Displaying publications 1 - 20 of 22 in total

Abstract:
Sort:
  1. Abdar M, Książek W, Acharya UR, Tan RS, Makarenkov V, Pławiak P
    Comput Methods Programs Biomed, 2019 Oct;179:104992.
    PMID: 31443858 DOI: 10.1016/j.cmpb.2019.104992
    BACKGROUND AND OBJECTIVE: Coronary artery disease (CAD) is one of the commonest diseases around the world. An early and accurate diagnosis of CAD allows a timely administration of appropriate treatment and helps to reduce the mortality. Herein, we describe an innovative machine learning methodology that enables an accurate detection of CAD and apply it to data collected from Iranian patients.

    METHODS: We first tested ten traditional machine learning algorithms, and then the three-best performing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features.

    RESULTS: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field.

    CONCLUSIONS: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.

    Matched MeSH terms: Databases, Factual/statistics & numerical data
  2. Bauer M, Glenn T, Alda M, Andreassen OA, Angelopoulos E, Ardau R, et al.
    J Psychiatr Res, 2015 May;64:1-8.
    PMID: 25862378 DOI: 10.1016/j.jpsychires.2015.03.013
    Environmental conditions early in life may imprint the circadian system and influence response to environmental signals later in life. We previously determined that a large springtime increase in solar insolation at the onset location was associated with a younger age of onset of bipolar disorder, especially with a family history of mood disorders. This study investigated whether the hours of daylight at the birth location affected this association.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  3. Chang CC, Gangaram HB, Hussein SH
    Med J Malaysia, 2008 Sep;63 Suppl C:68-71.
    PMID: 19227676
    The Malaysian Psoriasis Registry, established in 1998, is the first skin disease clinical registry in Malaysia. It aims to provide useful data on various aspects of psoriasis. Following an extensive revision of the registry form in 2007, a total of 509 psoriasis patients from 10 government dermatologic centres were reviewed in a three month pilot study. The onset of psoriasis was during the second to fourth decade of life in the majority of patients. There was no sexual and ethnic predilection. A positive family history was present in 21.2%, and more common in patients with younger disease onset. The main aggravating factors of psoriasis were stress, sunlight and infection. Plaque psoriasis was the commonest clinical type (80.9%). Joint disease was present in 17.3% of patients, among which mono-/oligoarticular type being the commonest. Nail changes occurred in 68%. More psoriasis patients were overweight and obese compared to the normal population. The mean Dermatologic Life Quality Index (DLQI) score was 8.08 +/- 6.29, and changes during subsequent follow-up may reflect therapeutic effectiveness. This study enabled evaluation of the revised registry form and helped in identifying shortcomings in the implementation of the registry.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  4. Chang KM, Ong TC
    Med J Malaysia, 2008 Sep;63 Suppl C:66-7.
    PMID: 19227675
    Treatment option of Haematological malignancies has expanded over the last decade. The outcome of treatment is expected to be better compare to previously. However, study of treatment outcome for haematological malignancies has not been carried out in Malaysia. The goal of this study is to measure the treatment outcome in patients with haematological malignancy.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  5. Charan J, Dutta S, Kaur R, Bhardwaj P, Sharma P, Ambwani S, et al.
    Expert Opin Drug Saf, 2021 Sep;20(9):1125-1136.
    PMID: 34162299 DOI: 10.1080/14740338.2021.1946513
    BACKGROUND: Elevated inflammatory cytokines in Coronavirus disease 2019 (COVID-19) affect the lungs leading to pneumonitis with a poor prognosis. Tocilizumab, a type of humanized monoclonal antibody antagonizing interleukin-6 receptors, is currently utilized to treat COVID-19. The present study reviews tocilizumab adverse drug events (ADEs) reported in the World Health Organization (WHO) pharmacovigilance database.

    RESEARCH DESIGN AND METHODS: All suspected ADEs associated with tocilizumab between April to August 2020 were analyzed based on COVID-19 patients' demographic and clinical variables, and severity of involvement of organ system.

    RESULTS: A total of 1005 ADEs were reported among 513 recipients. The majority of the ADEs (46.26%) were reported from 18-64 years, were males and reported spontaneously. Around 80%, 20%, and 64% were serious, fatal, and administered intravenously, respectively. 'Injury, Poisoning, and Procedural Complications' remain as highest (35%) among categorized ADEs. Neutropenia, hypofibrinogenemia were common hematological ADEs. The above 64 years was found to have significantly lower odds than of below 45 years. In comparison, those in the European Region have substantially higher odds compared to the Region of Americas.

