Development and validation of a decision tree model for prediction of insomnia risk among ischemic stroke convalescence patients

Development and validation of a decision tree model for prediction of insomnia risk among ischemic stroke convalescence patients | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Development and validation of a decision tree model for prediction of insomnia risk among ischemic stroke convalescence patients Xuefeng Sun, Zilin Wang, Yuqing Song, Deyu Cong, Shu Sun, Xinye Zhang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6248505/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Aug, 2025 Read the published version in BMC Public Health → Version 1 posted 19 You are reading this latest preprint version Abstract Background: Insomnia is a prevalent complication among ischemic stroke convalescence (ISC) patients. Although the interplay of clinical, psychological, and social factors remains unclear in ISC patients, a model prediction system was necessary. Limited research developed a prediction model for insomnia risk. Objectives: To construct a decision tree model for insomnia risk among ISC patients based on the classification and regression tree algorithm. Design: Across-sectional study. Setting: China. Participants: The study enrolled 823 adult ISC patients between February 2023 and October 2024. Participants were recruited from stroke units in two tertiary hospitals in Jilin Province. Methods: A decision tree model was guided by the TRIPOD+AI report. The Pittsburgh Sleep Quality Index (PSQI), Fatigue Severity Scale (FSS), Social Support Scale (SSRS) and other scales were used to collect data. The confusion matrix, ROC curves, H-L test, and calibration curve were employed for internal and external validation by using a bootstrap resampling method. 623 patients were used to construct the decision tree model, while the remaining 200 non-homologous cases were used for external validation. Results: This study showed that the prevalence of insomnia among ISC patients was 37.72 %. Univariate analysis revealed that factors such as BMI, SAS, SSRS, FSS, SDS, and NIHSS were critical. The decision tree model yielded 24 paths with a depth of 6. The predictive contribution was ranked as follows: SAS > SSRS > FSS > SDS > BMI > NIHSS, which were identified to create the nomogram. Internal validation indicated that the model had strong predictive accuracy at 88.2%, with a sensitivity of 0.96, specificity of 0.84, and a Youden index of 0.80. The area under the curve was 0.96 (95% CI: 0.93~0.98; p < 0.001); Additionally, the H-L test showed that the model was well-calibrated (χ2 = 9.36, p = 0.404). External validation proved that the model had stability across different data. Conclusion: This decision tree model demonstrates potential for predicting insomnia in ISC patients, and these predictors can inform the development of future insomnia management strategies. The ultimate objective is to alleviate the distress caused by insomnia and to facilitate the recovery process in stroke patients. Insomnia Ischemic stroke convalescence Decision tree Predictive model Nomogram Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 1 Background Stroke is a prevalent neurological disease that profoundly impacts individuals' lives, health, and overall well-being. It is the second leading cause of death and a primary cause of disability, imposing a considerable global burden on healthcare resources and infrastructure. 1 Ischemic stroke, the most common type, accounts for 80% of all stroke cases. 2 Stroke survivors often endure long-term symptoms, including motor dysfunction, visual impairment, cognitive and verbal communication impairments, emotional difficulties, sexual function, and sleep disturbance. 3 Research has shown a high prevalence of post-stroke insomnia, affecting 75 ~ 95% of stroke patients globally. 4 This condition frequently emerges during recovery from ischemic stroke, yet it remains an under-recognized complication in clinical practice. A cohort study in Australia found that 29.8% of stroke patients experienced poor sleep quality, 5 and a survey in Brazil reported that 70.6% of stroke patients had poor sleep quality within the first year post-stroke. 6 The fifth edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) defines insomnia as a condition characterized by difficulty falling asleep, maintaining sleep, or waking up too early in the morning and being unable to fall back asleep. These symptoms must occur at least three nights per week for three months, leading to dissatisfaction with sleep quality or quantity. 7 Insomnia is a common complication following a stroke, though its underlying mechanisms remain poor and complex to understand. Several factors contribute to post-stroke insomnia. First, brain injury itself can damage the sleep-wake regulation center in the thalamus. 8 Second, psychological issues such as anxiety and depression, which often arise after a stroke, may exacerbate insomnia. 9 Third, complications of cerebrovascular diseases, such as cardiopulmonary diseases, epilepsy, and infections, may further fragment sleep and contribute to insomnia. 10 In addition, nighttime levels of melatonin, gamma-aminobutyric acid, and total antioxidant concentrations in stroke patients may be related to insomnia. 11 Current evidence suggests that intestinal flora and its metabolites influence the development of post-stroke insomnia. They do so primarily through the regulation of the nervous system regulation, 12 disruption of the blood-brain barrier, 13 and by affecting the function of the hypothalamic-pituitary-adrenal axis. 14 Evaluating insomnia in patients is challenging due to the subjective nature of their symptoms, making it difficult to assess using simple medical examinations. As a result, there was a generally low awareness and screening rate for post-stroke insomnia, which increased the risk of poor prognosis and stroke recurrence. 15 Identified factors related to insomnia in ischemic stroke convalescence (ISC) patients included sociodemographic characteristics, and clinical factors, as well as depression and anxiety. 16 The occurrence and development of insomnia in these patients stem from the combined influence of clinical, psychological, and social factors, which may interact in complex ways. However, the specific pathways of these interactions and their contributions to insomnia remain unclear. Consequently, establishing a prediction model for insomnia in ISC patients, along with early identification and screening of high-risk groups, has become an urgent issue that demands attention. Currently, the assessment of sleep in ISC patients primarily relies on subjective or objective measurement tools, such as traditional logistic regression analysis. 17 With the advent of the big data era, the role of data mining technology in the medical field has become increasingly prominent. Decision tree models, in particular, have been employed in research related to stroke, infection, frailty, pressure injuries, and mild cognitive impairment. 18 , 19 , 20 The decision tree model for insomnia risk in ISC patients was constructed through the classification and regression tree (CART) algorithm in machine learning. This algorithm is capable of analyzing both categorical and continuous variables, effectively utilizing all available sample data, managing high-dimensional data, screening important variables, and achieving relatively high prediction accuracy. 21 In our study, we identified the key predictive variables for insomnia in ISC patients. Using the CART algorithm, we were able to clearly present the contribution values and thresholds of these variables. This allowed doctors and nurses to formulate a decision-making path for assessing insomnia risk, which can serve as a valuable reference for the clinical management of post-stroke insomnia. 2 Methods 2.1 Study design and patients This is a clinical investigation study conducted in accordance with the ethical standards of The Third Affiliated Hospital of Changchun University of Chinese Medicine and approved by the Ethics Committee in August 2024. 2.2 Initial predictors From the reviewed literature, twenty-two factors have been identified as related to insomnia in ISC patients, including (a) gender; (b) age; (c) marital status; (d) educational level; (e) insurance type; (f) monthly income; (g) FMA score; (h) stroke location; (i) stroke severity; (j) body mass index; (k) ADL; (l) hypertension; (m) diabetes mellitus; (n) coronary heart disease; (0) arrhythmia; (p) hyperlipidemia; (q) smoking; (r) alcohol; (s) fatigue; (t) depression; (u) anxiety; (v) social support. 2.3 Study criteria Participants met the diagnostic criteria for both ischemic stroke and insomnia. 22 The inclusion criteria were as follows: (a) aged between 40 and 75 years; (b) in the recovery period; (c) had their first disease; (d) capable of completing the questionnaire and scales independently, with sufficient behavioral and language abilities. The exclusion criteria were: (a) patients with impaired consciousness, cognition, or understanding and expression following ischemic stroke; (b) patients with pre-existing insomnia diagnoses or treatments before the ischemic stroke; (c) individuals currently using or having previously used sleeping medications; (d) patients with severe complications from other systems such as heart, liver, lung and kidney. 2.4 Data collection During hospitalization, general information including age, sex, height, weight, marital status, insurance type, smoking and drinking status, and clinical comorbidities were collected. Additionally, patients’ stroke location, degree of neurological impairment, motor balance scores for upper and lower limbs, and daily activity scores were collected. The Pittsburgh Sleep Quality Index (PSQI) was used to evaluate the sleep quality of ISC patients. 23 A PSQI score above 7 points indicated poor sleep quality (insomnia), while a score of 7 or below indicated good sleep quality (non-insomnia). Fatigue Severity Scale (FSS) was often used to evaluate the post-stroke fatigue level among patients. 24 A score below 36 indicated minimal fatigue, while a score of or above 36 may warrant further medical evaluation. The anxiety and depression were assessed by the Self-rating anxiety scale (SAS) and Self-rating depression scale (SDS), respectively. 25 The higher total scores reflected more severe levels of anxiety and depression among ISC patients. Social support was measured using the SSRS. Higher scores indicated greater levels of social support. 26 2.5 Statistical analysis and sample size calculating Data statistics and analysis was performed using SPSS 24.0 software. Continuous data were described using mean and standard deviations (for normally distributed data) or medians and interquartile range (IQR) (for skewed distributed data). Categorical data were summarized as frequencies and proportions. For continuous variables with normal distribution, a two independent samples t-test was used for group comparison when variances were homogeneous. For skewed continuous variables, the rank sum test was employed for comparison between groups, while the Chi-squared test was used for categorical variables. A p -value of < 0.05 was considered statistically significant. Model construction utilized the CART algorithm, a decision tree model proposed by Breiman and his colleagues in 1984. 27 This algorithm addresses both classification and regression problems by minimizing the Gini coefficient or squared error, thus dividing the root node into two child nodes. This splitting process is repeated, further dividing nodes until no additional splits are possible. Statistically significant variables obtained from single-factor analysis were used as potential initial factors affecting insomnia in ISC patients. Fill in the missing values by means of mean and median. The model parameter settings include: the random seed number is 94, the complexity parameter is 0.01, the minimum sample split is 3, and the maxdepth is 6. The model was implemented using R version 4.2.2 and R Studio. For model verification, the Bootstrap method with 1000 repeated samplings was employed for internal validation. A confusion matrix, ROC curve, H-L test, and calibration curve were used for internal and external validation. According to the events per variable (EPV) rule, we adopted an EPV of 10, accounting for a 5% loss during the investigation, thus requiring 623 samples for this study. 3 Results 3.1 Characteristics of participants The sociodemographic and clinical characteristics of the insomnia and non-insomnia groups were presented in Table 1. Among the 623 participants, the average age was 61(55, 67) years. There were 417 male ISC patients (66.9 %), significantly more than 206 female ISC patients (33.1 %). The average BMI of participants was 23.57 (22.55, 24.98) kg / m 2 , and the BMI values ranged from 17.3 to 38.28 kg/m 2 . Regarding educational background, the proportions of different education levels among participants were 7.7 %, 24.1 %, 33.9 %, and 34.3 %. Additionally, 38.8% of participants were smokers, while 34.8% reported drinking alcohol. Table 1 Patient characteristics between insomnia and non-insomnia groups (n = 623) Demographic factors Total (n = 623) n (%) Insomnia (n = 235) n (%) Non-insomnia (n = 388) n (%) c 2 /Z p -value Age [median (IQR)] 61 (55, 67) 60 (54, 66) 61 (56, 67) 0.895 0.399 Gender Male 417 (66.9) 151 (64.3) 266 (68.6) 1.223 0.269 Female 206 (33.1) 84 (35.7) 122 (31.4) Education level Primary or below 48 (7.7) 16 (6.8) 32 (8.2) 3.771 0.287 Junior school 150 (24.1) 48 (20.4) 102 (26.3) High school 211 (33.9) 83 (35.3) 128 (33.0) College or above 214 (34.3) 88 (37.4) 126 (32.5) Marital status Married 564 (90.5) 213 (90.6) 351 (90.5) 1.690 0.655 Single 9 (1.4) 4 (1.7) 5 (1.3) Divorced 17 (2.7) 8 (3.4) 9 (2.3) Widowed 33 (5.3) 10 (4.3) 23 (5.9) Insurance type Urban residents 407 (65.3) 150 (63.8) 257 (66.2) 5.373 0.068 Rural cooperative 146 (23.4) 50 (21.3) 96 (24.7) Other 70 (11.2) 35 (14.9) 35 (9.0) Monthly income(R) ≤2000 92 (14.8) 25 (10.6) 67 (17.3) 5.735 0.125 2000～4000 203 (32.6) 76 (32.3) 127 (32.7) 4000～6000 206 (33.1) 84 (35.7) 122 (31.4) ≥6000 122 (19.6) 50 (21.3) 72 (18.6) Smoking status Current smoker 242 (38.8) 91 (38.7) 151 (38.9) 0.002 0.962 Non-current smoker 381 (61.2) 144 (61.3) 237 (61.1) Continued Demographic factors Total (n = 623) n (%) Insomnia (n = 235) n (%) Non-insomnia (n = 388) n (%) c 2 /Z p- value Alcohol status Drinker 217 (34.8) 84 (35.7) 133 (34.3) 0.139 0.710 Non-drinker 406 (65.2) 151 (64.3) 255 (65.7) BMI(Kg/m 2 ) [median (IQR)] 23.57 (22.55, 24.98) 24.51 (23.04, 25.39) 23.24 (22.31, 24.73) 3.058 ＜ 0.001 ** Stroke location Anterior circulation 182 (29.2) 59 (25.1) 123 (31.7) 3.078 0.079 Posterior circulation 441 (70.8) 176 (74.9) 265 (68.3) Hypertension Yes 401 (64.4) 162 (68.9) 239 (61.6) 3.436 0.064 No 222 (35.6) 73 (31.1) 149 (38.4) Diabetes Yes 263 (42.2) 104 (44.3) 159 (41.0) 0.644 0.422 No 360 (57.8) 131 (55.7) 229 (59.0) Coronary heart disease Yes 107 (17.2) 42 (17.9) 65 (16.8) 0.129 0.719 No 516 (82.8) 193 (82.1) 323 (83.2) Hyperlipidemia Yes 155 (24.9) 63 (26.8) 92 (23.7) 0.751 0.386 No 468 (75.1) 172 (73.2) 296 (76.3) Arhythmia Yes 121 (19.4) 51 (21.7) 70 (18.0) 1.253 0.263 No 502 (80.6) 184 (78.3) 318 (82.0) FMA [median (IQR)] 62 (40, 83) 56 (25, 85) 63 (43, 83) 0.593 0.874 NIHSS [median (IQR)] 4 (3, 6) 5 (3, 6) 4 (2, 5) 1.945 0.001 ** BI [median (IQR)] 60 (45, 75) 60 (45, 75) 60 (45, 75) 0.486 0.972 FSS [median (IQR)] 26 (19, 34) 35 (29, 38) 21 (17, 27) 7.245 ＜ 0.001 ** SAS [median (IQR)] 36 (31, 46) 48 (44, 51) 33 (29, 36) 9.231 ＜ 0.001 ** SDS [median (IQR)] 36 (31, 44) 45 (38, 50) 33 (30, 36) 6.667 ＜ 0.001 ** SSRS [median (IQR)] 45 (40, 48) 39 (36, 42) 47 (45, 49) 8.485 ＜ 0.001 ** Note: BMI, Body Mass Index. FMA, Fugl-Meyer Assessment Scale. NIHSS, National Institute of Health stroke scale. BI, Barthel Index. FSS, fatigue severity scale. SAS, Self-Rating Anxiety Scale. SDS, Self-rating Depression Scale. SSRS, social support rate scale. The comparison between insomnia group and non-insomnia group reveals significant differences: * p < 0.05; ** p < 0.001. 