Pezzotti Giuseppe, Kobara Miyuki, Asai Tenma, Nakaya Tamaki, Miyamoto Nao, Adachi Tetsuya, Yamamoto Toshiro, Kanamura Narisato, Ohgitani Eriko, Marin Elia, Zhu Wenliang, Nishimura Ichiro, Mazda Osam, Nakata Tetsuo, Makimura Koichi
Ceramic Physics Laboratory, Kyoto Institute of Technology, Kyoto, Japan.
Department of Immunology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan.
Front Microbiol. 2021 Nov 12;12:769597. doi: 10.3389/fmicb.2021.769597. eCollection 2021.
Invasive fungal infections caused by yeasts of the genus carry high morbidity and cause systemic infections with high mortality rate in both immunocompetent and immunosuppressed patients. Resistance rates against antifungal drugs vary among species, the most concerning specie being , which exhibits resistance to all major classes of available antifungal drugs. The presently available identification methods for species face a severe trade-off between testing speed and accuracy. Here, we propose and validate a machine-learning approach adapted to Raman spectroscopy as a rapid, precise, and labor-efficient method of clinical microbiology for identification and drug efficacy assessments. This paper demonstrates that the combination of Raman spectroscopy and machine learning analyses can provide an insightful and flexible mycology diagnostic tool, easily applicable on-site in the clinical environment.
由该属酵母引起的侵袭性真菌感染在免疫功能正常和免疫抑制患者中均具有高发病率，并导致全身感染且死亡率高。不同种对抗真菌药物的耐药率有所不同，最令人担忧的种是，它对所有主要类别的现有抗真菌药物均表现出耐药性。目前可用的该种鉴定方法在检测速度和准确性之间面临严峻权衡。在此，我们提出并验证一种适用于拉曼光谱的机器学习方法，作为一种快速、精确且省力的临床微生物学方法用于该种鉴定和药物疗效评估。本文证明拉曼光谱与机器学习分析相结合可提供一种有洞察力且灵活的真菌学诊断工具，易于在临床环境中现场应用。
