Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Scientia Psychiatrica Sriwijaya Journal of Forensic and Medicolegal
Abu Bakar
Department of Radiology, CMHC Research Center, Palembang, Indonesia
Biochemistry, Genetics & Molecular Biology Health Professions Immunology & microbiology Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Neuroscience Public Health

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Neural Network Versus Stepwise Regression for Forensic Stature Estimation from Percutaneous Tibial Dimensions in South Sumatran Malay Adults Sari Sulistyoningsih; Abu Bakar; Eduardo Michael Perez; Ifah Shandy
Sriwijaya Journal of Forensic and Medicolegal Vol. 3 No. 2 (2025): Sriwijaya Journal of Forensic and Medicolegal
Publisher : Phlox Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59345/sjfm.v3i2.248

Abstract

Background. Stature estimation from skeletal elements underpins forensic biological profiling and is decisive in disaster victim identification, yet no validated osteometric standard exists for the South Sumatran Malay population. Objective. To develop population-specific stature-estimation equations from percutaneous tibial dimensions and to compare stepwise multiple linear regression (SMLR) with a multilayer perceptron artificial neural network (MLP-ANN). Methods. 450 healthy South Sumatran Malay adults (225 male, 225 female) aged 20-50 years were enrolled at CMHC Research Center, and reported per STROBE. Five percutaneous right-tibial dimensions were measured by one certified anthropologist under the Martin and Saller convention (all relative technical errors of measurement below 1.5%), and a stratified 70:30 partition withheld 135 observations for testing. SMLR was compared against a grid-search-optimised 5-64-32-16-1 MLP-ANN. Results. Sexual dimorphism was large for every dimension (Cohen's d 1.42-1.75; all p < 0.001). Percutaneous tibial length was the strongest single predictor (males r = 0.812, 95% CI 0.762-0.852). The calibration-corrected pooled regression reached R2 = 0.742 with RMSE ±4.82 cm, whereas the network reached R2 = 0.914 (95% CI 0.891-0.933) and RMSE ±2.78 cm: ΔR2 = 0.172 (bootstrap 95% CI 0.141-0.203), a 23.2% gain in explained variance and a 42.3% reduction in error that narrows the 95% forensic identification window from ±9.45 cm to ±5.45 cm. Conclusion. These first population-specific, artificial-intelligence-driven standards materially improve the biological profiling of incomplete human remains in Indonesian medicolegal and disaster victim identification practice.
Transferability of an Antidepressant-Response DNA Methylation Signature to rTMS Outcomes in Treatment-Resistant Depression Rachmat Hidayat; Abu Bakar; Sohyuk Kim
Scientia Psychiatrica Vol. 7 No. 4 (2026): Scientia Psychiatrica
Publisher : HM Publisher in collaboration with CMHC Research Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37275/scipsy.v7i4.222

Abstract

Background. Baseline DNA methylation has been linked to antidepressant outcomes. Candidate signals need cross-treatment testing before translational interpretation. Objective. To test whether five antidepressant-response CpGs in CHN2, JAK2, SCN7A, and IQANK1 transfer to outcomes after repetitive transcranial magnetic stimulation (rTMS) in treatment-resistant depression. Methods. This secondary analysis used 46 participants of the public GSE300009 cohort with baseline blood methylation and paired Patient Health Questionnaire-9 (PHQ-9) scores. The primary outcome was PHQ-9 improvement. Response (≥50% improvement) and remission (end-treatment PHQ-9 <5) were secondary. Effects per 1-SD higher CpG M-value were estimated with covariate-adjusted linear models (HC3 standard errors) and bias-reduced logistic models. Holm correction, rank correlations, leave-one-out diagnostics, sensitivity analyses, and repeated nested five-fold cross-validation tested robustness and incremental prediction. Results. Mean PHQ-9 fell from 22.3 to 8.9. Calculated response occurred in 31 participants (67.4%) and remission in 18 (39.1%). After multiplicity correction, no CpG was associated with continuous improvement (Holm-adjusted p = 1.000). Two CHN2 CpGs showed nominal inverse associations with remission, not response: cg06926818, odds ratio 0.36 (95% confidence interval 0.15–0.84), p = 0.018, Holm-adjusted p = 0.089; cg23687322, odds ratio 0.41 (0.19–0.89), p = 0.024, Holm-adjusted p = 0.095. Under one-standard-error regularization, adding the CpGs left root-mean-square error unchanged. The area under the receiver-operating-characteristic curve rose by 0.012 for response and 0.059 for remission, with intervals compatible with no benefit. Conclusion. The panel did not transfer as a dependable marker of continuous improvement or response. CHN2-remission signals remain hypothesis-generating. Larger, prospectively harmonized external validation must precede clinical use.
Co-Authors Eduardo Michael Perez Ifah Shandy RACHMAT HIDAYAT Sari Sulistyoningsih Sohyuk Kim