Medicine
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/12
This repository contains the published and unpublished research of the Faculty of Medicine by the staff members of the faculty
Browse
17 results
Search Results
Item 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.Item Non-invasive diagnostic approach for diabetes using pulse wave analysis and deep learning(MDPI, 2024) Gunathilaka, H.; Rajapaksha, R.; Kumarika, T.; Perera, D.; Herath, U.; Jayathilaka, C.; Liyanage, J.; Kalingamudali, S.The surging prevalence of diabetes globally necessitates advancements in non-invasive diagnostics, particularly for the early detection of cardiovascular anomalies associated with the condition. This study explores the efficacy of Pulse Wave Analysis (PWA) for distinguishing diabetic from non-diabetic individuals through morphological examination of pressure pulse waveforms. The research unfolds in four phases: data accrual, preprocessing, Convolutional Neural Network (CNN) model construction, and performance evaluation. Data were procured using a multipara patient monitor, resulting in 2000 pulse waves equally divided between healthy individuals and those with diabetes. These were used to train, validate, and test three distinct CNN architectures: the conventional CNN, Visual Geometry Group (VGG16), and Residual Networks (ResNet18). The accuracy, precision, recall, and F1 score gauged each model’s proficiency. The CNN demonstrated a training accuracy of 82.09% and a testing accuracy of 80.6%. The VGG16, with its deeper structure, surpassed the baseline with training and testing accuracies of 90.2% and 86.57%, respectively. ResNet18 excelled, achieving a training accuracy of 92.50% and a testing accuracy of 92.00%, indicating its robustness in pattern recognition within pulse wave data. Deploying deep learning for diabetes screening marks progress, suggesting clinical use and future studies on bigger datasets for refinement.Item Values-based education: Integrating professionalism into the curriculum(Taylor & Francis Group, 2023) Mohanna, K.; Perera, D.Item Duplication errors due to brand name confusion; It is not always the name-Short case series(John Wiley & Sons, 2023) Mamunuwa, N.; Jayamanne, S.; Wijekoon, N.; Coombes, J.; Perera, D.; Shanika, T.; Mohamed, F.; Lynch, C.; de Silva, A.; Dawson, A.Confusion of drug names has been identified as a leading cause of medication errors and potential iatrogenic harm. Most of these errors occur because of look-alike or sound-alike drugs. This case series gives examples of duplication errors due to brand confusion, where there are no similarities in the names.Item Domain-Specific learning among medical students(Basic Medical Scientists Association, 2012) Perera, D.; Ramanayake, R.P.J.C.; de Silva, A.H.W.; Sumanasekara, R.D.N.; Jayasinghe, L.R.; Gunasekara, R.; Chandrasiri, P.Background: The aim of this study was to investigate undergraduate medical student’s domain-specific learning. Method: The research tool was a structured essay question formulated to assess factual and affective knowledge and application and synthesis of knowledge .The question was administered to 151 students. Results: Mean score on the recall question was significantly higher than the other two domains. Total scores of female students were significantly higher than male students (P<0.05). Gender-wise difference in scores was not significant in any specific domain area. There was no significant relationship between factual knowledge and total scores. However, there was a significant linear relationship between total scores and the two areas of affective knowledge (r=0.78) and application and synthesis of knowledge (r=0.6). Findings indicate that affective knowledge and application of knowledge are closely related to overall acquisition of knowledge (P<0.0005). Conclusion: Teaching and assessment in higher-order knowledge domains and affective knowledge needs to be developed. Questions dealing with affective knowledge and testing higher-order cognitive abilities are more discriminatory than questions testing at the recall level.Item General practice is ‘different’: qualitative study of acculturation experiences of East Staffordshire general practice specialty trainees(Royal College of General Practitioners, 2020) Perera, D.; Mohanna, K.BACKGROUND Undergraduate medical education and postgraduate foundation training are largely secondary care based. General practice trainees also spend nearly half of their training in hospital rotations. Little is known about factors that support effective transition into general practice specialty training or belongingness experiences throughout training. AIM To explore the reported experiences