3.2 The prevalence of insomnia and univariate analyses of the potential predictive factors among ISC patients The evaluation results indicated that 235 participants (37.72%) had insomnia, while 388 participants (62.28%) did not. The PSQI score for the insomnia group was 9, with an interquartile range of 8 to 11. Univariate analysis results are presented in Table 1. Variables significantly associated with insomnia ( p < 0.05) and incorporated decision tree algorithm analysis were BMI, NIHSS, FSS, SAS, SDS, and SSRS. 3.3 Construction of predictive decision tree model of insomnia The dataset, consisting of 623 samples, was divided into a training set and a validation set in a 7:3 ratio, with 436 samples allocated to the training set. Variables including BMI, NIHSS, FSS, SAS, SDS, and SSRS were incorporated into the model. The score distribution within the decision tree structure was illustrated in Figure 1, showing a total of 24 nodes and a depth of 6. Each variable’s contribution to the model was ranked as follows: SAS = 113.47, SSRS = 85.35, FSS = 63.96, SDS = 63.03, BMI = 17.70, and NIHSS = 6.73 (Figure 2). The analysis identified the SAS score as having the highest influence on insomnia risk, whereas the NIHSS had the lowest. Furthermore, Figure 1 showed the SAS score at the root node of the tree, underscoring that anxiety was the most significant factor in predicting insomnia among ISC patients. The algorithm identified a total of 24 decision paths, as detailed in Table 2. Each decision path described the corresponding critical threshold of the predictive variables that affect insomnia. The sleep states of ISC patients varied depending on the specific path, leading to different incidences of insomnia. Table 2 Decision path of the insomnia prediction model for ISC patients Decision Paths SAS SSRS FSS SDS BMI NIHSS Rate (%) Outcome Insomnia Non-insomnia 1 SAS ≥ 40 78 22 insomnia 2 SAS < 40 7 93 non-insomnia 3 SAS ≥ 40 SSRS < 44 88 12 insomnia 4 SAS ≥ 40 SSRS ≥ 44 27 71 non-insomnia 5 SAS ≥ 40 SSRS ≥ 44 BMI ≥ 24 60 40 insomnia 6 SAS ≥ 40 SSRS ≥ 44 BMI < 24 11 89 non-insomnia 7 SAS ≥ 40 SSRS < 44 FSS ≥ 21 90 10 insomnia 8 SAS ≥ 40 SSRS < 44 FSS < 21 50 50 insomnia 9 SAS ≥ 40 SSRS < 41 FSS≥21 96 4 insomnia 10 SAS ≥ 40 41≤SSRS<44≤SSRS<44SSRS<44≤SSRS<44 FSS≥21 76 24 insomnia 11 SAS≥46 41≤SSRS<44 FSS≥21 100 0 insomnia 12 40≤SAS<46 41≤SSRS<44 FSS≥21 55 45 insomnia 13 40≤SAS<46 41≤SSRS<44 FSS≥21 BMI≥22 69 31 insomnia 14 40≤SAS<46 41≤SSRS<44 FSS≥21 BMI<22 0 100 non-insomnia 15 SAS<40 SSRS<38 67 33 insomnia 16 SAS<40 SSRS≥38 6 94 non-insomnia 17 SAS<40 SSRS≥38 SDS≥45 50 50 insomnia 18 SAS<40 SSRS≥38 SDS<45 4 96 non-insomnia 19 37≤SAS<40 SSRS≥38 SDS<45 20 80 non-insomnia 20 SAS<37 SSRS≥38 SDS<45 2 98 non-insomnia 21 37≤SAS<40 38≤SSRS<46 SDS<45 38 62 insomnia 22 37≤SAS<40 SSRS≥46 SDS<45 5 95 non-insomnia 23 37≤SAS<40 38≤SSRS<46 SDS<45 NIHSS≥3 55 45 insomnia 24 37≤SAS<40 38≤SSRS<46 SDS<45 NIHSS<3 0 100 non-insomnia Note: BMI, Body Mass Index. FMA, Fugl-Meyer Assessment Scale. NIHSS, National Institute of Health stroke scale. BI, Barthel Index. FSS, fatigue severity scale. SAS, Self-Rating Anxiety Scale. SDS, Self-rating Depression Scale. SSRS, social support rate scale. 3.4 Internal validation of a decision tree model for insomnia risk In the verification dataset containing 187 cases (Figure 3), the confusion matrix analysis showed that the model correctly predicted a total of 165 cases. Specifically, it predicted 73 cases of insomnia, of which 62 were actual cases of insomnia. Similarly, it predicted 114 cases as non-insomnia, correctly identifying 103 non-insomnia cases Based on these values, the model’s accuracy rate (ACC) on the test set was 88.2 %, indicating a relatively high prediction accuracy. ROC analysis yielded AUC of 0.96 ( p < 0.001, 95% CI: 0.93~0.98) (Figure 4). In addition, the model achieved a sensitivity of 0.96, a specificity of 0.84, and a Youden index of 0.80 (Figure 5). These results suggested that the model maintained strong discriminatory power, even after incorporating internal validation data. The H-L test results indicated that χ 2 = 9.36, p = 0.404. Additionally, the calibration curve closely aligned with the diagonal reference line (Figure 6), demonstrating that the model maintained strong calibration even after incorporating internal validation data. This result confirms that the model can accurately predict the incidence of insomnia among ISC patients. 3.5 External validation of a decision tree model for insomnia risk The baseline data of patients in the external validation dataset were showed in Table 3. A total of 200 ISC patients were included, the incidence rate of insomnia was 37.0 %, which was similar to the results of the dataset for model establishment. The accuracy of the model is 78.3%, which shows a slight decrease compared with the original model.(AUC = 0.88, 95 % CI: 0.78~0.95; p < 0.001). However, the H-L test proved that the model was well-calibrated (χ 2 = 0.14, p = 0.93) (Figure 7, 8, 9). This further validated that, even after introducing external non-homologous data, the model’s stability was still relatively strong. Table 3 Baseline characteristics of patients in the external validation dataset (n = 200) Demographic factors Total (n = 200) n (%) Insomnia (n = 74) n (%) Non-insomnia (n = 126) n (%) c 2 /Z p -value Age [median (IQR)] 63 (56, 68) 62 (53, 67) 63 (57, 68) 0.789 0.561 Gender Male 120 (60) 38 (51.4) 82 (65.1) 3.661 0.056 Female 80 (40) 36 (48.6) 44 (34.9) Education level Primary or below 15 (7.5) 4 (5.4) 11 (8.7) 5.689 0.128 Junior school 59 (29.5) 17 (23.0) 42 (33.3) High school 73 (36.5) 27 (36.5) 46 (36.5) College or above 53 (26.5) 26 (35.1) 27 (21.4) Marital status Married 186 (93.0) 69 (93.2) 117 (92.9) 3.840 0.271 Single 2 (1.0) 0 (0.0) 2 (1.6) Divorced 6 (3.0) 1 (1.4) 5 (4.0) Widowed 6 (3.0) 14 (5.4) 2 (1.6) Insurance type Urban residents 54 (27.0) 18 (24.3) 36 (28.6) 1.878 0.392 Rural cooperative 143 (71.5) 56 (75.7) 87 (69.0) Other 3 (1.5) 0 (0.0) 3 (2.4) Monthly income(R) ≤2000 25 (12.5) 11 (14.9) 14 (11.1) 4.882 0.181 2000～4000 92 (46.0) 27 (36.5) 65 (51.6) 4000～6000 66 (33.0) 30 (40.5) 36 (28.6) ≥6000 17 (8.5) 6 (8.1) 11 (8.7) Smoking status Current smoker 71 (35.5) 23 (31.1) 48 (38.1) 1.002 0.317 Non-current smoker 129 (64.5) 51 (68.9) 78 (61.9) Continued Demographic factors Total (n = 200) n (%) Insomnia (n = 74) n (%) Non-insomnia (n = 126) n (%) c 2 /Z p- value Alcohol status Drinker 59 (29.5) 20 (27.0) 39 (31.0) 0.345 0.557 Non-drinker 141 (70.5) 54 (73.0) 87 (69.0) BMI(Kg/m 2 ) [median (IQR)] 23.57 (22.55, 24.98) 24.68 (22.69, 26.85) 23.42 (22.62, 24.23) 2.534 ＜ 0.001 ** Stroke location Anterior circulation 63 (31.5) 20 (27.0) 43 (34.1) 1.089 0.297 Posterior circulation 137 (68.5) 54 (73.0) 83 (65.9) Hypertension Yes 127 (63.5) 42 (56.8) 85 (67.5) 2.304 0.129 No 73 (36.5) 32 (43.2) 41 (32.5) Diabetes Yes 64 (32.0) 24 (32.4) 40 (31.7) 0.010 0.920 No 136 (68.0) 50 (67.6) 86 (68.3) Coronary heart disease Yes 29 (14.5) 11 (14.9) 18 (14.3) 0.013 0.911 No 171 (85.5) 63 (85.1) 108 (85.7) Hyperlipidemia Yes 38 (19.0) 15 (20.3) 23 (18.3) 0.123 0.726 No 162 (81.0) 59 (19.7) 103 (81.7) Arhythmia Yes 32 (16.0) 11 (14.9) 21 (16.7) 0.113 0.737 No 168 (84.0) 63 (85.1) 105 (83.3) FMA [median (IQR)] 61 (45, 76) 63 (46, 82) 59 (43, 75) 0.861 0.449 NIHSS [median (IQR)] 4 (3, 5) 4 (3, 5) 5 (4, 6) 1.636 0.009 ** BI [median (IQR)] 65 (55, 75) 70 (60, 76) 65 (50, 75) 1.075 0.198 FSS [median (IQR)] 26 (22, 29) 27 (27, 34) 23 (20, 26) 4.599 ＜ 0.001 ** SAS [median (IQR)] 38 (34, 45) 45 (44, 49) 34 (31, 38) 5.239 ＜ 0.001 ** SDS [median (IQR)] 35 (31, 43) 41 (35, 46) 33 (30, 38) 2.919 ＜ 0.001 ** SSRS [median (IQR)] 44 (41, 46) 41 (39,43) 46 (43, 47) 3.710 ＜ 0.001 ** Note: The comparison between insomnia group and non-insomnia group reveals significant differences: * p < 0.05; ** p < 0.001. The total score of the nomogram for predicting the risk of insomnia among ISC patients ranged from 0 to 220, with the probability of insomnia between 0.1 and 0.9 (Figure 10). 4 Discussion This study aimed to explore the independent predictors of insomnia in ischemic ISC patients. The results revealed that the incidence of insomnia was relatively high among these patients, with anxiety, depression, social support, BMI, fatigue, and NIHSS scores emerging as key predictors. Stroke often leads patients to experience negative emotions. 28 Mental health issues following a stroke included low attention and memory, apathy, and depression. 9 , 29 Previous studies had shown that post-stroke depression was a significant cause of insomnia. 30 Our study results aligned with prior research, emphasizing that negative emotions were key factors contributing to post-stroke insomnia. In the decision tree model, the anxiety score had three decision thresholds set at 37, 40, and 46, with the anxiety score at the root node of the model. When SAS was less than 37, the incidence of insomnia was relatively low, at only 2%. However, as the SAS score increased, the risk of insomnia rose significantly accordingly. This may be due to autonomic nervous system disturbances among patients with anxiety, leading to emotional imbalance, tension, and fear, all of which severely disrupted sleep quality. 31 Consequently, alleviating anxiety may be essential for improving insomnia in these patients. Furthermore, a critical value of 45 was set for depression, with higher levels of depressive symptoms significantly impacting patients' sleep. Specifically, when the SDS score reached 45 or higher, patients were at greater risk of insomnia. In modern medicine, the role of psychological factors in patients’ rehabilitation is increasingly acknowledged. Therefore, medical staffs need to focus not only on physical recovery but also on comprehensive management of negative emotions to facilitate the rehabilitation process. Psychosocial factors have gained considerable attention as modifiable elements. Fewer studies examined how protective psychosocial factors affected the sleep quality of stroke patients. 32 , 33 Stroke survivors often require external emotional and material support to adapt to daily life and face changes. In light of this, our study analyzed social support as a relevant factor. The results of the decision tree model indicated that social support as a crucial factor in predicting insomnia, ranked just below the root node in importance. This variable had four decision thresholds: 38, 41, 44, and 46 points. When the SSRS score was ≥ 46, the incidence of insomnia was as low as 5%. At a stable level of patient anxiety, enhancing social support could effectively diminish the likelihood of insomnia. This benefit likely arises from the support provided by family, caregivers, and friends, which fosters a secure environment, lowers patient vigilance, and promotes better sleep quality. 34 Thus, a high level of social support can enhance the functional recovery of ISC patients and mitigate the risk of insomnia. These findings aligned with previous research. 35 Medical staff should prioritize not only physical recovery but also the social support needs of stroke patients, potentially improving sleep quality. The post-stroke fatigue could lead to several challenges, including difficulties in maintaining rehabilitation, decreased motivation, emotional challenges, reduced social interactions, and a loss of goals. 36 Our study identified a critical threshold in the FSS score within the decision tree model. This threshold suggested that patients with similar levels of anxiety and social support can lower their risk of insomnia by alleviating fatigue symptoms, highlighting a potential direct impact of fatigue on sleep quality. Poor sleep quality among patients with post-stroke fatigue may result from daytime sleepiness, which is closely linked to fatigue. 37 This finding reinforced the appropriateness of identifying fatigue as an independent predictor in the insomnia risk decision tree model. Choi-Kwon and Kim (2011) reported a correlation between poor sleep quality and elevated fatigue levels in stroke patients, particularly in older ISC patients, which aligned with our results. 38 However, fatigue severity and insomnia in ISC patients, along with factors such as age, daily activity levels, and other potential mediators, warrant further investigation to better understand their interactions. The BMI and NIHSS, as objective factors included in the decision tree model for predicting insomnia. Research has shown that ISC patients with high BMI are more likely to experience insomnia. 39 Furthermore, a higher BMI is positively correlated with overweight and obesity, which in turn increases insomnia risk. 40 In our study, decision paths 5, 6, 13, and 14 in the model demonstrated that effective BMI management can significantly reduce insomnia risk. The severity of neurological deficits could significantly affect sleep quality in post-stroke patients. 17 , 41 This may be due to irreversible nerve cell damage, which can lead to the release of toxic substances that cross the blood-brain barrier and disrupt the sleep-wake system. 3 In this study, we included ISC patients with NIHSS scores below 15, as patients with scores of 15 or above frequently exhibit severe cognitive impairments and communication disorders, which could complicate the study's findings. Patients with an NIHSS score of 3 or higher had a significantly increased risk of insomnia (up to 55%). Although NIHSS had the lowest predictive impact for insomnia among ISC patients, its critical value is useful in assessing risk. This highlighted the need for further research on the relationship between stroke severity and sleep quality. Limitations There were several limitations in this study. First, future research should consider include objective factors that influence insomnia, particularly serological biochemical indicators, gut flora, and metabolites. Second, while this study included 823 ISC patients, expanding the sample size in future studies will enhance the ability to identify more risk factors. Third, the use of convenience sampling may affect the accuracy and reliability of the results. Last, the insomnia risk decision tree model was validated using data from only one hospital; applying the model across multiple clinical settings in the future will improve its accuracy and generalizability. Implications for practice This study underlines the significance of conducting early insomnia screening for stroke patients during their recovery phase. Medical staffs, while facilitating patients' active rehabilitation, ought to place particular emphasis on factors like anxiety, depression, the extent of social support, and post-stroke fatigue. Concurrently, they should implement targeted interventions to address insomnia. Such measures are conducive to sustaining patients' psychological equilibrium, enhancing their sleep quality, and, ultimately, expediting the overall recovery process. 5 Conclusions The decision tree model developed in this study for predicting insomnia risk demonstrated high accuracy, showcasing excellent discrimination capabilities. To our knowledge, this was the first study to develop and evaluate such a model specifically for ISC patients. The nomogram provided an easy-to-use, personalized tool for insomnia prediction and further optimized clinical management. Both internal and external validations confirmed the model’s accuracy in predicting insomnia occurrence among ISC patients. In clinical applications, the nomogram could be integrated with existing sleep assessment scales, providing a comprehensive assessment of ISC patients. Declarations Declaration of Conflicting Interests We have no conflicts of interest to disclose. Authorship contribution statement X.S. and H.Z. wrote the main manuscript text and S.S., D.C., X.Z., Y.Z., Y.S., and Z.W prepared figures 1-10. All authors reviewed the manuscript. Acknowledgments The author sincerely thanks all medical staff and expresses sincere gratitude to all patients in the recovery period of ischemic stroke who participated in this study. In addition, thanks Xuewen Sun (Beijing Forestry University) for revising the grammar and vocabulary of the manuscript. Funding This study was funded by the Jilin Province Science and Technology Development Plan Project (Grant No. 232662SF0103109942), the National Natural Science Foundation of China (Grant No. 82074569), and the National Key R & D Program of China (Grant No. 2018YFC1706002). Ethical approval The registration number of this study is CZDSFYLL2024-056-01. This is a clinical investigation study approved by the Ethics Committee of The Third Affiliated Hospital of Changchun University of Chinese Medicine in August 2024. All participants were enrolled in the investigation using the principles of informed consent and confidentiality. Data availability statement The data will not be shared without permission of all authors. Please contact H.Z. if required. Consent for publication Not applicable. References Leone M, Ciccacci F, Orlando S, Petrolati S, Guidotti G, Majid NA, et al. Pandemics and Burden of Stroke and Epilepsy in Sub-Saharan Africa: Experience from a Longstanding Health Programme. Int J Environ Res Public Health. 