Rapid diagnosis of infection etiology in febrile pediatric oncology patients using infrared spectroscopy of leukocytes

• Published in: Journal of biophotonics 2020-02, Vol.13 (2), p.e201900215-n/a
• Main Authors: Agbaria, Adam H., Rosen, Guy Beck, Lapidot, Itshak, Rich, Daniel H., Mordechai, Shaul, Kapelushnik, Joseph, Huleihel, Mahmoud, Salman, Ahmad
• Format: Article
• Language: English
• Subjects: Algorithms; Antibiotics; Bacteria; Bacterial diseases; Bacterial infections; Blood; Chemotherapy; Diagnosis; Etiology; FTIR microscopy; Identification methods; Immune system; infection etiology; Infections; Infrared spectroscopy; Learning algorithms; Leukocytes; Leukopenia; Machine learning; Oncology; Patients; Pediatrics; Peripheral blood; Physicians; Signs and symptoms; Spectrum analysis; Viral infections
• ISSN: 1864-063X; 1864-0648
• DOI: 10.1002/jbio.201900215

Rapid diagnosis of the etiology of infection is highly important for an effective treatment of the infected patients. Bacterial and viral infections are serious diseases that can cause death in many cases. The human immune system deals with many viral and bacterial infections that cause no symptoms and pass quietly without treatment. However, oncology patients undergoing chemotherapy have a very weak immune system caused by leukopenia, and even minor pathogen infection threatens their lives. For this reason, physicians tend to prescribe immediately several types of antibiotics for febrile pediatric oncology patients (FPOPs). Uncontrolled use of antibiotics is one of the major contributors to the development of resistant bacteria. Therefore, for oncology patients, a rapid and objective diagnosis of the etiology of the infection is extremely critical. Current identification methods are time‐consuming (>24 h). In this study, the potential of midinfrared spectroscopy in tandem with machine learning algorithms is evaluated for rapid and objective diagnosis of the etiology of infections in FPOPs using simple peripheral blood samples. Our results show that infrared spectroscopy enables the diagnosis of the etiology of infection as bacterial or viral within 70 minutes after the collection of the blood sample with 93% sensitivity and 88% specificity. Bacterial and viral infections are responsible for major part of infectious diseases. Both infections have many common symptoms; thus, it is difficult to diagnose the type of infection based on these symptoms. Rapid diagnosis of the etiology of infection as bacterial or viral is highly important for the effective treatment of infected patients. Midinfrared spectroscopy in tandem with different machine learning classifiers was used successfully for this purpose.