Exploring the Relationship between Severity of Intervertebral Disc Degeneration and Dyslipidemia: A Deep Learning Approach

Exploring the Relationship between Severity of Intervertebral Disc Degeneration and Dyslipidemia: A Deep Learning Approach | 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 Article Exploring the Relationship between Severity of Intervertebral Disc Degeneration and Dyslipidemia: A Deep Learning Approach Lei Ding, Rui Gu, Xingyu Liu, Qing Li, Hengyan Cui, Shuang Cheng, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6250034/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Background: Intervertebral disc degeneration (IDD) is a chronic, noninflammatory, degenerative process that occurs in the lumbar spine and surrounding soft tissues. Although dyslipidemia has been proven to be related to degenerative changes in the lumbar spine, its relationship with IDD severity of IDD is not been fully explored and elucidated. This study employed deep learning to improve IDD prediction accuracy and suggest new preventive and therapeutic strategies for clinical application. Methods: We enrolled 369 IDD patients. Serum was collected and analyzed for high-density lipoprotein (HDL-C), low-density lipoprotein (LDL-C), lipoprotein (a), total cholesterol (TC), triglycerides (TG), apolipoprotein A1, apolipoprotein B (APO-B), apolipoprotein E (ApoE), lipoprotein (a) (LP(a)) levels, Apo B/Apo A1 ratio, and other baseline data. IDD was assessed according to the Pfirrmann grading system, and Grades I-III were categorized as low-grade disc degeneration, while Grades III-IV were considered moderate grade, Grades IV-V were considered high grade. We used a deep learning model with ProbSparse Self-Attention and Kolmogorov-Arnold Networks (KAN) to predict the degeneration scores. Moreover, we calculated the SHapley Additive ExPlanations (SHAP) values of the features to evaluate their importance. Results A total of 50 patients are enrolled in the low degeneration group, 179 in the moderate degeneration group, and 165 in the high degeneration group. According to the univariate analysis of the different degeneration groups, there are statistically significant differences in terms of age, low-density lipoprotein, apolipoprotein B, and Apo B/Apo A1 ratio (P <0.001, P = 0.036, and P = 0.046, P = 0.032, respectively, which were smaller than 0.05), but no statistically significant differences in terms of high-density lipoprotein, lipoprotein (a), total cholesterol (TC), triglycerides (TG), apolipoprotein A1, gender, fasting blood glucose concentration, and length of hospital stay (P =0.86, P =0.532, P =0.359, P =0.188, P =0.702, and P =0.348). By employing a deep learning model to assess the influence of various factors on disease severity, and examining the impact of four statistically significant factors (age, LDL, Apo B, and Apo B/Apo A1 ratio) on the severity of lumbar disc degeneration among the three groups, it is determined that age and cholesterol serve as predictors for the severity of intervertebral disc degeneration (IDD).Grouping patients by disc degeneration severity reveals that age significantly influences the moderate degeneration group, whereas Apo B and the Apo B/Apo A1 ratio are most impactful in the high degeneration group.compared between the moderate and high degeneration groups, when LDL-C values are the same, its impact is the greatest in the moderate degeneration group. Conclusion: Age significantly correlates with intervertebral disc degeneration, while the ratios of low-density lipoprotein, apolipoprotein B, and Apo B/Apo A1 are associated with varying degrees of disc degeneration across different groups.Age and cholesterol levels serve as indicators for assessing the severity of intervertebral disc degeneration. Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Dyslipidemia Intervertebral disc degeneration Deep learning Blood lipid Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction Intervertebral disc degeneration (IDD) is a common, chronic, progressive degenerative disease[ 1 , 2 ], with an incidence of approximately 46% in middle-aged and elderly individuals[ 3 ]. This condition seriously affects their quality of life and their physical and mental health[ 4 ]. Currently, the mechanisms of lumbar intervertebral disc degeneration[ 5 , 6 ] include extracellular matrix (ECM) degradation, changes in spinal mechanics, DNA damage, oxidative stress, cell signaling pathway disorders, and cellular senescence. However, the underlying pathological mechanisms have not yet been fully explored. Dyslipidemia is an umbrella term that encompasses all disorders of lipid metabolism[ 7 ]. In the past four decades, the prevalence of dyslipidemia in the Chinese population has increased significantly[ 8 – 11 ] and reached a high level[ 12 ]. Dyslipidemia can lead to systemic metabolic abnormalities. Most of the previous studies on dyslipidemia focused on heart disease, vascularity, and stroke[ 13 – 15 ], and multiple evidences [ 16 ] suggest that dyslipidemia is also a factor in the pathogenesis of other chronic diseases, such as chronic kidney disease, Alzheimer's disease, and osteoporosis. Dyslipidemia has also been one of the research topics of IDD because it accelerates the occurrence of degenerative diseases[ 17 , 18 ], and several studies[ 19 – 22 ] show that dyslipidemia is associated with lumbar disc degeneration and low back pain[ 17 ], and note that lowering lipid levels can effectively alleviate IDD and low back pain. Animal experiments have demonstrated that rats fed a high-cholesterol diet (HCD) exhibit some degenerative characteristics in the lumbar intervertebral disc compared to rats fed a standard diet[ 23 ]. In a study[ 24 ] on the association between metabolic syndrome (overweight OW, hypertension, dyslipidemia, and impaired glucose tolerance) and low back pain, metabolic syndrome has been proven to be associated with global disc degeneration of the spine. Currently, clinical approaches to diagnosing and treating low back pain or IDD primarily focus on corrective measures. However, predictive indicators for the progression of IDD are insufficiently explored, often resulting in patients reaching advanced stages of the condition before seeking medical attention, thereby necessitating invasive treatments like surgery.Although surgical treatment can restore lumbar spine balance and relieve pain to a certain extent, the recovery of these patients after treatment is still unpredictable, and the patients have significant recurrence rates after surgery.Therefore, it is important to explore whether blood lipid indicators can be used as biomarkers to predict disease severity. In recent years, owing to the complexity of medical data, artificial intelligence has become increasingly important in medical big data processing[ 25 – 27 ]. Deep learning and machine learning are comprehensively applied to various problems, such as disease diagnosis, and these facts and considerations motivate us to adopt deep learning to explore the relationship between clinical blood lipid indicators and lumbar degenerative diseases, improve the prediction accuracy of Intervertebral disc degeneration, and rapidly identify patients in the early progress stage, which can provide some new coping ideas for clinical preventive diagnosis and treatments. Materials and methods The Wuxi Hospital of Traditional Chinese Medicine Ethics Committee approved the study and waived the need for written informed consent due to its retrospective design.All procedures adhered to the Declaration of Helsinki. Study population This retrospective study gathered data from 369 patients with lumbar disc degeneration treated at the Department of Orthopedics and Traumatology, Wuxi Hospital of Traditional Chinese Medicine, between January 2023 and June 2024.The inclusion criteria were: (1) low back pain symptoms linked to lumbar spine movements (flexion, extension, lateral flexion, rotation) or postural changes; (2) positive signs of nerve root irritation, such as a straight leg raise test, strengthening test, or femoral traction test; and (3) comprehensive clinical data, including a confirmed low back pain diagnosis and lumbar MRI.Several laboratory tests were conducted, and the examination data remained intact.Exclusion criteria included: (1) patients younger than 18 years, (2) those with prior spinal surgery, and (3) individuals with a history of spinal tumors or tuberculosis.(4) Patients with cancer or those with more serious cardiovascular, liver and kidney, hematopoietic system, thyroid insufficiency, and other primary diseases; (5) pregnant and lactating patients; (6) patients who have used other drugs for the treatments within two weeks, and patients with severe colds; (7) refusal to participate in the investigation; or have mental disorders or behavioral disorders, and cannot persist in completing the investigation. Data Collection Basic patient information, including age, sex, height, weight, lifestyle habits (e.g., sedentary lifestyle), length of hospital stay, and total hospital costs. Serum lipid results Collection Serum samples were collected from 8:00 a.m. to 10:00 a.m. in a fasting vein, and the measured plasma samples were immediately measured using a fully automated biochemistry analyzer (Beckman Coulter AU5800, USA) for the standardized lipid levels. In addition, all subjects were required to undergo liver and kidney function and blood glucose tests. Statistical analysis Statistical analysis of the influencing factors among the three groups with varying degrees of degeneration was conducted using SPSS (version 26.0; SPSS Inc., Chicago, Illinois, USA).The Kolmogorov-Smirnov test assessed stultification data, one-way ANOVA evaluated normality, the Kruskal-Wallis test analyzed non-normality, and the chi-squared test examined count data.Continuous data were expressed as mean ± SD, while count data were presented as the number of cases with percentages. These data were then used in a multivariate analysis to construct a logistic regression model. Determination of the degree of Intervertebral disc degeneration All enrolled patients underwent 1.5 T/3.0 T conventional MRI scans (1.5 T Philips Ingenia or 3.0 T MR system). Two senior physicians (associate chief physicians) graded the sagittal t2-weighted images according to the Pfirrmann grading method. Intervertebral discs (IVDs) were [l1] graded from L1/2 to L5/S1, with the average grade representing the overall severity of IDD. Subjects with a mean degeneration score of Grades I-III were categorized as low-grade disc degeneration, while Grades III-IV were considered moderate grade; Grades IV-V were considered high grade. Deep learning analytics The importance of all factors (age, low-density lipoprotein, APO-B, and Apo B/Apo A1 ratio) on the severity of lumbar disc degeneration was tested using a deep learning model, and the significance of all factor inputs to the feature-importance experiments showed that age and cholesterol were much more important than other factors (features). We evaluated three input data scenarios between the three groups: we used only important features as input data, used all features as input data, and combined important features with all features. Results 1.Table 1 presents the baseline characteristics of the 369 participants in this study, comprising 219 females and 150 males, with an average age of 61.39 years, a mean BMI of 24.74 kg/m², and an average hospitalization duration of 9.38 days (SD = 3.98). 2. Table 2 shows that there were 47 patients in the low degeneration group, 169 in the moderate degeneration group, and 153 in the high degeneration group. The results were as follows: there were statistically significant age differences (P=0.001<0.05), significant <differences in cost(P=0.001<0.05), statistical differences in cost(P=0.0010.05), and no statistically significant differences in sex, lifestyle habits (sedentary), BMI, fasting blood glucose concentration, and length of hospitalization. Table 1: Baseline information of Characteristics Items Statistics Gender Male 150(40.65) Female 219(59.35) Sedentary Lifestyle NO 343(92.95) YES 26(7.05) Age(yr) 61.39±13.45 BMI (kg/m²) 24.74±3.91 HDL (mmol/L) 1.21±0.26 LDL (mmol/L) 2.94±0.81 Cholesterol (mmol/L) 4.70±1.02 Triglycerides (mmol/L) 1.67±0.97 Apo A1 (g/L) 1.29±0.18 Apo B (g/L) 0.93±0.29 Apo B/Apo A1 Ratio 0.74±0.24 Apo E (mg/dL) 4.13±1.31 Lipoprotein(a) (mg/dL) 204.92±205.13 Glucose (mmol/L) 5.22±1.40 Hospital Stay (days) 9.38±3.98 Cost (CNY)) 11472.27±3753.58 Table 2: General Characteristics vs. Degree of Degeneration Items Low Degeneration ( N =47) Moderate Degeneration ( N =169) H igh Degeneration ( N =153) Statistics P -value Gender (Male/Female) 23/24 70/99 57/96 2.11 0.348 Sedentary Lifestyle (No/Yes) Mar-44 155/14 144/9 0.743 0.69 Age (years) 52.98±10.69 58.88±14.20a 66.75±11.07ab 51.025 <0.001 BMI (kg/m²) 25.57±4.52 24.78±3.76 24.43±3.86 2.744 0.254 Fasting Glucose Concentration (mmol/L) 5.03±1.12 5.25±1.64 5.24±1.18 2.259 0.323 Hospital Stay (days) 8.70±2.67 9.01±3.88 9.99±4.35 5.831 0.054 Cost (CNY) 10951.03±4214.33 10915.25±3392.91 12247.67±3870.19 13.134 0.001 Note: Different superscript letters (a, b) indicate significant differences between groups. 