2021;18(5):2766. Boursin P, Paternotte S, Dercy B, Sabben C, Maïer B. Sémantique, épidémiologie et sémiologie des accidents vasculaires cérébraux [Semantics, epidemiology and semiology of stroke]. Soins. 2018;63(828):24–7. Byun E, Kohen R, Becker KJ, Kirkness CJ, Khot S, Mitchell PH. Stroke impact symptoms are associated with sleep-related impairment. Heart Lung. 2020;49(2):117–22. Moon HI, Yoon SY, Jeong YJ, Cho TH. Sleep disturbances negatively affect balance and gait function in post-stroke patients. NeuroRehabilitation. 2018;43(2):211–8. Iddagoda MT, Inderjeeth CA, Chan K, Raymond WD. Post-stroke sleep disturbances and rehabilitation outcomes: a prospective cohort study. Intern Med J. 2020;50(2):208–13. Oliveira GDP, Vago ERL, Prado GFD, Coelho FMS. The critical influence of nocturnal breathing complaints on the quality of sleep after stroke: the Pittsburgh Sleep Quality Index and STOP-BANG. Arq Neuropsiquiatr. 2017;75(11):785–8. Battle DE. Diagnostic and Statistical Manual of Mental Disorders (DSM). Codas. 2013;25(2):191–2. Wang X, Ji X. Interactions between remote ischemic conditioning and post-stroke sleep regulation. Front Med. 2021;15(6):867–76. Kusec A, Milosevich E, Williams OA, Chiu EG, Watson P, Carrick C, et al. Long-term psychological outcomes following stroke: the OX-CHRONIC study. BMC Neurol. 2023;23(1):426. Yu SY, Sun Q, Chen SN, Wang F, Chen R, Chen J, et al. Circadian Rhythm Disturbance in Acute Ischemic Stroke Patients and Its Effect on Prognosis. Cerebrovasc Dis. 2024;53(1):14–27. Zhang W, Li F, Zhang T. Relationship of nocturnal concentrations of melatonin, gamma-aminobutyric acid and total antioxidants in peripheral blood with insomnia after stroke: study protocol for a prospective non-randomized controlled trial. Neural Regen Res. 2017;12(8):1299–307. Besedovsky L, Lange T, Haack M. The Sleep-Immune Crosstalk in Health and Disease. Physiol Rev. 2019;99(3):1325–80. Westfall S, Lomis N, Kahouli I, Dia SY, Singh SP, Prakash S. Microbiome, probiotics and neurodegenerative diseases: deciphering the gut brain axis. Cell Mol Life Sci. 2017;74(20):3769–87. Hu W, Kong X, Wang H, Li Y, Luo Y. Ischemic stroke and intestinal flora: an insight into brain-gut axis. Eur J Med Res. 2022;27(1):73. Published 2022 May 25. Khot SP, Morgenstern LB. Sleep Stroke Stroke. 2019;50(6):1612–7. Kolmos M, Christoffersen L, Kruuse C. Recurrent Ischemic Stroke - A Systematic Review and Meta-Analysis. J Stroke Cerebrovasc Dis. 2021;30(8):105935. Mohandas P, Alomari Z, Arti F, Alhneif M, Alejandra Ruiz P, Ahmed AK, et al. A Systematic Review and Meta-Analysis on the Identification of Predictors Associated With Insomnia or Sleep Disturbance in Post-stroke Patients. Cureus. 2024;16(3):e56578. Ryu D, Sok S. Prediction model of quality of life using the decision tree model in older adult single-person households: a secondary data analysis. Front Public Health. 2023;11:1224018. Oh HS, Park HA. Decision tree model of the treatment-seeking behaviors among Korean cancer patients. Cancer Nurs. 2004;27(4):259–66. Song J, Gao Y, Yin P, Li Y, Li Y, Zhang J, et al. The Random Forest Model Has the Best Accuracy Among the Four Pressure Ulcer Prediction Models Using Machine Learning Algorithms. Risk Manag Healthc Policy. 2021;14:1175–87. Rawal B, Agarwal R. Improving accuracy of classification based on C4. 5 decision tree algorithm using big data analytics[C]//Computational Intelligence in Data Mining: Proceedings of the International Conference on CIDM 2017. Springer Singapore, 2019: 203–211. Riemann D, Espie CA, Altena E, Arnardottir ES, Baglioni C, Bassetti CLA, et al. The European Insomnia Guideline: An update on the diagnosis and treatment of insomnia 2023. J Sleep Res. 2023;32(6):e14035. Falck RS, Best JR, Davis JC, Eng JJ, Middleton LE, Hall PA, et al. Sleep and cognitive function in chronic stroke: a comparative cross-sectional study. Sleep. 2019;42(5):zsz040. Krupp LB, LaRocca NG, Muir-Nash J, Steinberg AD. The fatigue severity scale. Application to patients with multiple sclerosis and systemic lupus erythematosus. Arch Neurol. 1989;46(10):1121–3. Zung WW. K. A self-rating depression scale[J]. Arch Gen Psychiatry. 1965;12(1):63–70. Shuiyuan X. The theoretical basis and research application of social support rating scale[J]. J Clin Psychiatry. 1994;2:98–100. Grajski KA, Breiman L, Di Viana G, Freeman WJ. Classification of EEG spatial patterns with a tree-structured methodology: CART. IEEE Trans Biomed Eng. 1986;33(12):1076–86. Rafsten L, Danielsson A, Sunnerhagen KS. Anxiety after stroke: A systematic review and meta-analysis. J Rehabil Med. 2018;50(9):769–78. Chen R, Guo Y, Kuang Y, Zhang Q. Effects of home-based exercise interventions on post-stroke depression: A systematic review and network meta-analysis. Int J Nurs Stud. 2024;152:104698. Schöttke H, Giabbiconi CM. Post-stroke depression and post-stroke anxiety: prevalence and predictors. Int Psychogeriatr. 2015;27(11):1805–12. Kim WH, Jung HY, Choi HY, Park CH, Kim ES, Lee SJ, et al. The associations between insomnia and health-related quality of life in rehabilitation units at 1month after stroke. J Psychosom Res. 2017;96:10–4. Glozier N, Moullaali TJ, Sivertsen B, Kim D, Mead G, Jan S, et al. The Course and Impact of Poststroke Insomnia in Stroke Survivors Aged 18 to 65 Years: Results from the Psychosocial Outcomes In StrokE (POISE) Study. Cerebrovasc Dis Extra. 2017;7(1):9–20. Iwuozo EU, Enyikwola JO, Asor PM, Onyia UI, Nwazor EO, Obiako RO. Sleep disturbances and associated factors amongst stroke survivors in North Central, Nigeria. Niger Postgrad Med J. 2023;30(3):193–9. Zhao Y, Hu B, Liu Q, Wang Y, Zhao Y, Zhu X. Social support and sleep quality in patients with stroke: The mediating roles of depression and anxiety symptoms. Int J Nurs Pract. 2022;28(3):e12939. Xiao H, Zhang Y, Kong D, Li S, Yang N. The Effects of Social Support on Sleep Quality of Medical Staff Treating Patients with Coronavirus Disease 2019 (COVID-19) in January and February 2020 in China. Med Sci Monit. 2020;26:e923549. Sato M, Hyakuta T. Awareness and support for post-stroke fatigue among medical professionals in the recovery phase rehabilitation ward. Jpn J Compr Rehabil Sci. 2023;14:39–48. Lee J, Choi YS, Jeong YJ, Lee J, Kim JH, Kim SH. Poor-quality sleep is associated with metabolic syndrome in Korean adults. Tohoku J Exp Med. 2013;231(4):281–91. Choi-Kwon S, Kim JS. Poststroke fatigue: an emerging, critical issue in stroke medicine. Int J Stroke. 2011;6(4):328–36. Shi Y, Zhou W. Interactive Effects of Dietary Inflammatory Index with BMI for the Risk of Stroke among Adults in the United States: Insight from NHANES 2011–2018. J Nutr Health Aging. 2023;27(4):277–84. Muhammad T, Gharge S, Meher T. The associations of BMI, chronic conditions and lifestyle factors with insomnia symptoms among older adults in India. PLoS ONE. 2022;17(9):e0274684. Xu H, Li W, Chen J, Zhang P, Rong S, Tian J, et al. Associations between insomnia and large vessel occlusion acute ischemic stroke: An observational study. Clin (Sao Paulo). 2023;78:100297. Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterialforEditors.docx Cite Share Download PDF Status: Published Journal Publication published 19 Aug, 2025 Read the published version in BMC Public Health → Version 1 posted Editorial decision: Revision requested 18 Jun, 2025 Reviews received at journal 15 Jun, 2025 Reviewers agreed at journal 15 Jun, 2025 Reviews received at journal 15 Jun, 2025 Reviewers agreed at journal 15 Jun, 2025 Reviews received at journal 14 Jun, 2025 Reviewers agreed at journal 12 Jun, 2025 Reviews received at journal 10 Jun, 2025 Reviewers agreed at journal 27 May, 2025 Reviewers agreed at journal 24 May, 2025 Reviewers agreed at journal 22 May, 2025 Reviews received at journal 16 Apr, 2025 Reviewers agreed at journal 12 Apr, 2025 Reviewers agreed at journal 11 Apr, 2025 Reviewers invited by journal 11 Apr, 2025 Editor assigned by journal 11 Apr, 2025 Editor invited by journal 25 Mar, 2025 Submission checks completed at journal 21 Mar, 2025 First submitted to journal 21 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-6248505","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":442125781,"identity":"63979308-7558-4461-90a3-7aa8c9074605","order_by":0,"name":"Xuefeng Sun","email":"","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xuefeng","middleName":"","lastName":"Sun","suffix":""},{"id":442125784,"identity":"d9cb743b-010e-4ed6-bc4f-354419b3a052","order_by":1,"name":"Zilin Wang","email":"","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Zilin","middleName":"","lastName":"Wang","suffix":""},{"id":442125789,"identity":"c9a5c2db-c305-4f6a-8dea-99d8c75d3adf","order_by":2,"name":"Yuqing Song","email":"","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yuqing","middleName":"","lastName":"Song","suffix":""},{"id":442125792,"identity":"9e72eed0-1884-4420-a7ab-b760ba03f98e","order_by":3,"name":"Deyu Cong","email":"","orcid":"","institution":"The Affiliated Hospital to Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Deyu","middleName":"","lastName":"Cong","suffix":""},{"id":442125794,"identity":"2473fa12-072b-4d07-9b1d-acef83a996d2","order_by":4,"name":"Shu Sun","email":"","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Shu","middleName":"","lastName":"Sun","suffix":""},{"id":442125796,"identity":"dc42c6f4-5011-49f5-8afc-fda3e5f44b82","order_by":5,"name":"Xinye Zhang","email":"","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xinye","middleName":"","lastName":"Zhang","suffix":""},{"id":442125799,"identity":"6e1141fe-ee1c-4aca-9689-aefd3a6b809c","order_by":6,"name":"Ye Zhang","email":"","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Ye","middleName":"","lastName":"Zhang","suffix":""},{"id":442125801,"identity":"69ce4b65-973d-4d46-baaf-5d452045fbda","order_by":7,"name":"Hongshi Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAs0lEQVRIiWNgGAWjYBAC+/kHmx///GcjR7wWAwnmY8YMbGnGpGhhS5BmYDuU2EC0FnPpHgPjAp4D6X3HExg/fMwhQovlnDMGj2dI3MmdeeYBs+TMbcRYcyDHwIDH4FnuhhsJbMy8xGqR4Ek4nG5AtBaDG2kJ0jwHDicQr0Wy5/Axw5kNaYYzzzxsJs4v/OyNzQ8+NtjI8x1PPvjhI1F+gYMDJEQNTEsCqTpGwSgYBaNgpAAAyIM9YAlk2JwAAAAASUVORK5CYII=","orcid":"","institution":"Changchun University of Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Hongshi","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-03-18 02:08:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6248505/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6248505/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12889-025-24025-z","type":"published","date":"2025-08-19T16:12:55+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80815235,"identity":"75fa5a3a-b1f5-47ec-9f13-617eb698c52c","added_by":"auto","created_at":"2025-04-17 10:57:11","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":154120,"visible":true,"origin":"","legend":"\u003cp\u003eDecision tree model diagram of insomnia risk for ISC patients. The colors of the nodes signified different outcomes: green nodes indicated insomnia, blue nodes indicated non-insomnia and darker shades signified a higher proportion of patients with insomnia or non-insomnia.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/413fbb8ccc4498ef532e6ba1.png"},{"id":80816403,"identity":"347c9816-a2b1-4cac-a7d7-2cbf4a058460","added_by":"auto","created_at":"2025-04-17 11:13:11","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":31309,"visible":true,"origin":"","legend":"\u003cp\u003eThe feature importance of predictor variables in the decision tree for ISC patients.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/d3a810f72da213400fe6d925.png"},{"id":80815740,"identity":"fdc55e71-4462-4d87-ae53-bc7232cff685","added_by":"auto","created_at":"2025-04-17 11:05:11","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":11898,"visible":true,"origin":"","legend":"\u003cp\u003eThe confusion matrix results for internal validation of the decision tree model. \"0\" represented non-insomnia, and \"1\" represented insomnia.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/0288a4909417f991d0aba143.png"},{"id":80816524,"identity":"a11c9824-3fcb-44a0-b53b-430be40db62d","added_by":"auto","created_at":"2025-04-17 11:21:11","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":68026,"visible":true,"origin":"","legend":"\u003cp\u003eROC curve for internal validation of decision tree model. The area under the ROC curve (AUC) was a comprehensive indicator to evaluate the performance of a prediction model.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/3bdd858af184e368db8f15f0.png"},{"id":80815239,"identity":"69ade43e-7409-4b30-be1a-31f37030d88d","added_by":"auto","created_at":"2025-04-17 10:57:11","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":20955,"visible":true,"origin":"","legend":"\u003cp\u003eSensitivity, specificity, and Youden index of the decision tree model.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/e6c904ed6d256edf1ec31f85.png"},{"id":80815246,"identity":"312f19f0-85b5-4b32-a586-0ef2c590d8b4","added_by":"auto","created_at":"2025-04-17 10:57:11","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":38330,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration curve for internal validation of decision tree model. The closer the red curve is to the reference line, the higher the calibration degree of the model will be.\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/8211cf30dbb8f36b558c3712.png"},{"id":80815747,"identity":"e6dbad12-f8a7-465f-94c6-37a8015e31d1","added_by":"auto","created_at":"2025-04-17 11:05:11","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":24035,"visible":true,"origin":"","legend":"\u003cp\u003eThe confusion matrix results for external validation of the decision tree model.\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/c44ba6cb35901dfc31f9a5eb.png"},{"id":80815287,"identity":"d3617f71-13e4-4b4d-b030-473f44f621f2","added_by":"auto","created_at":"2025-04-17 10:57:13","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":30999,"visible":true,"origin":"","legend":"\u003cp\u003eROC curve for external validation of decision tree model.\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/e51fbaa85579e6e848b1bbfa.png"},{"id":80815252,"identity":"e004873f-609f-42cc-945a-863583231c12","added_by":"auto","created_at":"2025-04-17 10:57:11","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":23628,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration curve for external validation of decision tree model.\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/4573c540874156cea1baf07a.png"},{"id":80816412,"identity":"90f732ca-5386-4b54-9e75-b31024bf29a3","added_by":"auto","created_at":"2025-04-17 11:13:12","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":26426,"visible":true,"origin":"","legend":"\u003cp\u003eNomogram predicting the probability of insomnia among ISC patients.\u003c/p\u003e","description":"","filename":"10.png","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/ad78ac786f5e1bca05853836.png"},{"id":89847105,"identity":"f2ade07c-c843-4ab4-a420-8d7638edb2c9","added_by":"auto","created_at":"2025-08-25 16:39:58","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1652587,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/137fec6f-10d4-4682-bf6c-265291670c75.pdf"},{"id":80815757,"identity":"3740435b-5488-43fd-a3df-969e73a3319a","added_by":"auto","created_at":"2025-04-17 11:05:12","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":3745394,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterialforEditors.docx","url":"https://assets-eu.researchsquare.com/files/rs-6248505/v1/f089b71491a4678217faad24.