Sriwijaya Journal of Forensic and Medicolegal

Artificial Intelligence Versus Stepwise Regression for Stature Estimation from Tibial Dimensions: A Forensic Osteometric Study in South Sumatran Malay Adults

Sari Sulistyoningsih — 2026-04-29

Introduction: Stature estimation from skeletal elements constitutes a foundational component of forensic biological profiling, critically supporting disaster victim identification in disaster-prone nations such as Indonesia. Traditional Stepwise Multiple Linear Regression (SMLR), while widely employed, is constrained by linearity assumptions that inadequately model the complex, multidimensional osteometric biology of population-specific cohorts.

Methods: This cross-sectional study enrolled 450 healthy adult South Sumatran Malay participants (225 males, 225 females), aged 20–50 years, from Palembang and surrounding regencies. Five percutaneous tibial measurements were acquired under standardized protocols by a single trained anthropologist. A 70:30 stratified train-test split yielded 315 training and 135 test observations. Predictive performance of SMLR was rigorously compared against an optimized three-hidden-layer Multilayer Perceptron Artificial Neural Network (MLP-ANN).

Result: Significant sexual dimorphism was demonstrated across all variables (independent samples t-test, p < 0.001). Percutaneous Tibial Length (PTL) was the strongest individual stature predictor (males: r = 0.812; females: r = 0.795). The best SMLR pooled model (PTL + PDB + DDB) achieved R-squared = 0.742 and RMSE = ±4.82 cm. The MLP-ANN substantially outperformed SMLR across all subgroups, achieving a pooled R-squared of 0.914 and RMSE of ±2.78 cm-representing a 23.2% improvement in R-squared and a 42.3% reduction in prediction error.

Conclusion: These population-specific AI-driven standards offer forensic practitioners in the Indonesian medicolegal context a markedly more reliable tool for biological profiling of incomplete human remains.

Procedural Failures as Independent Predictors of Delayed Intracranial Foreign Body Diagnosis in Mild Traumatic Brain Injury: A Multivariable Logistic Regression Analysis from North Sumatra, Indonesia

Aisyah Andina Rasyid — 2026-04-30

Introduction: Retained intracranial foreign bodies in patients presenting with a Glasgow Coma Scale (GCS) score of 15 represent a rare but potentially fatal diagnostic pitfall in emergency trauma management, carrying profound medicolegal consequences under Indonesian health legislation. This retrospective multi-centre cohort study identified independent procedural risk factors predicting delayed diagnosis (>24 hours) of intracranial foreign bodies among mild traumatic brain injury (mTBI) patients in North Sumatra, Indonesia.

Methods: Medical records from 1,240 mTBI patients (GCS 13–15) presenting to three tertiary trauma centres were reviewed; 45 cases with confirmed intracranial foreign bodies were identified, of whom 14 (31.1%) experienced delayed diagnosis.

Results: Bivariate analyses demonstrated that failure to perform digital wound palpation (78.6% vs. 9.7%, p<0.001) and non-adherence to neuroimaging guidelines (71.4% vs. 9.7%, p<0.001) were significantly overrepresented in the delayed group. Multivariable logistic regression, adjusted for age, sex, mechanism of injury, and centre, identified non-adherence to computed tomography guidelines (adjusted odds ratio [aOR] 8.71, 95% CI 3.80–21.45, p<0.001), failure to palpate the wound bed (aOR 6.42, 95% CI 2.15–18.50, p<0.001), and an initial GCS of 15 (aOR 3.15, 95% CI 1.42–7.21, p=0.012) as significant independent predictors. Model calibration was excellent (Hosmer–Lemeshow p=0.711; accuracy 88.4%).

Conclusion: A sentinel autopsy case demonstrated the fatal sequence: an undetected stone caused subarachnoid haemorrhage, brainstem compression, and asphyxial death. Strict protocol enforcement for secondary physical survey completion and CT guideline adherence is imperative to prevent fatal outcomes and mitigate medicolegal liability in Indonesian emergency departments.

