Promoting Physical Activity and Nutrition in People With Stroke

Predicting mortality in brain stroke patients using neural networks: outcomes analysis in a longitudinal study

In this study, Neural Networks (NN) modelling has emerged as a promising tool for predicting outcomes in patients with Brain Stroke (BS) by identifying key risk factors. In this longitudinal study, we enrolled 332 patients form Imam hospital in Ardabil, Iran, with mean age: 77.4 (SD 10.4) years, and 50.6% were male. Diagnosis of BS was confirmed using both computerized tomography scan and magnetic resonance imaging, and risk factor and outcome data were collected from the hospital's BS registry, and by telephone follow-up over a period of 10 years, respectively. Using a multilayer perceptron NN approach, we analysed the impact of various risk factors on time to mortality and mortality from BS. A total of 100 NN classification algorithm were trained utilizing STATISTICA 13 software, and the optimal model was selected for further analysis based on their diagnostic performance. We also calculated Kaplan-Meier survival probabilities and conducted Log-rank tests. The five selected NN models exhibited impressive accuracy ranges of 81-85%. However, the optimal model stood out for its superior diagnostic indices. Mortality rate in the training and the validation data set was 7.9 (95% CI 5.7-11.0) per 1000 and 8.2 (7.1-9.6) per 1000, respectively (P = 0.925). The optimal model highlighted significant risk factors for BS mortality, including smoking, lower education, advanced age, lack of physical activity, a history of diabetes, all carrying substantial importance weights. Our study provides compelling evidence that the NN approach is highly effective in predicting mortality in patients with BS based on key risk factors, and has the potential to significantly enhance the accuracy of prediction. Moreover, our findings could inform more effective prevention strategies for BS, ultimately leading to better patient outcomes.

Evidence-Based Lifestyle Guidelines and Self-Management Strategies Utilized by Women with Polycystic Ovary Syndrome

Polycystic ovary syndrome (PCOS) is a complex endocrine disorder, affecting 13% of reproductive-aged women. While lifestyle management is the first-line treatment for improving complications, women experience challenges with implementation. This cross-sectional study aims to identify the types and sources of dietary and physical activity (PA) interventions implemented by women with PCOS and understand how they use self-management strategies to support lifestyle change. An online questionnaire was disseminated via a consumer-based PCOS website (May 2015-2016). Women (n = 1167) were aged 18-45 years and primarily born within the United States (70%). A quarter or less of women (diet 25%, PA 14%) sought lifestyle advice from health professionals (medical clinicians or dietitians) compared to over half (diet 59%, PA 67%) using alternative sources, namely from online platforms. While only 33% and 16% of women reported following formal dietary or PA guidelines, respectively, 57% had implemented a 'special diet' to manage their condition, many of which were inconsistent with evidence-based practice in PCOS. Participants also displayed a low level of engagement with important self-management behaviors, including goal setting and positive self-talk. These findings suggest that online information may promote inaccurate and ineffective lifestyle advice and emphasize the need to increase engagement with qualified health professionals.

Factors affecting the adoption of health-promoting behaviours in patients with polycystic ovary syndrome: a cross-sectional study

OBJECTIVE

This study aimed to investigate health-promoting lifestyle status and associated risk factors in patients with polycystic ovary syndrome (PCOS).

DESIGN

Cross-sectional study.

SETTING

This study was conducted at a tertiary hospital in Guizhou, China from December 2020 to June 2021.

PARTICIPANTS

A total of 366 participants (18-45 years) diagnosed with PCOS were recruited from the outpatient departments.

MEASURES

Sociodemographic characteristics were collected, and health-promoting behaviours were measured using the Health-Promoting Lifestyle Profile scale. Anxiety status was measured using the Zung's Self-Rating Anxiety Scale, depression status using the Zung's Self-Rating Depression Scale and self-efficacy using the Managing Chronic Disease 6-Item Scale. Multiple stepwise linear regression was conducted to assess the risk factors associated with the health-promoting behaviours of the study participants.

