Next Article in Journal
Instrumental Activities of Daily Living—A Good Tool to Prospectively Assess Disability after a Second Contralateral Hip Fracture?
Previous Article in Journal
Improving the Care of Older Patients by Decreasing Potentially Inappropriate Medications, Potential Medication Omissions, and Serious Drug Events Using Pharmacogenomic Data about Variability in Metabolizing Many Medications by Seniors
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Geriatrics
Volume 5
Issue 4
10.3390/geriatrics5040066
geriatrics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Factors Predicting the Utilization of Center-Based Cardiac Rehabilitation Program

by
Lufei Young
1,*,†,
Qi Zhang
2,†,
Eric Lian
3,
Kimberly Roberts
4,
Neal Weintraub
3,5,
Yanbin Dong
6,
Haidong Zhu
6,
Hongyan Xu
7,
Pascha Schafer
3 and
Stephanie Dunlap
3
1
College of Nursing, Augusta University, Augusta, GA 30912, USA
2
The Nethersole School of Nursing, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong 999077, China
3
Departments of Medicine, Medical College of Georgia, Augusta University, Augusta, GA 30912, USA
4
Department of Nursing, School of Health Sentences, Georgia Highlands College, Rome, GA 30161, USA
5
Vascular Biology Center, Medical College of Georgia, Augusta University, Augusta, GA 30912, USA
6
Georgia Prevention Institute, Medical College of Georgia, Augusta University, Augusta, GA 30912, USA
7
Department of Biostats & Data, Medical College of Georgia, Augusta University, Augusta, GA 30912, USA
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Geriatrics 2020, 5(4), 66; https://doi.org/10.3390/geriatrics5040066
Submission received: 30 August 2020 / Revised: 18 September 2020 / Accepted: 22 September 2020 / Published: 28 September 2020
(This article belongs to the Section Cardiogeriatrics)
Browse Figures
Review Reports Versions Notes

Abstract

:
Although cardiac rehabilitation (CR) is clearly beneficial to improving patients’ physical functioning and reducing heart disease progression, significant proportions of patients do not complete CR programs. To evaluate the prevalence and predictors of completion of a center-based CR program in eligible cardiac patients, existing data collected from electronic medical records were used. To identify the predictors of CR completion, we used principal components analysis (PCA) and an artificial neural network (ANN) module. Among 685 patients, 61.4% (n = 421) completed the program, 31.7% (n = 217) dropped out, and 6.9% (n = 47) were referred but failed to initiate the program. PCA was conducted to consolidate baseline data into three factors—(1) psychosocial factors (depression, anxiety, and quality of life), (2) age, and (3) BMI, which explained 66.8% of the total variance. The ANN model produced similar results as the PCA. Patients who completed CR sessions had greater extremity strength and flexibility, longer six-minute walk distance, more CR knowledge, and a better quality of life. The present study demonstrated that patients who were older, obese, and who had depression, anxiety, or a low quality of life were less likely to complete the CR program.

1. Introduction

Cardiovascular disease (CVD) is the leading cause of mortality and morbidity, and has a rising clinical and economic burden worldwide [1,2]. In management of CVD, cardiac rehabilitation (CR) is the standard treatment to promote lifestyle changes and modify risk factors for many CVD patients [3]. CR is a secondary prevention program comprised of multifaceted interventions, focused on supervised exercise training, medication management, nutritional education, psychosocial counselling, and comprehensive support [4]. Participation in CR was proven to be a beneficial element of cardiac care [5,6,7,8,9], and patients enrolled in CR exhibit reduced mortality, by up to 30% [10]. American Heart Association promotes the importance of referring appropriate patients to CR and recognizes this aspect of care in their clinical practice guidelines [11,12]. Nevertheless, only 15–30% of eligible candidates actually attend CR programs [13,14,15]. In addition, the benefits of CR are dependent on the patient’s long-term adherence to the program; among those who participate, 43% to 51% drop out within six months and up to 90% fail to complete one year [16,17]. CR incompletion rates vary in different studies and might be influenced by patient characteristics, psychological factors, social support, logistical issues, financial constraints, etc. To date, the predictors of completing a CR program are not fully understood. Therefore, the primary aim of the present study was to identify factors associated with CR completion rate among CVD patients.

2. Materials and Methods

2.1. Study Design

This study used a secondary, retrospective cohort study design. De-identified clinical data collected from the electronic medical record (EMR) were used for analysis.

2.2. Study Population

The de-identified medical records of 685 patients who were eligible to attend an academic medical center-based CR program in the Southeastern US, between April 2012 and April 2018 were included. The study included patients who (1) had an acute coronary syndrome; (2) underwent percutaneous coronary intervention, open-heart surgery (such as coronary artery bypass surgery, valve surgery or heart transplant); (3) had stable chronic heart failure; and (4) had current stable angina (chest pain). The patients who did not have 3-months of data available for review were excluded from the study. The study was approved by Augusta University Institutional Review Board (1295531 on 27 August 2018 and 1609080 on 27 July 2020)

2.3. Study Setting

The study participants were patients who were eligible for a 12-week CR program, after discharge from hospital. The CR program included three 1-h sessions per week, with a total of 36 exercise sessions. The supervised exercise training consisted of warm-up, stretching, treadmill, bicycle ergometer, and arm ergometer, with each activity performed over 10–20 min. Psychological support and nutritional counseling were offered to all patients. Blood pressure, heart rate, as well as exercise intensity were monitored by physical therapists during the CR program. Based on the completion status, we divided the participants into 3 groups—graduates, dropouts, and referrals. Graduates were patients who completed 36 CR sessions, dropouts withdrew from the program prior to completion, and referrals were sent for but failed to initiate the CR program.

