Displaying all 6 publications

Abstract:
Sort:
  1. Wong PC, Abdullah SS, Shapiai MI
    Sci Rep, 2024 Jul 24;14(1):17037.
    PMID: 39043757 DOI: 10.1038/s41598-024-66874-5
    The classification of Alzheimer's disease (AD) using deep learning models is hindered by the limited availability of data. Medical image datasets are scarce due to stringent regulations on patient privacy, preventing their widespread use in research. Moreover, although open-access databases such as the Open Access Series of Imaging Studies (OASIS) are available publicly for providing medical image data for research, they often suffer from imbalanced classes. Thus, to address the issue of insufficient data, this study proposes the integration of a generative adversarial network (GAN) that can achieve comparable accuracy with a reduced data requirement. GANs are unsupervised deep learning networks commonly used for data augmentation that generate high-quality synthetic data to overcome data scarcity. Experimental data from the OASIS database are used in this research to train the GAN model in generating synthetic MRI data before being included in a pretrained convolutional neural network (CNN) model for multistage AD classification. As a result, this study has demonstrated that a multistage AD classification accuracy above 80% can be achieved even with a reduced dataset. The exceptional performance of GANs positions them as a solution for overcoming the challenge of insufficient data in AD classification.
  2. Seah LH, Jeevan NH, Othman MI, Jaya P, Ooi YS, Wong PC, et al.
    Forensic Sci Int, 2003 Dec 17;138(1-3):134-7.
    PMID: 14642733
    Allele frequencies for the 15 STR loci in the AmpFlSTR Identifiler kit were determined and compared for the three main ethnic groups of the Malaysian population comprising 210 Malays, 219 Chinese and 209 Indians. Blood was placed on FTA paper and DNA was purified in-situ.
  3. Hassan SK, Wong PC, Seevaunnamtum P, Che Omar S, Nik Mohamad NA
    Malays J Med Sci, 2024 Jun;31(3):117-124.
    PMID: 38984244 DOI: 10.21315/mjms2024.31.3.8
    BACKGROUND: Phenylephrine (PE) is one of the vasopressor used to treat hypotension during anaesthesia. The primary aim of this study was to compare the effect of prophylactic infusion and rescue bolus of PE on the haemodynamic changes during spinal anaesthesia (SA) for Caesarean section (CS) in obese parturients.

    METHODS: A total of 74 obese parturients scheduled for elective CS under SA were randomised into two groups; Group A (n = 37) received prophylactic PE infusion starting at 50 μg min-1 and adjusted according to the given algorithm and Group B (n = 37) received 100 μg PE bolus to treat hypotension. The measured parameters were systolic blood pressure (SBP), diastolic blood pressure (DBP), mean arterial pressure (MAP), the total requirement of PE and neonatal Apgar score.

    RESULTS: Six patients were excluded from the analysis due to missing data and only 68 were analysed. Group A showed significantly higher SBP, DBP and MAP than Group B (P < 0.05). The requirement of PE was higher in Group A than Group B [817.7 (265.7) μg versus 360.6 (156.0) μg; P = < 0.05]. Both groups had no difference in terms of the neonatal Apgar score.

    CONCLUSION: Prophylactic PE infusion provided better haemodynamic control than therapeutic boluses in obese parturients undergoing CS under SA.

Related Terms
Filters
Contact Us

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

External Links