Browsing by Author "Gunathilaka, H.J."

Now showing 1 - 2 of 2

Assessment of anxiety, depression, stress, and associated psychological morbidities among patients receiving ayurvedic treatment for different health Issues: first study from Sri Lanka.
(Hindawi Pub. Co., 2019) Gunathilaka, H.J.; Vitharana, P.; Udayanga, L.; Gunathilaka, N.
BACKGROUND:Good mental condition is a vital part of health. Physical impairments would potentially have psychiatric manifestations during the course of a disease that could cause patients to experience a wide range of psychological conditions. This study was conducted to determine prevalence of anxiety, depression, stress, and psychological morbidities among the patients who received warded treatments at Gampaha Wickramarachchi Ayurveda Teaching Hospital, Sri Lanka. METHODS: A total of 148 patients admitted to the hospital were selected for the study on a random systematic basis under four systemic groups (gastrointestinal, integumentary, musculoskeletal, and nervous system) depending on the chief complaint. The presence of depressive, anxiety, and stress symptoms was assessed by the Depression Anxiety Stress Scale 21 item version (DASS 21). The General Linear Model (GLM) was used for statistical analysis. RESULTS:Over 50% of the participants in all four patient groups belonged to age group of 35 to 65 years, encompassing the fraction of population that actively contribute to the workforce in the society. Stress, anxiety, and depression values of patients belonging to different complications varied significantly, as indicated by GLM (p < 0.05). Patients diagnosed with integumentary system-related issues denoted the highest stress levels (27.7 ± 2.54), while the mean stress values among the other systemic groups were not significantly different among each other. The highest anxiety levels were indicated by patients with nervous system-related issues (18.6 ± 1.51), while the lowest anxiety levels were indicated by patients with integumentary disorders (6.0 ± 2.73). The highest depression level was identified from patients suffering from integumentary system-related disorders (31.7 ± 3.42), followed by nervous system (23.2 ± 1.78), gastrointestinal (19.5 ± 3.77), and musculoskeletal (16.8 ± 1.57) disorders. CONCLUSION:Overall, high distress levels were observed among the majority of the patients. Furthermore, integumentary issues may lead to significant psychological impacts. As most of the patients seek for Ayurveda treatments when their diseased condition becomes chronic, it is vital to focus on a biopsychosocial approach to patient assessment and patient care, in actual practice.
Pilot study for non-invasive diabetes detection through classification of photoplethysmography signals using convolutional neural networks
(University of Kelaniya, 2024) Gunathilaka, H.J.; Rajapaksha, R.; Kumarika, T.; Perera, D.; Herath, U.; Jayathilaka, C.; Liyanage, J.A.; Kalingamudali, S.R.D.
Diabetes is a chronic disorder affecting vascular health, often altering pulse wave characteristics. Traditional pulse wave analysis (PWA) methods face challenges such as variability and complexity of signals. This study aims to overcome these limitations by leveraging deep learning models for more accurate and efficient classification. The methodology used in this study involves four key steps: data collection, data preprocessing, Convolutional Neural Network (CNN) model development, and model evaluation. Primary data were collected using a multipara patient monitor, including finger photoplethysmography (PPG) signals, blood pressure, mean arterial pressure, oxygen saturation, and pulse rate. Single pulse wave cycles from 60 healthy individuals and 60 patients with type 2 diabetes underwent preprocessing. The CNN model was trained using 50 PPG images from each group and achieved a training accuracy of 92%. The prediction capability of the model was evaluated using 20 unseen images, comprising 10 healthy and 10 diabetes PPG images. It attained a 90% overall test accuracy in distinguishing between PPG images of individuals with diabetes and those who are healthy. These findings suggest that CNNbased analysis of PPG signals provides a precise, non-invasive tool for diabetes screening. To further enhance accuracy, future studies should focus on increasing the dataset size and performing hyperparameter tuning to optimize the CNN model.