2.4. Study Variables and Measures

In order to identify potential factors associated with CR completion, participants’ characteristics were captured at baseline, prior to the CR program and 3 months after baseline. The data included sociodemographic variables (e.g., age, gender), clinical variables (e.g., primary cardiac diagnosis, resting heart rate, blood pressure, weight, height, body mass index (BMI), percentage of body fat), laboratory variables (e.g., total cholesterol, high-density lipoproteins (HDL), triglycerides, low-density lipoproteins (LDL), fasting blood glucose (FBG), hemoglobin A1C (HbA1c)), and physical performance variables (e.g., 6-min work test (6MWT), extremity flexibility, and strength assessment). CR knowledge test [18] was used to assess patients’ knowledge regarding cardiac rehabilitation. Health-related quality of life (HRQoL) was measured by self-report, using the Short Form-36 [19] questionnaires general health (SF36GH) scales and physical functioning (SF36PF) scales. Both subscales are commonly used to assess HRQoL in cardiac patients. Higher scores in general health and physical functioning indicate better HRQoL. The Hospital Anxiety and Depression Scale [20] (HADS) was used to assess patients’ psychological symptoms. The psychometric properties of SF36 and HAD were established in a cardiac population [21,22,23].

2.5. Statistical Methods

All statistical analyses were performed using IBM SPSS statistics for Windows, version 26.0 (IBM Corp, Armonk, NY, USA). Data were displayed as mean ± SD or percentage (N) for numerical variables or categorical variables, respectively. For all analyses, two-tailed t-tests were used with a level of statistical significance set at p < 0.05. The student’s paired t-test was used to examine differences before and after, for each group. One-way analysis of variance (ANOVA) was employed to identify the relationships between variables.
Principal components analysis (PCA), a statistical procedure aimed to reduce the dimensionality of multiple correlated measurements to fewer numbers of linearly uncorrelated variables, was used to investigate the variation of the original data [24,25]. PCA can highlight the common variation between the original variables to condense the data, thus, identifying the most relevant principal components to explain CR utilization status (Graduate, Dropout, and Referral). Each principal component (PC) is, by definition, not related to another. The first PC (PC1) obtained accounts for the highest amount of the total variation between the original explanatory variables, while the next components (PC2, PC3…), respectively, accounted for less variation. Moreover, Kaiser–Meyer–Olkin (KMO) and the Bartlett test of sphericity was performed to verify the appropriateness of the sample, a varimax rotation was used to improve the interpretability of performing PCA, and the cut-off point was a variable loading ≥ 0.6.
Artificial neural network (ANN) modules are non-linear mapping structures that imitate the learning process of the human brain. They are powerful tools for processing problems involving non-linear and complex data, especially when the underlying data relationship is imprecise and noisy. Variables that are identified by linear modeling to be statistically associated with CR utilization status (Graduate, Dropout, and Referral) were used for neural network modeling. The data set included three distinct sets—training, testing, and validation. The training set was used to learn data patterns, the testing set was to evaluate the generalization ability of the trained network, and the validation set was used to check the trained network performance. The ANN procedure was carried out using a PC laptop computer, equipped with a 64-bit operating system, 2.90 GHz microprocessor, and 8.00 GB of RAM.
In this study, we used clinical data to identify the predictive model of CR utilization, which posed significant challenges for statistical analysis. The clinical data collected over time were voluminous, with large number of variables that were correlated or uncorrelated. There were many different types of observations with different levels of measure and measurement scales, which made it difficult to standardize. Large number of missing data reduced power and validity. The temporal relationships between variable were often nonlinear [26]. PCA is recommended as an alternative to classical regression analysis of multivariable clinical data [27,28]. However, the drawback of PCA is that it only recognizes the linear relationships, which limits its ability to identify nonlinear relationships between clinical variables [28,29], as the main strength of ANN is to handle nonlinear and multidimensional dependencies [29,30]. However, to identify the best-fit predictive model, ANN can be labor-intensive and time consuming, when dealing with a large number of clinical variables embedded in multi-layer and multi-level data structures [30]. To improve efficiency, PCA was first performed to reduce the input dimensions before ANN. PCA also helped develop ANN training sets and enhance the specificity of a predictive model by reducing dimensionality and removing the correlated variables. Then, ANN used the principal components obtained by the PCA method to develop a better performed predictive model with higher accuracy [28,29,30]. Using both PCA and ANN could help address challenges in clinical data analysis and interpretation. The combination of PCA and ANN is a valid and effective approach to reduce residual errors, make proper classification, recognize relationship patterns, and test an unlimited number of related or unrelated factors among a large number of clinical observations [28,29,30].

3. Results

3.1. Baseline Characteristics

The baseline demographic and clinical characteristics of the study population is summarized in Table 1. Of the 685 patients included in the study, 421 (61.4%) of them completed 36 sessions, 217 (31.7%) dropped out, and 47 (6.9%) were referred to by a physician but failed to initiate the program. The average age of the study population was 64 years, ranging from 24 to 89. Male patients accounted for 65% of the study population. A total of 42% underwent coronary artery bypass grafting (CABG) or percutaneous coronary intervention, 28% had a stable angina, 20% had acute coronary syndrome, and 8% had a stable heart failure.

