Muhammed Emin Parlak

Dr. Muhammed Emin Parlak

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2024 in Egyptian Journal of Forensic Sciences
Verified
Journal Article
Open access
PDF file
MPMuhammed Emin Parlak
Muhammed Emin Parlak
BÖBengü Berrak Özkul
Bengü Berrak Özkul
MOMucahit Oruç
Mucahit Oruç
OCOsman Celbiş
Osman Celbiş
Background: For over a century, anthropometric techniques, widely used by anthropologists and adopted by medical scientists, have been utilized for predicting stature and sex. This study, conducted on a Eastern Turkish sample, aims to predict sex and stature using foot measurements through linear methods and Artificial Neural Networks. Our research was conducted on 134 medical students, comprising 69 males and 65 females. Stature and weight were measured in a standard anatomical position in the Frankfurt Horizontal Plane with a stadiometer of 0.1 cm precision. Measurements of both feet's height, length, and breadth were taken using a Vernier caliper, osteometric board, and height scale. The data were analyzed using SPSS 26.00. Results: It was observed that all foot dimensions in males were significantly larger than in females. Sex prediction using linear methods yielded an accuracy of 94.8%, with a stature estimation error of 4.15 cm. When employing Artificial Neural Networks, sex prediction accuracy increased to 97.8%, and the error in stature estimation was reduced to 4.07 cm. Conclusions: Our findings indicate that Artificial Neural Networks can work more effectively with such data. Using Artificial Neural Networks, the accuracy of sex prediction for both feet exceeded 95%. Additionally, the error in stature estimation was reduced compared to the formulas obtained through linear methods.

3 March 2025 in Egyptian Journal of Forensic Sciences
Verified
Journal Article
Open access
PDF file
MPMuhammed Emin Parlak
Muhammed Emin Parlak
YEYasin Etli
Yasin Etli
MBMurat Beyhan
Murat Beyhan
KKKubilay Kanat
Kubilay Kanat
HKHüseyin Alper Kızıloğlu
Hüseyin Alper Kızıloğlu
Background: Piriform aperture is an anatomical region that has been very little studied in terms of sex estimation. Ensemble learning is similarly an unstudied area in sex estimation from human skeletal remains. In this study, it was aimed to perform sex estimation by using the anthropometric measurements of piriform aperture obtained by computed tomography and 3D reconstruction techniques, discriminant function analysis, machine learning algorithms, and ensemble learning method. A total of 442 cases, 226 male and 216 female, aged between 21 and 89 were included in the study. After sex estimation was performed using discriminant analysis, K-nearest neighbor, Gaussian Naive Bayes, multilayer perceptron neural networks, decision trees, support vector machines, and random forest algorithms, a random forest model that accepted the results of these seven methods as predictors was created, and sex estimation was performed again with ensemble learning. Results: Sex prediction results were obtained with a maximum accuracy of 76.5% with discriminant analysis, 84.2% with machine learning algorithms, and 85.7% with the ensemble learning method. Conclusions: In conclusion, it was seen that piriform aperture showed moderate sexual dimorphism. Sex estimation results could be further improved with machine learning algorithms and especially with the ensemble learning method.

20 April 2026 in Forensic Science International
Verified
Journal Article
Closed access
MPMuhammed Emin Parlak
Muhammed Emin Parlak
ZGZekiye Şeyma Gümüşboğa
Zekiye Şeyma Gümüşboğa
EGErkal Gümüşboğa
Erkal Gümüşboğa
MYMesut Yılmaz
Mesut Yılmaz
TATuba Aydan
Tuba Aydan

23 August 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
MDMustafa Doğan
Mustafa Doğan
MPMuhammed Emin Parlak
Muhammed Emin Parlak
KKKadir Sezer Koçak
Kadir Sezer Koçak
YEYasin Etli
Yasin Etli
BÖBora Özdemir
Bora Özdemir
Katibe Tugce TemurKatibe Tugce Temur
Katibe Tugce Temur
Background/Objectives: Dental age estimation is important in clinical and forensic practice, particularly when skeletal indicators are unavailable or compromised. Machine-learning models often achieve lower regression errors than conventional dental methods; however, whether this translates into better classification performance at legally relevant age thresholds remains unclear. This study compared the Demirjian and Willems methods with several machine learning models for overall accuracy and threshold-specific performance at the jurisdiction-specific ages of 12 and 15 years. Methods: A total of 1384 panoramic radiographs from individuals aged 8.00–15.99 years were retrospectively evaluated. The developmental stages of the seven left mandibular permanent teeth and sex were used as model inputs. Linear Regression, Decision Tree, Random Forest, Support Vector Regression, Multilayer Perceptron, Gradient Boosting, and XGBoost were trained using cross-validation and evaluated on an internal holdout set. Performance was assessed using regression errors, age-group-specific bias, sensitivity, specificity, balanced accuracy, and likelihood ratios. Results: Machine-learning models generally produced lower errors than conventional methods. In the holdout set, the lowest mean absolute error was 0.512 years for Support Vector Regression and Gradient Boosting, followed by 0.519 years for XGBoost, compared with 0.649 and 0.654 years for the Willems and Demirjian methods. However, lower regression error did not consistently improve threshold-specific performance. At 12 years, machine learning models increased sensitivity but reduced specificity and positive likelihood ratios relative to Willems. At 15 years, Linear Regression and Random Forest produced no positive predictions, whereas the better-performing models showed results similar to Willems. Conclusions: Lower regression error does not necessarily indicate better forensic threshold-specific classification performance. Dental age-estimation models should therefore be validated using threshold-specific likelihood ratios, classification metrics, and age-group-specific bias in addition to overall prediction errors.

