EUVIMEDEUVIMED entdecken
Crossref

ATR-FTIR spectroscopic characterization and interpretable machine learning for time since injury estimation in rat scabs

Hao Xiao, Wenjing Shen, Running Mao, Qiang Chen, Minzhu Zhao, Hongwei Li, Jianbo Li, Qi Wang

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-12 · 363 · 128456

DOI: 10.1016/j.saa.2026.128456 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-12. Verfasst von Hao Xiao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Forensic Medicine, Faculty of Basic Medical Sciences, Chongqing Medical University, Chongqing 400016, China. Hauptthemen laut MEDLINE: Machine Learning. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Chongqing Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate estimation of time since injury (TSI) remains a major challenge in forensic science. In this study, attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy combined with chemometric and machine learning methods was used to characterize the temporal spectral evolution of scabs and to establish quantitative prediction models for TSI. ATR-FTIR spectra were collected from scab samples obtained from Sprague-Dawley rats at different post-injury time points. After spectral preprocessing, principal component analysis (PCA) was performed to evaluate overall spectral variation, and the predictive performance of multiple regression models was compared. Variable importance in projection (VIP) and Shapley additive explanations (SHAP) were further employed to identify the key spectral regions contributing to TSI prediction. The results showed that both protein-related regions and carbohydrate/nucleic acid-related regions exhibited distinct time-dependent changes. Partial least squares regression, used as the baseline model, demonstrated good robustness in the independent external validation set (R2P = 0.900, RMSEP = 15.291 h), whereas Ridge regression achieved the best overall predictive performance (R2CV = 0.922, RMSECV = 14.456 h; R2P = 0.924, RMSEP = 13.341 h). Both VIP and SHAP consistently highlighted the 1540-1520 and 1640-1620 cm-1 intervals, with additional contributions from phosphate/carbohydrate-associated regions around 1050-1030 cm-1. These findings demonstrate that ATR-FTIR spectroscopy, integrated with interpretable machine learning, provides a robust and objective analytical strategy for quantitative TSI estimation in forensic practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAnimalsSpectroscopy, Fourier Transform InfraredPrincipal Component AnalysisRats, Sprague-DawleyRatsLeast-Squares AnalysisTime Factors

Stichwörter der Autor:innen

ATR-FTIR spectroscopyChemometricsForensic medicineMachine learningScabTime since injury

Autor:innen und Institutionen

  • Department of Forensic Medicine, Faculty of Basic Medical Sciences, Chongqing Medical University, Chongqing 400016, China.
  • Institute of Chongqing Forensic Science Center of Public Security Bureau, Chongqing 400707, China. Electronic address: hwljf103@aliyun.com.
  • Department of Forensic Medicine, Faculty of Basic Medical Sciences, Chongqing Medical University, Chongqing 400016, China. Electronic address: 100390@cqmu.edu.cn.
  • Department of Forensic Medicine, Faculty of Basic Medical Sciences, Chongqing Medical University, Chongqing 400016, China. Electronic address: forensic.wangqi@cqmu.edu.cn.

Förderung

  • Chongqing Medical University

Zitieren

APA

Xiao, H., Shen, W., Mao, R., Chen, Q., Zhao, M., Li, H., Li, J., & Wang, Q. (2026). ATR-FTIR spectroscopic characterization and interpretable machine learning for time since injury estimation in rat scabs. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 363, 128456. https://doi.org/10.1016/j.saa.2026.128456

Vancouver

Xiao H, Shen W, Mao R, Chen Q, Zhao M, Li H, et al. ATR-FTIR spectroscopic characterization and interpretable machine learning for time since injury estimation in rat scabs. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;363:128456. doi:10.1016/j.saa.2026.128456

BibTeX
@article{Xiao2026,
  author = {Xiao, Hao and Shen, Wenjing and Mao, Running and Chen, Qiang and Zhao, Minzhu and Li, Hongwei and Li, Jianbo and Wang, Qi},
  title = {ATR-FTIR spectroscopic characterization and interpretable machine learning for time since injury estimation in rat scabs},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {363},
  pages = {128456},
  doi = {10.1016/j.saa.2026.128456}
}
Kostenlos starten →