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and validation of a decision tree model for prediction of insomnia risk among ischemic stroke convalescence patients","fulltext":[{"header":"1 Background","content":"\u003cp\u003eStroke is a prevalent neurological disease that profoundly impacts individuals' lives, health, and overall well-being. It is the second leading cause of death and a primary cause of disability, imposing a considerable global burden on healthcare resources and infrastructure.\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e Ischemic stroke, the most common type, accounts for 80% of all stroke cases.\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e Stroke survivors often endure long-term symptoms, including motor dysfunction, visual impairment, cognitive and verbal communication impairments, emotional difficulties, sexual function, and sleep disturbance.\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e Research has shown a high prevalence of post-stroke insomnia, affecting 75\u0026thinsp;~\u0026thinsp;95% of stroke patients globally.\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e This condition frequently emerges during recovery from ischemic stroke, yet it remains an under-recognized complication in clinical practice. A cohort study in Australia found that 29.8% of stroke patients experienced poor sleep quality,\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e and a survey in Brazil reported that 70.6% of stroke patients had poor sleep quality within the first year post-stroke.\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eThe fifth edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) defines insomnia as a condition characterized by difficulty falling asleep, maintaining sleep, or waking up too early in the morning and being unable to fall back asleep. These symptoms must occur at least three nights per week for three months, leading to dissatisfaction with sleep quality or quantity.\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e Insomnia is a common complication following a stroke, though its underlying mechanisms remain poor and complex to understand. Several factors contribute to post-stroke insomnia. First, brain injury itself can damage the sleep-wake regulation center in the thalamus.\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e Second, psychological issues such as anxiety and depression, which often arise after a stroke, may exacerbate insomnia.\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e Third, complications of cerebrovascular diseases, such as cardiopulmonary diseases, epilepsy, and infections, may further fragment sleep and contribute to insomnia.\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e In addition, nighttime levels of melatonin, gamma-aminobutyric acid, and total antioxidant concentrations in stroke patients may be related to insomnia.\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e Current evidence suggests that intestinal flora and its metabolites influence the development of post-stroke insomnia. They do so primarily through the regulation of the nervous system regulation,\u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e disruption of the blood-brain barrier,\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e and by affecting the function of the hypothalamic-pituitary-adrenal axis.\u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eEvaluating insomnia in patients is challenging due to the subjective nature of their symptoms, making it difficult to assess using simple medical examinations. As a result, there was a generally low awareness and screening rate for post-stroke insomnia, which increased the risk of poor prognosis and stroke recurrence.\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e Identified factors related to insomnia in ischemic stroke convalescence (ISC) patients included sociodemographic characteristics, and clinical factors, as well as depression and anxiety.\u003csup\u003e\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e The occurrence and development of insomnia in these patients stem from the combined influence of clinical, psychological, and social factors, which may interact in complex ways. However, the specific pathways of these interactions and their contributions to insomnia remain unclear. Consequently, establishing a prediction model for insomnia in ISC patients, along with early identification and screening of high-risk groups, has become an urgent issue that demands attention.\u003c/p\u003e \u003cp\u003eCurrently, the assessment of sleep in ISC patients primarily relies on subjective or objective measurement tools, such as traditional logistic regression analysis.\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u003c/sup\u003e With the advent of the big data era, the role of data mining technology in the medical field has become increasingly prominent. Decision tree models, in particular, have been employed in research related to stroke, infection, frailty, pressure injuries, and mild cognitive impairment.\u003csup\u003e\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e,\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e,\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e The decision tree model for insomnia risk in ISC patients was constructed through the classification and regression tree (CART) algorithm in machine learning. This algorithm is capable of analyzing both categorical and continuous variables, effectively utilizing all available sample data, managing high-dimensional data, screening important variables, and achieving relatively high prediction accuracy.\u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eIn our study, we identified the key predictive variables for insomnia in ISC patients. Using the CART algorithm, we were able to clearly present the contribution values and thresholds of these variables. This allowed doctors and nurses to formulate a decision-making path for assessing insomnia risk, which can serve as a valuable reference for the clinical management of post-stroke insomnia.\u003c/p\u003e"},{"header":"2 Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study design and patients\u003c/h2\u003e \u003cp\u003e This is a clinical investigation study conducted in accordance with the ethical standards of The Third Affiliated Hospital of Changchun University of Chinese Medicine and approved by the Ethics Committee in August 2024.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Initial predictors\u003c/h2\u003e \u003cp\u003eFrom the reviewed literature, twenty-two factors have been identified as related to insomnia in ISC patients, including (a) gender; (b) age; (c) marital status; (d) educational level; (e) insurance type; (f) monthly income; (g) FMA score; (h) stroke location; (i) stroke severity; (j) body mass index; (k) ADL; (l) hypertension; (m) diabetes mellitus; (n) coronary heart disease; (0) arrhythmia; (p) hyperlipidemia; (q) smoking; (r) alcohol; (s) fatigue; (t) depression; (u) anxiety; (v) social support.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Study criteria\u003c/h2\u003e \u003cp\u003eParticipants met the diagnostic criteria for both ischemic stroke and insomnia.\u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e The inclusion criteria were as follows: (a) aged between 40 and 75 years; (b) in the recovery period; (c) had their first disease; (d) capable of completing the questionnaire and scales independently, with sufficient behavioral and language abilities. The exclusion criteria were: (a) patients with impaired consciousness, cognition, or understanding and expression following ischemic stroke; (b) patients with pre-existing insomnia diagnoses or treatments before the ischemic stroke; (c) individuals currently using or having previously used sleeping medications; (d) patients with severe complications from other systems such as heart, liver, lung and kidney.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Data collection\u003c/h2\u003e \u003cp\u003eDuring hospitalization, general information including age, sex, height, weight, marital status, insurance type, smoking and drinking status, and clinical comorbidities were collected. Additionally, patients\u0026rsquo; stroke location, degree of neurological impairment, motor balance scores for upper and lower limbs, and daily activity scores were collected. The Pittsburgh Sleep Quality Index (PSQI) was used to evaluate the sleep quality of ISC patients.\u003csup\u003e\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e A PSQI score above 7 points indicated poor sleep quality (insomnia), while a score of 7 or below indicated good sleep quality (non-insomnia). Fatigue Severity Scale (FSS) was often used to evaluate the post-stroke fatigue level among patients.\u003csup\u003e\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e A score below 36 indicated minimal fatigue, while a score of or above 36 may warrant further medical evaluation. The anxiety and depression were assessed by the Self-rating anxiety scale (SAS) and Self-rating depression scale (SDS), respectively.\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e The higher total scores reflected more severe levels of anxiety and depression among ISC patients. Social support was measured using the SSRS. Higher scores indicated greater levels of social support.\u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Statistical analysis and sample size calculating\u003c/h2\u003e \u003cp\u003eData statistics and analysis was performed using SPSS 24.0 software. Continuous data were described using mean and standard deviations (for normally distributed data) or medians and interquartile range (IQR) (for skewed distributed data). Categorical data were summarized as frequencies and proportions. For continuous variables with normal distribution, a two independent samples t-test was used for group comparison when variances were homogeneous. For skewed continuous variables, the rank sum test was employed for comparison between groups, while the Chi-squared test was used for categorical variables. A \u003cem\u003ep\u003c/em\u003e-value of \u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/p\u003e \u003cp\u003eModel construction utilized the CART algorithm, a decision tree model proposed by Breiman and his colleagues in 1984.\u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e This algorithm addresses both classification and regression problems by minimizing the Gini coefficient or squared error, thus dividing the root node into two child nodes. This splitting process is repeated, further dividing nodes until no additional splits are possible. Statistically significant variables obtained from single-factor analysis were used as potential initial factors affecting insomnia in ISC patients. Fill in the missing values by means of mean and median. The model parameter settings include: the random seed number is 94, the complexity parameter is 0.01, the minimum sample split is 3, and the maxdepth is 6. The model was implemented using R version 4.2.2 and R Studio.\u003c/p\u003e \u003cp\u003eFor model verification, the Bootstrap method with 1000 repeated samplings was employed for internal validation. A confusion matrix, ROC curve, H-L test, and calibration curve were used for internal and external validation. According to the events per variable (EPV) rule, we adopted an EPV of 10, accounting for a 5% loss during the investigation, thus requiring 623 samples for this study.\u003c/p\u003e \u003c/div\u003e"},{"header":"3 Results","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003e3.1 Characteristics of participants\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe sociodemographic and clinical characteristics of the insomnia and non-insomnia groups were presented in Table 1. Among the 623 participants, the average age was 61(55, 67) years. There were 417 male ISC patients (66.9 %), significantly more than 206 female ISC patients (33.1 %). The average BMI of participants was 23.57 (22.55, 24.98) kg / m\u003csup\u003e2\u003c/sup\u003e, and the BMI values ranged from 17.3 to 38.28 kg/m\u003csup\u003e2\u003c/sup\u003e. Regarding educational background, the proportions of different education levels among participants were 7.7 %, 24.1 %, 33.9 %, and 34.3 %. Additionally, 38.8% of participants were smokers, while 34.8% reported drinking alcohol.\u003c/p\u003e\n\u003cp\u003eTable 1 Patient characteristics between insomnia and non-insomnia groups (n = 623)\u003c/p\u003e\n\u003ctable width=\"113%\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eDemographic factors\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003eTotal (n = 623)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003eInsomnia (n = 235)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003eNon-insomnia (n = 388)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003ec\u003csup\u003e2\u003c/sup\u003e/Z\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eAge [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e61 (55, 67)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e60 (54, 66)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e61 (56, 67)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e0.895\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.399\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eGender\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMale\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e417 (66.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e151 (64.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e266 (68.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"9%\"\u003e\n\u003cp\u003e1.223\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.269\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eFemale\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e206 (33.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e84 (35.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e122 (31.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eEducation level\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003ePrimary or below\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e48 (7.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e16 (6.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e32 (8.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"9%\"\u003e\n\u003cp\u003e3.771\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"11%\"\u003e\n\u003cp\u003e0.287\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eJunior school\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e150 (24.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e48 (20.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e102 (26.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eHigh school\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e211 (33.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e83 (35.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e128 (33.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eCollege or above\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e214 (34.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e88 (37.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e126 (32.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMarital status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMarried\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e564 (90.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e213 (90.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e351 (90.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"9%\"\u003e\n\u003cp\u003e1.690\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"11%\"\u003e\n\u003cp\u003e0.655\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eSingle\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e9 (1.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e4 (1.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e5 (1.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eDivorced\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e17 (2.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e8 (3.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e9 (2.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eWidowed\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e33 (5.