    CONCLUSION: Neutropenia, superinfections, reactivation of latent infections, hepatitis, and cardiac abnormalities were common ADEs observed that necessitate proper monitoring and reporting.

    Matched MeSH terms: Databases, Factual/statistics & numerical data
  6. Chow LS, Rajagopal H, Paramesran R, Alzheimer's Disease Neuroimaging Initiative
    Magn Reson Imaging, 2016 07;34(6):820-831.
    PMID: 26969762 DOI: 10.1016/j.mri.2016.03.006
    Medical Image Quality Assessment (IQA) plays an important role in assisting and evaluating the development of any new hardware, imaging sequences, pre-processing or post-processing algorithms. We have performed a quantitative analysis of the correlation between subjective and objective Full Reference - IQA (FR-IQA) on Magnetic Resonance (MR) images of the human brain, spine, knee and abdomen. We have created a MR image database that consists of 25 original reference images and 750 distorted images. The reference images were distorted with six types of distortions: Rician Noise, Gaussian White Noise, Gaussian Blur, DCT compression, JPEG compression and JPEG2000 compression, at various levels of distortion. Twenty eight subjects were chosen to evaluate the images resulting in a total of 21,700 human evaluations. The raw scores were then converted to Difference Mean Opinion Score (DMOS). Thirteen objective FR-IQA metrics were used to determine the validity of the subjective DMOS. The results indicate a high correlation between the subjective and objective assessment of the MR images. The Noise Quality Measurement (NQM) has the highest correlation with DMOS, where the mean Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank Order Correlation Coefficient (SROCC) are 0.936 and 0.938 respectively. The Universal Quality Index (UQI) has the lowest correlation with DMOS, where the mean PLCC and SROCC are 0.807 and 0.815 respectively. Student's T-test was used to find the difference in performance of FR-IQA across different types of distortion. The superior IQAs tested statistically are UQI for Rician noise images, Visual Information Fidelity (VIF) for Gaussian blur images, NQM for both DCT and JPEG compressed images, Peak Signal-to-Noise Ratio (PSNR) for JPEG2000 compressed images.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  7. Devi Beena CR, Tang TS, Gerard LC
    Med J Malaysia, 2008 Sep;63 Suppl C:63-5.
    PMID: 19230250
    Carcinoma of the cervix is the most common malignancy in many developing countries. The purpose of this pilot study on cervical cancer patients treated at selected sites in Malaysia is to examine the achievability of collecting information on patients. The data was collected from the medical records of the patients using case report form. The results reveal that more than 90% of the forms had completed data from all sites. The pilot study has demonstrated that it is feasible to register and collect information on cervical cancer patients using the case report forms. Treatment outcome obtained from this data will form the baseline to establish existing clinical practice and will be useful for treating physicians to monitor the treatment outcome and the late complications and with longer followup to measure the disease free and overall survival. In addition, it is an useful tool as the national indicator.
    Matched MeSH terms: Databases, Factual/statistics & numerical data*
  8. Ding WY, Lee CK, Choon SE
    Int J Dermatol, 2010 Jul;49(7):834-41.
    PMID: 20618508 DOI: 10.1111/j.1365-4632.2010.04481.x
    BACKGROUND: Adverse drug reactions are most commonly cutaneous in nature. Patterns of cutaneous adverse drug reactions (ADRs) and their causative drugs vary among the different populations previously studied.
    OBJECTIVE: Our aim is to determine the clinical pattern of drug eruptions and the common drugs implicated, particularly in severe cutaneous ADRs in our population.
    MATERIALS AND METHODS: This study was done by analyzing the database established for all adverse cutaneous drug reactions seen from January 2001 until December 2008.
    RESULTS: A total of 281 cutaneous ADRs were seen in 280 patients. The most common reaction pattern was maculopapular eruption (111 cases, 39.5%) followed by Stevens-Johnson Syndrome (SJS: 79 cases, 28.1%), drug reaction with eosinophilia and systemic symptoms (DRESS: 19 cases, 6.8%), toxic epidermal necrolysis (TEN: 16 cases, 5.7 %), urticaria/angioedema (15 cases, 5.3%) and fixed drug eruptions (15 cases, 5.3%). Antibiotics (38.8%) and anticonvulsants (23.8%) accounted for 62.6% of the 281 cutaneous ADRs seen. Allopurinol was implicated in 39 (13.9%), carbamazepine in 29 (10.3%), phenytoin in 27 (9.6%) and cotrimoxazole in 26 (9.3%) cases. Carbamazepine, allopurinol and cotrimoxazole were the three main causative drugs of SJS/TEN accounting for 24.0%, 18.8% and 12.5% respectively of the 96 cases seen whereas DRESS was mainly caused by allopurinol (10 cases, 52.6%) and phenytoin (3 cases, 15.8%).
