among US Adults. Diabetes Care 2004, 27, 2444–2449. [Google Scholar] [CrossRef] [PubMed]
- James, P.T.; Leach, R.; Kalamara, E.; Shayeghi, M. The Worldwide Obesity Epidemic. Obes. Res. 2001, 9, 228S–233S. [Google Scholar] [CrossRef] [PubMed]
- James, P.T. Obesity: The Worldwide Epidemic. Clin. Dermatol. 2004, 22, 276–280. [Google Scholar] [CrossRef] [PubMed]
- Riccardi, G.; Giacco, R.; Rivellese, A.A. Dietary Fat, Insulin Sensitivity and the Metabolic Syndrome. Clin. Nutr. 2004, 23, 447–456. [Google Scholar] [CrossRef] [PubMed]
- Riccardi, G.; Rivellese, A.A. Dietary Treatment of the Metabolic Syndrome—The Optimal Diet. Br. J. Nutr. 2000, 83, S143–S148. [Google Scholar] [CrossRef]
- Salas-Salvadó, J.; Fernández-Ballart, J.; Ros, E.; Martinez-Gonzalez, M.-A.; Fitó, M.; Estruch, R.; Corella, D.; Fiol, M.; Gómez-Gracia, E.; Arós, F. Effect of a Mediterranean Diet Supplemented with Nuts on Metabolic Syndrome Status: One-Year Results of the PREDIMED Randomized Trial. Arch. Intern. Med. 2008, 168, 2449–2458. [Google Scholar] [CrossRef] [PubMed]
- Grundy, S.M.; Cleeman, J.I.; Daniels, S.R.; Donato, K.A.; Eckel, R.H.; Franklin, B.A.; Gordon, D.J.; Krauss, R.M.; Savage, P.J.; Smith, S.C., Jr. Diagnosis and Management of the Metabolic Syndrome: An American Heart Association/National Heart, Lung, and Blood Institute Scientific Statement. Circulation 2005, 112, 2735–2752. [Google Scholar] [CrossRef]
- Kassi, E.; Pervanidou, P.; Kaltsas, G.; Chrousos, G. Metabolic Syndrome: Definitions and Controversies. BMC Med. 2011, 9, 48. [Google Scholar] [CrossRef]
- Trigka, M.; Dritsas, E. Predicting the Occurrence of Metabolic Syndrome Using Machine Learning Models. Computation 2023, 11, 170. [Google Scholar] [CrossRef]
- Chen, M.; Hao, Y.; Hwang, K.; Wang, L.; Wang, L. Disease Prediction by Machine Learning over Big Data from Healthcare Communities. IEEE Access 2017, 5, 8869–8879. [Google Scholar] [CrossRef]
- Ivanović, D.; Kupusinac, A.; Stokić, E.; Doroslovački, R.; Ivetić, D. ANN Prediction of Metabolic Syndrome: A Complex Puzzle That Will Be Completed. J. Med. Syst. 2016, 40, 264. [Google Scholar] [CrossRef]
- Partridge, L.; Deelen, J.; Slagboom, P.E. Facing up to the Global Challenges of Ageing. Nature 2018, 561, 45–56. [Google Scholar] [CrossRef]
- Castro-Barquero, S.; Ruiz-León, A.M.; Sierra-Pérez, M.; Estruch, R.; Casas, R. Dietary Strategies for Metabolic Syndrome: A Comprehensive Review. Nutrients 2020, 12, 2983. [Google Scholar] [CrossRef]
- Xu, H.; Li, X.; Adams, H.; Kubena, K.; Guo, S. Etiology of Metabolic Syndrome and Dietary Intervention. Int. J. Mol. Sci. 2018, 20, 128. [Google Scholar] [CrossRef]
- Chen, T.; Guestrin, C. Xgboost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
- Therneau, T.M.; Grambsch, P.M.; Therneau, T.M.; Grambsch, P.M. The Cox Model; Springer: Cham, Switzerland, 2000; ISBN 1-4419-3161-9. [Google Scholar]
- Lv, K.; Cui, C.; Fan, R.; Zha, X.; Wang, P.; Zhang, J.; Zhang, L.; Ke, J.; Zhao, D.; Cui, Q.; et al. Detection of Diabetic Patients in People with Normal Fasting Glucose Using Machine Learning. BMC Med. 2023, 21, 342. [Google Scholar] [CrossRef]
- Lloyd-Jones, D.M.; Hong, Y.; Labarthe, D.; Mozaffarian, D.; Appel, L.J.; Van Horn, L.; Greenlund, K.; Daniels, S.; Nichol, G.; Tomaselli, G.F. Defining and Setting National Goals for Cardiovascular Health Promotion and Disease Reduction: The American Heart Association’s Strategic Impact Goal through 2020 and beyond. Circulation 2010, 121, 586–613. [Google Scholar] [CrossRef]