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e10 (4.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e23 (5.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eInsurance type\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eUrban residents\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e407 (65.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e150 (63.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e257 (66.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"3\" width=\"9%\"\u003e\n\u003cp\u003e5.373\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"3\" width=\"11%\"\u003e\n\u003cp\u003e0.068\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eRural cooperative\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e146 (23.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e50 (21.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e96 (24.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eOther\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e70 (11.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e35 (14.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e35 (9.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMonthly income(R)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e\u0026le;2000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e92 (14.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e25 (10.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e67 (17.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"9%\"\u003e\n\u003cp\u003e5.735\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"11%\"\u003e\n\u003cp\u003e0.125\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e2000～4000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e203 (32.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e76 (32.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e127 (32.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e4000～6000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e206 (33.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e84 (35.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e122 (31.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e\u0026ge;6000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e122 (19.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e50 (21.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e72 (18.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eSmoking status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eCurrent smoker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e242 (38.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e91 (38.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e151 (38.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"9%\"\u003e\n\u003cp\u003e0.002\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.962\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eNon-current smoker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e381 (61.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e144 (61.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e237 (61.1)\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\u003eContinued\u003c/p\u003e\n\u003ctable width=\"120%\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eDemographic factors\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003eTotal (n = 623)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003eInsomnia (n = 235)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003eNon-insomnia (n = 388)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003ec\u003csup\u003e2\u003c/sup\u003e/Z\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u003cem\u003ep-\u003c/em\u003evalue\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eAlcohol status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eDrinker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e217 (34.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e84 (35.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e133 (34.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.139\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.710\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNon-drinker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e406 (65.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e151 (64.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e255 (65.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eBMI(Kg/m\u003csup\u003e2\u003c/sup\u003e) [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e23.57 (22.55, 24.98)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e24.51 (23.04, 25.39) \u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e23.24 (22.31, 24.73)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e3.058\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eStroke location\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eAnterior circulation\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e182 (29.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e59 (25.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e123 (31.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e3.078\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.079\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003ePosterior circulation\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e441 (70.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e176 (74.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e265 (68.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eHypertension\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e401 (64.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e162 (68.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e239 (61.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e3.436\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.064\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e222 (35.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e73 (31.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e149 (38.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eDiabetes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e263 (42.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e104 (44.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e159 (41.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.644\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.422\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e360 (57.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e131 (55.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e229 (59.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eCoronary heart disease\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e107 (17.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e42 (17.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e65 (16.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.129\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.719\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e516 (82.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e193 (82.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e323 (83.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eHyperlipidemia\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e155 (24.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e63 (26.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e92 (23.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.751\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.386\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e468 (75.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e172 (73.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e296 (76.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eArhythmia\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e121 (19.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e51 (21.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e70 (18.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e1.253\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.263\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e502 (80.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e184 (78.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e318 (82.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eFMA [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e62 (40, 83)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e56 (25, 85)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e63 (43, 83)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e0.593\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.874\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNIHSS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e4 (3, 6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e5 (3, 6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e4 (2, 5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e1.945\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eBI [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e60 (45, 75)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e60 (45, 75)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e60 (45, 75)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e0.486\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.972\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eFSS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e26 (19, 34)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e35 (29, 38)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e21 (17, 27)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e7.245\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eSAS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e36 (31, 46)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e48 (44, 51)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e33 (29, 36)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e9.231\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eSDS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e36 (31, 44)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e45 (38, 50)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e33 (30, 36)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e6.667\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eSSRS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e45 (40, 48)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e39 (36, 42)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e47 (45, 49)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e8.485\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eNote: BMI, Body Mass Index. FMA, Fugl-Meyer Assessment Scale. NIHSS, National Institute of Health stroke scale. BI, Barthel Index. FSS, fatigue severity scale. SAS, Self-Rating Anxiety Scale. SDS, Self-rating Depression Scale. SSRS, social support rate scale. The comparison between insomnia group and non-insomnia group reveals significant differences: * \u003cem\u003ep\u003c/em\u003e \u0026lt; 0.05; ** \u003cem\u003ep\u003c/em\u003e \u0026lt; 0.001.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e3.2 The prevalence of insomnia and univariate analyses of the potential predictive factors among ISC patients\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe evaluation results indicated that 235 participants (37.72%) had insomnia, while 388 participants (62.28%) did not. The PSQI score for the insomnia group was 9, with an interquartile range of 8 to 11. Univariate analysis results are presented in Table 1. Variables significantly associated with insomnia (\u003cem\u003ep\u003c/em\u003e \u0026lt; 0.05) and incorporated decision tree algorithm analysis were BMI, NIHSS, FSS, SAS, SDS, and SSRS.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e3.3 Construction of predictive decision tree model of insomnia\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe dataset, consisting of 623 samples, was divided into a training set and a validation set in a 7:3 ratio, with 436 samples allocated to the training set. Variables including BMI, NIHSS, FSS, SAS, SDS, and SSRS were incorporated into the model. The score distribution within the decision tree structure was illustrated in Figure 1, showing a total of 24 nodes and a depth of 6. Each variable\u0026rsquo;s contribution to the model was ranked as follows: SAS = 113.47, SSRS = 85.35, FSS = 63.96, SDS = 63.03, BMI = 17.70, and NIHSS = 6.73 (Figure 2). The analysis identified the SAS score as having the highest influence on insomnia risk, whereas the NIHSS had the lowest. Furthermore, Figure 1 showed the SAS score at the root node of the tree, underscoring that anxiety was the most significant factor in predicting insomnia among ISC patients. The algorithm identified a total of 24 decision paths, as detailed in Table 2. Each decision path described the corresponding critical threshold of the predictive variables that affect insomnia. The sleep states of ISC patients varied depending on the specific path, leading to different incidences of insomnia.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 2 Decision path of the insomnia prediction model for ISC patients\u003c/p\u003e\n\u003ctable width=\"136%\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"2\" width=\"8%\"\u003e\n\u003cp\u003eDecision Paths\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003eSAS\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"12%\"\u003e\n\u003cp\u003eSSRS\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"8%\"\u003e\n\u003cp\u003eFSS\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"8%\"\u003e\n\u003cp\u003eSDS\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"8%\"\u003e\n\u003cp\u003eBMI\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"9%\"\u003e\n\u003cp\u003eNIHSS\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd colspan=\"2\" width=\"20%\"\u003e\n\u003cp\u003eRate (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"12%\"\u003e\n\u003cp\u003eOutcome\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eInsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eNon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e78\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e22\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026lt; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e7\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e93\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026lt; 44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e88\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e12\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026ge; 44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e27\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e71\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e5\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026ge; 44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eBMI \u0026ge; 24\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e60\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026ge; 44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eBMI \u0026lt; 24\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e11\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e89\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e7\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026lt; 44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS \u0026ge; 21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e90\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e10\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e8\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026lt; 44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS \u0026lt; 21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e50\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e50\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e9\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS \u0026lt; 41\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS\u0026ge;21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e96\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e10\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS \u0026ge; 