A proof-of-concept diagnostic platform for neonatal calf diarrhea using serum infrared spectroscopy and predictive analytics


Ceran N., GURBANOV R.

Analytical Biochemistry, cilt.705, 2025 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 705
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1016/j.ab.2025.115924
  • Dergi Adı: Analytical Biochemistry
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aquatic Science & Fisheries Abstracts (ASFA), BIOSIS, Biotechnology Research Abstracts, CAB Abstracts, Chemical Abstracts Core, Chimica, Compendex, EMBASE, Veterinary Science Database
  • Anahtar Kelimeler: Infrared spectroscopy, Machine learning, Neonatal calf diarrhea, Non-invasive diagnosis, Predictive analytics, Spectrochemical index
  • Bilecik Şeyh Edebali Üniversitesi Adresli: Evet

Özet

This study presents a novel diagnostic platform for the rapid and non-invasive detection of neonatal calf diarrhea using ATR-FTIR spectroscopy combined with predictive analytics. Neonatal calf diarrhea is a leading cause of economic losses and animal welfare issues in the cattle industry, and current diagnostic methods are often time-consuming and require invasive sampling. Our approach leverages the unique biochemical fingerprints of serum obtained from healthy, diseased, and recovered calves. The spectral data were preprocessed and analyzed using Principal Component Analysis to extract key molecular features, which were subsequently classified using Linear Discriminant Analysis and Support Vector Machines. These predictive models demonstrated high accuracy in distinguishing the physiological states of the calves, underscoring the potential of this platform as a reliable diagnostic tool. Another significant innovation of this work is the development of the 1080 cm−1/3300 cm−1 spectrochemical index, a single, interpretable parameter derived from the ratio of the PO2− symmetric stretching band to the Amide A band. This quantitative index correlates with molecular-level changes associated with disease progression and recovery, further enhancing diagnostic precision and enabling timely intervention. The integration of spectral data into an easily interpretable metric contributes to improved animal welfare and sustainable livestock management practices.