3. After the normality test (KS test, large-sample test) of all patients’ baseline characteristics, it was found [l2] that only low-density lipoprotein met [l3] the normality test, and the other baseline features did not meet the normal false premise. Therefore, in the one-way difference analysis, one-way ANOVA was used for low-density lipoprotein, and the Cruscal-Volris (H-K) test was used for the remaining continuous variables. (Additional Table 3) 4.Differential analysis of the blood lipid index under different degeneration groups was performed, except for low-density lipoprotein.A one-way ANOVA was conducted, and the Kruskal-Wallis test (H-value) was applied to other continuous variables.Statistically significant differences were observed among the three groups in low-density lipoprotein, apolipoprotein B, and the Apo B/Apo A1 ratio, with P-values of 0.036, 0.046, and 0.032, respectively.Statistically significant LDL concentrations were observed in both mild and severe degeneration, as well as moderate and severe degeneration (P=0.036).Apolipoprotein B showed a significant association with moderate to severe degeneration (P=0.046).Statistically significant differences were observed in Apo B/Apo A1 ratios for moderate and severe degeneration (P=0.032), while no significant differences were found in high-density lipoprotein, cholesterol, triglycerides, apolipoprotein A1, apolipoprotein E, and lipoprotein (a) across varying degrees of degeneration.(Additional Table 4) Table 3: Normality Test of Baseline Characteristics by Different Degrees of Degeneration Items Degeneration Degree (Low=1, Moderate =2, High=3) KS Statistic P =- value Age 1 0.102 0.200* 2 0.094 0.001 3 0.127 0.000 BMI Index 1 0.177 0.001 2 0.087 0.003 3 0.097 0.001 HDL 1 0.151 0.009 2 0.123 0.000 3 0.076 0.029 LDL 1 0.122 0.076 2 0.061 0.200* 3 0.036 0.200* Cholesterol 1 0.103 0.200* 2 0.090 0.002 3 0.082 0.013 Triglycerides 1 0.136 0.029 2 0.132 0.000 3 0.187 0.000 Apo A1 1 0.104 0.200* 2 0.078 0.014 3 0.051 0.200* Apo B 1 0.103 0.200* 2 0.085 0.005 3 0.070 0.061 Apo B/Apo A1 1 0.084 0.200* 2 0.077 0.016 3 0.078 0.024 Apo E 1 0.135 0.033 2 0.088 0.003 3 0.164 0.000 Lipoprotein(a) 1 0.210 0.000 2 0.199 0.000 3 0.168 0.000 Glucose 1 0.213 0.000 2 0.245 0.000 3 0.161 0.000 Hospital Stay (days) 1 0.158 0.005 2 0.123 0.000 3 0.113 0.000 Cost 1 0.174 0.001 2 0.054 0.200* 3 0.084 0.011 Note: An asterisk (*) indicates a non-significant P value. Table 4: Comparison of Baseline Characteristics among Different Degrees of Degeneration Items Low Degeneration ( N =47) Moderate Degeneration ( N =169) High Degeneration ( N =153) Statistics P-value HDL (mmol/L) 1.24±0.27 1.21±0.26 1.20±0.25 0.302 0.86 LDL (mmol/L) 3.09±0.78 3.01±0.78 2.81±0.83ab 3.367 0.036 Cholesterol (mmol/L) 4.80±0.95 4.74±0.94 4.63±1.12 2.049 0.359 Triglycerides (mmol/L) 1.76±0.94 1.69±0.88 1.61±1.07 3.345 0.188 Apo A1 (g/L) 1.29±0.17 1.29±0.18 1.29±0.17 0.708 0.702 Apo B (g/L) 0.98±0.29 0.96±0.29 0.89±0.29b 6.137 0.046 Apo B/Apo A1 Ratio 0.77±0.23 0.76±0.24 0.70±0.24b 6.876 0.032 Apo E (mg/dL) 4.08±1.21 4.20±1.26 4.08±1.39 0.853 0.653 Lipoprotein(a) (mg/dL) 173.64±145.85 204.08±214.00 215.46±210.72 1.261 0.532 Note: a indicates pairwise comparison with Degeneration - Mild; b indicates pairwise comparison with Degeneration - Severe. 5. Lipid analysis based on deep learning The main Idea of our proposed learning model is to harness a critical subset of data to extract the predominant features, while leveraging the complete dataset to capture the nuanced details of features. The model primarily consists of a feature extraction module and a feature fusion module. The feature extraction module is composed of ProbSparse Self-Attention modules[28], and the feature fusion module is constituted by KAN modules. Specifically, one instance of the ProbSparse Self-Attention module is configured to distill the salient feature interactions within a critical subset of input data, the other one is employed to extract the interactions within all input data. The subsequent integration of the outputs of ProbSparse Self-Attention modules is facilitated through a feature fusion module, which employs Kolmogorov-Arnold Networks (KAN)[29] modules to substitute the conventional linear layer. This strategic substitution aims at augmenting the model capacity for precise fitting, thus enhancing the overall model performance. We use the metric of SHAP (SHapley Additive exPlanations) to measure the importance of features to the model output (prediction results). SHAP values are derived from cooperative game theory and obtained based on Shapley values. We constructed a model to analyze the SHAP value of each feature for disease severity by inputting all indicators in blood lipids and baseline indicators, such as (age and BMI). To evaluate the impact of combining important features on the prediction results, we designed three input data scenarios: (1) only important features are used as input data; (2) all features are used as input data; (3) a combination of important features with all features. The experimental findings indicate that, as shown in Figure 2, age and cholesterol (CHOL) are more significant than other features in assessing lumbar disc degeneration.(2) From Figures 2 and 3, we find that the MSE loss values are approximately the same under the three input data scenarios, which indicates that the choice of input data scenario has little impact on the prediction accuracy of the model.(3) In general, when the severity of IDDs is not graded, we can combine the cholesterol level in the blood lipid value and the age of the patient to comprehensively predict the severity. Discussion With the economic development of China and changes in people's diet and work styles, the incidence of overweight/obese patients is rapidly increasing, and an increasing number of people are suffering from metabolic diseases[ 30 ]. Spinal degeneration researchers have increasingly focused on dyslipidemia as a key area of interest in recent times[ 31 ]. It is widely recognized that dyslipidemia can lead to spinal degeneration through segmental atherosclerosis of the lumbar arteries; however, the effect of lipids on the occurrence and development of lumbar disc degeneration is still unclear. In a recent review of Rheumatoid Arthritis (RA) and lipid abnormalities, it is noted[ 32 , 33 ] that the systemic inflammatory state in the early stages of RA leads to abnormal lipid metabolism, and lipid abnormalities can reinforce the autoimmune, inflammatory, and cardiovascular risks of rheumatoid arthritis. The study[ 34 ]followed up patients for 6 months after PLIF/TLIF and found that patients treated with statins for high cholesterol had a reduced incidence of pseudo arthropathy compared with those treated with no medication[ 13 ]. A meta-analysis suggested that dyslipidemia could be a risk factor for disc degeneration and herniation[ 35 ]. Previously, a long-term (2012–2022) National Health and Nutrition Survey[ 36 ] in Korea reported that dyslipidemia was positively associated with the incidence of chronic low back pain, and treatment of dyslipidemia may help reduce the risk of chronic low back pain later in life. These clinical studies have shown that there is a clear correlation between dyslipidemia and lumbar degenerative diseases, that is, dyslipidemia could be a risk factor for the occurrence and development of IDD. Nevertheless, there is minimal discourse on how specific lipid constituents may affect the progression of the disease[ 15 , 24 ]. In recent years, researchers have increasingly focused on certain unconventional blood lipid indices and ratios, including apolipoprotein B (APO-B), apolipoprotein E (ApoE), and the Apo B/Apo A1 ratio. Recent studies on dyslipidemia have demonstrated that the risk level of vascular disease can be more accurately assessed using APO B and LP (A), and it is now recommended that these two indicators should be included in the criteria for assessing lipid abnormalities[ 37 , 38 ]. As early as 1999, some scientists mentioned that the Apo B/Apo A1 ratio is related to spine health[ 37 ], and an elevated Apo B/Apo A1 ratio is a potential risk factor for osteonecrosis. A cross-sectional study in 2021[ 38 ] also reported that elevated Apo B/Apo AI levels were associated with an increased risk of IDD. The results also showed that the Apo B/Apo A1 ratio was associated with the degree of intervertebral degeneration among the different groups, which provides a new research perspective on blood lipid indices and spinal health. In addition, because of the convenience of serum lipid testing and the potential of being a biomarker, if the relationship between intervertebral disc degeneration and dyslipidemia can be explored, multidimensional early diagnosis and treatment of intervertebral disc degeneration can be conducted and improved significantly, and more valuable insights regarding the pathogenesis of intervertebral disc degeneration can be provided for future research. Cholesterol is an important driver of the peripheral inflammatory response and plays an important role in initiating the development of inflammatory states[ 39 ]. In the context of an imbalance in cholesterol homeostasis (e.g., hypercholesterolemia), cholesterol accumulates in macrophages and other immune cells, thereby promoting inflammation[ 40 ]. The pathological mechanism underlying lumbar degeneration[ 18 ] is closely associated with peripheral inflammation. The results of deep learning algorithms also proved that cholesterol is related to the degree of lumbar disc degeneration, and that cholesterol can promote IDD has been validated in both in vitro and in vivo experiments. Unfortunately, there was no statistically significant difference between cholesterol and IDD severity in the data analysis of this study, which is contrary to the previous findings of other researchers; therefore, we consider that the reason for these differences may be that the sample distribution is middle-aged and elderly samples, and the group has poor control of lipids. In view of the poor results of this study, our group needs to conduct an intervention study on patients with intervertebral disc degeneration and cholesterol abnormalities in the future, increase the collection of follow-up information, and further investigate whether cholesterol is related to intervertebral disc degeneration. In this study, we developed a deep learning model to investigate the impact of various dyslipidemia parameters on predicting the severity of lumbar degeneration. As SHAP (SHAPLEY Additive explanation) provides a clear and comprehensive method for assessing the contribution of individual features to model output, we employed SHAP as a metric to quantify the importance of features in relation to the predictions of the model. We analyzed the effects of four statistically significant factors (age, low-density lipoprotein, APO-B, and Apo B/Apo A1 ratio) on the severity of lumbar disc degeneration among the three groups and found that in the low degeneration group, age was negatively correlated with disease severity, and LDL-C, APO-B, and Apo B/Apo A1 ratios were positively correlated with disease severity. In the moderate degeneration group, age and LDL-C levels were positively correlated with disease severity, whereas APO-B and Apo B/Apo A1 ratios were negatively correlated with disease severity. In the high degeneration group, all four factors were positively correlated with the degree of disease. In addition, it should be noted that age had the greatest effect on disease severity in the moderate degeneration group, whereas the APO-B and Apo B/Apo A1 ratios had the greatest effect in the high degeneration group. The LDL-C value had a greater effect in the moderate degeneration group when the LDL-C value was the same in the moderate and high degeneration groups. These results are consistent with our previous conclusions. After observing the overall SHAP values in the three groups, we found that the SHAP values of the four factors in the three groups were basically close to zero, indicating that the prediction results are mainly affected by a few factors, and thus we further analyzed the blood lipid level and population degeneration score of patients with degenerative diseases, and analyzed the high-density lipoprotein (HDL-C), low-density lipoprotein (LDL-C), total cholesterol (TC), Triglycerides (TG) and lipoprotein (a), apolipoprotein A1, apolipoprotein B (APO-B), apolipoprotein E (ApoE), lipoprotein (a) (LP (a)), Apo B/Apo A1 ratio, fasting blood glucose level, age, and BMI were used as different features input into the model, and the analysis results showed that the SHAP values of age and CHOL (cholesterol) were significantly higher than those of other features, indicating that age and CHOL have a greater impact on the degree of lumbar disc degeneration. The combination of age and cholesterol level is a preferable predictor of the disease severity. (Additional Fig. 4 ) Abnormal lipid metabolism usually leads to obesity; however, no significant association between BMI and lumbar disc degeneration has been found in previous studies or in