of general practice trainee transition into general practice, training in hospital settings, and views of the future. METHOD Semi-structured interviews with 18 purposively selected trainees plus observation and stakeholder discussions by a visiting Sri Lankan general practice trainee attending the vocational training scheme in a participant observer role. RESULTS Mastering core skills of general practice, undergraduate and early experience in general practice during specialty training, and general practice trainer guidance and role modelling facilitated transition. A reduced sense of belongingness during hospital rotations impacted on training and work. Building bridging social connections, personal agency initiatives to bring general practice relevance into hospital training, and secondary care affiliative behaviours were adaptive strategies. Allocation to more general practice relevant duties was thought to create value within the hospital team. General practice trainees are thriving with the support of general practice trainers and colleagues, vocational training scheme, and good work/life balance. International graduates require additional support in specific areas. CONCLUSION Adequate support towards transition into general practice and fostering belongingness in hospital settings is important due to the wider impact on training, patient care, and primary/secondary care integration. We propose a theoretical explanation based on Wenger’s social learning model, which may have useful practical implications.Item A Comparative analysis of the outcome of malaria case surveillance strategies in Sri Lanka in the prevention of re-establishment phase(BioMed Central, 2021) Gunasekera, W.M.K.T.A.W.; Premaratne, R.; Fernando, D.; Munaz, M.; Piyasena, M.G.Y.; Perera, D.; Wickremasinghe, R.; Ranaweera, K.D.N.P.; Mendis, K.BACKGROUND: Sri Lanka sustained its malaria-free status by implementing, among other interventions, three core case detection strategies namely Passive Case Detection (PCD), Reactive Case Detection (RACD) and Proactive Case Detection (PACD). The outcomes of these strategies were analysed in terms of their effectiveness in detecting malaria infections for the period from 2017 to 2019. METHODS: Comparisons were made between the surveillance methods and between years, based on data obtained from the national malaria database and individual case reports of malaria patients. The number of blood smears examined microscopically was used as the measure of the volume of tests conducted. The yield from each case detection method was calculated as the proportion of blood smears which were positive for malaria. Within RACD and PACD, the yield of sub categories of travel cohorts and spatial cohorts was ascertained for 2019. RESULTS: A total of 158 malaria cases were reported in 2017-2019. During this period between 666,325 and 725,149 blood smears were examined annually. PCD detected 95.6 %, with a yield of 16.1 cases per 100,000 blood smears examined. RACD and PACD produced a yield of 11.2 and 0.3, respectively. The yield of screening the sub category of travel cohorts was very high for RACD and PACD being 806.5 and 44.9 malaria cases per 100,000 smears, respectively. Despite over half of the blood smears examined being obtained by screening spatial cohorts within RACD and PACD, the yield of both was zero over all three years. CONCLUSIONS: The PCD arm of case surveillance is the most effective and, therefore, has to continue and be further strengthened as the mainstay of malaria surveillance. Focus on travel cohorts within RACD and PACD should be even greater. Screening of spatial cohorts, on a routine basis and solely because people are resident in previously malarious areas, may be wasteful, except in situations where the risk of local transmission is very high, or is imminent. These findings may apply more broadly to most countries in the post-elimination phase. KEYWORDS: Active case detection; Malaria case surveillance; Malaria in Sri Lanka; Passive case detection; Prevention of re-establishment of malaria; Proactive case detection; Reactive case detection; Spatial cohorts; Travel cohorts; Yield.Item Case report: Opportunities for Medication Review and Reconciliation by a Clinical Pharmacist to Prevent Drug-Related Hospital Re-Admissions: Evidence from a Case Series in Sri Lanka(Pharmaceutical Journal of Sri Lanka, 2018) Shanika, L.G.T.; Wijekoon, C.N.; Jayamanne, S.; Coombes, J.; Perera, D.; Pathiraja, V.M.; Mamunuwa, N.; Mohamed, F.; Coombes, I.; Lynch, C.; de Silva, H.A.; Dawson, A.H.ABSTRACT: Medication review by a clinical pharmacist improves quality use of medicines in patients by identifying, reducing and preventing drug