RESULTS

The participants had a poor health-promoting behaviours (88.54±17.44). The highest score in all dimensions was spiritual growth (16.68±4.98), while physical activity (12.71±2.68) was the lowest. Multiple regression analysis revealed that the main factors influencing the development and maintenance of health-promoting behaviours among participants were education (B=10.788, p<0.001), depression (B=-0.377, p<0.001), anxiety (B=-0.333, p<0.001) and self-efficacy (B=0.938, p=0.002). The model showed 74.40% variance shared between the dependent and independent variables (R²=74.40, F=264.633, p<0.001).

CONCLUSION

Health-promoting behaviours are minimal among patients with PCOS, and improving negative emotions and enhancing behavioural awareness and self-efficacy are necessary to increase the adoption of health-promoting behaviours among patients with PCOS.

TRIAL REGISTRATION NUMBER

ChiCTR2000034572.

Physical activity for a meaningful and purposeful life in typical adults: a cross-sectional study

Abstract Introduction Physical activity is a part of life and an essential element for health and well-being. Investigating the meaning and purpose that physical activity adds to life will guide occupation-based interventions. Objective This cross-sectional study aimed to examine the relationship between physical activity level and meaning and purpose in life in typical adults. Method The study included a total of 300 typical adults (181 female, 119 male). Demographic characteristics of the participants, such as age, gender, and educational status, were recorded. The International Physical Activity Questionnaire, the Life Attitude Profile-Revised, and the Purpose in Life Test were used as measurement tools. Spearman correlation coefficient was used to analyse the relationship between nonparametric variables. Results A weak positive correlation was found between the physical activity total scores, meaning in life sub-scores and total scores (r=0.25, p<0.01), and purpose in life total scores (r=0.16, p<0.01). Conclusion Our findings revealed that people engaging in more physical activity had a sense of meaning and purpose in life. Physical activity must take place in occupational therapy practices as an occupation that adds meaning and purpose to an individual's life. Further research is needed on this subject.

Relationships between self-management strategies and physical activity and diet quality in women with polycystic ovary syndrome

OBJECTIVE

To determine the relationships of self-management strategies and physical activity (PA) and diet quality in women with PCOS.

METHODS

An online cross-sectional study involving women (n = 501), 18-45 years in the general Australian community with a self-reported PCOS diagnosis. The self-management and lifestyle behaviour questionnaires were completed between August 2017 and March 2018.

RESULTS

Implementation of PA related self-management strategies increased the odds of meeting PA recommendations [Odds ratio (OR): 2.929 (95%CI: 2.172, 3.951), p < 0.001] but had no association with body mass index (BMI) [OR: 0.-0.984 (95%CI: -1.010, 0.959), p = 0.217] nor perception of self weight [OR: 1.382 (95% CI: 0.700, 2.725), p = 0.352]. Nutrition related self-management strategies were inversely associated with BMI [OR: - 0.115 (95%CI: -7.159, -0.980), p = 0.010] but had no association with diet quality [OR: 0.183 (95%CI: -2.328, 2.800), p = 0.855], energy intake [OR: - 0.092 (95%CI: -1204.443, 527.496) p = 0.438] or weight [OR: - 0.034 (95%CI: -4.020, 1.930), p = 0.491].

CONCLUSIONS

PA self-management strategies were associated with meeting PA recommendations. Nutrition strategies were associated with lower BMI but not diet quality, energy intake or weight in women with PCOS.

PRACTICE IMPLICATIONS

Other behaviour change determinants (e.g. education, skills and self-efficacy) should be considered when designing a PCOS lifestyle programme in conjunction with self-management strategies.

The outcome in patients with brain stroke: A deep learning neural network modeling

Background:

The artificial intelligence field is obtaining ever-increasing interests for enhancing the accuracy of diagnosis and the quality of patient care. Deep learning neural network (DLNN) approach was considered in patients with brain stroke (BS) to predict and classify the outcome by the risk factors.