25 May 2023 in TOGÜ Sağlık Bilimleri Dergisi
Verified
Journal Article
Closed access
HKHüseyin Alper Kiziloğlu
Hüseyin Alper Kiziloğlu
MPMuhammed Emin Parlak
Muhammed Emin Parlak
Özet Amaç: Kemik iliği ödemi tanım olarak kemik medullasında sıvının anormal bir şekilde artmasına denir. Etyolojide travmatik ve non-travmatik birçok faktör rol almaktadır. Bu çalışmada travmatik olgularda tespit edilen kemik iliği ödemi ve kontüzyonu kavramına dikkat çekmek ve adli tıp yaklaşımında sonuç belirlemek amaçlanmıştır. Yöntem: Ocak 2020 ile Mayıs 2021 tarihleri arasında bir sağlık kuruluşunun radyoloji kliniğine manyetik rezonans görüntüleme (MRG) çekilmek için başvuran hastalardan, kas-iskelet sistemi için çekimi olan görüntüler retrospektif olarak incelendi. İncelemede travma tanılı olgular dikkate alınarak kemik iliği ödemi ve kontüzyonu varlığı- yokluğu şeklinde kategorize edildi. Görüntüleme işlemi 1,5 Tesla Simens Magnetom Aera cihazı ile yapıldı. Bulgular: Travma öyküsü ile gelen ancak belirgin bir osteopatoloji tespit edilmeyen 153 olgudan 74 (% 48,4) tanesinde kemik iliği ödemi saptandı. Bu olguların tamamında künt travma öyküsü mevcuttu. Olguların 40’ı (%54,0) kadın, 34’ü (%46,0) erkek idi. Kemik iliği ödemi saptanan 74 olgunun 39’unda (% 52,8) kemik kontüzyonu tespit edildi. Sonuç: Son olarak Haziran 2019’da güncellenen “Türk Ceza Kanunu’nda Tanımlanan Yaralama Suçlarının Adli Tıp Açısından Değerlendirilmesi Rehberinde” travmatik kemik iliği ödemi ve kontüzyonu kavramının yer almadığını görmekteyiz. İlerleyen dönemlerde adli tıp rehberlerinde bir yaralanma kriteri olarak yer alması gerektiği düşüncesindeyiz. Ayrıca vücut üzerine etkisi göz önüne alındığında; “Basit bir tıbbi müdahale ile giderilebilecek ölçüde hafif olmadığı” olarak skorlanmasının uygun olduğu kanaatindeyiz.

31 August 2026 in Turkish Journal of Forensic Medicine
Verified
Journal Article
Open access
MKMurat Kamalak
Murat Kamalak
AGAbuzer Gulderen
Abuzer Gulderen
MPMuhammed Emin Parlak
Muhammed Emin Parlak
Aim: Synthetic cannabinoids (SC) are one of the fastest-spreading and most concerning classes of new psychoactive substances. Originally synthesized for scientific research, these compounds have rapidly begun to be abused due to their potent psychoactive effects. Compared to Δ9-tetrahydrocannabinol (THC), most SC act as full agonists at cannabinoid receptors, thereby increasing potency and toxicity. The aim of this review is to provide information on the rapidly spreading use of synthetic cannabinoids, including their epidemiology, chemical diversity, pharmacodynamics, pharmacokinetics, and clinical outcomes, and to shed light on the trends in SC research by conducting a bibliometric analysis of original articles and reviews published in the Web of Science. Methods: Electronic literature search was conducted in the electronic literature using the keywords “synthetic cannabinoids, synthetic cannabinoid epidemiology, synthetic cannabinoid pharmacodynamics, pharmacokinetics, and clinical effects” for the review. Articles written in languages other than English and Turkish were excluded from the study. For the bibliometric analysis, data obtained by searching Web of Science using the operator ‘synthetic cannabinoid*’ OR ‘synthetic cannabinoid receptor agonist*’ OR ‘SCRA’ were analyzed using the WOSviewer application. Results: The analysis revealed that synthetic cannabinoids continue to emerge with new compounds and that their prevalence is increasing. The number of publications related to synthetic cannabinoids has shown an upward trend in recent years, supported by the data.Conclusion: Synthetic cannabinoids, which have become a significant health issue due to their increasing use.