the present study. Studies[ 41 – 43 ] have shown the need to distinguish obesity classifications (general obesity/central obesity), and a few clinical studies[ 44 ] have suggested that abdominal fat is a better predictor of the severity of intervertebral disc degeneration than BMI. This study only explored the relationship between BMI and the degree of lumbar disc degeneration and did not include waist circumference, abdominal circumference, leg circumference, etc. in the study variables because the simple BMI value only describes the proportion of the total body fat of an individual and cannot adequately explain the relationship between waist and abdominal fat, muscle proportion, and lumbar disc degeneration. In recent years, an increasing number of researchers[ 45 – 47 ] have focused on the relationship between the paravertebral muscle-fat ratio and lumbar intervertebral disc degeneration. Another limitation of this study is the retrospective study method, if a very long-term study can be conducted, the follow-up data of patients can be increased in the study, and the changes in the degree of lumbar disc degeneration after the control of lipids in patients with dyslipidemia could be observed, and these follow-up data could reveal the prognosis of dyslipidemia metabolism and IDD more comprehensively. In addition, the research focus should also be on the mechanism of lumbar disc degeneration in patients with obesity and diabetes caused by metabolic diseases because BMI and blood glucose concentration in this study have no statistical significance for lumbar disc degeneration, which is worthy of further exploration and research. A large-scale longitudinal follow-up will be conducted to analyze the data on lumbar disc degeneration in patients of different ages and BMI segments. Conclusion Our study indicates that age significantly correlates with disc degeneration severity. Additionally, the levels of low-density lipoprotein, apolipoprotein B, and the Apo B/Apo A1 ratio are associated with disc degeneration. Thus, age and cholesterol metrics can serve as predictors for the severity of disc degeneration.In future clinical practice, managing lipids is crucial for preventing lumbar spine disease in middle-aged and older adults, with treatments focusing on cholesterol, apolipoprotein B, and the Apo B/Apo A1 ratio potentially providing new avenues for managing lumbar degenerative diseases. Declarations Author Contribution D.L. and ZY.H. wrote the main text of the manuscript. R.G and XY.L. organized, managed, and analyzed the collected data, and constructed the analysis model. Q.L. and HY.C provided constructive suggestions for this paper. S.C., YX.S, and TJ.Z collected the clinical data. All authors reviewed the manuscript. They have made substantial, direct, and intellectual contributions to this work and approved its publication. Data Availability All data generated or analyzed during this study are included in this published article and its supplementary information files. References N.N. Knezevic, K.D. Candido, J.W.S. Vlaeyen, J. Van Zundert, S.P. Cohen, Low back pain, Lancet 398(10294) (2021) 78-92. I.L. Mohd Isa, S.L. Teoh, N.H. Mohd Nor, S.A. Mokhtar, Discogenic Low Back Pain: Anatomy, Pathophysiology and Treatments of Intervertebral Disc Degeneration, Int J Mol Sci 24(1) (2022). J. Jiang, J. Huang, H. Deng, H. Liao, X. Fang, X. Zhan, S. Wu, Y. Xue, Current status and time trends of lipid and use of statins among older adults in China-real world data from primary community health institutions, Front Public Health 11 (2023) 1138411. M. Zhang, Q. Deng, L. Wang, Z. Huang, M. Zhou, Y. Li, Z. Zhao, Y. Zhang, L. Wang, Prevalence of dyslipidemia and achievement of low-density lipoprotein cholesterol targets in Chinese adults: A nationally representative survey of 163,641 adults, Int J Cardiol 260 (2018) 196-203. X. Chen, A. Zhang, K. Zhao, H. Gao, P. Shi, Y. Chen, Z. Cheng, W. Zhou, Y. Zhang, The role of oxidative stress in intervertebral disc degeneration: Mechanisms and therapeutic implications, Ageing Res Rev 98 (2024) 102323. S. Kirnaz, C. Capadona, T. Wong, J.L. Goldberg, B. Medary, F. Sommer, L.B. McGrath, Jr., R. Härtl, Fundamentals of Intervertebral Disc Degeneration, World Neurosurg 157 (2022) 264-273. A.J. Berberich, R.A. Hegele, A Modern Approach to Dyslipidemia, Endocr Rev 43(4) (2022) 611-653. W. Yang, J. Xiao, Z. Yang, L. Ji, W. Jia, J. Weng, J. Lu, Z. Shan, J. Liu, H. Tian, Q. Ji, D. Zhu, J. Ge, L. Lin, L. Chen, X. Guo, Z. Zhao, Q. Li, Z. Zhou, G. Shan, J. He, Serum lipids and lipoproteins in Chinese men and women, Circulation 125(18) (2012) 2212-21. Repositioning of the global epicentre of non-optimal cholesterol, Nature 582(7810) (2020) 73-77. L. Pan, Z. Yang, Y. Wu, R.X. Yin, Y. Liao, J. Wang, B. Gao, L. Zhang, The prevalence, awareness, treatment and control of dyslipidemia among adults in China, Atherosclerosis 248 (2016) 2-9. S. Opoku, Y. Gan, E.A. Yobo, D. Tenkorang-Twum, W. Yue, Z. Wang, Z. Lu, Awareness, treatment, control, and determinants of dyslipidemia among adults in China, Sci Rep 11(1) (2021) 10056. J.J. Li, S.P. Zhao, D. Zhao, G.P. Lu, D.Q. Peng, J. Liu, Z.Y. Chen, Y.L. Guo, N.Q. Wu, S.K. Yan, Z.W. Wang, R.L. Gao, 2023 Chinese guideline for lipid management, Front Pharmacol 14 (2023) 1190934. F. Mach, C. Baigent, A.L. Catapano, K.C. Koskinas, M. Casula, L. Badimon, M.J. Chapman, G.G. De Backer, V. Delgado, B.A. Ference, I.M. Graham, A. Halliday, U. Landmesser, B. Mihaylova, T.R. Pedersen, G. Riccardi, D.J. Richter, M.S. Sabatine, M.R. Taskinen, L. Tokgozoglu, O. Wiklund, 2019 ESC/EAS Guidelines for the management of dyslipidaemias: lipid modification to reduce cardiovascular risk, Eur Heart J 41(1) (2020) 111-188. Z. Reiner, A.L. Catapano, G. De Backer, I. Graham, M.R. Taskinen, O. Wiklund, S. Agewall, E. Alegria, M.J. Chapman, P. Durrington, S. Erdine, J. Halcox, R. Hobbs, J. Kjekshus, P.P. Filardi, G. Riccardi, R.F. Storey, D. Wood, ESC/EAS Guidelines for the management of dyslipidaemias: the Task Force for the management of dyslipidaemias of the European Society of Cardiology (ESC) and the European Atherosclerosis Society (EAS), Eur Heart J 32(14) (2011) 1769-818. A. Pirillo, M. Casula, E. Olmastroni, G.D. Norata, A.L. Catapano, Global epidemiology of dyslipidaemias, Nat Rev Cardiol 18(10) (2021) 689-700. C. Li, F. Wang, L. Cui, S. Li, J. Zhao, L. Liao, Association between abnormal lipid metabolism and tumor, Front Endocrinol (Lausanne) 14 (2023) 1134154. U. Lendahl, P. Nilsson, C. Betsholtz, Emerging links between cerebrovascular and neurodegenerative diseases-a special role for pericytes, EMBO Rep 20(11) (2019) e48070. L. Yuan, Z. Huang, W. Han, R. Chang, B. Sun, M. Zhu, C. Li, J. Yan, B. Liu, H. Yin, W. Ye, The impact of dyslipidemia on lumbar intervertebral disc degeneration and vertebral endplate modic changes: a cross-sectional study of 1035 citizens in China, BMC Public Health 23(1) (2023) 1302. W. Li, Z. Ding, H. Zhang, Q. Shi, D. Wang, S. Zhang, S. Xu, B. Gao, M. Yan, The Roles of Blood Lipid-Metabolism Genes in Immune Infiltration Could Promote the Development of IDD, Front Cell Dev Biol 10 (2022) 844395. S. Li, J. Du, Y. Huang, S. Gao, Z. Zhao, Z. Chang, X. Zhang, B. He, From hyperglycemia to intervertebral disc damage: exploring diabetic-induced disc degeneration, Front Immunol 15 (2024) 1355503. J. Chen, J. Yan, S. Li, J. Zhu, J. Zhou, J. Li, Y. Zhang, Z. Huang, L. Yuan, K. Xu, W. Chen, W. Ye, Atorvastatin inhibited TNF-α induced matrix degradation in rat nucleus pulposus cells by suppressing NLRP3 inflammasome activity and inducing autophagy through NF-κB signaling, Cell Cycle 20(20) (2021) 2160-2173. Y. Zhou, X. Chen, Q. Tian, J. Zhang, M. Wan, X. Zhou, X. Xu, X. Cao, X. Zhou, L. Zheng, Deletion of ApoE Leads to Intervertebral Disc Degeneration via Aberrant Activation of Adipokines, Spine (Phila Pa 1976) 47(12) (2022) 899-907. J. Yan, S. Li, Y. Zhang, Z. Deng, J. Wu, Z. Huang, T. Qin, Y. Xiao, J. Zhou, K. Xu, W. Ye, Cholesterol Induces Pyroptosis and Matrix Degradation via mSREBP1-Driven Endoplasmic Reticulum Stress in Intervertebral Disc Degeneration, Front Cell Dev Biol 9 (2021) 803132. Z. Huang, J. Chen, Y. Su, M. Guo, Y. Chen, Y. Zhu, G. Nie, R. Ke, H. Chen, J. Hu, Impact of dyslipidemia on the severity of symptomatic lumbar spine degeneration: A retrospective clinical study, Front Nutr 9 (2022) 1033375. R.C. Deo, Machine Learning in Medicine, Circulation 132(20) (2015) 1920-30. Y. Chen, J. Wang, C. Wang, M. Liu, Q. Zou, Deep learning models for disease-associated circRNA prediction: a review, Brief Bioinform 23(6) (2022). A.A. Theodosiou, R.C. Read, Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician, J Infect 87(4) (2023) 287-294. Y. Xu, M. Gong, J. Chen, T. Liu, K. Zhang, K. Batmanghelich, Generative-Discriminative Complementary Learning, Proc AAAI Conf Artif Intell 34(4) (2020) 6526-6533. M.A.A. Al-Qaness, S. Ni, TCNN-KAN: Optimized CNN by Kolmogorov-Arnold Network and Pruning Techniques for sEMG Gesture Recognition, IEEE J Biomed Health Inform Pp (2024). N.W.S. Chew, C.H. Ng, D.J.H. Tan, G. Kong, C. Lin, Y.H. Chin, W.H. Lim, D.Q. Huang, J. Quek, C.E. Fu, J. Xiao, N. Syn, R. Foo, C.M. Khoo, J.W. Wang, G.K. Dimitriadis, D.Y. Young, M.S. Siddiqui, C.S.P. Lam, Y. Wang, G.A. Figtree, M.Y. Chan, D.E. Cummings, M. Noureddin, V.W. Wong, R.C.W. Ma, C.S. Mantzoros, A. Sanyal, M.D. Muthiah, The global burden of metabolic disease: Data from 2000 to 2019, Cell Metab 35(3) (2023) 414-428.e3. Y. Zhang, Y. Zhao, M. Wang, M. Si, J. Li, Y. Hou, J. Jia, L. Nie, Serum lipid levels are positively correlated with lumbar disc herniation--a retrospective study of 790 Chinese patients, Lipids Health Dis 15 (2016) 80. A.I. Venetsanopoulou, E. Pelechas, P.V. Voulgari, A.A. Drosos, The lipid paradox in rheumatoid arthritis: the dark horse of the augmented cardiovascular risk, Rheumatol Int 40(8) (2020) 1181-1191. A.A. Drosos, A.A. Venetsanopoulou, E. Pelechas, P.V. Voulgari, Exploring Cardiovascular Risk Factors and Atherosclerosis in Rheumatoid Arthritis, Eur J Intern Med 128 (2024) 1-9. M.S. Lavu, N.B. Eghrari, P.S. Makineni, D.C. Kaelber, J.W. Savage, D.W. Pelle, Low-Density Lipoprotein Cholesterol and Statin Usage Are Associated With Rates of Pseudarthrosis Following Single-Level Posterior Lumbar Interbody Fusion, Spine (Phila Pa 1976) 49(6) (2024) 369-377. K. Hoffeld, M. Lenz, P. Egenolf, M. Weber, V. Heck, P. Eysel, M.J. Scheyerer, Patient-related risk factors and lifestyle factors for lumbar degenerative disc disease: a systematic review, Neurochirurgie 69(5) (2023) 101482. S. Kim, S.M. Lee, Dyslipidemia Is Positively Associated with Chronic Low Back Pain in Korean Women: Korean National Health and Nutrition Examination Survey 2010-2012, Healthcare (Basel) 12(1) (2024). K. Miyanishi, T. Yamamoto, T. Irisa, Y. Noguchi, Y. Sugioka, Y. Iwamoto, Increased level of apolipoprotein B/apolipoprotein A1 ratio as a potential risk for osteonecrosis, Ann Rheum Dis 58(8) (1999) 514-6. F. Chen, T. Wu, C. Bai, S. Guo, W. Huang, Y. Pan, H. Zhang, D. Wu, Q. Fu, Q. Chen, X. Li, L. Li, Serum apolipoprotein B/apolipoprotein A1 ratio in relation to intervertebral disk herniation: a cross-sectional frequency-matched case-control study, Lipids Health Dis 20(1) (2021) 79. S.B. Hansen, H. Wang, The shared role of cholesterol in neuronal and peripheral inflammation, Pharmacol Ther 249 (2023) 108486. A.R. Tall, L. Yvan-Charvet, Cholesterol, inflammation and innate immunity, Nat Rev Immunol 15(2) (2015) 104-16. J. Zhu, Y. Zhang, Y. Wu, Y. Xiang, X. Tong, Y. Yu, Y. Qiu, S. Cui, Q. Zhao, N. Wang, Y. Jiang, G. Zhao, Obesity and Dyslipidemia in Chinese Adults: A Cross-Sectional Study in Shanghai, China, Nutrients 14(11) (2022). C. Zheng, Y. Liu, C. Xu, S. Zeng, Q. Wang, Y. Guo, J. Li, S. Li, M. Dong, X. Luo, Q. Wu, Association between obesity and the prevalence of dyslipidemia in middle-aged and older people: an observational study, Sci Rep 14(1) (2024) 11974. X. Shi, L. Chai, D. Zhang, J. Fan, Association between complementary anthropometric measures and all-cause mortality risk in adults: NHANES 2011-2016, Eur J Clin Nutr (2024). M. Wang, H. Yuan, F. Lei, S. Zhang, L. Jiang, J. Yan, D. Feng, Abdominal Fat is a Reliable Indicator of Lumbar Intervertebral Disc Degeneration than Body Mass Index, World Neurosurg 182 (2024) e171-e177. R.J. Crawford, T. Volken, Á. Ni Mhuiris, C.C. Bow, J.M. Elliott, M.A. Hoggarth, D. Samartzis, Geography of Lumbar Paravertebral Muscle Fatty Infiltration: The Influence of Demographics, Low Back Pain, and Disability, Spine (Phila Pa 1976) 44(18) (2019) 1294-1302. B. Rosenstein, J. Burdick, A. Roussac, M. Rye, N. Naghdi, S. Valentin, T. Licka, M. Sean, P. Tétreault, J. Elliott, M. Fortin, The assessment of paraspinal muscle epimuscular fat in participants with and without low back pain: A case-control study, J Biomech 163 (2024) 111928. E.E. Özcan-Ekşi, M. Ekşi, M.A. Akçal, Severe Lumbar Intervertebral Disc Degeneration Is Associated with Modic Changes and Fatty Infiltration in the Paraspinal Muscles at all Lumbar Levels, Except for L1-L2: A Cross-Sectional Analysis of 50 Symptomatic Women and 50 Age-Matched Symptomatic Men, World Neurosurg 122 (2019) e1069-e1077. Additional Declarations