3.2. Comparison between Baseline and 3 Months

Comparison analyses were performed in the three groups (Graduates, Dropouts, and Referrals) at baseline and at 3 months (the standard duration of our program). Graduates exhibited greater extremity strength and flexibility, longer six-minute walk distance (6MWT), superior CR knowledge score, and a higher SF-36 PF score (all p < 0.001 by paired t-test). Moreover, the Graduates had significantly reduced anxiety and depression compared to Dropouts and Referrals, after completing CR (p = 0.000, paired t-test). While both Dropouts and Referrals had increased 6MWT distance (p = 0.038 and p = 0.001) and 6MWT Metabolic equivalent of tasks (METs) (p = 0.038 and p = 0.001), respectively, after 3 months, significant changes were not observed in the other variables (Figure 1 and Figure 2, Supplementary Materials Table S1).

3.3. Predictors of CR Completion

One-way ANOVA test was used to analyze the demographic factors contributing to the CR completion status. According to the results presented in Table 2, there was a statistically significant difference between the three groups regarding mean age, BMI, CR knowledge test, HADS Anxiety, HADS Depression, SF36GH, and PF (p < 0.05).
Principal component analysis (PCA) was conducted to consolidate baseline data into three factors, which explained 66.8% of the total variance. The Kaiser-Meyer-Olkin (KMO) statistic was 0.75, which exceeded the minimum recommendation of 0.60, and the Bartlett test of sphericity was statistically significant (χ2 = 267.885, p < 0.001), both indicating that the sampling adequacy and correlation matrix was satisfactory for PCA.
The first principal components (PC1) addressed psychosocial variables (including SF36GH, HADS Depression, HADS Anxiety, and SF36PF), which accounted for 38.5% of the variance. The second principal component (PC2), which only included age as a variable, contributed to 14.5% of the variation. Finally, the third principal component (PC3), which included BMI variables, explained an additional 13.8% of the variation. PCA showed that patients who were older, obese, and who had depression, anxiety, or a low quality of life, were less likely to complete the CR program. A summary of the loadings, after varimax rotation, related to the variables in each component, is provided in Table 3. Figure S1 shows the scree plot of the three components. A detailed analysis of the score of each observation on the three PC analyses, as well as the contributing effect of each variable, are presented in Figure 3.
Finally, ANN was used to validate the results from PCA. It used feed-forward architecture with multi-layered perception. The same seven variables identified by linear modeling were confirmed in the input layer of the ANN module (Table 4). The description diagram of the ANN model, generated by the software iterations, is presented in Figure 4. Our results identified the input layer comprised of seven neurons, which validated the findings generated from PCA. The output layer consisted of three neurons, representing three groups, based on CR utilization status. The hidden layer located between the input and output layers, contained mathematical functions that performed nonlinear transformations of the input entered into the network. The percent incorrect predictions for the training and testing steps were 0.197 and 0.229, respectively (Table 5), which was acceptable. The algorithm for determination of predictor importance, also termed “specificity,” is presented in Figure S2. After the nonlinear transformation in the hidden layer and two-step modeling (training and testing), ANN was able to classify all study subjects into three groups, based on the minimal number of predictors needed, as they were entered into the input layer of the network.

4. Discussion

This study aimed to identify the predictors of CR completion among patients with CVD. Among patients who were eligible for CR, approximately 32% of them dropped out, and 7% referred patients failed to initiate CR therapy. Identified predictors of completion fall into three categories—psychosocial, demographic, and clinical aspects, which account for 66.8% of the total variation among the studied variables.
The psychosocial domain included HRQoL (assessed by SF-36 PF and SFGH), anxiety, and depression (assessed by HADS). Consistent with previous studies, HRQoL played a significant role in patients’ decision to utilize CR. Compared to patients who completed CR, those who failed to initiate or complete the CR program had lower HRQoL at baseline. Most studies reported an improvement of HRQoL after CR completion, which was congruent with our findings, but few studies examined the impact of HRQoL on CR utilization in CVD patients [31]. Unlike graduates, who had significantly improved the quality of life after completing CR, those who dropped out or who were referred but did not attend CR showed no significant improvement in QoL over time, after hospital discharge, suggesting that this is a critical window of time for patients to attend CR. In addition, HRQoL is related to psychological anxiety and depression [32], which was significantly improved in those who completed CR. Interestingly, our study also showed that anxiety and depression predicted CR completion. Thus, CVD patients need to improve their quality of life and reduce their anxiety and depression, which in turn might lead to higher CR adherence. This finding was in accordance with recent clinical studies [33].
As reported in previous studies conducted by Lane et al. [8] and Petrie et al. [34], age was the only factor in the demographic domain that was significantly associated with underutilization of CR. The potential explanations included physical constraints, health status, lack of transportation, and insufficient family support. Older cardiac patients were also more likely to be single, widowed, or to live alone with less social support, leading to the underutilization of CR. Additionally, the average number of comorbidities increased monotonically with age. These comorbidities might hamper participation in exercise sessions and create barriers to completing the CR program.
Among all variables examined in the clinical domain, BMI was found to predict CR completion. Recent studies provided strong evidence that obesity is associated with physical inactivity [35]. Physically inactive patients are more likely to drop out or fail to initiate a CR program [35]. The majority of participants in our study were overweight or obese (the average BMI was 31). The average BMI was higher in the Dropout and Referral groups than the Graduate group, at baseline (34, 32, and 30, respectively). CR programs could help obese patients achieve better health outcomes by managing their blood pressure, diabetes, and lipid levels. The effect of CR was dose-dependent, which meant that the number of sessions attended was positively associated with weight loss and reductions in blood pressure. Therefore, additional studies are needed to identify factors influencing obese patients’ decision making on CR utilization, thus, enabling development of a tailored intervention to promote CR utilization in obese cardiac patients.
There are several limitations in our study. First, this study was an observational investigation using a convenient sample of patient data from a single CR program in an academic, hospital-based setting. Therefore, the results might not be generalized to national or international CR patients. Based on a recent study describing national CR participants’ characteristics [36], however, our study included a heterogeneous and representative sample, comparable to national CR patients. In addition, the advanced statistical modeling helped reduce bias and improve generalizability to other CR programs across the nation. We used the combination of principal component analysis (PCA) and artificial neural network (ANN) analysis to examine predictors of both CR completion and attendance. PCA detects the common variation between the original variables and condenses the data. In the present study, a large number of explanatory variables makes PCA reliable for the purpose of the study. ANN was able to detect non-linear relationships that were not identified by PCA. The combination of PCA and ANN is a valid and effective approach to enhance model predictive accuracy, when dealing with complex clinical data with large missing values.
Second, the list of explanatory variables that could contribute to CR utilization was limited to what was available in the EMR. Factors such as economic scarcity, financial scarcity, social support, health belief, health literacy, and personality traits, were not available in EMR [37]. These missing variables could lead to misleading conclusions regarding the relative importance of the characteristics examined here. On the other hand, the selected variables were captured by most CR programs nationwide and used to develop clinically feasible interventions to promote CR utilization. Third, the HRQoL and mental health assessments were obtained from patients’ self-reports, which was not validated by objective measures and thus could have led to bias. To date, objective and clinically feasible measures of HRQoL, anxiety, and depression are not identified or reported. As a result, future studies are needed to replicate and expand our findings.