40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e41\u0026le;SSRS\u0026lt;44\u0026le;SSRS\u0026lt;44SSRS\u0026lt;44\u0026le;SSRS\u0026lt;44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS\u0026ge;21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e76\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e24\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e11\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS\u0026ge;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e41\u0026le;SSRS\u0026lt;44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS\u0026ge;21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e100\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e12\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e40\u0026le;SAS\u0026lt;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e41\u0026le;SSRS\u0026lt;44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS\u0026ge;21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e55\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e13\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e40\u0026le;SAS\u0026lt;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e41\u0026le;SSRS\u0026lt;44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS\u0026ge;21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eBMI\u0026ge;22\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e69\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e31\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e40\u0026le;SAS\u0026lt;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e41\u0026le;SSRS\u0026lt;44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eFSS\u0026ge;21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eBMI\u0026lt;22\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e100\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e15\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026lt;38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e67\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e33\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e16\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026ge;38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e94\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e17\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026ge;38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026ge;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e50\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e50\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e18\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026ge;38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e96\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e19\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e37\u0026le;SAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026ge;38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e20\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e80\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e20\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003eSAS\u0026lt;37\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026ge;38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e98\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e21\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e37\u0026le;SAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e38\u0026le;SSRS\u0026lt;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e62\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e22\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e37\u0026le;SAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003eSSRS\u0026ge;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e5\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e95\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e23\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e37\u0026le;SAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e38\u0026le;SSRS\u0026lt;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003eNIHSS\u0026ge;3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e55\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003einsomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e24\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e37\u0026le;SAS\u0026lt;40\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e38\u0026le;SSRS\u0026lt;46\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003eSDS\u0026lt;45\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003eNIHSS\u0026lt;3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"8%\"\u003e\n\u003cp\u003e0\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003e100\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"12%\"\u003e\n\u003cp\u003enon-insomnia\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eNote: BMI, Body Mass Index. FMA, Fugl-Meyer Assessment Scale. NIHSS, National Institute of Health stroke scale. BI, Barthel Index. FSS, fatigue severity scale. SAS, Self-Rating Anxiety Scale. SDS, Self-rating Depression Scale. SSRS, social support rate scale.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e3.4 Internal validation of a decision tree model for insomnia risk\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn the verification dataset containing 187 cases (Figure 3), the confusion matrix analysis showed that the model correctly predicted a total of 165 cases. Specifically, it predicted 73 cases of insomnia, of which 62 were actual cases of insomnia. Similarly, it predicted 114 cases as non-insomnia, correctly identifying 103 non-insomnia cases Based on these values, the model\u0026rsquo;s accuracy rate (ACC) on the test set was 88.2 %, indicating a relatively high prediction accuracy.\u003c/p\u003e\n\u003cp\u003eROC analysis yielded AUC of 0.96 (\u003cem\u003ep\u003c/em\u003e \u0026lt; 0.001, 95% CI: 0.93~0.98) (Figure 4). In addition, the model achieved a sensitivity of 0.96, a specificity of 0.84, and a Youden index of 0.80 (Figure 5). These results suggested that the model maintained strong discriminatory power, even after incorporating internal validation data.\u003c/p\u003e\n\u003cp\u003eThe H-L test results indicated that \u0026chi;\u003csup\u003e2\u003c/sup\u003e = 9.36, \u003cem\u003ep \u003c/em\u003e= 0.404. Additionally, the calibration curve closely aligned with the diagonal reference line (Figure 6), demonstrating that the model maintained strong calibration even after incorporating internal validation data. This result confirms that the model can accurately predict the incidence of insomnia among ISC patients.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e3.5 External validation of a decision tree model for insomnia risk\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe baseline data of patients in the external validation dataset were showed in Table 3. A total of 200 ISC patients were included, the incidence rate of insomnia was 37.0 %, which was similar to the results of the dataset for model establishment. The accuracy of the model is 78.3%, which shows a slight decrease compared with the original model.(AUC = 0.88, 95 % CI: 0.78~0.95; \u003cem\u003ep \u003c/em\u003e\u0026lt; 0.001). However, the H-L test proved that the model was well-calibrated (\u0026chi;\u003csup\u003e2\u003c/sup\u003e = 0.14, \u003cem\u003ep\u003c/em\u003e = 0.93) (Figure 7, 8, 9). This further validated that, even after introducing external non-homologous data, the model\u0026rsquo;s stability was still relatively strong.\u003c/p\u003e\n\u003cp\u003eTable 3 Baseline characteristics of patients in the external validation dataset (n = 200)\u003c/p\u003e\n\u003ctable width=\"113%\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eDemographic factors\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003eTotal (n = 200)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003eInsomnia (n = 74)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003eNon-insomnia (n = 126)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003ec\u003csup\u003e2\u003c/sup\u003e/Z\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eAge [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e63 (56, 68)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e62 (53, 67)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e63 (57, 68)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e0.789\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.561\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eGender\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMale\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e120 (60)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e38 (51.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e82 (65.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"9%\"\u003e\n\u003cp\u003e3.661\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.056\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eFemale\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e80 (40)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e36 (48.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e44 (34.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eEducation level\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003ePrimary or below\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e15 (7.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e4 (5.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e11 (8.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"9%\"\u003e\n\u003cp\u003e5.689\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"11%\"\u003e\n\u003cp\u003e0.128\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eJunior school\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e59 (29.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e17 (23.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e42 (33.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eHigh school\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e73 (36.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e27 (36.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e46 (36.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eCollege or above\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e53 (26.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e26 (35.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e27 (21.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMarital status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMarried\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e186 (93.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e69 (93.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e117 (92.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"9%\"\u003e\n\u003cp\u003e3.840\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"11%\"\u003e\n\u003cp\u003e0.271\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eSingle\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e2 (1.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e0 (0.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e2 (1.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eDivorced\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e6 (3.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e1 (1.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e5 (4.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eWidowed\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e6 (3.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e14 (5.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e2 (1.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eInsurance type\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eUrban residents\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e54 (27.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e18 (24.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e36 (28.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"3\" width=\"9%\"\u003e\n\u003cp\u003e1.878\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"3\" width=\"11%\"\u003e\n\u003cp\u003e0.392\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eRural cooperative\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e143 (71.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e56 (75.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e87 (69.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eOther\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e3 (1.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e0 (0.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e3 (2.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eMonthly income(R)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e\u0026le;2000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e25 (12.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e11 (14.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e14 (11.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"9%\"\u003e\n\u003cp\u003e4.882\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"4\" width=\"11%\"\u003e\n\u003cp\u003e0.181\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e2000～4000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e92 (46.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e27 (36.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e65 (51.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e4000～6000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e66 (33.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e30 (40.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e36 (28.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003e\u0026ge;6000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e17 (8.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e6 (8.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e11 (8.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eSmoking status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"9%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eCurrent smoker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e71 (35.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e23 (31.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e48 (38.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"9%\"\u003e\n\u003cp\u003e1.002\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.317\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"19%\"\u003e\n\u003cp\u003eNon-current smoker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"15%\"\u003e\n\u003cp\u003e129 (64.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"20%\"\u003e\n\u003cp\u003e51 (68.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"23%\"\u003e\n\u003cp\u003e78 (61.9)\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\u003eContinued\u003c/p\u003e\n\u003ctable width=\"120%\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eDemographic factors\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003eTotal (n = 200)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003eInsomnia (n = 74)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003eNon-insomnia (n = 126)\u003c/p\u003e\n\u003cp\u003en (%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003ec\u003csup\u003e2\u003c/sup\u003e/Z\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u003cem\u003ep-\u003c/em\u003evalue\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eAlcohol status\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eDrinker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e59 (29.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e20 (27.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e39 (31.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.345\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.557\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNon-drinker\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e141 (70.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e54 (73.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e87 (69.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eBMI(Kg/m\u003csup\u003e2\u003c/sup\u003e) [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e23.57 (22.55, 24.98)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e24.68 (22.69, 26.85)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e23.42 (22.62, 24.23)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e2.534\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eStroke location\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eAnterior circulation\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e63 (31.