No competing interests reported. Supplementary Files Rawdata.xlsx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 08 Sep, 2025 Reviews received at journal 29 Jul, 2025 Reviewers agreed at journal 15 Jul, 2025 Reviews received at journal 30 May, 2025 Reviewers agreed at journal 21 May, 2025 Reviews received at journal 21 May, 2025 Reviewers agreed at journal 06 May, 2025 Reviewers invited by journal 06 May, 2025 Editor assigned by journal 06 May, 2025 Editor invited by journal 26 Mar, 2025 Submission checks completed at journal 23 Mar, 2025 First submitted to journal 23 Mar, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6250034","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":453755797,"identity":"92db284e-cce1-4bc6-bfd2-bd18487bf2d4","order_by":0,"name":"Lei Ding","email":"","orcid":"","institution":"Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Ding","suffix":""},{"id":453755798,"identity":"bc14c6e6-f66e-48be-ac80-061691a63167","order_by":1,"name":"Rui Gu","email":"","orcid":"","institution":"Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Gu","suffix":""},{"id":453755799,"identity":"d9142141-7126-4fd2-a12e-70abc642c549","order_by":2,"name":"Xingyu Liu","email":"","orcid":"","institution":"jungar banner mongolia hospital","correspondingAuthor":false,"prefix":"","firstName":"Xingyu","middleName":"","lastName":"Liu","suffix":""},{"id":453755800,"identity":"66cb3a2c-e5a6-41b0-aa66-1b95b04a36d4","order_by":3,"name":"Qing Li","email":"","orcid":"","institution":"Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Qing","middleName":"","lastName":"Li","suffix":""},{"id":453755801,"identity":"240e62e0-e810-4ef3-916c-9388b40f3d4b","order_by":4,"name":"Hengyan Cui","email":"","orcid":"","institution":"Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Hengyan","middleName":"","lastName":"Cui","suffix":""},{"id":453755802,"identity":"ce06b69e-3653-4d15-a400-dd01112743be","order_by":5,"name":"Shuang Cheng","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Shuang","middleName":"","lastName":"Cheng","suffix":""},{"id":453755803,"identity":"c1103676-c997-4af8-99ef-cb8cc4fd7132","order_by":6,"name":"Yuxue Shi","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yuxue","middleName":"","lastName":"Shi","suffix":""},{"id":453755804,"identity":"f4a5bd33-ce46-4ac5-85d6-cae91c356270","order_by":7,"name":"Tianjiao Zhu","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Tianjiao","middleName":"","lastName":"Zhu","suffix":""},{"id":453755805,"identity":"0fd2da19-2b98-4d93-93ce-8342bec5a556","order_by":8,"name":"Zhuoyi Hu","email":"","orcid":"","institution":"Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Zhuoyi","middleName":"","lastName":"Hu","suffix":""},{"id":453755806,"identity":"ddbb0e80-b5e8-4705-88be-ce89f21709f3","order_by":9,"name":"Yafeng Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie3QsQqCQBzH8ZOLm4xWRapXuBCsIepVlCAXm1ochaCx2d7imqLtD4Iu9wCOtThLPYBdWutpW9B9h/OG34cDEVKpfjWXViOEoL5rUSdShtj+jmgxx95n2U5o7hdWf0/8s8Yn9xzNhwxwcZUSDmtB9M0l4rYVoLXNgEypjDhZlApibBhwBwco8RjoxJCSRNsLQn3akKoDyXbEjLnrvgm0kyVP8awMYcIg3VoBXdnHhDhSYsb+LRdPjGmenB5BuBgesl0hJaJeMzBAHK9fhVv2r0lZfwZR+1SlUqn+sye7504jtY4IUAAAAABJRU5ErkJggg==","orcid":"","institution":"Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Yafeng","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-03-18 06:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6250034/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6250034/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82583265,"identity":"a7a09b44-f8af-4779-b715-b5511dc7dc0f","added_by":"auto","created_at":"2025-05-13 06:49:30","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":62136,"visible":true,"origin":"","legend":"\u003cp\u003eArchitecture of our proposed model.\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-6250034/v1/a560b35d0b75419610e50ba9.jpg"},{"id":82583266,"identity":"1a5c0f34-23f6-47f9-89c1-ee3cd44c924c","added_by":"auto","created_at":"2025-05-13 06:49:30","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":46790,"visible":true,"origin":"","legend":"\u003cp\u003eThe vertical axis represents the SHAP value of the feature, the horizontal axis represents the lipid metabolite, and the different-colored curves represent the characteristic SHAP value of the label.\u003c/p\u003e","description":"","filename":"2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-6250034/v1/4adaa43e9563e5d3758564e5.jpg"},{"id":82583268,"identity":"efd9b4d9-7c2b-48d0-8eea-d4add1193fe8","added_by":"auto","created_at":"2025-05-13 06:49:31","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":70350,"visible":true,"origin":"","legend":"\u003cp\u003e(a) MSE loss combining significant features with all features; (b) loss of MSE using only significant features as input data; (c) MSE loss using all features as input data Table 1 shows the MSE loss values for different input data scenarios.\u003c/p\u003e","description":"","filename":"3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-6250034/v1/b2bb68d6be7c35c2fad58aec.jpg"},{"id":82584846,"identity":"27e8d408-0d1d-4967-9cff-f259d720a5e8","added_by":"auto","created_at":"2025-05-13 06:57:30","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":51771,"visible":true,"origin":"","legend":"\u003cp\u003e(a) represents the low degeneration group; (b) represents the moderate degeneration group; (c) represents the low degeneration group. Figure 3 is a trend chart of the SHAP values for age, apolipoprotein B (APO-B), apolipoprotein E (ApoE), and the Apo B/Apo A1 ratio.\u003c/p\u003e","description":"","filename":"4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-6250034/v1/d103fda6456395ebc2a013d7.jpg"},{"id":82585156,"identity":"ac821c15-0e5c-4436-9f3a-d64683ec8280","added_by":"auto","created_at":"2025-05-13 07:05:31","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1005096,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6250034/v1/eabdc50b-04d9-49fd-8446-48c5e09543ab.pdf"},{"id":82583269,"identity":"f47042ee-54bf-4dcd-b76c-e6a9d28cc5ec","added_by":"auto","created_at":"2025-05-13 06:49:31","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":172566,"visible":true,"origin":"","legend":"","description":"","filename":"Rawdata.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6250034/v1/c01488558fce3d0810ea6290.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Exploring the Relationship between Severity of Intervertebral Disc Degeneration and Dyslipidemia: A Deep Learning Approach","fulltext":[{"header":"Introduction","content":"\u003cp\u003eIntervertebral disc degeneration (IDD) is a common, chronic, progressive degenerative disease[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e], with an incidence of approximately 46% in middle-aged and elderly individuals[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. This condition seriously affects their quality of life and their physical and mental health[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Currently, the mechanisms of lumbar intervertebral disc degeneration[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] include extracellular matrix (ECM) degradation, changes in spinal mechanics, DNA damage, oxidative stress, cell signaling pathway disorders, and cellular senescence. However, the underlying pathological mechanisms have not yet been fully explored.\u003c/p\u003e \u003cp\u003eDyslipidemia is an umbrella term that encompasses all disorders of lipid metabolism[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. In the past four decades, the prevalence of dyslipidemia in the Chinese population has increased significantly[\u003cspan additionalcitationids=\"CR9 CR10\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] and reached a high level[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. Dyslipidemia can lead to systemic metabolic abnormalities. Most of the previous studies on dyslipidemia focused on heart disease, vascularity, and stroke[\u003cspan additionalcitationids=\"CR14\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], and multiple evidences [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] suggest that dyslipidemia is also a factor in the pathogenesis of other chronic diseases, such as chronic kidney disease, Alzheimer's disease, and osteoporosis. Dyslipidemia has also been one of the research topics of IDD because it accelerates the occurrence of degenerative diseases[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e], and several studies[\u003cspan additionalcitationids=\"CR20 CR21\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e] show that dyslipidemia is associated with lumbar disc degeneration and low back pain[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e], and note that lowering lipid levels can effectively alleviate IDD and low back pain. Animal experiments have demonstrated that rats fed a high-cholesterol diet (HCD) exhibit some degenerative characteristics in the lumbar intervertebral disc compared to rats fed a standard diet[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. In a study[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] on the association between metabolic syndrome (overweight OW, hypertension, dyslipidemia, and impaired glucose tolerance) and low back pain, metabolic syndrome has been proven to be associated with global disc degeneration of the spine.\u003c/p\u003e \u003cp\u003eCurrently, clinical approaches to diagnosing and treating low back pain or IDD primarily focus on corrective measures. However, predictive indicators for the progression of IDD are insufficiently explored, often resulting in patients reaching advanced stages of the condition before seeking medical attention, thereby necessitating invasive treatments like surgery.Although surgical treatment can restore lumbar spine balance and relieve pain to a certain extent, the recovery of these patients after treatment is still unpredictable, and the patients have significant recurrence rates after surgery.Therefore, it is important to explore whether blood lipid indicators can be used as biomarkers to predict disease severity. In recent years, owing to the complexity of medical data, artificial intelligence has become increasingly important in medical big data processing[\u003cspan additionalcitationids=\"CR26\" citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. Deep learning and machine learning are comprehensively applied to various problems, such as disease diagnosis, and these facts and considerations motivate us to adopt deep learning to explore the relationship between clinical blood lipid indicators and lumbar degenerative diseases, improve the prediction accuracy of Intervertebral disc degeneration, and rapidly identify patients in the early progress stage, which can provide some new coping ideas for clinical preventive diagnosis and treatments.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cp\u003e The Wuxi Hospital of Traditional Chinese Medicine Ethics Committee approved the study and waived the need for written informed consent due to its retrospective design.All procedures adhered to the Declaration of Helsinki.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy population\u003c/h2\u003e \u003cp\u003eThis retrospective study gathered data from 369 patients with lumbar disc degeneration treated at the Department of Orthopedics and Traumatology, Wuxi Hospital of Traditional Chinese Medicine, between January 2023 and June 2024.The inclusion criteria were: (1) low back pain symptoms linked to lumbar spine movements (flexion, extension, lateral flexion, rotation) or postural changes; (2) positive signs of nerve root irritation, such as a straight leg raise test, strengthening test, or femoral traction test; and (3) comprehensive clinical data, including a confirmed low back pain diagnosis and lumbar MRI.Several laboratory tests were conducted, and the examination data remained intact.Exclusion criteria included: (1) patients younger than 18 years, (2) those with prior spinal surgery, and (3) individuals with a history of spinal tumors or tuberculosis.(4) Patients with cancer or those with more serious cardiovascular, liver and kidney, hematopoietic system, thyroid insufficiency, and other primary diseases; (5) pregnant and lactating patients; (6) patients who have used other drugs for the treatments within two weeks, and patients with severe colds; (7) refusal to participate in the investigation; or have mental disorders or behavioral disorders, and cannot persist in completing the investigation.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eData Collection\u003c/h3\u003e\n\u003cp\u003eBasic patient information, including age, sex, height, weight, lifestyle habits (e.g., sedentary lifestyle), length of hospital stay, and total hospital costs.\u003c/p\u003e\n\u003ch3\u003eSerum lipid results Collection\u003c/h3\u003e\n\u003cp\u003eSerum samples were collected from 8:00 a.m. to 10:00 a.m. in a fasting vein, and the measured plasma samples were immediately measured using a fully automated biochemistry analyzer (Beckman Coulter AU5800, USA) for the standardized lipid levels. In addition, all subjects were required to undergo liver and kidney function and blood glucose tests.