5. Conclusions

The study identified important factors predicting CR utilization. Our statistical modeling revealed three domains that explained 66.8% of the total variance, including age, BMI, HRQoL, anxiety, and depression. Pre-CR screening and tailored interventions are needed to promote CR utilization in high-risk populations.

Supplementary Materials

The following are available online at https://www.mdpi.com/2308-3417/5/4/66/s1. Figure S1: Scree plot indicating the amount of variance explained by each principal component. Figure S2: Receiver-operating characteristic (ROC) curves for the artificial neural network. Table S1: Difference between before and after cardiac rehabilitation according to three status groups.

Author Contributions

Conceptualization, L.Y., and Q.Z.; methodology, Q.Z.; software, Q.Z.; validation, N.W., Y.D., H.Z., H.X., P.S., and S.D.; formal analysis, Q.Z.; investigation, L.Y., K.R., and E.L.; resources, L.Y.; data curation, Q.Z.; writing—original draft preparation, L.Y. and Q.Z.; writing—review and editing, N.W., E.L., K.R., Y.D., H.Z., H.X., P.S., and S.D. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Acknowledgments

Weintraub is supported by grants HL124097, HL126949, HL134354, AR070029, and AG064895 from the National Institutes of Health.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Veronese, N.; Cereda, E.; Stubbs, B.; Solmi, M.; Luchini, C.; Manzato, E.; Sergi, G.; Manu, P.; Harris, T.; Fontana, L.; et al. Risk of cardiovascular disease morbidity and mortality in frail and pre-frail older adults: Results from a meta-analysis and exploratory meta-regression analysis. Ageing Res. Rev. 2017, 35, 63–73. [Google Scholar] [CrossRef] [PubMed]
  2. Perel, P.; Avezum, Á.; Huffman, M.D.; Pais, P.; Rodgers, A.; Vedanthan, R.; Wood, D.; Yusuf, S. Reducing Premature Cardiovascular Morbidity and Mortality in People with Atherosclerotic Vascular Disease: The World Heart Federation Roadmap for Secondary Prevention of Cardiovascular Disease. Glob. Heart 2015, 10, 99–110. [Google Scholar] [CrossRef] [PubMed]
  3. Bachmann, J.M.; Duncan, M.S.; Shah, A.S.; Greevy, R.A.; Lindenfeld, J.; Keteyian, S.J.; Thomas, R.J.; Whooley, M.A.; Wang, T.J.; Freiberg, M.S. Association of Cardiac Rehabilitation With Decreased Hospitalizations and Mortality After Ventricular Assist Device Implantation. JACC Heart Fail. 2018, 6, 130–139. [Google Scholar] [CrossRef] [PubMed]
  4. Ghisi, G.L.D.M.; Pesah, E.; Turk-Adawi, K.; Supervia, M.; Lopez-Jimenez, F.; Grace, S.L. Cardiac Rehabilitation Models around the Globe. J. Clin. Med. 2018, 7, 260. [Google Scholar] [CrossRef] [Green Version]
  5. Choo, C.C.; Chew, P.K.H.; Lai, S.-M.; Soo, S.-C.; Ho, C.S.H.; Ho, R.C.; Wong, R.C. Effect of Cardiac Rehabilitation on Quality of Life, Depression and Anxiety in Asian Patients. Int. J. Environ. Res. Public Health 2018, 15, 1095. [Google Scholar] [CrossRef] [Green Version]
  6. Del Pozo-Cruz, B.; Carrick-Ranson, G.; Reading, S.; Nolan, P.; Dalleck, L.C. The relationship between exercise dose and health-related quality of life with a phase III cardiac rehabilitation program. Qual. Life Res. 2018, 27, 993–998. [Google Scholar] [CrossRef]
  7. Duscha, B.D.; Piner, L.W.; Patel, M.P.; Craig, K.P.; Brady, M.; McGarrah, R.W.; Chen, C.; Kraus, W.E. Effects of a 12-week mHealth program on peak VO2 and physical activity patterns after completing cardiac rehabilitation: A randomized controlled trial. Am. Heart J. 2018, 199, 105–114. [Google Scholar] [CrossRef]
  8. Lane, D.; Carroll, D.; Ring, C.; Beevers, D.G.; Lip, G.Y.H. Mortality and Quality of Life 12 Months After Myocardial Infarction: Effects of Depression and Anxiety. Psychosom. Med. 2001, 63, 221–230. [Google Scholar] [CrossRef]
  9. Beauchamp, A.; Worcester, M.; Ng, A.; Murphy, B.; Tatoulis, J.; Grigg, L.; Newman, R.; Goble, A. Attendance at cardiac rehabilitation is associated with lower all-cause mortality after 14 years of follow-up. Heart 2013, 99, 620–625. [Google Scholar] [CrossRef] [Green Version]
  10. Anderson, L.; Thompson, D.R.; Oldridge, N. Exercise-based cardiac rehabilitation for coronary heart disease. Cochrane Database Syst. Rev. 2016. [Google Scholar] [CrossRef] [Green Version]
  11. Arena, R.; Williams, M.; Forman, D.E.; Cahalin, L.P.; Coke, L.; Myers, J.; Hamm, L.; Kris-Etherton, P.; Humphrey, R.; Bittner, V.; et al. Increasing Referral and Participation Rates to Outpatient Cardiac Rehabilitation: The Valuable Role of Healthcare Professionals in the Inpatient and Home Health Settings: A science advisory from the American Heart Association. Circulation 2012, 125, 1321–1329. [Google Scholar] [CrossRef] [PubMed]
  12. Mazzini, M.J.; Stevens, G.R.; Whalen, D.; Ozonoff, A.; Balady, G.J. Effect of an American Heart Association Get With the Guidelines Program-Based Clinical Pathway on Referral and Enrollment Into Cardiac Rehabilitation After Acute Myocardial Infarction. Am. J. Cardiol. 2008, 101, 1084–1087. [Google Scholar] [CrossRef] [PubMed]