    DISCUSSION: The reaction patterns and drugs causing cutaneous ADRs in our population are similar to those seen in other countries although we have a much higher proportion of severe cutaneous ADRs probably due to referral bias, different prescribing habit and a higher prevalence of HLA-B*1502 and HLA-B*5801 which are genetic markers for carbamazepine-induced SJS/TEN and allopurinol-induced SJS/TEN/DRESS respectively.
    CONCLUSION: The most common reaction pattern seen in our study population was maculopapular eruptions. Antibiotics, anticonvulsants and NSAIDs were the most frequently implicated drug groups. Carbamazepine and allopurinol were the two main causative drugs of severe ADRs in our population.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  9. Goh PP, Elias H, Norfariza N, Mariam I, National Eye Database Steering Committee
    Med J Malaysia, 2008 Sep;63 Suppl C:20-3.
    PMID: 19227672
    National Eye Database (www.acrm.org.my/ned) is a web based surveillance system which collects data on eye diseases and clinical performance in ophthalmology service. It is a prospective study with online data collection, concurrent descriptive data analysis and real time report. It includes cataract surgery registry, diabetic eye registry, glaucoma registry, contact lens related corneal ulcer surveillance and monthly ophthalmology service census. This article presents the methodology and some registries reports. The web based surveillance system has made dissemination of report prompt, easy and without barrier.
    Matched MeSH terms: Databases, Factual/statistics & numerical data*
  10. Hayati AN, Kamarul AK
    Med J Malaysia, 2008 Sep;63 Suppl C:50-4.
    PMID: 19227674
    To create a nationwide system to capture data on completed suicide in Malaysia i.e. the morbidity, geographic and temporal trends and the population at high risk of suicide. Data from this registry can later be used to stimulate and facilitate further research on suicide. This paper describes the rationale and processes involved in developing a national suicide registry in 2007. The diagnosis of suicide is based on the ICD-10 codes for fatal intentional self-harm (X60-X84). A case report form with an accompanying instruction manual had been prepared to ensure systematic and uniform data collection. State Forensic Pathologist's offices are responsible for data collection in their respective states, and in turn will submit the data to a central data management unit. Data collection began in July 2007 and currently in data cleaning process. Training for source data producers is ongoing. In 2008, the NSRM plans to involve university hospitals into its network as currently only Ministry of Health hospitals are involved. The NSRM will be launching its online application for case registration this year while an overview of results will be available via its public domain at www.nsrm.gov.my beginning 20 April 2008. To efficiently capture the data on suicide, a concerted effort between various agencies is needed. A lot of conceptual work and data base development remains to be done in order to position preventive efforts on a more solid foundation.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  11. Hosseinpoor AR, Nambiar D, Schlotheuber A, Reidpath D, Ross Z
    BMC Med Res Methodol, 2016 10 19;16(1):141.
    PMID: 27760520
    BACKGROUND: It is widely recognised that the pursuit of sustainable development cannot be accomplished without addressing inequality, or observed differences between subgroups of a population. Monitoring health inequalities allows for the identification of health topics where major group differences exist, dimensions of inequality that must be prioritised to effect improvements in multiple health domains, and also population subgroups that are multiply disadvantaged. While availability of data to monitor health inequalities is gradually improving, there is a commensurate need to increase, within countries, the technical capacity for analysis of these data and interpretation of results for decision-making. Prior efforts to build capacity have yielded demand for a toolkit with the computational ability to display disaggregated data and summary measures of inequality in an interactive and customisable fashion that would facilitate interpretation and reporting of health inequality in a given country.