\u003c/p\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eStatistical analysis of the influencing factors among the three groups with varying degrees of degeneration was conducted using SPSS (version 26.0; SPSS Inc., Chicago, Illinois, USA).The Kolmogorov-Smirnov test assessed stultification data, one-way ANOVA evaluated normality, the Kruskal-Wallis test analyzed non-normality, and the chi-squared test examined count data.Continuous data were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD, while count data were presented as the number of cases with percentages. These data were then used in a multivariate analysis to construct a logistic regression model.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eDetermination of the degree of Intervertebral disc degeneration\u003c/h3\u003e\n\u003cp\u003eAll enrolled patients underwent 1.5 T/3.0 T conventional MRI scans (1.5 T Philips Ingenia or 3.0 T MR system). Two senior physicians (associate chief physicians) graded the sagittal t2-weighted images according to the Pfirrmann grading method. Intervertebral discs (IVDs) were [l1] graded from L1/2 to L5/S1, with the average grade representing the overall severity of IDD. Subjects with a mean degeneration score of Grades I-III were categorized as low-grade disc degeneration, while Grades III-IV were considered moderate grade; Grades IV-V were considered high grade.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eDeep learning analytics\u003c/h2\u003e \u003cp\u003eThe importance of all factors (age, low-density lipoprotein, APO-B, and Apo B/Apo A1 ratio) on the severity of lumbar disc degeneration was tested using a deep learning model, and the significance of all factor inputs to the feature-importance experiments showed that age and cholesterol were much more important than other factors (features). We evaluated three input data scenarios between the three groups: we used only important features as input data, used all features as input data, and combined important features with all features.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e1.Table 1 presents the baseline characteristics of the 369 participants in this \u0026nbsp; study, \u0026nbsp;comprising \u0026nbsp;219 females and \u0026nbsp;150 males, with an \u0026nbsp;average age of 61.39 years, a mean \u0026nbsp;BMI of 24.74 kg/m\u0026sup2;, and an average hospitalization duration of 9.38 days \u0026nbsp; (SD \u0026nbsp;= 3.98).\u003c/p\u003e\n\u003cp\u003e2.\u0026nbsp;Table 2 shows that there were 47 patients in the low degeneration group, 169 in the moderate degeneration group, and 153 in the high degeneration group. The results were as follows: there were statistically significant age differences (P=0.001\u0026lt;0.05), significant \u0026lt;differences in cost(P=0.001\u0026lt;0.05), statistical differences in cost(P=0.0010.05), and no statistically significant differences in sex, lifestyle habits (sedentary), BMI, fasting blood glucose concentration, and length of hospitalization.\u003c/p\u003e\n\u003cp\u003eTable 1: Baseline information of Characteristics\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"552\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eItems\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStatistics\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eGender\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e150(40.65)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e219(59.35)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eSedentary Lifestyle\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e343(92.95)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eYES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e26(7.05)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eAge(yr)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e61.39\u0026plusmn;13.45\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eBMI (kg/m\u0026sup2;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e24.74\u0026plusmn;3.91\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eHDL (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e1.21\u0026plusmn;0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eLDL (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e2.94\u0026plusmn;0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eCholesterol (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e4.70\u0026plusmn;1.02\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eTriglycerides (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e1.67\u0026plusmn;0.97\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eApo A1 (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e1.29\u0026plusmn;0.18\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eApo B (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e0.93\u0026plusmn;0.29\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eApo B/Apo A1 Ratio\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e0.74\u0026plusmn;0.24\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eApo E (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e4.13\u0026plusmn;1.31\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eLipoprotein(a) (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e204.92\u0026plusmn;205.13\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eGlucose (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e5.22\u0026plusmn;1.40\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eHospital Stay (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e9.38\u0026plusmn;3.98\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 43.5572%;\"\u003e\n \u003cp\u003eCost (CNY))\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 56.4428%;\"\u003e\n \u003cp\u003e11472.27\u0026plusmn;3753.58\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 2: General Characteristics vs. Degree of Degeneration\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"588\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eItems\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eLow\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eDegeneration\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e(\u003cem\u003eN\u003c/em\u003e=47)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eModerate\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eDegeneration\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e(\u003cem\u003eN\u003c/em\u003e=169)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eH\u003c/strong\u003e\u003cstrong\u003eigh Degeneration\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;(\u003cem\u003eN\u003c/em\u003e=153)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStatistics\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP\u003c/strong\u003e\u003cstrong\u003e-value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eGender (Male/Female)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e23/24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e70/99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e57/96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e2.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.348\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eSedentary Lifestyle (No/Yes)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003eMar-44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e155/14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e144/9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.743\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.69\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eAge (years)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e52.98\u0026plusmn;10.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e58.88\u0026plusmn;14.20a\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e66.75\u0026plusmn;11.07ab\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e51.025\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eBMI (kg/m\u0026sup2;)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e25.57\u0026plusmn;4.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e24.78\u0026plusmn;3.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e24.43\u0026plusmn;3.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e2.744\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.254\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eFasting Glucose Concentration (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e5.03\u0026plusmn;1.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e5.25\u0026plusmn;1.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e5.24\u0026plusmn;1.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e2.259\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.323\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eHospital Stay (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e8.70\u0026plusmn;2.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e9.01\u0026plusmn;3.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e9.99\u0026plusmn;4.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e5.831\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.054\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 17.0358%;\"\u003e\n \u003cp\u003eCost (CNY)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e10951.03\u0026plusmn;4214.33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e10915.25\u0026plusmn;3392.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.5911%;\"\u003e\n \u003cp\u003e12247.67\u0026plusmn;3870.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e13.134\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.0954%;\"\u003e\n \u003cp\u003e0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eNote: Different superscript letters (a, b) indicate significant differences between groups.\u003c/p\u003e\n\u003cp\u003e3.\u0026nbsp;After the normality test (KS test, large-sample test) of all patients\u0026rsquo; baseline characteristics, it was found\u0026nbsp;[l2] that only low-density lipoprotein met\u0026nbsp;[l3] the normality test, and the other baseline features did not meet the normal false premise. Therefore, in the one-way difference analysis, one-way ANOVA was used for low-density lipoprotein, and the Cruscal-Volris (H-K) test was used for the remaining continuous\u0026nbsp;variables. (Additional Table 3)\u003c/p\u003e\n\u003cp\u003e4.Differential analysis of the blood lipid index under different degeneration groups was performed, except for low-density lipoprotein.A one-way ANOVA was conducted, and the Kruskal-Wallis test (H-value) was applied to other continuous variables.Statistically significant differences were observed among the three groups in low-density lipoprotein, apolipoprotein B, and the Apo B/Apo A1 ratio, \u0026nbsp;with \u0026nbsp;P-values of \u0026nbsp; 0.036, 0.046, and 0.032, respectively.Statistically significant LDL concentrations were observed in both mild and severe degeneration, as well as moderate and severe degeneration (P=0.036).Apolipoprotein B showed a significant association with moderate to severe degeneration (P=0.046).Statistically significant differences were observed in Apo B/Apo A1 ratios for moderate and severe degeneration (P=0.032), while no significant differences were found in high-density lipoprotein, cholesterol, triglycerides, apolipoprotein A1, apolipoprotein E, and lipoprotein (a) across \u0026nbsp;varying degrees of degeneration.