- LaValley, M.P. Logistic Regression. Circulation 2008, 117, 2395–2399. [Google Scholar] [CrossRef]
- Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Noble, W.S. What Is a Support Vector Machine? Nat. Biotechnol. 2006, 24, 1565–1567. [Google Scholar] [CrossRef]
- Patro, S.; Sahu, K.K. Normalization: A Preprocessing Stage. arXiv 2015, arXiv:1503.06462. [Google Scholar] [CrossRef]
- Parikh, R.; Mathai, A.; Parikh, S.; Sekhar, G.C.; Thomas, R. Understanding and Using Sensitivity, Specificity and Predictive Values. Indian J. Ophthalmol. 2008, 56, 45–50. [Google Scholar] [CrossRef]
- Huang, J.; Ling, C.X. Using AUC and Accuracy in Evaluating Learning Algorithms. IEEE Trans. Knowl. Data Eng. 2005, 17, 299–310. [Google Scholar] [CrossRef]
- Lobo, J.M.; Jiménez-Valverde, A.; Real, R. AUC: A Misleading Measure of the Performance of Predictive Distribution Models. Glob. Ecol. Biogeogr. 2008, 17, 145–151. [Google Scholar] [CrossRef]
- Hirode, G.; Wong, R.J. Trends in the Prevalence of Metabolic Syndrome in the United States, 2011–2016. JAMA 2020, 323, 2526–2528. [Google Scholar] [CrossRef]
- Ervin, R.B. Prevalence of Metabolic Syndrome among Adults 20 Years of Age and over, by Sex, Age, Race and Ethnicity, and Body Mass Index: United States, 2003–2006. Natl. Health Stat. Rep. 2009, 5, 1–7. [Google Scholar]
- Ahmad, O.B.; Boschi-Pinto, C.; Lopez, A.D.; Murray, C.J.; Lozano, R.; Inoue, M. Age Standardization of Rates: A New WHO Standard; World Health Organ: Geneva, Switzerland, 2001; Volume 9, pp. 1–14. [Google Scholar]
- Abete, I.; Goyenechea, E.; Zulet, M.A.; Martinez, J.A. Obesity and Metabolic Syndrome: Potential Benefit from Specific Nutritional Components. Nutr. Metab. Cardiovasc. Dis. 2011, 21, B1–B15. [Google Scholar] [CrossRef]
- Feldeisen, S.E.; Tucker, K.L. Nutritional Strategies in the Prevention and Treatment of Metabolic Syndrome. Appl. Physiol. Nutr. Metab. 2007, 32, 46–60. [Google Scholar] [CrossRef]
- Gray, A.; Feldman, H.A.; Mckinlay, J.B.; Longcope, C. Age, Disease, and Changing Sex Hormone Levels in Middle-Aged Men: Results of the Massachusetts Male Aging Study. J. Clin. Endocrinol. Metab. 1991, 73, 1016–1025. [Google Scholar] [CrossRef]
- Wu, F.; Zhuang, P.; Zhan, C.; Shen, X.; Jiao, J.; Zhang, Y. Egg and Dietary Cholesterol Consumption and the Prevalence of Metabolic Syndrome: Findings from a Population-Based Nationwide Cohort. J. Acad. Nutr. Diet. 2022, 122, 758–770.e5. [Google Scholar] [CrossRef] [PubMed]
- Wong, S.K.; Chin, K.-Y.; Ima-Nirwana, S. Vitamin C: A Review on Its Role in the Management of Metabolic Syndrome. Int. J. Med. Sci. 2020, 17, 1625–1638. [Google Scholar] [CrossRef] [PubMed]
- Park, S.; Ham, J.-O.; Lee, B.-K. Effects of Total Vitamin A, Vitamin C, and Fruit Intake on Risk for Metabolic Syndrome in Korean Women and Men. Nutrition 2015, 31, 111–118. [Google Scholar] [CrossRef] [PubMed]
- Devasagayam, T.P.A.; Kamat, J.P.; Mohan, H.; Kesavan, P.C. Caffeine as an Antioxidant: Inhibition of Lipid Peroxidation Induced by Reactive Oxygen Species. Biochim. Biophys. Acta (BBA)-Biomembr. 1996, 1282, 63–70. [Google Scholar] [CrossRef]