Materials and Methods:

A total of 332 patients with BS (mean age: 77.4 [standard deviation: 10.4] years, 50.6% – male) from Imam Khomeini Hospital, Ardabil, Iran, during 2008–2018 participated in this prospective study. Data were gathered from the available documents of the BS registry. Furthermore, the diagnosis of BS was considered based on computerized tomography scans and magnetic resonance imaging. The DLNN strategy was applied to predict the effects of the main risk factors on mortality. The quality of the model was measured by diagnostic indices.

Results:

The finding of this study for 81 selected models demonstrated that ranges of accuracy, sensitivity, and specificity are 90.5%–99.7%, 83.8%–100%, and 89.8%–99.5%, respectively. Based on the optimal model (tangent hyperbolic activation function with the minimum–maximum hidden units of 10–20, max epochs of 400, momentum of 0.5, and learning rate of 0.1), the most important predictors for BS mortality were time interval after 10 years (accuracy = 92.2%), age category (75.6%), the history of hyperlipoproteinemia (66.9%), and education level (66.9%). The other independent variables are at moderate importance (66.6%) which include sex, employment status, residential place, smoking habits, history of heart disease, cerebrovascular accident type, blood pressure, diabetes, oral contraceptive pill use, and physical activity.

Conclusion:

The best means for dropping the BS load is effective BS prevention. DLNN strategy showed a surprising presentation in the prediction of BS mortality based on the main risk factors with an excellent diagnostic accuracy. Moreover, the time interval after 10 years, age, the history of hyperlipoproteinemia, and education level are the most important predictors for BS.

An LSTM-Based Prediction Method for Lower Limb Intention Perception by Integrative Analysis of Kinect Visual Signal

Recently, computer vision and deep learning technology has been applied in various gait rehabilitation researches. Considering the long short-term memory (LSTM) network has been proved an excellent performance in learn sequence feature representations, we proposed a lower limb joint trajectory prediction method based on LSTM for conducting active rehabilitation on a rehabilitation robotic system. Our approach based on synergy theory exploits that the follow-up lower limb joint trajectory, i.e. limb intention, could be generated by joint angles of the previous swing process of upper limb which were acquired from Kinect platform, an advanced computer vision platform for motion tracking. A customize Kinect-Treadmill data acquisition platform was built for this study. With this platform, data acquisition on ten healthy subjects is processed in four different walking speeds to acquire the joint angles calculated by Kinect visual signals of upper and lower limb swing. Then, the angles of hip and knee in one side which were presented as lower limb intentions are predicted by the fore angles of the elbow and shoulder on the opposite side via a trained LSTM model. The results indicate that the trained LSTM model has a better estimation of predicting the lower limb intentions, and the feasibility of Kinect visual signals has been validated as well.

Training and Practice Patterns in Cancer Rehabilitation: A Survey of Physiatrists Specializing in Oncology Care

BACKGROUND

Cancer rehabilitation is an integral part of the continuum of care for survivors. Due to the increasing number of survivors, physiatrists commonly see cancer patients in their general practices. Essential to guiding the field is to understand the current training and practice patterns of cancer rehabilitation physicians.

OBJECTIVES

To assess current trends in training and practice for cancer rehabilitation physicians, including the level of burnout among providers in this field.

DESIGN

Cross-sectional descriptive survey study.

SETTING

Online survey.

PARTICIPANTS

American physicians who are affiliated with the Cancer Rehabilitation Physician Consortium (CRPC) of the American Academy of Physical Medicine and Rehabilitation (AAPM&R). The CRPC is a group of cancer rehabilitation providers (both fellowship-trained and not fellowship-trained) with the mission of furthering cancer rehabilitation medicine through education, research, and networking.

METHODS

All CRPC physicians were invited to complete a voluntary and anonymous 43-question online survey. The survey was conceived by a group of eight experts interested in providing additional information to the current literature regarding the training and practice in the cancer rehabilitation field.