(Additional Table 4)\u003c/p\u003e\n\u003cp\u003eTable 3: Normality Test of Baseline Characteristics by Different Degrees of Degeneration\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"520\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eItems\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eDegeneration Degree (Low=1,\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eModerate\u003c/strong\u003e\u003cstrong\u003e=2, High=3)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eKS Statistic\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP\u003c/strong\u003e\u003cstrong\u003e=-\u003c/strong\u003e\u003cstrong\u003evalue\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eAge\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.102\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.094\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.001\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.127\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eBMI Index\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.177\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.001\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.087\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.003\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.097\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.001\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eHDL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.151\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.009\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.123\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.076\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.029\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eLDL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.122\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.076\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.061\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.036\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eCholesterol\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.103\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.090\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.002\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.082\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.013\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eTriglycerides\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.136\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.029\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.132\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.187\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eApo A1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.104\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.078\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.014\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.051\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eApo B\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.103\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.085\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.005\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.070\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.061\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eApo B/Apo A1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.084\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.077\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.016\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.078\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.024\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eApo E\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.135\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.033\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.088\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.003\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.164\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eLipoprotein(a)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.210\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.199\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.168\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eGlucose\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.213\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.245\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.161\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eHospital Stay (days)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.158\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.005\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.123\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.113\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.000\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003eCost\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.174\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.001\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.054\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.200*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 30.9021%;\"\u003e\n \u003cp\u003e \u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.084\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 23.0326%;\"\u003e\n \u003cp\u003e0.011\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eNote: An asterisk (*) indicates a non-significant P value.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 4: Comparison of Baseline Characteristics among Different Degrees of Degeneration\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"586\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eItems\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003eLow Degeneration (\u003cem\u003eN\u003c/em\u003e=47)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003eModerate\u003c/p\u003e\n \u003cp\u003eDegeneration (\u003cem\u003eN\u003c/em\u003e=169)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003eHigh\u003c/p\u003e\n \u003cp\u003eDegeneration (\u003cem\u003eN\u003c/em\u003e=153)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003eStatistics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eHDL (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.24\u0026plusmn;0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.21\u0026plusmn;0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.20\u0026plusmn;0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.302\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eLDL (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e3.09\u0026plusmn;0.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e3.01\u0026plusmn;0.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e2.81\u0026plusmn;0.83ab\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e3.367\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.036\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eCholesterol (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e4.80\u0026plusmn;0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e4.74\u0026plusmn;0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e4.63\u0026plusmn;1.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e2.049\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.359\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eTriglycerides (mmol/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.76\u0026plusmn;0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.69\u0026plusmn;0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.61\u0026plusmn;1.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e3.345\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.188\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eApo A1 (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.29\u0026plusmn;0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.29\u0026plusmn;0.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e1.29\u0026plusmn;0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.708\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.702\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eApo B (g/L)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e0.98\u0026plusmn;0.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e0.96\u0026plusmn;0.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e0.89\u0026plusmn;0.29b\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e6.137\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.046\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eApo B/Apo A1 Ratio\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e0.77\u0026plusmn;0.23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e0.76\u0026plusmn;0.24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e0.70\u0026plusmn;0.24b\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e6.876\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.032\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eApo E (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e4.08\u0026plusmn;1.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e4.20\u0026plusmn;1.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e4.08\u0026plusmn;1.39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.853\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.653\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 16.8942%;\"\u003e\n \u003cp\u003eLipoprotein(a) (mg/dL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e173.64\u0026plusmn;145.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e204.08\u0026plusmn;214.00\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 19.6246%;\"\u003e\n \u003cp\u003e215.46\u0026plusmn;210.72\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e1.261\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 12.116%;\"\u003e\n \u003cp\u003e0.532\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"6\" style=\"width: 100%;\"\u003e\n \u003cp\u003eNote: a indicates pairwise comparison with Degeneration - Mild; b indicates pairwise comparison with Degeneration - Severe.\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e5.\u0026nbsp;Lipid analysis based on deep learning\u003c/p\u003e\n\u003cp\u003eThe main Idea of our proposed learning model is to harness a critical subset of data to extract the predominant features, while leveraging the complete dataset to capture the nuanced details of features. The model primarily consists of a feature extraction module and a feature fusion module. The feature extraction module is composed of ProbSparse Self-Attention modules[28], and the feature fusion module is constituted by KAN modules. Specifically, one instance of the ProbSparse Self-Attention module is configured to distill the salient feature interactions within a critical subset of input data, the other one is employed to extract the interactions within all input data. The subsequent integration of the outputs of ProbSparse Self-Attention modules is facilitated through a feature fusion module, which employs Kolmogorov-Arnold Networks (KAN)[29]\u0026nbsp;modules to substitute the conventional linear layer. This strategic substitution aims at augmenting the model capacity for precise fitting, thus enhancing the overall model performance.\u003c/p\u003e\n\u003cp\u003eWe use the metric of SHAP (SHapley Additive exPlanations)\u0026nbsp;to measure the importance of features to the model output (prediction results). SHAP values are derived from cooperative game theory and obtained based on Shapley values. We constructed a model to analyze the SHAP value of each feature for disease severity by inputting all indicators in blood lipids and baseline indicators, such as (age and BMI).\u003c/p\u003e\n\u003cp\u003eTo evaluate the impact of combining important features on the prediction results, we designed three input data scenarios: (1) only important features are used as input data;\u0026nbsp;(2) all features are used as input data; (3) a combination of important features with all features.\u003c/p\u003e\n\u003cp\u003eThe experimental findings indicate that, as shown in Figure 2, age and cholesterol (CHOL) are more significant than other features in assessing lumbar disc degeneration.(2) From Figures 2 and 3, we find that the MSE loss values are approximately the same under the three input data scenarios, which indicates that the choice of input data scenario has little impact on the prediction accuracy of the model.(3) In general, when the severity of IDDs is not graded, we can combine the cholesterol level in the blood lipid value and the age of the patient to comprehensively predict the severity.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eWith the economic development of China and changes in people's diet and work styles, the incidence of overweight/obese patients is rapidly increasing, and an increasing number of people are suffering from metabolic diseases[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. Spinal degeneration researchers have increasingly focused on dyslipidemia as a key area of interest in recent times[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. It is widely recognized that dyslipidemia can lead to spinal degeneration through segmental atherosclerosis of the lumbar arteries; however, the effect of lipids on the occurrence and development of lumbar disc degeneration is still unclear. In a recent review of Rheumatoid Arthritis (RA) and lipid abnormalities, it is noted[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e] that the systemic inflammatory state in the early stages of RA leads to abnormal lipid metabolism, and lipid abnormalities can reinforce the autoimmune, inflammatory, and cardiovascular risks of rheumatoid arthritis. The study[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]followed up patients for 6 months after PLIF/TLIF and found that patients treated with statins for high cholesterol had a reduced incidence of pseudo arthropathy compared with those treated with no medication[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. A meta-analysis suggested that dyslipidemia could be a risk factor for disc degeneration and herniation[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]. Previously, a long-term (2012\u0026ndash;2022) National Health and Nutrition Survey[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e] in Korea reported that dyslipidemia was positively associated with the incidence of chronic low back pain, and treatment of dyslipidemia may help reduce the risk of chronic low back pain later in life. These clinical studies have shown that there is a clear correlation between dyslipidemia and lumbar degenerative diseases, that is, dyslipidemia could be a risk factor for the occurrence and development of IDD. Nevertheless, there is minimal discourse on how specific lipid constituents may affect the progression of the disease[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. In recent years, researchers have increasingly focused on certain unconventional blood lipid indices and ratios, including