- Azam, S.; Hadi, N.; Khan, N.U.; Hadi, S.M. Antioxidant and Prooxidant Properties of Caffeine, Theobromine and Xanthine. Med. Sci. Monit. Int. Med. J. Exp. Clin. Res. 2003, 9, BR325-30. [Google Scholar]
- Wu, F.; Liu, R.; Shen, X.; Xu, H.; Sheng, L. Study on the Interaction and Antioxidant Activity of Theophylline and Theobromine with SOD by Spectra and Calculation. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 2019, 215, 354–362. [Google Scholar] [CrossRef] [PubMed]
- Ponce, O.; Benassi, R.; Cesar, T. Orange Juice Associated with a Balanced Diet Mitigated Risk Factors of Metabolic Syndrome: A Randomized Controlled Trial. J. Nutr. Intermed. Metab. 2019, 17, 100101. [Google Scholar] [CrossRef]
- Kreisberg, R.A.; Kasim, S. Cholesterol Metabolism and Aging. Am. J. Med. 1987, 82, 54–60. [Google Scholar] [CrossRef] [PubMed]
- Feldman, H.A.; Longcope, C.; Derby, C.A.; Johannes, C.B.; Araujo, A.B.; Coviello, A.D.; Bremner, W.J.; McKinlay, J.B. Age Trends in the Level of Serum Testosterone and Other Hormones in Middle-Aged Men: Longitudinal Results from the Massachusetts Male Aging Study. J. Clin. Endocrinol. Metab. 2002, 87, 589–598. [Google Scholar] [CrossRef]
- Ferrini, R.L.; Barrett-Connor, E. Sex Hormones and Age: A Cross-Sectional Study of Testosterone and Estradiol and Their Bioavailable Fractions in Community-Dwelling Men. Am. J. Epidemiol. 1998, 147, 750–754. [Google Scholar] [CrossRef]
- Berry, D.C.; Jin, H.; Majumdar, A.; Noy, N. Signaling by Vitamin A and Retinol-Binding Protein Regulates Gene Expression to Inhibit Insulin Responses. Proc. Natl. Acad. Sci. USA 2011, 108, 4340–4345. [Google Scholar] [CrossRef] [PubMed]
- Yang, Q.; Graham, T.E.; Mody, N.; Preitner, F.; Peroni, O.D.; Zabolotny, J.M.; Kotani, K.; Quadro, L.; Kahn, B.B. Serum Retinol Binding Protein 4 Contributes to Insulin Resistance in Obesity and Type 2 Diabetes. Nature 2005, 436, 356–362. [Google Scholar] [CrossRef] [PubMed]
- Reifen, R. Vitamin A as an Anti-Inflammatory Agent. Proc. Nutr. Soc. 2002, 61, 397–400. [Google Scholar] [CrossRef] [PubMed]
- Wolf, J.E. Potential Anti-Inflammatory Effects of Topical Retinoids and Retinoid Analogues. Adv. Ther. 2002, 19, 109–118. [Google Scholar] [CrossRef]
- Amengual, J.; Ribot, J.; Bonet, M.L.; Palou, A. Retinoic Acid Treatment Enhances Lipid Oxidation and Inhibits Lipid Biosynthesis Capacities in the Liver of Mice. Cell. Physiol. Biochem. 2006, 25, 657–666. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Cai, C.; Li, H.; Zhang, L.; Li, J.; Duan, S.; Fang, Z.; Li, C.; Chen, H.; Alharbi, M.; Ye, L.; et al. Machine Learning Identification of Nutrient Intake Variations across Age Groups in Metabolic Syndrome and Healthy Populations. Nutrients 2024, 16, 1659. https://doi.org/10.3390/nu16111659
Cai C, Li H, Zhang L, Li J, Duan S, Fang Z, Li C, Chen H, Alharbi M, Ye L, et al. Machine Learning Identification of Nutrient Intake Variations across Age Groups in Metabolic Syndrome and Healthy Populations. Nutrients. 2024; 16(11):1659. https://doi.org/10.3390/nu16111659
Chicago/Turabian StyleCai, Chenglin, Hongyu Li, Lijia Zhang, Junqi Li, Songqi Duan, Zhengfeng Fang, Cheng Li, Hong Chen, Metab Alharbi, Lin Ye, and et al. 2024. "Machine Learning Identification of Nutrient Intake Variations across Age Groups in Metabolic Syndrome and Healthy Populations" Nutrients 16, no. 11: 1659. https://doi.org/10.3390/nu16111659