  13. Suaya, J.A.; Shepard, D.S.; Normand, S.-L.T.; Ades, P.A.; Prottas, J.; Stason, W.B. Use of Cardiac Rehabilitation by Medicare Beneficiaries After Myocardial Infarction or Coronary Bypass Surgery. Circulation 2007, 116, 1653–1662. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  14. Bethell, H.J.; Evans, J.A.; Turner, S.C.; Lewin, R.J.P. The rise and fall of cardiac rehabilitation in the United Kingdom since 1998. J. Public Health 2007, 29, 57–61. [Google Scholar] [CrossRef]
  15. Grace, S.L.; Chessex, C.; Arthur, H.; Chan, S.; Cyr, C.; Dafoe, W.; Juneau, M.; Oh, P.; Suskin, N. Systematizing Inpatient Referral to Cardiac Rehabilitation 2010: Canadian Association of Cardiac Rehabilitation and Canadian Cardiovascular Society Joint Position Paper. Can. J. Cardiol. 2011, 27, 192–199. [Google Scholar] [CrossRef]
  16. Oldridge, N.B. Cardiac rehabilitation exercise programme. Compliance and compliance-enhancing strategies. Sports Med. 1988, 6, 42–55. [Google Scholar] [CrossRef]
  17. Ades, P.A.; Waldmann, M.L.; McCann, W.J.; Weaver, S.O. Predictors of cardiac rehabilitation participation in older coronary patients. Arch. Intern. Med. 1992, 152, 1033–1035. [Google Scholar] [CrossRef]
  18. Gallagher, R.; Roach, K.; Belshaw, J.; Kirkness, A.; Sadler, L.; Warrington, D. A pre-test post-test study of a brief educational intervention demonstrates improved knowledge of potential acute myocardial infarction symptoms and appropriate responses in cardiac rehabilitation patients. Aust. Crit. Care 2013, 26, 49–54. [Google Scholar] [CrossRef]
  19. Ruta, D. Short form 36 questionnaire. J. Epidemiol. Community Health. 1995, 49, 555. [Google Scholar] [CrossRef] [Green Version]
  20. Tiringer, I.; Simon, A.; Herrfurth, D.; Suri, I.; Szalai, K.; Veress, A. Occurrence of anxiety and depression disorders after acute cardiac events during hospital rehabilitation. Application of the Hospital Anxiety and Depression Scale as a screening instrument. Psychiatr. Hung. 2008, 23, 430–443. [Google Scholar]
  21. Failde, I.; Ramos, I. Validity and reliability of the SF-36 Health Survey Questionnaire in patients with coronary artery disease. J. Clin. Epidemiol. 2000, 53, 359–365. [Google Scholar] [CrossRef]
  22. Hunt-Shanks, T.; Blanchard, C.; Reid, R.; Fortier, M.; Cappelli, M. A psychometric evaluation of the Hospital Anxiety and Depression Scale in cardiac patients: Addressing factor structure and gender invariance. Br. J. Health Psychol. 2010, 15, 97–114. [Google Scholar] [CrossRef] [PubMed]
  23. Stafford, L.; Berk, M.; Jackson, H.J. Validity of the Hospital Anxiety and Depression Scale and Patient Health Questionnaire-9 to screen for depression in patients with coronary artery disease. Gen. Hosp. Psychiatry 2007, 29, 417–424. [Google Scholar] [CrossRef] [PubMed]
  24. Daffertshofer, A.; Lamoth, C.J.C.; Meijer, O.G.; Beek, P.J. PCA in studying coordination and variability: A tutorial. Clin. Biomech. 2004, 19, 415–428. [Google Scholar] [CrossRef]
  25. Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning. Data Mining Inference and Prediction, 2nd ed.; Springer: New York, NY, USA, 2009. [Google Scholar]
  26. Soleimani, A.; Abbasi, A.; Nejatian, M.; Salarifar, M.; Darabian, S.; Karimi, A.A.; Davoodi, S.; Kassaian, E.; Abbasi, S.H.; Sheikhfathollahi, M. Factors predicting discontinuation of a hospital-based cardiac rehabilitation programme. Kardiol. Pol. 2009, 67, 147–148. [Google Scholar]
  27. Hripcsak, G.; Bakken, S.; Stetson, P.D.; Patel, V.L. Mining complex clinical data for patient safety research: A framework for event discovery. J. Biomed. Inform. 2003, 36, 120–130. [Google Scholar] [CrossRef] [Green Version]
  28. Bucinski, A.; Bączek, T.; Krysiński, J.; Szoszkiewicz, R.; Załuski, J. Clinical data analysis using artificial neural networks (ANN) and principal component analysis (PCA) of patients with breast cancer after mastectomy. Rep. Pr. Oncol. Radiother. 2007, 12, 9–17. [Google Scholar] [CrossRef] [Green Version]
  29. Qiu, J.; Du, K.-L.; Wang, H.; Lu, J.; Zhang, B. Neural Network Implementations for PCA and Its Extensions. ISRN Artif. Intell. 2012, 2012, 1–19. [Google Scholar] [CrossRef] [Green Version]
  30. Mostaar, A.; Sattari, M.R.; Hosseini, S.; Deevband, M.R. Use of Artificial Neural Networks and PCA to Predict Results of Infertility Treatment in the ICSI Method. J. Biomed. Phys. Eng. 2019, 9, 679–686. [Google Scholar] [CrossRef]
  31. Bouwmans, C.A.M.; Vemer, P.; Van Straten, A.; Tan, S.S.; Roijen, L.H.-V. Health-Related Quality of Life and Productivity Losses in Patients with Depression and Anxiety Disorders. J. Occup. Environ. Med. 2014, 56, 420–424. [Google Scholar] [CrossRef]
  32. Pardaens, S.; De Smedt, D.; De Bacquer, D.; Willems, A.-M.; Verstreken, S.; De Sutter, J. Comorbidities and Psychosocial Characteristics as Determinants of Dropout in Outpatient Cardiac Rehabilitation. J. Cardiovasc. Nurs. 2017, 32, 14–21. [Google Scholar] [CrossRef] [PubMed]