related problems and hospital re-admissions. This service is new to Sri Lanka. We present two cases from a non-randomized controlled trial conducted in a tertiary care hospital in Sri Lanka. The first case is from the control group where no clinical pharmacist was engaged and the next case is from the intervention group. The first case was a drug related hospital re-admission because of missing medicines in the discharge prescription and the second case was a re-admission which was prevented by the intervention of a ward pharmacist by performing a clinical medication review of the prescription.Item Ward-based clinical pharmacists and hospital readmission: a non-randomized controlled trial in Sri Lanka(2018) Shanika, L.G.T.; Jayamanne, S.; Wijekoon, C.N.; Coombes, J.; Perera, D.; Mohamed, F.; Coombes, I.; de Silva, H.A.; Dawson, A.H.OBJECTIVE: To assess if a ward-based clinical pharmacy service resolving drug-related problems improved medication appropriateness at discharge and prevented drug-related hospital readmissions. METHOD: Between March and September 2013, we recruited patients with noncommunicable diseases in a Sri Lankan tertiary-care hospital, for a non-randomized controlled clinical trial. The intervention group received usual care and clinical pharmacy service. The intervention pharmacist made prospective medication reviews, identified drug-related problems and discussed recommendations with the health-care team and patients. At discharge, the patients received oral and written medication information. The control group received usual care. We used the medication appropriateness index to assess appropriateness of prescribing at discharge. During a six-month follow-up period, a pharmacist interviewed patients to identify drug-related hospital readmissions. RESULTS: Data from 361 patients in the intervention group and 354 patients in the control group were available for analysis. Resolutions of drug-related problems were higher in the intervention group than in the control group (57.6%; 592/1027, versus 13.2%; 161/1217; P < 0.001) and the medication was more appropriate in the intervention group. Mean score of medication appropriateness index per patient was 1.25 versus 4.3 in the control group (P < 0.001). Patients in the intervention group were less likely to be readmitted due to drug-related problems (44 patients of 311 versus 93 of 311 in the control group; P < 0.001). CONCLUSION: A ward-based clinical pharmacy service improved appropriate prescribing, reduced drug-related problems and readmissions for patients with noncommunicable diseases. Implementation of such a service could improve health care in Sri Lanka and similar settings.Item Impact of a ward-based clinical pharmacist on improving medication knowledge and adherence in patients with chronic non-communicable diseases(Sri lanka Medical Association, 2015) Shanika, L.G.T.; Wijekoon, N.; Jayamanne, S.; Coombes, J.; Coombes, I.; Perera, D.; Pathiraja, V.; Dawson, A.; de Silva, H.A.INTRODUCTION AND OBJECTIVES: This is the first study done in Sri Lanka to evaluate the benefit of a ward-based pharmacist on improving medication knowledge and adherence in patients with chronic non-communicable diseases. METHOD: This is a part of a controlled trial conducted in a tertiary care hospital to evaluate ward-based clinical pharmacy service. Intervention group (IG) received a ward-based pharmacist's service during hospitalization to optimize the patients' drug therapy. At discharge the pharmacist counseled patients regarding all aspects (name, indication, dose, frequency, side effects, and actions for side effects, timing, monitoring and storage) of long term medications and written instructions were also provided. Control group (CG) received usual care without a ward-based pharmacist. The knowledge and adherence were assessed over the phone on the 6th day after discharge by a different pharmacist. Previously validated knowledge and adherence questionnaires were used. RESULTS: There were 334 and 311 patients in the IG and CG, respectively, The IG had a significantly higher average medication knowledge compared to the CG {IG-75.81+19.14 vs. CG-40.84+19.20; P < 0.001). Proportion of drugs with correct answers, to all 9 dimensions tested, was greater in the IG compared to the CG (P < 0.001). IG had a significantly higher medication adherence score compared to the CG (IG-92.97±15.04 vs. CG-80.42±28,29; P <0.001). A significantly large number of individuals in the IG had high adherence score on Morisky adherence scale compared to the CG (P < 0.001). CONCLUSION: Discharge counseling by a ward-based pharmacist improves medication knowledge and adherence of patients on long term medications.