apolipoprotein B (APO-B), apolipoprotein E (ApoE), and the Apo B/Apo A1 ratio. Recent studies on dyslipidemia have demonstrated that the risk level of vascular disease can be more accurately assessed using APO B and LP (A), and it is now recommended that these two indicators should be included in the criteria for assessing lipid abnormalities[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. As early as 1999, some scientists mentioned that the Apo B/Apo A1 ratio is related to spine health[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e], and an elevated Apo B/Apo A1 ratio is a potential risk factor for osteonecrosis. A cross-sectional study in 2021[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e] also reported that elevated Apo B/Apo AI levels were associated with an increased risk of IDD. The results also showed that the Apo B/Apo A1 ratio was associated with the degree of intervertebral degeneration among the different groups, which provides a new research perspective on blood lipid indices and spinal health. In addition, because of the convenience of serum lipid testing and the potential of being a biomarker, if the relationship between intervertebral disc degeneration and dyslipidemia can be explored, multidimensional early diagnosis and treatment of intervertebral disc degeneration can be conducted and improved significantly, and more valuable insights regarding the pathogenesis of intervertebral disc degeneration can be provided for future research. Cholesterol is an important driver of the peripheral inflammatory response and plays an important role in initiating the development of inflammatory states[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. In the context of an imbalance in cholesterol homeostasis (e.g., hypercholesterolemia), cholesterol accumulates in macrophages and other immune cells, thereby promoting inflammation[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. The pathological mechanism underlying lumbar degeneration[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] is closely associated with peripheral inflammation.\u003c/p\u003e \u003cp\u003eThe results of deep learning algorithms also proved that cholesterol is related to the degree of lumbar disc degeneration, and that cholesterol can promote IDD has been validated in both in vitro and in vivo experiments. Unfortunately, there was no statistically significant difference between cholesterol and IDD severity in the data analysis of this study, which is contrary to the previous findings of other researchers; therefore, we consider that the reason for these differences may be that the sample distribution is middle-aged and elderly samples, and the group has poor control of lipids. In view of the poor results of this study, our group needs to conduct an intervention study on patients with intervertebral disc degeneration and cholesterol abnormalities in the future, increase the collection of follow-up information, and further investigate whether cholesterol is related to intervertebral disc degeneration.\u003c/p\u003e \u003cp\u003eIn this study, we developed a deep learning model to investigate the impact of various dyslipidemia parameters on predicting the severity of lumbar degeneration. As SHAP (SHAPLEY Additive explanation) provides a clear and comprehensive method for assessing the contribution of individual features to model output, we employed SHAP as a metric to quantify the importance of features in relation to the predictions of the model. We analyzed the effects of four statistically significant factors (age, low-density lipoprotein, APO-B, and Apo B/Apo A1 ratio) on the severity of lumbar disc degeneration among the three groups and found that in the low degeneration group, age was negatively correlated with disease severity, and LDL-C, APO-B, and Apo B/Apo A1 ratios were positively correlated with disease severity. In the moderate degeneration group, age and LDL-C levels were positively correlated with disease severity, whereas APO-B and Apo B/Apo A1 ratios were negatively correlated with disease severity. In the high degeneration group, all four factors were positively correlated with the degree of disease. In addition, it should be noted that age had the greatest effect on disease severity in the moderate degeneration group, whereas the APO-B and Apo B/Apo A1 ratios had the greatest effect in the high degeneration group. The LDL-C value had a greater effect in the moderate degeneration group when the LDL-C value was the same in the moderate and high degeneration groups. These results are consistent with our previous conclusions. After observing the overall SHAP values in the three groups, we found that the SHAP values of the four factors in the three groups were basically close to zero, indicating that the prediction results are mainly affected by a few factors, and thus we further analyzed the blood lipid level and population degeneration score of patients with degenerative diseases, and analyzed the high-density lipoprotein (HDL-C), low-density lipoprotein (LDL-C), total cholesterol (TC), Triglycerides (TG) and lipoprotein (a), apolipoprotein A1, apolipoprotein B (APO-B), apolipoprotein E (ApoE), lipoprotein (a) (LP (a)), Apo B/Apo A1 ratio, fasting blood glucose level, age, and BMI were used as different features input into the model, and the analysis results showed that the SHAP values of age and CHOL (cholesterol) were significantly higher than those of other features, indicating that age and CHOL have a greater impact on the degree of lumbar disc degeneration. The combination of age and cholesterol level is a preferable predictor of the disease severity. (Additional Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e)\u003c/p\u003e \u003cp\u003eAbnormal lipid metabolism usually leads to obesity; however, no significant association between BMI and lumbar disc degeneration has been found in previous studies or in the present study. Studies[\u003cspan additionalcitationids=\"CR42\" citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e] have shown the need to distinguish obesity classifications (general obesity/central obesity), and a few clinical studies[\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e] have suggested that abdominal fat is a better predictor of the severity of intervertebral disc degeneration than BMI. This study only explored the relationship between BMI and the degree of lumbar disc degeneration and did not include waist circumference, abdominal circumference, leg circumference, etc. in the study variables because the simple BMI value only describes the proportion of the total body fat of an individual and cannot adequately explain the relationship between waist and abdominal fat, muscle proportion, and lumbar disc degeneration. In recent years, an increasing number of researchers[\u003cspan additionalcitationids=\"CR46\" citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e] have focused on the relationship between the paravertebral muscle-fat ratio and lumbar intervertebral disc degeneration. Another limitation of this study is the retrospective study method, if a very long-term study can be conducted, the follow-up data of patients can be increased in the study, and the changes in the degree of lumbar disc degeneration after the control of lipids in patients with dyslipidemia could be observed, and these follow-up data could reveal the prognosis of dyslipidemia metabolism and IDD more comprehensively. In addition, the research focus should also be on the mechanism of lumbar disc degeneration in patients with obesity and diabetes caused by metabolic diseases because BMI and blood glucose concentration in this study have no statistical significance for lumbar disc degeneration, which is worthy of further exploration and research. A large-scale longitudinal follow-up will be conducted to analyze the data on lumbar disc degeneration in patients of different ages and BMI segments.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eOur study indicates that age significantly correlates with disc degeneration severity. Additionally, the levels of low-density lipoprotein, apolipoprotein B, and the Apo B/Apo A1 ratio are associated with disc degeneration. Thus, age and cholesterol metrics can serve as predictors for the severity of disc degeneration.In future clinical practice, managing lipids is crucial for preventing lumbar spine disease in middle-aged and older adults, with treatments focusing on cholesterol, apolipoprotein B, and the Apo B/Apo A1 ratio potentially providing new avenues for managing lumbar degenerative diseases.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eD.L. and ZY.H. wrote the main text of the manuscript. R.G and XY.L. organized, managed, and analyzed the collected data, and constructed the analysis model. Q.L. and HY.C provided constructive suggestions for this paper. S.C., YX.S, and TJ.Z collected the clinical data. All authors reviewed the manuscript. They have made substantial, direct, and intellectual contributions to this work and approved its publication.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eAll data generated or analyzed during this study are included in this published article and its supplementary information files.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eN.N. Knezevic, K.D. Candido, J.W.S. Vlaeyen, J. Van Zundert, S.P. Cohen, Low back pain, Lancet 398(10294) (2021) 78-92.\u003c/li\u003e\n\u003cli\u003eI.L. Mohd Isa, S.L. Teoh, N.H. Mohd Nor, S.A. Mokhtar, Discogenic Low Back Pain: Anatomy, Pathophysiology and Treatments of Intervertebral Disc Degeneration, Int J Mol Sci 24(1) (2022).\u003c/li\u003e\n\u003cli\u003eJ. Jiang, J. Huang, H. Deng, H. Liao, X. Fang, X. Zhan, S. Wu, Y. Xue, Current status and time trends of lipid and use of statins among older adults in China-real world data from primary community health institutions, Front Public Health 11 (2023) 1138411.\u003c/li\u003e\n\u003cli\u003eM. Zhang, Q. Deng, L. Wang, Z. Huang, M. Zhou, Y. Li, Z. Zhao, Y. Zhang, L. Wang, Prevalence of dyslipidemia and achievement of low-density lipoprotein cholesterol targets in Chinese adults: A nationally representative survey of 163,641 adults, Int J Cardiol 260 (2018) 196-203.\u003c/li\u003e\n\u003cli\u003eX. Chen, A. Zhang, K. Zhao, H. Gao, P. Shi, Y. Chen, Z. Cheng, W. Zhou, Y. Zhang, The role of oxidative stress in intervertebral disc degeneration: Mechanisms and therapeutic implications, Ageing Res Rev 98 (2024) 102323.\u003c/li\u003e\n\u003cli\u003eS. Kirnaz, C. Capadona, T. Wong, J.L. Goldberg, B. Medary, F. Sommer, L.B. McGrath, Jr., R. H\u0026auml;rtl, Fundamentals of Intervertebral Disc Degeneration, World Neurosurg 157 (2022) 264-273.\u003c/li\u003e\n\u003cli\u003eA.J. Berberich, R.A. Hegele, A Modern Approach to Dyslipidemia, Endocr Rev 43(4) (2022) 611-653.\u003c/li\u003e\n\u003cli\u003eW. Yang, J. Xiao, Z. Yang, L. Ji, W. Jia, J. Weng, J. Lu, Z. Shan, J. Liu, H. Tian, Q. Ji, D. Zhu, J. Ge, L. Lin, L. Chen, X. Guo, Z. Zhao, Q. Li, Z. Zhou, G. Shan, J. He, Serum lipids and lipoproteins in Chinese men and women, Circulation 125(18) (2012) 2212-21.\u003c/li\u003e\n\u003cli\u003eRepositioning of the global epicentre of non-optimal cholesterol, Nature 582(7810) (2020) 73-77.\u003c/li\u003e\n\u003cli\u003eL. Pan, Z. Yang, Y. Wu, R.X. Yin, Y. Liao, J. Wang, B. Gao, L. Zhang, The prevalence, awareness, treatment and control of dyslipidemia among adults in China, Atherosclerosis 248 (2016) 2-9.\u003c/li\u003e\n\u003cli\u003eS. Opoku, Y. Gan, E.A. Yobo, D. Tenkorang-Twum, W. Yue, Z. Wang, Z. Lu, Awareness, treatment, control, and determinants of dyslipidemia among adults in China, Sci Rep 11(1) (2021) 10056.\u003c/li\u003e\n\u003cli\u003eJ.J. Li, S.P. Zhao, D. Zhao, G.P. Lu, D.Q. Peng, J. Liu, Z.Y. Chen, Y.L. Guo, N.Q. Wu, S.K. Yan, Z.W. Wang, R.L. Gao, 2023 Chinese guideline for lipid management, Front Pharmacol 14 (2023) 1190934.\u003c/li\u003e\n\u003cli\u003eF. Mach, C. Baigent, A.L. Catapano, K.C. Koskinas, M. Casula, L. Badimon, M.J. Chapman, G.G. De Backer, V. Delgado, B.A. Ference, I.M. Graham, A. Halliday, U. Landmesser, B. Mihaylova, T.R. Pedersen, G. Riccardi, D.J. Richter, M.S. Sabatine, M.R. Taskinen, L. Tokgozoglu, O. Wiklund, 2019 ESC/EAS Guidelines for the management of dyslipidaemias: lipid modification to reduce cardiovascular risk, Eur Heart J 41(1) (2020) 111-188.\u003c/li\u003e\n\u003cli\u003eZ. Reiner, A.L. Catapano, G. De Backer, I. Graham, M.R. Taskinen, O. Wiklund, S. Agewall, E. Alegria, M.J. Chapman, P. Durrington, S. Erdine, J. Halcox, R. Hobbs, J. Kjekshus, P.P. Filardi, G. Riccardi, R.F. Storey, D. Wood, ESC/EAS Guidelines for the management of dyslipidaemias: the Task Force for the management of dyslipidaemias of the European Society of Cardiology (ESC) and the European Atherosclerosis Society (EAS), Eur Heart J 32(14) (2011) 1769-818.\u003c/li\u003e\n\u003cli\u003eA. Pirillo, M. Casula, E. Olmastroni, G.D. Norata, A.L. Catapano, Global epidemiology of dyslipidaemias, Nat Rev Cardiol 18(10) (2021) 689-700.\u003c/li\u003e\n\u003cli\u003eC. Li, F. Wang, L. Cui, S. Li, J. Zhao, L. Liao, Association between abnormal lipid metabolism and tumor, Front Endocrinol (Lausanne) 14 (2023) 1134154.