Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/34181
Title: Point-of-care detection of fibrosis in liver transplant surgery using near-infrared spectroscopy and machine learning.
Austin Authors: Sharma, Varun J;Adegoke, John A;Fasulakis, Michael;Green, Alexander;Goh, Su K;Peng, Xiuwen;Liu, Yifan;Jackett, Louise A ;Vago, Angela ;Poon, Eric K W;Starkey, Graham M ;Moshfegh, Sarina;Muthya, Ankita;D'Costa, Rohit;James, Fiona L ;Gordon, Claire L ;Jones, Robert M ;Afara, Isaac O;Wood, Bayden R;Raman, Jaishankar
Affiliation: Thoracic Surgery
Centre for Biospectroscopy Monash University Melbourne Victoria Australia.
Department of Engineering University of Melbourne Melbourne Victoria Australia.
Centre for Biospectroscopy Monash University Melbourne Victoria Australia.
Department of Surgery, Melbourne Medical School University of Melbourne Melbourne Victoria Australia.
Victorian Liver Transplant Unit
Department of Engineering University of Melbourne Melbourne Victoria Australia.
Anatomical Pathology
Department of Surgery, Melbourne Medical School University of Melbourne Melbourne Victoria Australia.;Liver & Intestinal Transplant Unit Austin Health Melbourne Victoria Australia.
Department of Microbiology and Immunology, Peter Doherty Institute for Infection and Immunity University of Melbourne Melbourne Victoria Australia.
Department of Surgery, Melbourne Medical School University of Melbourne Melbourne Victoria Australia.;Liver & Intestinal Transplant Unit Austin Health Melbourne Victoria Australia.
Department of Surgery, Melbourne Medical School University of Melbourne Melbourne Victoria Australia.
DonateLife Victoria Carlton Victoria Australia.;Department of Intensive Care Medicine Melbourne Health Melbourne Victoria Australia.
Department of Infectious Diseases Austin Health Melbourne Victoria Australia.
Infectious Diseases
Department of Surgery, Melbourne Medical School University of Melbourne Melbourne Victoria Australia.;Liver & Intestinal Transplant Unit Austin Health Melbourne Victoria Australia.
School of Information Technology and Electrical Engineering Faculty of Engineering, Architecture, and Information Technology Brisbane Queensland Australia.;Biomedical Spectroscopy Laboratory, Department of Applied Physics University of Eastern Finland Kuopio Finland.
Centre for Biospectroscopy Monash University Melbourne Victoria Australia.
Issue Date: Nov-2023
Date: 2023
Publication information: Health Science Reports 2023-11; 6(11)
Abstract: Visual assessment and imaging of the donor liver are inaccurate in predicting fibrosis and remain surrogates for histopathology. We demonstrate that 3-s scans using a handheld near-infrared-spectroscopy (NIRS) instrument can identify and quantify fibrosis in fresh human liver samples. We undertook NIRS scans on 107 samples from 27 patients, 88 from 23 patients with liver disease, and 19 from four organ donors. Liver disease patients had a median immature fibrosis of 40% (interquartile range [IQR] 20-60) and mature fibrosis of 30% (10%-50%) on histopathology. The organ donor livers had a median fibrosis (both mature and immature) of 10% (IQR 5%-15%). Using machine learning, this study detected presence of cirrhosis and METAVIR grade of fibrosis with a classification accuracy of 96.3% and 97.2%, precision of 96.3% and 97.0%, recall of 96.3% and 97.2%, specificity of 95.4% and 98.0% and area under receiver operator curve of 0.977 and 0.999, respectively. Using partial-least square regression machine learning, this study predicted the percentage of both immature (R 2 = 0.842) and mature (R 2 = 0.837) with a low margin of error (root mean square of error of 9.76% and 7.96%, respectively). This study demonstrates that a point-of-care NIRS instrument can accurately detect, quantify and classify liver fibrosis using machine learning.
URI: https://ahro.austin.org.au/austinjspui/handle/1/34181
DOI: 10.1002/hsr2.1652
ORCID: 0000-0002-5008-4113
0000-0002-2998-1127
Journal: Health Science Reports
Start page: e1652
PubMed URL: 37920655
ISSN: 2398-8835
Type: Journal Article
Subjects: chemometrics
liver
near‐infrared spectroscopy
spectromics
transplant
vibrational spectroscopy
Appears in Collections:Journal articles

Show full item record

Page view(s)

20
checked on Feb 25, 2024

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.