  33. Petrie, K.J.; Weinman, J.; Sharpe, N.; Buckley, J. Role of patients’ view of their illness in predicting return to work and functioning after myocardial infarction: Longitudinal study. BMJ 1996, 312, 1191–1194. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  34. Ridderstråle, M.; Johansson, L.E.; Rastam, L.; Lindblad, U. Increased risk of obesity associated with the variant allele of the PPARGC1A Gly482Ser polymorphism in physically inactive elderly men. Diabetologia 2006, 49, 496–500. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  35. Resurrección, D.M.; Motrico, E.; Rubio-Valera, M.; Mora-Pardo, J.A.; Moreno-Peral, P. Reasons for dropout from cardiac rehabilitation programs in women: A qualitative study. PLoS ONE 2018, 13, e0200636. [Google Scholar] [CrossRef] [Green Version]
  36. Ritchey, M.D.; Maresh, S.; McNeely, J.; Shaffer, T.; Jackson, S.L.; Keteyian, S.J.; Brawner, C.A.; Whooley, M.A.; Chang, T.; Stolp, H.; et al. Tracking Cardiac Rehabilitation Participation and Completion Among Medicare Beneficiaries to Inform the Efforts of a National Initiative. Circ. Cardiovasc. Qual. Outcomes 2020, 13, 005902. [Google Scholar] [CrossRef]
  37. Beauchamp, A.; Sheppard, R.; Wise, F.; Jackson, A. Health Literacy of Patients Attending Cardiac Rehabilitation. J. Cardiopulm. Rehabil. Prev. 2020, 40, 249–254. [Google Scholar] [CrossRef]
Geriatrics 05 00066 g001 550
Figure 1. Physical assessment before and after cardiac rehabilitation in the three patient groups (Graduate, Dropout, and Referral). (a) Six-minute walk test (6MWT) distance differences in paired t-tests; (b) flexibility differences in paired t-tests; (c) strength assessment of left arm differences in paired t-tests; and (d) strength assessment of right arm differences in paired t-tests. * p < 0.05, ** p < 0.01, and *** p < 0.001.
Figure 1. Physical assessment before and after cardiac rehabilitation in the three patient groups (Graduate, Dropout, and Referral). (a) Six-minute walk test (6MWT) distance differences in paired t-tests; (b) flexibility differences in paired t-tests; (c) strength assessment of left arm differences in paired t-tests; and (d) strength assessment of right arm differences in paired t-tests. * p < 0.05, ** p < 0.01, and *** p < 0.001.
Geriatrics 05 00066 g001
Geriatrics 05 00066 g002 550
Figure 2. Psychosocial assessment before versus after cardiac rehabilitation in the three patient groups. (a) Hospital anxiety and depression scale (HADS) anxiety differences in paired t tests; (b) HADS depression differences in paired t tests; (c) Short Form 36 for general health (SF36GH) differences in paired t tests; (d) Short Form 36 for physical functioning (SF36PF) differences in paired t tests; and (e) cardiac rehabilitation (CR) knowledge test differences in paired t-tests. * p < 005, *** p < 0.001.
Figure 2. Psychosocial assessment before versus after cardiac rehabilitation in the three patient groups. (a) Hospital anxiety and depression scale (HADS) anxiety differences in paired t tests; (b) HADS depression differences in paired t tests; (c) Short Form 36 for general health (SF36GH) differences in paired t tests; (d) Short Form 36 for physical functioning (SF36PF) differences in paired t tests; and (e) cardiac rehabilitation (CR) knowledge test differences in paired t-tests. * p < 005, *** p < 0.001.
Geriatrics 05 00066 g002
Geriatrics 05 00066 g003 550
Figure 3. 3D-plot indicating the score of each observation on the three principal components, as well as the contributing effect of each variable (expressed as the product of loadings and singular values). HADS, hospital anxiety and depression scale; SF, Short Form; and BMI, body mass index.
Figure 3. 3D-plot indicating the score of each observation on the three principal components, as well as the contributing effect of each variable (expressed as the product of loadings and singular values). HADS, hospital anxiety and depression scale; SF, Short Form; and BMI, body mass index.
Geriatrics 05 00066 g003
Geriatrics 05 00066 g004 550
Figure 4. The architecture of the typical neural network utilized in the artificial neural network module. BMI, body mass index; CR, cardiac rehabilitation; HADS, hospital anxiety and depression scale; SF, Short Form; GH, general health; and PF, physical functioning.
Figure 4. The architecture of the typical neural network utilized in the artificial neural network module. BMI, body mass index; CR, cardiac rehabilitation; HADS, hospital anxiety and depression scale; SF, Short Form; GH, general health; and PF, physical functioning.
Geriatrics 05 00066 g004
Table
Table 1. Baseline patient characteristics across cardiac rehabilitation status categories.
Table 1. Baseline patient characteristics across cardiac rehabilitation status categories.
CharacteristicTotalGraduateDrop-OutReferral
