Glaucoma Characterization by Machine Learning of Tear Metabolic Fingerprinting

Jiao Wu; Mengqiao Xu; Wanshan Liu; Yida Huang; Ruimin Wang; Wei Chen; Lei Feng; Ning Liu; Xiaodong Sun; Minwen Zhou; Kun Qian

doi:10.1002/smtd.202200264

Glaucoma Characterization by Machine Learning of Tear Metabolic Fingerprinting

Small Methods. 2022 May;6(5):e2200264. doi: 10.1002/smtd.202200264. Epub 2022 Apr 7.

Authors

Jiao Wu^{1

2}, Mengqiao Xu³, Wanshan Liu^{1

2}, Yida Huang^{1

2}, Ruimin Wang^{1

2}, Wei Chen^{1

2}, Lei Feng⁴, Ning Liu⁵, Xiaodong Sun³, Minwen Zhou³, Kun Qian^{1

2}

Affiliations

¹ State Key Laboratory for Oncogenes and Related Genes, School of Biomedical Engineering and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200030, P. R. China.
² Division of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, 160 Pujian Road, Shanghai, 200127, P. R. China.
³ Department of Ophthalmology, Shanghai General Hospital, National Clinical Research Center for Eye Diseases, Shanghai Key Laboratory of Fundus Disease, Shanghai Engineering Center for Visual Science and Photomedicine, Shanghai Engineering Center for Precise Diagnosis and Treatment of Eye Diseases, Shanghai Jiao Tong University School of Medicine, Shanghai, 200080, P. R. China.
⁴ Instrumental Analysis Center, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China.
⁵ School of Electronics Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, P. R. China.

PMID: 35388987
DOI: 10.1002/smtd.202200264

Abstract

Glaucoma is a common optic neuropathy disease affecting over 76 million people. Both timely diagnosis and progression monitoring are critical but challenging. Conventional characterization of glaucoma needs a combination of methods, calling for tedious procedures and experienced doctors. Herein, a platform through machine learning of tear metabolic fingerprinting (TMF) using nanoparticle enhanced laser desorption-ionization mass spectrometry is built. Direct TMF is obtained noninvasively, with fast speed and high reproducibility, using trace tear samples (down to 10 nL). Consequently, glaucoma patients are screened against healthy controls with the area under the curve (AUC) of 0.866, through machine learning of TMF. Further, primary open-angle glaucoma (POAG) is differentiated from primary angle-closure glaucoma (PACG) and an early-stage POAG is identified. Finally, a biomarker panel of six metabolites for glaucoma characterization (including screening, subtyping, and early diagnosis) with AUC of 0.827-0.891 is constructed, showing related metabolic pathways. The work will provide insights into eye diseases not limited to glaucoma.

Keywords: biomarkers; glaucoma; mass spectrometry; metabolic fingerprinting; tears.

MeSH terms

Glaucoma* / diagnosis
Glaucoma, Angle-Closure* / diagnosis
Glaucoma, Open-Angle* / diagnosis
Humans
Intraocular Pressure
Machine Learning
Reproducibility of Results

Abstract

MeSH terms

Grants and funding