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e20 (27.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e43 (34.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e1.089\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.297\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003ePosterior circulation\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e137 (68.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e54 (73.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e83 (65.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eHypertension\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e127 (63.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e42 (56.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e85 (67.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e2.304\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.129\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e73 (36.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e32 (43.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e41 (32.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eDiabetes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e64 (32.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e24 (32.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e40 (31.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.010\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.920\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e136 (68.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e50 (67.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e86 (68.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eCoronary heart disease\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e29 (14.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e11 (14.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e18 (14.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.013\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.911\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e171 (85.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e63 (85.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e108 (85.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eHyperlipidemia\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e38 (19.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e15 (20.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e23 (18.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.123\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.726\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e162 (81.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e59 (19.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e103 (81.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eArhythmia\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e32 (16.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e11 (14.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e21 (16.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"6%\"\u003e\n\u003cp\u003e0.113\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd rowspan=\"2\" width=\"11%\"\u003e\n\u003cp\u003e0.737\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e168 (84.0)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e63 (85.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e105 (83.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eFMA [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e61 (45, 76)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e63 (46, 82)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e59 (43, 75)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e0.861\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.449\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eNIHSS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e4 (3, 5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e4 (3, 5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e5 (4, 6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e1.636\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.009\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eBI [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e65 (55, 75)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e70 (60, 76)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e65 (50, 75)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e1.075\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e0.198\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eFSS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e26 (22, 29)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e27 (27, 34)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e23 (20, 26)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e4.599\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eSAS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e38 (34, 45)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e45 (44, 49)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e34 (31, 38)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e5.239\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eSDS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e35 (31, 43)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e41 (35, 46)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e33 (30, 38)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e2.919\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"24%\"\u003e\n\u003cp\u003eSSRS [median (IQR)]\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"16%\"\u003e\n\u003cp\u003e44 (41, 46)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"18%\"\u003e\n\u003cp\u003e41 (39,43)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"22%\"\u003e\n\u003cp\u003e46 (43, 47)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"6%\"\u003e\n\u003cp\u003e3.710\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd width=\"11%\"\u003e\n\u003cp\u003e＜ 0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eNote: The comparison between insomnia group and non-insomnia group reveals significant differences: * \u003cem\u003ep\u003c/em\u003e \u0026lt; 0.05; ** \u003cem\u003ep\u003c/em\u003e \u0026lt; 0.001.\u003c/p\u003e\n\u003cp\u003eThe total score of the nomogram for predicting the risk of insomnia among ISC patients ranged from 0 to 220, with the probability of insomnia between 0.1 and 0.9 (Figure 10).\u003c/p\u003e"},{"header":"4 Discussion","content":"\u003cp\u003eThis study aimed to explore the independent predictors of insomnia in ischemic ISC patients. The results revealed that the incidence of insomnia was relatively high among these patients, with anxiety, depression, social support, BMI, fatigue, and NIHSS scores emerging as key predictors.\u003c/p\u003e \u003cp\u003eStroke often leads patients to experience negative emotions.\u003csup\u003e\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e Mental health issues following a stroke included low attention and memory, apathy, and depression.\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e,\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e Previous studies had shown that post-stroke depression was a significant cause of insomnia.\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e Our study results aligned with prior research, emphasizing that negative emotions were key factors contributing to post-stroke insomnia. In the decision tree model, the anxiety score had three decision thresholds set at 37, 40, and 46, with the anxiety score at the root node of the model. When SAS was less than 37, the incidence of insomnia was relatively low, at only 2%. However, as the SAS score increased, the risk of insomnia rose significantly accordingly. This may be due to autonomic nervous system disturbances among patients with anxiety, leading to emotional imbalance, tension, and fear, all of which severely disrupted sleep quality.\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e Consequently, alleviating anxiety may be essential for improving insomnia in these patients. Furthermore, a critical value of 45 was set for depression, with higher levels of depressive symptoms significantly impacting patients' sleep. Specifically, when the SDS score reached 45 or higher, patients were at greater risk of insomnia. In modern medicine, the role of psychological factors in patients\u0026rsquo; rehabilitation is increasingly acknowledged. Therefore, medical staffs need to focus not only on physical recovery but also on comprehensive management of negative emotions to facilitate the rehabilitation process.\u003c/p\u003e \u003cp\u003ePsychosocial factors have gained considerable attention as modifiable elements. Fewer studies examined how protective psychosocial factors affected the sleep quality of stroke patients.\u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e,\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e Stroke survivors often require external emotional and material support to adapt to daily life and face changes. In light of this, our study analyzed social support as a relevant factor. The results of the decision tree model indicated that social support as a crucial factor in predicting insomnia, ranked just below the root node in importance. This variable had four decision thresholds: 38, 41, 44, and 46 points. When the SSRS score was \u0026ge;\u0026thinsp;46, the incidence of insomnia was as low as 5%. At a stable level of patient anxiety, enhancing social support could effectively diminish the likelihood of insomnia. This benefit likely arises from the support provided by family, caregivers, and friends, which fosters a secure environment, lowers patient vigilance, and promotes better sleep quality.\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u003c/sup\u003e Thus, a high level of social support can enhance the functional recovery of ISC patients and mitigate the risk of insomnia. These findings aligned with previous research.\u003csup\u003e\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e Medical staff should prioritize not only physical recovery but also the social support needs of stroke patients, potentially improving sleep quality.\u003c/p\u003e \u003cp\u003eThe post-stroke fatigue could lead to several challenges, including difficulties in maintaining rehabilitation, decreased motivation, emotional challenges, reduced social interactions, and a loss of goals.\u003csup\u003e\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u003c/sup\u003e Our study identified a critical threshold in the FSS score within the decision tree model. This threshold suggested that patients with similar levels of anxiety and social support can lower their risk of insomnia by alleviating fatigue symptoms, highlighting a potential direct impact of fatigue on sleep quality. Poor sleep quality among patients with post-stroke fatigue may result from daytime sleepiness, which is closely linked to fatigue.\u003csup\u003e\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u003c/sup\u003e This finding reinforced the appropriateness of identifying fatigue as an independent predictor in the insomnia risk decision tree model. Choi-Kwon and Kim (2011) reported a correlation between poor sleep quality and elevated fatigue levels in stroke patients, particularly in older ISC patients, which aligned with our results.\u003csup\u003e\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e\u003c/sup\u003e However, fatigue severity and insomnia in ISC patients, along with factors such as age, daily activity levels, and other potential mediators, warrant further investigation to better understand their interactions.\u003c/p\u003e \u003cp\u003eThe BMI and NIHSS, as objective factors included in the decision tree model for predicting insomnia. Research has shown that ISC patients with high BMI are more likely to experience insomnia.\u003csup\u003e\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e\u003c/sup\u003e Furthermore, a higher BMI is positively correlated with overweight and obesity, which in turn increases insomnia risk.\u003csup\u003e\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e\u003c/sup\u003e In our study, decision paths 5, 6, 13, and 14 in the model demonstrated that effective BMI management can significantly reduce insomnia risk. The severity of neurological deficits could significantly affect sleep quality in post-stroke patients.\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e,\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u003c/sup\u003e This may be due to irreversible nerve cell damage, which can lead to the release of toxic substances that cross the blood-brain barrier and disrupt the sleep-wake system.\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e In this study, we included ISC patients with NIHSS scores below 15, as patients with scores of 15 or above frequently exhibit severe cognitive impairments and communication disorders, which could complicate the study's findings. Patients with an NIHSS score of 3 or higher had a significantly increased risk of insomnia (up to 55%). Although NIHSS had the lowest predictive impact for insomnia among ISC patients, its critical value is useful in assessing risk. This highlighted the need for further research on the relationship between stroke severity and sleep quality.\u003c/p\u003e \u003cp\u003e \u003cb\u003eLimitations\u003c/b\u003e \u003c/p\u003e \u003cp\u003eThere were several limitations in this study. First, future research should consider include objective factors that influence insomnia, particularly serological biochemical indicators, gut flora, and metabolites. Second, while this study included 823 ISC patients, expanding the sample size in future studies will enhance the ability to identify more risk factors. Third, the use of convenience sampling may affect the accuracy and reliability of the results. Last, the insomnia risk decision tree model was validated using data from only one hospital; applying the model across multiple clinical settings in the future will improve its accuracy and generalizability.\u003c/p\u003e \u003cp\u003e \u003cb\u003eImplications for practice\u003c/b\u003e \u003c/p\u003e \u003cp\u003eThis study underlines the significance of conducting early insomnia screening for stroke patients during their recovery phase. Medical staffs, while facilitating patients' active rehabilitation, ought to place particular emphasis on factors like anxiety, depression, the extent of social support, and post-stroke fatigue. Concurrently, they should implement targeted interventions to address insomnia. Such measures are conducive to sustaining patients' psychological equilibrium, enhancing their sleep quality, and, ultimately, expediting the overall recovery process.\u003c/p\u003e"},{"header":"5 Conclusions","content":"\u003cp\u003eThe decision tree model developed in this study for predicting insomnia risk demonstrated high accuracy, showcasing excellent discrimination capabilities. To our knowledge, this was the first study to develop and evaluate such a model specifically for ISC patients. The nomogram provided an easy-to-use, personalized tool for insomnia prediction and further optimized clinical management. Both internal and external validations confirmed the model\u0026rsquo;s accuracy in predicting insomnia occurrence among ISC patients. In clinical applications, the nomogram could be integrated with existing sleep assessment scales, providing a comprehensive assessment of ISC patients.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eDeclaration of Conflicting Interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe have no conflicts of interest to disclose.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthorship contribution statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eX.S. and H.Z. wrote the main manuscript text and S.S., D.C., X.Z., Y.Z., Y.S., and Z.W prepared figures 1-10. All authors reviewed the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe author sincerely thanks all medical staff and expresses sincere gratitude to all patients in the recovery period of ischemic stroke who participated in this study. In addition, thanks Xuewen Sun (Beijing Forestry University) for revising the grammar and vocabulary of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was funded by the Jilin Province Science and Technology Development Plan Project (Grant No. 232662SF0103109942), the National Natural Science Foundation of China (Grant No. 82074569), and the National Key R \u0026amp; D Program of China (Grant No. 2018YFC1706002).