Browsing by Author "Alqahtani, Ola"

Now showing 1 - 2 of 2

Restricted
Does Integrating Cognitive Behavioural Therapy into Cardiac Rehabilitation Improve Depression and Quality of Life in Adults with Cardiovascular Disease? A Systematic Review.
(Cardiff University, 2025) Alqahtani, Ola; Gale, Nichola
Does Integrating Cognitive Behavioural Therapy into Cardiac Rehabilitation Improve Depression and Quality of Life in Adults with Cardiovascular Disease? A Systematic Review. Background & Rationale Cardiovascular disease (CVD) is the world’s leading cause of death and disability, placing significant clinical and economic burdens on healthcare systems. While cardiac rehabilitation (CR) encompassing exercise, education, and routine psychosocial support has been shown to improve clinical outcomes, up to thirty percent of cardiac patients experience clinically meaningful depressive symptoms which reduce CR adherence and long-term success. Cognitive behavioural therapy (CBT) offers a structured approach to modifying maladaptive thoughts and behaviours, potentially addressing psychological barriers more effectively than generic psychosocial support. However, many reviews have evaluated heterogeneous ‘psychological interventions’ rather than isolating CBT’s specific impact. This systematic review set out to determine whether CBT, when integrated into CR, alleviates depression and enhances health-related quality of life (HRQoL) more effectively than CR alone. Methods A systematic literature search was conducted across five major databases (Medline, EMBASE, CINAHL, Cochrane CENTRAL, and PsycINFO) from inception to the most recent feasible date, adhering to PRISMA guidelines for study selection and reporting. Six randomised controlled trials, totalling 708 participants, satisfied the inclusion criteria by focusing on adults (≥18 years) undergoing CR for various cardiac conditions (such as myocardial infarction, heart failure, or post-cardiac surgery). Studies which integrated structured CBT sessions into standard CR were compared to CR alone or other forms of standard care. The primary outcome was the reduction in depressive symptoms, measured by validated scales (e.g., the Hamilton Rating Scale for Depression or the Hospital Anxiety and Depression Scale (HADS)). Secondary outcomes involved changes in HRQoL, assessed by either generic or cardiac-specific instruments (such as the Minnesota Living with Heart Failure Questionnaire). Quality appraisal followed the Joanna Briggs Institute guidelines and due to heterogeneity in intervention formats, population characteristics, and outcome measures, a narrative synthesis approach was applied rather than a meta-analysis. Key Findings and Discussion Although the six trials varied in terms of sample size, intervention intensity, and follow-up duration, they shared an overarching conclusion that integrating CBT within CR can lead to notable reductions in depressive symptoms and meaningful improvements in HRQoL. The degree of benefit was generally greater in patients presenting with moderate-to-severe baseline depression. Face-to-face CBT delivery typically achieved better adherence (often exceeding 75%) and larger effect sizes, whereas fully digital CBT programmes suffered from low engagement (approximately 15% module completion). These findings suggest that the personal interaction and therapeutic alliance inherent in face-to-face sessions remain critical for maximising CBT’s clinical impact in cardiac populations, particularly those facing multiple stressors related to their disease. CBT combined with exercise, in several trials, appeared to deliver synergistic benefits for depression and HRQoL, possibly through complementary behavioural (cognitive restructuring and skill-building) and physiological (improved cardiovascular function) mechanisms. The interplay between exercise encouragement and cognitive-behavioural strategies against fear-avoidance thinking also emerged as an important determinant of enhanced functional capacity and sustained improvements in mood. Limitations Several limitations may constrain the generalisability of these results. First, the overall sample predominantly comprised of male participants (approximately two-thirds were male), leaving questions regarding whether women, who often exhibit different depressive symptom profiles and a greater prevalence of depression post-myocardial infarction, would experience similar outcomes. Second, varied measures of depression and HRQoL, along with wide differences in the intervention ‘dose’ (ranging from five-session brief interventions to twelve-week combined programmes), precluded direct quantitative comparisons across studies. Some trials were also underpowered and only a few extended follow-up beyond six to twelve months. Digital CBT approaches did not yield strong results in this review but that may reflect poor adherence rather than intrinsic ineffectiveness, highlighting a need for more engaging and personalised technological platforms. Finally, these RCTs spanned multiple healthcare settings in Europe and the United States where infrastructural and cultural factors might influence both the feasibility of CBT delivery and participant engagement. Conclusions and Recommendations This review provides evidence that structured CBT, when delivered in tandem with cardiac rehabilitation, can significantly alleviate depressive symptoms and promote better quality of life. The most robust outcomes were observed in trials that targeted moderate-to-severe depression, employed face-to-face group or individual CBT sessions, and ensured consistent patient follow-up. These findings strengthen the case for systematically screening CR entrants for depressive symptoms and offering a dedicated CBT component to those above a certain severity threshold. Practical feasibility can be enhanced by training nurses, physiotherapists, or other allied professionals in CBT skills, as illustrated in studies where task shifting maintained strong outcomes. Policy-making bodies, such as national cardiac societies and health agencies, may wish to recommend CBT as a priority psychological intervention in CR programmes, particularly for patients with moderate or severe depression. Future research should further refine the optimal ‘dose’ of CBT, compare blended or stepped-care digital and in-person models, and evaluate the cost-effectiveness to guide broader adoption. By focusing on cognitive restructuring and behaviour change within the supportive framework of CR, healthcare systems can potentially improve both the mental health and functional recovery of individuals with CVD.
3 0
Restricted
Efficient Deep Learning for Plant Disease Classification in Resource Constrained Environment
(The University of Georgia, 2024) Alqahtani, Ola; Ramaswamy, Lakshmish
Deep Neural Networks (DNNs) have been widely used in today’s applications. In many applications such as video analytics, face recognition, computer vision, and classification problems like plant disease classification, etc. DNN models are constrained by efficiency constraints (e.g., latency). Many deep learning applications require low inference latency, which must fall within the parameters set by a service level objective. The prediction of the inference time of DNN models raises another problem which are the limited resources of Internet of Things devices. These devices need an effective way to run DNN models on them. One of the most widely discussed technological developments since the Internet of Things is edge machine learning (Edge ML), and with good reason. Edge Machine Learning is a fast-growing well-known technological improvement since the existence of the Internet of Things (IoT). Edge ML allows smart devices to use machine learning and deep learning techniques to analyze data using servers locally or at the device level, which reduces the need for cloud networks. This is caused by a variety of issues, including poor internet access, expensive cloud resources, low-resource edge devices, and a high failure rate of Internet of Things (IoT) devices, either because of battery or connection issues. Finding a way to effectively run the DNN models locally on IoT devices is crucial.
34 0