\u003c/li\u003e\n\u003cli\u003eU. Lendahl, P. Nilsson, C. Betsholtz, Emerging links between cerebrovascular and neurodegenerative diseases-a special role for pericytes, EMBO Rep 20(11) (2019) e48070.\u003c/li\u003e\n\u003cli\u003eL. Yuan, Z. Huang, W. Han, R. Chang, B. Sun, M. Zhu, C. Li, J. Yan, B. Liu, H. Yin, W. Ye, The impact of dyslipidemia on lumbar intervertebral disc degeneration and vertebral endplate modic changes: a cross-sectional study of 1035 citizens in China, BMC Public Health 23(1) (2023) 1302.\u003c/li\u003e\n\u003cli\u003eW. Li, Z. Ding, H. Zhang, Q. Shi, D. Wang, S. Zhang, S. Xu, B. Gao, M. Yan, The Roles of Blood Lipid-Metabolism Genes in Immune Infiltration Could Promote the Development of IDD, Front Cell Dev Biol 10 (2022) 844395.\u003c/li\u003e\n\u003cli\u003eS. Li, J. Du, Y. Huang, S. Gao, Z. Zhao, Z. Chang, X. Zhang, B. He, From hyperglycemia to intervertebral disc damage: exploring diabetic-induced disc degeneration, Front Immunol 15 (2024) 1355503.\u003c/li\u003e\n\u003cli\u003eJ. Chen, J. Yan, S. Li, J. Zhu, J. Zhou, J. Li, Y. Zhang, Z. Huang, L. Yuan, K. Xu, W. Chen, W. Ye, Atorvastatin inhibited TNF-\u0026alpha; induced matrix degradation in rat nucleus pulposus cells by suppressing NLRP3 inflammasome activity and inducing autophagy through NF-\u0026kappa;B signaling, Cell Cycle 20(20) (2021) 2160-2173.\u003c/li\u003e\n\u003cli\u003eY. Zhou, X. Chen, Q. Tian, J. Zhang, M. Wan, X. Zhou, X. Xu, X. Cao, X. Zhou, L. Zheng, Deletion of ApoE Leads to Intervertebral Disc Degeneration via Aberrant Activation of Adipokines, Spine (Phila Pa 1976) 47(12) (2022) 899-907.\u003c/li\u003e\n\u003cli\u003eJ. Yan, S. Li, Y. Zhang, Z. Deng, J. Wu, Z. Huang, T. Qin, Y. Xiao, J. Zhou, K. Xu, W. Ye, Cholesterol Induces Pyroptosis and Matrix Degradation via mSREBP1-Driven Endoplasmic Reticulum Stress in Intervertebral Disc Degeneration, Front Cell Dev Biol 9 (2021) 803132.\u003c/li\u003e\n\u003cli\u003eZ. Huang, J. Chen, Y. Su, M. Guo, Y. Chen, Y. Zhu, G. Nie, R. Ke, H. Chen, J. Hu, Impact of dyslipidemia on the severity of symptomatic lumbar spine degeneration: A retrospective clinical study, Front Nutr 9 (2022) 1033375.\u003c/li\u003e\n\u003cli\u003eR.C. Deo, Machine Learning in Medicine, Circulation 132(20) (2015) 1920-30.\u003c/li\u003e\n\u003cli\u003eY. Chen, J. Wang, C. Wang, M. Liu, Q. Zou, Deep learning models for disease-associated circRNA prediction: a review, Brief Bioinform 23(6) (2022).\u003c/li\u003e\n\u003cli\u003eA.A. Theodosiou, R.C. Read, Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician, J Infect 87(4) (2023) 287-294.\u003c/li\u003e\n\u003cli\u003eY. Xu, M. Gong, J. Chen, T. Liu, K. Zhang, K. Batmanghelich, Generative-Discriminative Complementary Learning, Proc AAAI Conf Artif Intell 34(4) (2020) 6526-6533.\u003c/li\u003e\n\u003cli\u003eM.A.A. Al-Qaness, S. Ni, TCNN-KAN: Optimized CNN by Kolmogorov-Arnold Network and Pruning Techniques for sEMG Gesture Recognition, IEEE J Biomed Health Inform Pp (2024).\u003c/li\u003e\n\u003cli\u003eN.W.S. Chew, C.H. Ng, D.J.H. Tan, G. Kong, C. Lin, Y.H. Chin, W.H. Lim, D.Q. Huang, J. Quek, C.E. Fu, J. Xiao, N. Syn, R. Foo, C.M. Khoo, J.W. Wang, G.K. Dimitriadis, D.Y. Young, M.S. Siddiqui, C.S.P. Lam, Y. Wang, G.A. Figtree, M.Y. Chan, D.E. Cummings, M. Noureddin, V.W. Wong, R.C.W. Ma, C.S. Mantzoros, A. Sanyal, M.D. Muthiah, The global burden of metabolic disease: Data from 2000 to 2019, Cell Metab 35(3) (2023) 414-428.e3.\u003c/li\u003e\n\u003cli\u003eY. Zhang, Y. Zhao, M. Wang, M. Si, J. Li, Y. Hou, J. Jia, L. Nie, Serum lipid levels are positively correlated with lumbar disc herniation--a retrospective study of 790 Chinese patients, Lipids Health Dis 15 (2016) 80.\u003c/li\u003e\n\u003cli\u003eA.I. Venetsanopoulou, E. Pelechas, P.V. Voulgari, A.A. Drosos, The lipid paradox in rheumatoid arthritis: the dark horse of the augmented cardiovascular risk, Rheumatol Int 40(8) (2020) 1181-1191.\u003c/li\u003e\n\u003cli\u003eA.A. Drosos, A.A. Venetsanopoulou, E. Pelechas, P.V. Voulgari, Exploring Cardiovascular Risk Factors and Atherosclerosis in Rheumatoid Arthritis, Eur J Intern Med 128 (2024) 1-9.\u003c/li\u003e\n\u003cli\u003eM.S. Lavu, N.B. Eghrari, P.S. Makineni, D.C. Kaelber, J.W. Savage, D.W. Pelle, Low-Density Lipoprotein Cholesterol and Statin Usage Are Associated With Rates of Pseudarthrosis Following Single-Level Posterior Lumbar Interbody Fusion, Spine (Phila Pa 1976) 49(6) (2024) 369-377.\u003c/li\u003e\n\u003cli\u003eK. Hoffeld, M. Lenz, P. Egenolf, M. Weber, V. Heck, P. Eysel, M.J. Scheyerer, Patient-related risk factors and lifestyle factors for lumbar degenerative disc disease: a systematic review, Neurochirurgie 69(5) (2023) 101482.\u003c/li\u003e\n\u003cli\u003eS. Kim, S.M. Lee, Dyslipidemia Is Positively Associated with Chronic Low Back Pain in Korean Women: Korean National Health and Nutrition Examination Survey 2010-2012, Healthcare (Basel) 12(1) (2024).\u003c/li\u003e\n\u003cli\u003eK. Miyanishi, T. Yamamoto, T. Irisa, Y. Noguchi, Y. Sugioka, Y. Iwamoto, Increased level of apolipoprotein B/apolipoprotein A1 ratio as a potential risk for osteonecrosis, Ann Rheum Dis 58(8) (1999) 514-6.\u003c/li\u003e\n\u003cli\u003eF. Chen, T. Wu, C. Bai, S. Guo, W. Huang, Y. Pan, H. Zhang, D. Wu, Q. Fu, Q. Chen, X. Li, L. Li, Serum apolipoprotein B/apolipoprotein A1 ratio in relation to intervertebral disk herniation: a cross-sectional frequency-matched case-control study, Lipids Health Dis 20(1) (2021) 79.\u003c/li\u003e\n\u003cli\u003eS.B. Hansen, H. Wang, The shared role of cholesterol in neuronal and peripheral inflammation, Pharmacol Ther 249 (2023) 108486.\u003c/li\u003e\n\u003cli\u003eA.R. Tall, L. Yvan-Charvet, Cholesterol, inflammation and innate immunity, Nat Rev Immunol 15(2) (2015) 104-16.\u003c/li\u003e\n\u003cli\u003eJ. Zhu, Y. Zhang, Y. Wu, Y. Xiang, X. Tong, Y. Yu, Y. Qiu, S. Cui, Q. Zhao, N. Wang, Y. Jiang, G. Zhao, Obesity and Dyslipidemia in Chinese Adults: A Cross-Sectional Study in Shanghai, China, Nutrients 14(11) (2022).\u003c/li\u003e\n\u003cli\u003eC. Zheng, Y. Liu, C. Xu, S. Zeng, Q. Wang, Y. Guo, J. Li, S. Li, M. Dong, X. Luo, Q. Wu, Association between obesity and the prevalence of dyslipidemia in middle-aged and older people: an observational study, Sci Rep 14(1) (2024) 11974.\u003c/li\u003e\n\u003cli\u003eX. Shi, L. Chai, D. Zhang, J. Fan, Association between complementary anthropometric measures and all-cause mortality risk in adults: NHANES 2011-2016, Eur J Clin Nutr (2024).\u003c/li\u003e\n\u003cli\u003eM. Wang, H. Yuan, F. Lei, S. Zhang, L. Jiang, J. Yan, D. Feng, Abdominal Fat is a Reliable Indicator of Lumbar Intervertebral Disc Degeneration than Body Mass Index, World Neurosurg 182 (2024) e171-e177.\u003c/li\u003e\n\u003cli\u003eR.J. Crawford, T. Volken, \u0026Aacute;. Ni Mhuiris, C.C. Bow, J.M. Elliott, M.A. Hoggarth, D. Samartzis, Geography of Lumbar Paravertebral Muscle Fatty Infiltration: The Influence of Demographics, Low Back Pain, and Disability, Spine (Phila Pa 1976) 44(18) (2019) 1294-1302.\u003c/li\u003e\n\u003cli\u003eB. Rosenstein, J. Burdick, A. Roussac, M. Rye, N. Naghdi, S. Valentin, T. Licka, M. Sean, P. T\u0026eacute;treault, J. Elliott, M. Fortin, The assessment of paraspinal muscle epimuscular fat in participants with and without low back pain: A case-control study, J Biomech 163 (2024) 111928.\u003c/li\u003e\n\u003cli\u003eE.E. \u0026Ouml;zcan-Ekşi, M. Ekşi, M.A. Ak\u0026ccedil;al, Severe Lumbar Intervertebral Disc Degeneration Is Associated with Modic Changes and Fatty Infiltration in the Paraspinal Muscles at all Lumbar Levels, Except for L1-L2: A Cross-Sectional Analysis of 50 Symptomatic Women and 50 Age-Matched Symptomatic Men, World Neurosurg 122 (2019) e1069-e1077.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Dyslipidemia, Intervertebral disc degeneration, Deep learning, Blood lipid","lastPublishedDoi":"10.21203/rs.3.rs-6250034/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6250034/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground: \u003c/strong\u003eIntervertebral disc degeneration (IDD) is a chronic, noninflammatory, degenerative process that occurs in the lumbar spine and surrounding soft tissues. Although dyslipidemia has been proven to be related to degenerative changes in the lumbar spine, its relationship with IDD severity of IDD is not been fully explored and elucidated. This study employed deep learning to improve IDD prediction accuracy and suggest new preventive and therapeutic strategies for clinical application.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003e We enrolled 369 IDD patients. Serum was collected and analyzed for high-density lipoprotein (HDL-C), low-density lipoprotein (LDL-C), lipoprotein (a), total cholesterol (TC), triglycerides (TG), apolipoprotein A1, apolipoprotein B (APO-B), apolipoprotein E (ApoE), lipoprotein (a) (LP(a)) levels, Apo B/Apo A1 ratio, and other baseline data. IDD was assessed according to the Pfirrmann grading system, and Grades I-III were categorized as low-grade disc degeneration, while Grades III-IV were considered moderate grade, Grades IV-V were considered high grade. We used a deep learning model with ProbSparse Self-Attention and Kolmogorov-Arnold Networks (KAN) to predict the degeneration scores. Moreover, we calculated the SHapley Additive ExPlanations (SHAP) values of the features to evaluate their importance.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults \u003c/strong\u003eA total of 50 patients are enrolled in the low degeneration group, 179 in the moderate degeneration group, and 165 in the high degeneration group. According to the univariate analysis of the different degeneration groups, there are statistically significant differences in terms of age, low-density lipoprotein, apolipoprotein B, and Apo B/Apo A1 ratio (P \u0026lt;0.001, P = 0.036, and P = 0.046, P = 0.032, respectively, which were smaller than 0.05), but no statistically significant differences in terms of high-density lipoprotein, lipoprotein (a), total cholesterol (TC), triglycerides (TG), apolipoprotein A1, gender, fasting blood glucose concentration, and length of hospital stay (P =0.86, P =0.532, P =0.359, P =0.188, P =0.702, and P =0.348).\u003c/p\u003e\n\u003cp\u003eBy employing a deep learning model to assess the influence of various factors on disease severity, and examining the impact of four statistically significant factors (age, LDL, Apo B, and Apo B/Apo A1 ratio) on the severity of lumbar disc degeneration among the three groups, it is determined that age and cholesterol serve as predictors for the severity of intervertebral disc degeneration (IDD).Grouping patients by disc degeneration severity reveals that age significantly influences the moderate degeneration group, whereas Apo B and the Apo B/Apo A1 ratio are most impactful in the high degeneration group.compared between the moderate and high degeneration groups, when LDL-C values are the same, its impact is the greatest in the moderate degeneration group.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion: \u0026nbsp;\u003c/strong\u003eAge significantly correlates with intervertebral disc degeneration, while the ratios of low-density lipoprotein, apolipoprotein B, and Apo B/Apo A1 are associated with varying degrees of disc degeneration across different groups.Age and cholesterol levels serve as indicators for assessing the severity of intervertebral disc degeneration.\u003c/p\u003e","manuscriptTitle":"Exploring the Relationship between Severity of Intervertebral Disc Degeneration and Dyslipidemia: A Deep Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-13 06:49:26","doi":"10.21203/rs.3.rs-6250034/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-08T05:42:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-29T20:00:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"131420031953392345700144035085896641184","date":"2025-07-15T19:45:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-30T21:04:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"134463985843737469640357431413440484139","date":"2025-05-21T17:32:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-21T07:33:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"200453096631545497888927316698185314347","date":"2025-05-07T03:07:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-06T21:49:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-06T17:00:15+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-03-26T10:20:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-23T15:54:37+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-23T15:53:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c37dfdee-c5a2-4443-92e0-afc0b34df81b","owner":[],"postedDate":"May 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":48251988,"name":"Health sciences/Diseases"},{"id":48251989,"name":"Health sciences/Health care"},{"id":48251990,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-10-16T07:53:41+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-13 06:49:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6250034","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6250034","identity":"rs-6250034","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}