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe registration number of this study is CZDSFYLL2024-056-01. This is a clinical investigation study approved by the Ethics Committee of The Third Affiliated Hospital of Changchun University of Chinese Medicine in August 2024. All participants were enrolled in the investigation using the principles of informed consent and confidentiality.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data will not be shared without permission of all authors. Please contact H.Z. if required.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eLeone M, Ciccacci F, Orlando S, Petrolati S, Guidotti G, Majid NA, et al. Pandemics and Burden of Stroke and Epilepsy in Sub-Saharan Africa: Experience from a Longstanding Health Programme. Int J Environ Res Public Health. 2021;18(5):2766.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBoursin P, Paternotte S, Dercy B, Sabben C, Ma\u0026iuml;er B. S\u0026eacute;mantique, \u0026eacute;pid\u0026eacute;miologie et s\u0026eacute;miologie des accidents vasculaires c\u0026eacute;r\u0026eacute;braux [Semantics, epidemiology and semiology of stroke]. Soins. 2018;63(828):24\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eByun E, Kohen R, Becker KJ, Kirkness CJ, Khot S, Mitchell PH. Stroke impact symptoms are associated with sleep-related impairment. Heart Lung. 2020;49(2):117\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoon HI, Yoon SY, Jeong YJ, Cho TH. Sleep disturbances negatively affect balance and gait function in post-stroke patients. NeuroRehabilitation. 2018;43(2):211\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIddagoda MT, Inderjeeth CA, Chan K, Raymond WD. Post-stroke sleep disturbances and rehabilitation outcomes: a prospective cohort study. Intern Med J. 2020;50(2):208\u0026ndash;13.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOliveira GDP, Vago ERL, Prado GFD, Coelho FMS. The critical influence of nocturnal breathing complaints on the quality of sleep after stroke: the Pittsburgh Sleep Quality Index and STOP-BANG. Arq Neuropsiquiatr. 2017;75(11):785\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBattle DE. Diagnostic and Statistical Manual of Mental Disorders (DSM). Codas. 2013;25(2):191\u0026ndash;2.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang X, Ji X. Interactions between remote ischemic conditioning and post-stroke sleep regulation. Front Med. 2021;15(6):867\u0026ndash;76.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKusec A, Milosevich E, Williams OA, Chiu EG, Watson P, Carrick C, et al. Long-term psychological outcomes following stroke: the OX-CHRONIC study. BMC Neurol. 2023;23(1):426.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu SY, Sun Q, Chen SN, Wang F, Chen R, Chen J, et al. Circadian Rhythm Disturbance in Acute Ischemic Stroke Patients and Its Effect on Prognosis. Cerebrovasc Dis. 2024;53(1):14\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang W, Li F, Zhang T. Relationship of nocturnal concentrations of melatonin, gamma-aminobutyric acid and total antioxidants in peripheral blood with insomnia after stroke: study protocol for a prospective non-randomized controlled trial. Neural Regen Res. 2017;12(8):1299\u0026ndash;307.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBesedovsky L, Lange T, Haack M. The Sleep-Immune Crosstalk in Health and Disease. Physiol Rev. 2019;99(3):1325\u0026ndash;80.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWestfall S, Lomis N, Kahouli I, Dia SY, Singh SP, Prakash S. Microbiome, probiotics and neurodegenerative diseases: deciphering the gut brain axis. Cell Mol Life Sci. 2017;74(20):3769\u0026ndash;87.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu W, Kong X, Wang H, Li Y, Luo Y. Ischemic stroke and intestinal flora: an insight into brain-gut axis. Eur J Med Res. 2022;27(1):73. Published 2022 May 25.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhot SP, Morgenstern LB. Sleep Stroke Stroke. 2019;50(6):1612\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKolmos M, Christoffersen L, Kruuse C. Recurrent Ischemic Stroke - A Systematic Review and Meta-Analysis. J Stroke Cerebrovasc Dis. 2021;30(8):105935.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMohandas P, Alomari Z, Arti F, Alhneif M, Alejandra Ruiz P, Ahmed AK, et al. A Systematic Review and Meta-Analysis on the Identification of Predictors Associated With Insomnia or Sleep Disturbance in Post-stroke Patients. Cureus. 2024;16(3):e56578.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRyu D, Sok S. Prediction model of quality of life using the decision tree model in older adult single-person households: a secondary data analysis. Front Public Health. 2023;11:1224018.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOh HS, Park HA. Decision tree model of the treatment-seeking behaviors among Korean cancer patients. Cancer Nurs. 2004;27(4):259\u0026ndash;66.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSong J, Gao Y, Yin P, Li Y, Li Y, Zhang J, et al. The Random Forest Model Has the Best Accuracy Among the Four Pressure Ulcer Prediction Models Using Machine Learning Algorithms. Risk Manag Healthc Policy. 2021;14:1175\u0026ndash;87.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRawal B, Agarwal R. Improving accuracy of classification based on C4. 5 decision tree algorithm using big data analytics[C]//Computational Intelligence in Data Mining: Proceedings of the International Conference on CIDM 2017. Springer Singapore, 2019: 203\u0026ndash;211.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRiemann D, Espie CA, Altena E, Arnardottir ES, Baglioni C, Bassetti CLA, et al. The European Insomnia Guideline: An update on the diagnosis and treatment of insomnia 2023. J Sleep Res. 2023;32(6):e14035.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFalck RS, Best JR, Davis JC, Eng JJ, Middleton LE, Hall PA, et al. Sleep and cognitive function in chronic stroke: a comparative cross-sectional study. Sleep. 2019;42(5):zsz040.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKrupp LB, LaRocca NG, Muir-Nash J, Steinberg AD. The fatigue severity scale. Application to patients with multiple sclerosis and systemic lupus erythematosus. Arch Neurol. 1989;46(10):1121\u0026ndash;3.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZung WW. K. A self-rating depression scale[J]. Arch Gen Psychiatry. 1965;12(1):63\u0026ndash;70.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShuiyuan X. The theoretical basis and research application of social support rating scale[J]. J Clin Psychiatry. 1994;2:98\u0026ndash;100.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGrajski KA, Breiman L, Di Viana G, Freeman WJ. Classification of EEG spatial patterns with a tree-structured methodology: CART. IEEE Trans Biomed Eng. 1986;33(12):1076\u0026ndash;86.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRafsten L, Danielsson A, Sunnerhagen KS. Anxiety after stroke: A systematic review and meta-analysis. J Rehabil Med. 2018;50(9):769\u0026ndash;78.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen R, Guo Y, Kuang Y, Zhang Q. Effects of home-based exercise interventions on post-stroke depression: A systematic review and network meta-analysis. Int J Nurs Stud. 2024;152:104698.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSch\u0026ouml;ttke H, Giabbiconi CM. Post-stroke depression and post-stroke anxiety: prevalence and predictors. Int Psychogeriatr. 2015;27(11):1805\u0026ndash;12.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim WH, Jung HY, Choi HY, Park CH, Kim ES, Lee SJ, et al. The associations between insomnia and health-related quality of life in rehabilitation units at 1month after stroke. J Psychosom Res. 2017;96:10\u0026ndash;4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGlozier N, Moullaali TJ, Sivertsen B, Kim D, Mead G, Jan S, et al. The Course and Impact of Poststroke Insomnia in Stroke Survivors Aged 18 to 65 Years: Results from the Psychosocial Outcomes In StrokE (POISE) Study. Cerebrovasc Dis Extra. 2017;7(1):9\u0026ndash;20.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIwuozo EU, Enyikwola JO, Asor PM, Onyia UI, Nwazor EO, Obiako RO. Sleep disturbances and associated factors amongst stroke survivors in North Central, Nigeria. Niger Postgrad Med J. 2023;30(3):193\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao Y, Hu B, Liu Q, Wang Y, Zhao Y, Zhu X. Social support and sleep quality in patients with stroke: The mediating roles of depression and anxiety symptoms. Int J Nurs Pract. 2022;28(3):e12939.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXiao H, Zhang Y, Kong D, Li S, Yang N. The Effects of Social Support on Sleep Quality of Medical Staff Treating Patients with Coronavirus Disease 2019 (COVID-19) in January and February 2020 in China. Med Sci Monit. 2020;26:e923549.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSato M, Hyakuta T. Awareness and support for post-stroke fatigue among medical professionals in the recovery phase rehabilitation ward. Jpn J Compr Rehabil Sci. 2023;14:39\u0026ndash;48.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee J, Choi YS, Jeong YJ, Lee J, Kim JH, Kim SH. Poor-quality sleep is associated with metabolic syndrome in Korean adults. Tohoku J Exp Med. 2013;231(4):281\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi-Kwon S, Kim JS. Poststroke fatigue: an emerging, critical issue in stroke medicine. Int J Stroke. 2011;6(4):328\u0026ndash;36.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShi Y, Zhou W. Interactive Effects of Dietary Inflammatory Index with BMI for the Risk of Stroke among Adults in the United States: Insight from NHANES 2011\u0026ndash;2018. J Nutr Health Aging. 2023;27(4):277\u0026ndash;84.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMuhammad T, Gharge S, Meher T. The associations of BMI, chronic conditions and lifestyle factors with insomnia symptoms among older adults in India. PLoS ONE. 2022;17(9):e0274684.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXu H, Li W, Chen J, Zhang P, Rong S, Tian J, et al. Associations between insomnia and large vessel occlusion acute ischemic stroke: An observational study. Clin (Sao Paulo). 2023;78:100297.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Insomnia, Ischemic stroke convalescence, Decision tree, Predictive model, Nomogram","lastPublishedDoi":"10.21203/rs.3.rs-6248505/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6248505/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground: \u003c/strong\u003eInsomnia is a prevalent complication among ischemic stroke convalescence (ISC) patients. Although the interplay of clinical, psychological, and social factors remains unclear in ISC patients, a model prediction system was necessary. Limited research developed a prediction model for insomnia risk.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eObjectives: \u003c/strong\u003eTo construct a decision tree model for insomnia risk among ISC patients based on the classification and regression tree algorithm.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDesign:\u003c/strong\u003e Across-sectional study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSetting: \u003c/strong\u003eChina.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eParticipants:\u003c/strong\u003e The study enrolled 823 adult ISC patients between February 2023 and October 2024. Participants were recruited from stroke units in two tertiary hospitals in Jilin Province.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eA decision tree model was guided by the TRIPOD+AI report. The Pittsburgh Sleep Quality Index (PSQI), Fatigue Severity Scale (FSS), Social Support Scale (SSRS) and other scales were used to collect data. The confusion matrix, ROC curves, H-L test, and calibration curve were employed for internal and external validation by using a bootstrap resampling method. 623 patients were used to construct the decision tree model, while the remaining 200 non-homologous cases were used for external validation.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults: \u003c/strong\u003eThis study showed that the prevalence of insomnia among ISC patients was 37.72 %. Univariate analysis revealed that factors such as BMI, SAS, SSRS, FSS, SDS, and NIHSS were critical. The decision tree model yielded 24 paths with a depth of 6. The predictive contribution was ranked as follows: SAS \u0026gt; SSRS \u0026gt; FSS \u0026gt; SDS \u0026gt; BMI \u0026gt; NIHSS, which were identified to create the nomogram. Internal validation indicated that the model had strong predictive accuracy at 88.2%, with a sensitivity of 0.96, specificity of 0.84, and a Youden index of 0.80. The area under the curve was 0.96 (95% CI: 0.93~0.98; p \u0026lt; 0.001); Additionally, the H-L test showed that the model was well-calibrated (χ2 = 9.36, p = 0.404). External validation proved that the model had stability across different data.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion: \u003c/strong\u003eThis decision tree model demonstrates potential for predicting insomnia in ISC patients, and these predictors can inform the development of future insomnia management strategies. The ultimate objective is to alleviate the distress caused by insomnia and to facilitate the recovery process in stroke patients.\u003c/p\u003e","manuscriptTitle":"Development and validation of a decision tree model for prediction of insomnia risk among ischemic stroke convalescence patients","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-17 10:57:06","doi":"10.21203/rs.3.rs-6248505/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-18T11:27:39+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-16T02:53:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"217588666992824202251028691069341342914","date":"2025-06-16T02:00:44+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-16T01:36:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"543295148833614803264984497550995699","date":"2025-06-16T01:16:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-14T13:30:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"141599899105219256538272213017174635610","date":"2025-06-12T05:35:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-10T13:32:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"132487641914930185794021020540746995406","date":"2025-05-27T09:01:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"27865389421478333050834864828564877483","date":"2025-05-24T07:26:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"32656219192092917722712489980411648354","date":"2025-05-22T11:35:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-16T07:26:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307220948592404034292584294542740394394","date":"2025-04-12T19:51:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"61175185252668733045897012675996192592","date":"2025-04-11T07:02:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-11T06:20:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-11T06:09:12+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-03-25T11:05:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-21T13:16:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Public Health","date":"2025-03-21T13:14:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2fbc2174-bfa8-4572-9383-a0704a86c597","owner":[],"postedDate":"April 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-08-25T16:30:42+00:00","versionOfRecord":{"articleIdentity":"rs-6248505","link":"https://doi.org/10.1186/s12889-025-24025-z","journal":{"identity":"bmc-public-health","isVorOnly":false,"title":"BMC Public Health"},"publishedOn":"2025-08-19 16:12:55","publishedOnDateReadable":"August 19th, 2025"},"versionCreatedAt":"2025-04-17 10:57:06","video":"","vorDoi":"10.1186/s12889-025-24025-z","vorDoiUrl":"https://doi.org/10.1186/s12889-025-24025-z","workflowStages":[]},"version":"v1","identity":"rs-6248505","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6248505","identity":"rs-6248505","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}