Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Sinergi Journal of Electronics, Electromedical Engineering, and Medical Informatics Narra J
Gazali, Syahrul
Unknown Affiliation
Biochemistry, Genetics & Molecular Biology Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Medicine & Pharmacology Public Health

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Plasma interleukin 6 as an outcome predictor of traumatic brain injury patients Ichwan, Khairunnisa; Gazali, Syahrul; Suherman, Suherman; Desiana, Desiana; Nurjannah, Nurjannah
Narra J Vol. 3 No. 3 (2023): December 2023
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narra.v3i3.234

Abstract

Traumatic brain injury is one of the leading causes of death and disability in young adults. Previous studies have suggested that neuroinflammatory process involves the overexpression of interleukin 6 (IL-6); however, data on the predictive ability of IL-6 is limited and conflicting in traumatic head injury patients. The aim of this study was to assess the ability of plasma IL-6 as a predictor of outcome in head injury patients. A cross-sectional study was conducted between June and December 2020 among traumatic head injury patients admitted to Dr. Zainoel Abidin Hospital, Banda Aceh, Indonesia. Demographic, clinical data, and IL-6 level were collected and measured on admission. The outcome was assessed by the Glasgow outcome scale extended (GOSE) in the first- and third-month of post-injury. A total of 50 traumatic brain injury patients were recruited of which 54% were male, 64% had mild head injury, 82% had leukocytosis, and 60% had non-bleeding head CT scan. The mean of IL-6 level was 79.32 pg/mL while the GOSE scores ranged from 1 (death) to 8 (upper good recovery). Early IL-6 level (<24 hours post-injury) was significantly correlated with worse outcome in traumatic head injury, though the correlation strength was moderate (p<0.001; r=-0.42). As a predictor, IL-6 yielded the area under curve (AUC) value of 93.5% (p<0.001) and a cut-off point of 46.33 pg/mL. The sensitivity and specificity of this predictor were 87.5% and 95.24%, respectively. In conclusion, early IL-6 level can be used as a predictor for traumatic head injury. Nevertheless, further multi-center study with a bigger sample size is needed to confirm this finding.
Heavy–Light Soft-Vote Fusion of EEG Heatmaps for Autism Spectrum Disorder Detection Melinda, Melinda; Gazali, Syahrul; Away, Yuwaldi; Rafiki, Aufa; Wong, W.K; Muliyadi, Muliyadi; Rusdiana, Siti
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 8 No 1 (2026): January
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v8i1.1377

Abstract

Autism spectrum disorder is a neurodevelopmental condition that affects social communication and behaviour, and diagnosis still relies on subjective behavioural assessment. Electroencephalography provides a noninvasive view of brain activity but is noisy and often analysed with handcrafted features or evaluation schemes that risk data leakage. This study proposes a deep learning pipeline that combines wavelet denoising, EEG-to-image encoding, and heavy-light decision fusion for autism detection from EEG. Sixteen-channel EEG from children and adolescents with autism and typically developing peers in the KAU dataset is denoised using discrete wavelet transform shrinkage, segmented into fixed 4 second windows, and rendered as pseudo colour heatmaps. These images are used to fine-tune five ImageNet pretrained architectures under a unified training protocol with 5-fold cross-validation. Heavy-light fusion combines one heavyweight backbone and one lightweight backbone through weighted soft voting on class posterior probabilities. The strongest single model, ConvNeXt Tiny, attains about 97.25 percent accuracy and 97.10 percent F1 score at the window level. The best heavy light pair, ConvNeXt plus ShuffleNet, reaches about 99.56 percent accuracy and 99.53 percent F1, with sensitivity and specificity in the 99 percent range. Fusion mainly reduces missed ASD windows without increasing false alarms, indicating complementary error patterns between heavy and light models. These findings show that the proposed denoise encode classify pipeline with heavy light fusion yields more robust autism EEG classification than individual backbones and can support EEG-based decision support in autism screening.
Comparative analysis of EEG pre-processing in ASD using Hanning and Blackman Harris filters Melinda, Melinda; Waladah, Buleun; Yunidar, Yunidar; Mahfuzha, Raudhatul; Gazali, Syahrul; Rusdiana, Siti; Basir, Nurlida
SINERGI Vol 30, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2026.1.023

Abstract

This study investigates the effectiveness of two Finite Impulse Response (FIR) filter designs based on the Hanning and Blackman-Harris windows for preprocessing electroencephalography (EEG) signals collected from both neurotypical individuals and those diagnosed with Autism Spectrum Disorder (ASD). EEG signals were recorded using a 16-channel setup and band-pass filtered between 0.5 and 40 Hz to isolate relevant neural activity. Subsequently, the signals were processed independently using each FIR filter type. Performance evaluation was conducted using four quantitative metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), and Power Spectral Density (PSD). The Hanning window filter showed MAE values ranging from 0.079 to 0.325, MSE from 0.026 to 0.177, SNR between 7.56 and 15.86 dB, and PSD values from 5.3 to 9.08 × 10⁻³. These results demonstrate good noise attenuation while preserving signal morphology. In contrast, the Blackman-Harris window produced higher MAE (0.061–0.318) and MSE (0.019–0.172) but achieved significantly greater SNR improvements (7.77–17.4 dB) and tighter control over PSD (4.904 – 8.442 × 10⁻³), indicating superior noise suppression and reduced spectral leakage. A paired t-test confirmed that differences in all four performance metrics were statistically significant (p < 0.05) across both neurotypical and ASD subject groups. Despite the Hanning filter's computational simplicity, the Blackman-Harris filter demonstrated more robust performance, making it a more suitable choice for high-fidelity EEG signal analysis in clinical diagnostics and neuroscience research.  
Co-Authors Basir, Nurlida Desiana Desiana, Desiana Ichwan, Khairunnisa Junaidi Junaidi Mahfuzha, Raudhatul Melda Fitria Melinda Melinda Muliyadi Muliyadi Nurjannah Nurjannah Rafiki, Aufa Siti Rusdiana Suherman, Suherman Waladah, Buleun Wong, W.K Yunidar Yuwaldi Away