Comprehension-Based Informed Consent Efficacy in High-Risk Surgeries: A Structural Equation Modeling Study Among Indonesian Patients in a Collectivistic Cultural Context

Mustafa Mahmud — 2026-05-04

Introduction: Comprehension-based informed consent (IC) represents the ethical and medicolegal foundation of surgical practice, yet its adequacy in collectivistic societies remains insufficiently studied. This study evaluated IC efficacy among high-risk surgical patients in an Indonesian tertiary hospital and identified sociodemographic, psychosocial, and clinical determinants using binary logistic regression within a structural equation modeling (SEM) analytical framework.

Methods: A cross-sectional study enrolled 320 adult patients undergoing high-risk elective surgery (cardiac, thoracic, major abdominal, and orthopaedic) at Private Hospital X, Palembang, South Sumatra, Indonesia, from January to December 2024. Validated instruments assessed IC Comprehension Score (ICCS), Health Literacy Level (HLL), Surgeon Communication Quality (SCQ), Family Influence Score (FIS), Collectivism Index (CI), and IC Efficacy Score (ICE, 0–100). Adequate IC efficacy was defined as ICE ≥ 70. Bivariat analysis used Chi-Square and Mann-Whitney U tests. Multivariable binary logistic regression was performed with all continuous predictors standardised.

Results: Mean ICCS was 49.4 ± 20.0 and mean ICE was 40.5 ± 19.8. Only 19 participants (5.9%) achieved adequate IC efficacy. Education level was significantly associated with IC efficacy adequacy (χ²=58.9, p<0.001). Spearman correlations revealed strong positive associations between ICCS and ICE (rho=0.773, p<0.001) and HLL and ICE (rho=0.566, p<0.001), and a weak negative association between FIS and ICE (rho=−0.139, p=0.012). In multivariable analysis, ICCS was the sole statistically significant independent predictor of adequate IC efficacy (OR=13.75, 95% CI [3.32–56.92], p<0.001); the model explained 55.4% of variance (Nagelkerke R²=0.554).

Conclusion: Comprehension-based IC efficacy is markedly insufficient in this high-risk surgical collectivistic setting, with only 5.9% achieving adequacy. IC Comprehension Score was the sole independent determinant of IC efficacy, underscoring the imperative for structured, comprehension-focused, and culturally tailored IC interventions in Indonesian and comparable surgical settings.

Sociocultural Determinants of Clinical Autopsy Refusal and Their Medicolegal Impact on Diagnostic Accuracy in Indonesian Tertiary Hospitals

Yuniarti Maretha Pasaribu — 2026-05-07

Introduction: Clinical autopsy refusal remains a critical barrier to diagnostic quality assurance and medicolegal accountability in Indonesian hospital medicine. This retrospective cohort study enrolled 324 consecutive inpatient deaths across three tertiary referral hospitals in Palembang, South Sumatra (January 2019 – December 2023), to characterize sociocultural determinants of autopsy refusal and their impact on diagnostic accuracy and time-to-correct-diagnosis.

Methods: The primary outcome was next-of-kin refusal of clinical autopsy consent; secondary outcomes included diagnostic discrepancy classified by the Goldman system, and time-to-correct-diagnosis analyzed by Kaplan-Meier survival analysis with log-rank testing. Multivariate logistic regression with bootstrap-derived confidence intervals identified independent predictors of refusal.

Results: The overall autopsy refusal rate was 84.0% (272/324). Independent predictors were Javanese ethnicity (OR 3.64, 95% CI 1.77–7.48; p<0.001), Islamic religious affiliation (OR 2.49, 95% CI 1.42–4.37; p=0.001), primary or no formal education (OR 2.36, 95% CI 1.19–4.68; p=0.014), age per 10-year increment (OR 1.18, 95% CI 1.05–1.33; p=0.006), and low household income below 2 million IDR (OR 1.76, 95% CI 1.00–3.10; p=0.049). The model demonstrated good discrimination (C-statistic 0.81) and calibration (Hosmer-Lemeshow p=0.43). Major diagnostic discrepancy (Goldman Class I–II) occurred in 26.1% of the refused cohort versus 13.5% in the consented cohort (p=0.047). Median time-to-correct-diagnosis was 19 days (95% CI 15–24) in the refused group versus 5 days (95% CI 3–8) in the consented group (log-rank p<0.001).

Conclusion: These findings provide robust evidence for the medicolegal urgency of addressing sociocultural barriers to autopsy consent through culturally sensitive policy reform in Indonesia.