Mean ± SD or N (%)Mean ± SD or N (%)Mean ± SD or N (%)Mean ± SD or N (%)
Status (Graduate, Drop out, Referral)685 (100%)421 (61.4)217 (31.7)47 (6.9)
Age 64.0 ± 12.565.8 ± 11.760.9 ± 13.069.4 ± 14.3
Gendermale443 (64.7)274 (65.1)133 (61.3)36 (76.6)
female242 (35.3)147 (34.9)84 (38.7)11 (23.4)
Primary diagnosisArrhythmia3 (0.4)2 (0.5)1 (0.5)
Stable angina189 (27.6)115 (27.4)84 (38.7)17 (36.1)
Acute coronary syndrome135 (19.7)76 (18.1)49 (22.6)10 (21.3)
Stable heart failure54 (7.9)33 (7.8)18 (8.3)3 (6.4)
CABG or PTCA 288 (42.0)187 (44.4)57 (26.3)17 (36.2)
Other16 (2.3)8 (1.9)8 (3.7)
Resting HR 71.9 ± 12.171.4 ± 11.872.9 ± 12.873.6 ± 12.4
SBP 127.1 ± 20.7127.4 ± 19.8126.8 ± 23.1125.8 ± 16.9
DBP 72.0 ± 12.372.7 ± 12.170.8 ± 13.171.1 ± 10.4
TC 162.3 ± 49.4159.9 ± 46.1165.3 ± 54.2162.0 ± 42.6
HDL 42.5 ± 13.943.4 ± 13.341.2 ± 13.343.43 ± 20.8
Trig 163.1 ± 272.0139.2 ± 95.7190.0 ± 401.1177.8 ± 157.2
LDL 91.5 ± 40.691.9 ± 40.591.7 ± 41.987.9 ± 33.0
FBG 123.4 ± 93.2123.8 ± 107.7123.2 ± 63.3121.4 ± 40.3
Hemoglobin A1c 6.9 ± 6.07.0 ± 7.66.7 ± 1.96.8 ± 1.7
Weight 201.7 ± 49.6200.4 ± 49.8203.2 ± 49.8206.8 ± 47.5
Height 67.6 ± 4.268.0 ± 3.867.1 ± 4.466.6 ± 5.7
BMI 31.1 ± 8.030.4 ± 6.831.8 ± 8.034.0 ± 15.2
%BF 34.1 ± 8.233.7 ± 8.434.7 ± 7.936.8 ± 6.1
SD, standard deviation; CABG, Coronary artery bypass grafting; PTCA, Percutaneous transluminal coronary angioplasty; HR, heart rate; SBP, systolic blood pressure; DBP, diastolic blood pressure; TC, Total Cholesterol; HDL, High-density lipoprotein; Trig, Triglycerides; LDL, Low-density lipoprotein; FBG, Fasting blood glucose; BMI, body mass index; and % BF, Percentage of body fat.
Table
Table 2. One-way ANOVA factors contributing to the status groups.
Table 2. One-way ANOVA factors contributing to the status groups.
VariablesFp-Value
Age 4.3690.014 *
6MWT distance0.2160.806
6MWT Mets0.2200.803
Resting heart rate1.2200.296
Systolic BP0.1490.861
Diastolic BP1.8210.163
Limb flexibility0.2760.759
Left arm strength0.8390.433
Right arm strength0.0470.954
BMI5.1170.006 **
% of body fat 2.5640.078
CR Knowledge test3.6220.027 *
HADS Anxiety 4.3810.013 *
HADS Depression 4.1370.017 *
SF36GH6.7170.001 ***
SF36PF2.9660.052
* p < 0.05, ** p < 0.01, and *** p < 0.005 F, F Statistics; 6MWT, six-minute walk; BP, blood pressure; BMI, body mass index; HADS, hospital anxiety and depression scale; SF, Short Form; GH, general health; and PF, physical functioning.
Table
Table 3. Variable loading matrix and explained variance related to each PC after varimax rotation.
Table 3. Variable loading matrix and explained variance related to each PC after varimax rotation.
VariableComponent
PC1PC2PC3
SF36 GH0.872−0.0940.066
HADS Depression−0.852 *−0.030−0.057
HADS Anxiety−0.808 *0.187−0.037
SF36 PF 0.761 *0.3420.145
Age0.341−0.681 *0.325
BMI−0.2130.096−0.835 *
CR Knowledge test−0.3620.4690.516
Extraction Method: Principal Component Analysis. Rotation Method: Varimax with Kaiser Normalization. Rotation converged in 7 iterations; 3 components were extracted. * A factor loading of one independent variable was considered as large if its absolute value ≥ 0.6. PC, Principal component; SF, Short Form; GH, general health; HADS, hospital anxiety and depression scale; PF, physical functioning; BMI, body mass index; and CR, cardiac rehabilitation.
Table
Table 4. ANN parameter estimates.
Table 4. ANN parameter estimates.
PredictorPredicted
Hidden Layer 1Output Layer
H(1:1)H(1:2)H(1:3)H(1:4)GraduateDrop OutReferral
Input Layer(Bias)−0.9910.5080.3511.082
Age−0.669−0.014−0.094−0.393
BMI0.0380.3530.4590.016
CR Knowledge test−0.165−0.5040.030−0.247
HADS Anxiety0.2480.225−0.2150.110
HADS Depression0.157−0.6390.4370.143
SF36GH0.0960.0810.1840.134
SF36PF−0.2700.285−0.402−0.233
Hidden Layer 1(Bias) 1.2390.097−1.422
H(1:1) −0.751−0.1890.609
H(1:2) 0.8850.402−0.740
H(1:3) −0.4130.069−0.329
H(1:4) 0.2480.853−0.461
The prediction weights generated by the neural network for each interaction among the 7 pre-incision factors (“input layer”) and the 4 nodes (“hidden layer”), and the output weights of each node to the prediction of CR status—bias weights, were also contributed from the input layer and the hidden layer.
Table
Table 5. Model summary of the artificial neural network.
Table 5. Model summary of the artificial neural network.
Training Model SummaryValue
Cross Entropy Error42.709
Percent Incorrect Predictions19.7%
Stopping Rule Used1 consecutive step(s) with no decrease in error a
Training Time0:00:00.02
Testing Model SummaryValue
Cross Entropy Error19.417
Percent Incorrect Predictions22.9%
Dependent Variable: Status (Graduate, Dropout, and Referral). a, error computations are based on the testing sample. This model displayed a summary of the neural network results by partition, and overall, including the sum of squares errors in the training and testing groups, the relative errors in the training and testing groups, the stopping rule used to stop training, and the training time.