MAIN OUTCOME MEASUREMENTS

Training, practice, opioid prescribing, and professional support.

RESULTS

Thirty-seven of 50 physicians participated (response rate = 74%). Respondents were from various states, the three most common being New York (16%, n = 6), Texas (16%, n = 6), and Massachusetts (11%, n = 4). About 57% (n = 21) of the respondents were employed in an academic medical center and 73% (n = 27) reported their primary departmental affiliation was Physical Medicine and Rehabilitation (PM&R). Approximately 78% (n = 29) credited mentorship early in training for their interest in the field. More than half (54%, n = 20) either strongly agreed or agreed that cancer rehabilitation fellowship training is necessary for graduating physiatrists who plan to treat oncology patients/survivors. National PM&R meetings were the primary source of continuing education for 86% (n = 31). Sixty-five percent (n = 24), strongly agreed or agreed that cancer rehabilitation physiatrists should know how to prescribe opioids, and 35% (n = 13) reported prescribing them when appropriate. About 54% (n = 20) rated their level of burnout as low or very low, and more than half (51%, n = 19) believed their burnout level was lower than physiatrists treating other rehabilitation populations.

CONCLUSIONS

Cancer rehabilitation is a growing subspecialty in PM&R, and most physiatrists in general practice will treat many survivors-often for neurologic or musculoskeletal impairments related to cancer or its treatment. Cancer rehabilitation physicians perceive that they have relatively low levels of burnout, and early mentorship and fellowship training is beneficial. Professional conferences and mentorship are a primary source for continuing education.

LEVEL OF EVIDENCE

IV.

Effect of high-intensity exercise on cardiorespiratory fitness in stroke survivors: A systematic review and meta-analysis

BACKGROUND

Knowledge of the optimal protocol and safety of particularly high-intensity exercise applied to individuals with stroke is lacking.

OBJECTIVE

This systematic review and meta-analysis aimed to investigate the effect of high-intensity exercise on cardiorespiratory fitness in stroke survivors.

METHODS

We performed a systematic electronic search for articles in MedLine via PubMed, EMBASE, Web of Science, Cochrane Central Register of Controlled Trials, CINAHL, and SPORTSDiscus up to April 1, 2019. Peak oxygen consumption (VO₂peak), 6-min walk test (6MWT), fastest 10-m walk test (10MWT), and adverse events were assessed. The standardized mean difference (SMD), weighted mean difference (WMD), and odds ratios (ORs) were used to compute the effect size, and subgroup analysis was conducted to test the consistency of results as well as sensitivity analysis to assess the robustness of the results. The quality of evidence was assessed with the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) system.

RESULTS

We included 17 studies (PEDro score≥4) in the meta-analysis. Post-intervention, high-intensity exercise had a significant effect on peak oxygen uptake (VO₂peak; SMD=0.56, P<0.01, I²=8%; WMD=2.53mL/kg/min; high quality of evidence) and 6MWT (SMD=0.26, P<0.01, I²=40%; WMD=17.08m; moderate quality of evidence) but not fastest 10MWT (SMD=0.33, P=0.27, I²=77%; WMD=0.05m/s; low quality of evidence). Subgroup analysis showed better effects of higher-intensity treadmill training (≥70% heart rate reserve/VO₂peak) for a longer duration (≥12 weeks) on VO₂peak and 6MWT in sub-acute or chronic stroke survivors. The high-intensity exercise and control groups did not differ in adverse events including falls [odds ratio (OR) 1.40, P=0.35, I²=11%; low quality of evidence], pain (OR 3.34, P=0.09, I²=0%; moderate quality of evidence), or skin injuries (OR 1.08, P=0.90, I²=0%; low quality of evidence).

CONCLUSIONS

Our meta-analysis suggests that high-intensity exercise is beneficial for cardiorespiratory fitness in stroke survivors and might be safe as a novel intervention in cardiopulmonary rehabilitation after stroke.