    METHODS: To answer this demand, the Health Equity Assessment Toolkit (HEAT), was developed between 2014 and 2016. The software, which contains the World Health Organization's Health Equity Monitor database, allows the assessment of inequalities within a country using over 30 reproductive, maternal, newborn and child health indicators and five dimensions of inequality (economic status, education, place of residence, subnational region and child's sex, where applicable).

    RESULTS/CONCLUSION: HEAT was beta-tested in 2015 as part of ongoing capacity building workshops on health inequality monitoring. This is the first and only application of its kind; further developments are proposed to introduce an upload data feature, translate it into different languages and increase interactivity of the software. This article will present the main features and functionalities of HEAT and discuss its relevance and use for health inequality monitoring.

    Matched MeSH terms: Databases, Factual/statistics & numerical data
  12. Khoo TB
    J Child Neurol, 2013 Jan;28(1):56-9.
    PMID: 22532543 DOI: 10.1177/0883073812439623
    In its 2010 report, the International League Against Epilepsy Commission on Classification and Terminology had made a number of changes to the organization, terminology, and classification of seizures and epilepsies. This study aims to test the usefulness of this revised classification scheme on children with epilepsies aged between 0 and 18 years old. Of 527 patients, 75.1% only had 1 type of seizure and the commonest was focal seizure (61.9%). A specific electroclinical syndrome diagnosis could be made in 27.5%. Only 2.1% had a distinctive constellation. In this cohort, 46.9% had an underlying structural, metabolic, or genetic etiology. Among the important causes were pre-/perinatal insults, malformation of cortical development, intracranial infections, and neurocutaneous syndromes. However, 23.5% of the patients in our cohort were classified as having "epilepsies of unknown cause." The revised classification scheme is generally useful for pediatric patients. To make it more inclusive and clinically meaningful, some local customizations are required.