Share and Cite

MDPI and ACS Style

Young, L.; Zhang, Q.; Lian, E.; Roberts, K.; Weintraub, N.; Dong, Y.; Zhu, H.; Xu, H.; Schafer, P.; Dunlap, S. Factors Predicting the Utilization of Center-Based Cardiac Rehabilitation Program. Geriatrics 2020, 5, 66. https://doi.org/10.3390/geriatrics5040066

AMA Style

Young L, Zhang Q, Lian E, Roberts K, Weintraub N, Dong Y, Zhu H, Xu H, Schafer P, Dunlap S. Factors Predicting the Utilization of Center-Based Cardiac Rehabilitation Program. Geriatrics. 2020; 5(4):66. https://doi.org/10.3390/geriatrics5040066

Chicago/Turabian Style

Young, Lufei, Qi Zhang, Eric Lian, Kimberly Roberts, Neal Weintraub, Yanbin Dong, Haidong Zhu, Hongyan Xu, Pascha Schafer, and Stephanie Dunlap. 2020. "Factors Predicting the Utilization of Center-Based Cardiac Rehabilitation Program" Geriatrics 5, no. 4: 66. https://doi.org/10.3390/geriatrics5040066

APA Style

Young, L., Zhang, Q., Lian, E., Roberts, K., Weintraub, N., Dong, Y., Zhu, H., Xu, H., Schafer, P., & Dunlap, S. (2020). Factors Predicting the Utilization of Center-Based Cardiac Rehabilitation Program. Geriatrics, 5(4), 66. https://doi.org/10.3390/geriatrics5040066

Article Metrics

Back to TopTop