    Study site: The pediatric neurology clinic at the Institute of Pediatrics, Kuala
    Lumpur Hospital
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  13. Lim GC, Azura D
    Med J Malaysia, 2008 Sep;63 Suppl C:55-6.
    PMID: 19230247
    Cancer burden in Malaysia is increasing. Although there have been improvements in cancer treatment, these new therapies may potentially cause an exponential increase in the cost of cancer treatment. Therefore, justification for the use of these treatments is mandated. Availability of local data will enable us to evaluate and compare the outcome of our patients. This will help to support our clinical decision making and local policy, improve access to treatment and improve the provision and delivery of oncology services in Malaysia. The National Cancer Patient Registry was proposed as a database for cancer patients who seek treatment in Malaysia. It will be a valuable tool to provide timely and robust data on the actual setting in oncology practice, safety and cost effectiveness of treatment and most importantly the outcome of these patients.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  14. Muhammad Anwar Hau A
    Med J Malaysia, 2008 Sep;63 Suppl C:74.
    PMID: 19227678
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  15. Nor Aina E
    Med J Malaysia, 2008 Sep;63 Suppl C:72-3.
    PMID: 19227677
    Breast cancer is the most common cancer in most part of the world and it is the most common cancer among Malaysian women. In order to estimate the overall survival and prognosis, it was decided that a National Cancer Patient Registry-Breast cancer be set up. It would be a tracking system form for breast cancer patients in Malaysia to help treatment outcomes. There would be useful for evaluating clinical management.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  16. Pua KC, Khoo AS, Yap YY, Subramaniam SK, Ong CA, Gopala Krishnan G, et al.
    Med J Malaysia, 2008 Sep;63 Suppl C:59-62.
    PMID: 19230249
    Nasopharyngeal carcinoma (NPC) is a cancer which is common in Asia. We report the establishment and early results of a multi-institutional prospective study of nasopharyngeal carcinoma, which seeks to systematically collect data as well as blood and tumour tissue samples from patients diagnosed with nasopharyngeal cancer at six centres in Malaysia. A total of 484 confirmed NPC cases were reported from the six participating centres between 1st July 2007 and 29th February 2008. Of these, 225 were newly diagnosed cases, 53 were recurrent cases and 206 were in remission at the time of reporting. Amongst the newly diagnosed cases, the most common presenting symptom was the presence of neck lumps (42%). Ophthalmo-neurologic symptoms were the presenting symptoms of 11% of the new cases. The majority of cases (75%) presented at stage III/IV.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  17. Sabariah FJ, Ramesh N, Mahathar AW
    Med J Malaysia, 2008 Sep;63 Suppl C:45-9.
    PMID: 19227673
    The first Malaysian National Trauma Database was launched in May 2006 with five tertiary referral centres to determine the fundamental data on major trauma, subsequently to evaluate the major trauma management and to come up with guidelines for improved trauma care. A prospective study, using standardized and validated questionnaires, was carried out from May 2006 till April 2007 for all cases admitted and referred to the participating hospitals. During the one year period, 123,916 trauma patients were registered, of which 933 (0.75%) were classified as major trauma. Patients with blunt injury made up for 83.9% of cases and RTA accounted for 72.6% of injuries with 64.9% involving motorcyclist and pillion rider. 42.8% had severe head injury with an admission Glasgow Coma Scale (GCS) of 3-8 and the Revised Trauma Score (RTS) of 5-6 were recorded in 28.8% of patients. The distribution of Injury Severity Score (ISS) showed that 42.9% of cases were in the range of 16-24. Only 1.9% and 6.3% of the patients were reviewed by the Emergency Physician and Surgeon respectively. Patients with admission systolic blood pressure of less than 90 mmHg had a death rate of 54.6%. Patients with severe head injury (GCS < 9), 45.1% died while 79% patients with moderate head injury survived. There were more survivors within the higher RTS range compared to the lower RTS. Patients with direct admission accounted for 52.3% of survivors and there were 61.7% survivors for referred cases. In conclusion, NTrD first report has successfully demonstrated its significance in giving essential data on major trauma in Malaysia, however further expansion of the study may reflect more comprehensive trauma database in this country.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  18. Saokaew S, Sugimoto T, Kamae I, Pratoomsoot C, Chaiyakunapruk N
    PLoS One, 2015;10(11):e0141993.
    PMID: 26560127 DOI: 10.1371/journal.pone.0141993
    Health technology assessment (HTA) has been continuously used for value-based healthcare decisions over the last decade. Healthcare databases represent an important source of information for HTA, which has seen a surge in use in Western countries. Although HTA agencies have been established in Asia-Pacific region, application and understanding of healthcare databases for HTA is rather limited. Thus, we reviewed existing databases to assess their potential for HTA in Thailand where HTA has been used officially and Japan where HTA is going to be officially introduced.
    Matched MeSH terms: Databases, Factual/statistics & numerical data*
  19. Shabanzadeh P, Yusof R
    Comput Math Methods Med, 2015;2015:802754.
    PMID: 26336509 DOI: 10.1155/2015/802754
    Unsupervised data classification (or clustering) analysis is one of the most useful tools and a descriptive task in data mining that seeks to classify homogeneous groups of objects based on similarity and is used in many medical disciplines and various applications. In general, there is no single algorithm that is suitable for all types of data, conditions, and applications. Each algorithm has its own advantages, limitations, and deficiencies. Hence, research for novel and effective approaches for unsupervised data classification is still active. In this paper a heuristic algorithm, Biogeography-Based Optimization (BBO) algorithm, was adapted for data clustering problems by modifying the main operators of BBO algorithm, which is inspired from the natural biogeography distribution of different species. Similar to other population-based algorithms, BBO algorithm starts with an initial population of candidate solutions to an optimization problem and an objective function that is calculated for them. To evaluate the performance of the proposed algorithm assessment was carried on six medical and real life datasets and was compared with eight well known and recent unsupervised data classification algorithms. Numerical results demonstrate that the proposed evolutionary optimization algorithm is efficient for unsupervised data classification.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
  20. Wendy L, Radzi M
    Med J Malaysia, 2008 Sep;63 Suppl C:57-8.
    PMID: 19230248
    Colorectal cancer is emerging as one of the commonest cancers in Malaysia. Data on colorectal cancer from the National Cancer Registry is very limited. Comprehensive information on all aspects of colorectal cancer, including demographic details, pathology and treatment outcome are needed as the management of colorectal cancer has evolved rapidly over the years involving several disciplines including gastroenterology, surgery, radiology, pathology and oncology. This registry will be an important source of information that can help the development of guidelines to improve colorectal cancer care relevant to this country. The database will initially recruit all colorectal cancer cases from eight hospitals. The data will be stored on a customized web-based case report form. The database has begun collecting data from 1 October 2007 and will report on its first year findings at the end of 2008.
    Matched MeSH terms: Databases, Factual/statistics & numerical data
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links