A new rapid diagnostic system with ambient mass spectrometry and machine learning for colorectal liver metastasis.
Adult
Aged
Aged, 80 and over
Chromatography, High Pressure Liquid
/ methods
Colorectal Neoplasms
/ diagnosis
Female
Humans
Liver
/ pathology
Liver Neoplasms
/ diagnosis
Machine Learning
Male
Middle Aged
Prospective Studies
ROC Curve
Retrospective Studies
Spectrometry, Mass, Electrospray Ionization
/ methods
Colorectal cancer
Liver metastasis
Machine learning
Mass spectrometry
Rapid diagnosis
Journal
BMC cancer
ISSN: 1471-2407
Titre abrégé: BMC Cancer
Pays: England
ID NLM: 100967800
Informations de publication
Date de publication:
10 Mar 2021
10 Mar 2021
Historique:
received:
01
10
2020
accepted:
02
03
2021
entrez:
11
3
2021
pubmed:
12
3
2021
medline:
4
5
2021
Statut:
epublish
Résumé
Probe electrospray ionization-mass spectrometry (PESI-MS) can rapidly visualize mass spectra of small, surgically obtained tissue samples, and is a promising novel diagnostic tool when combined with machine learning which discriminates malignant spectrum patterns from others. The present study was performed to evaluate the utility of this device for rapid diagnosis of colorectal liver metastasis (CRLM). A prospectively planned study using retrospectively obtained tissues was performed. In total, 103 CRLM samples and 80 non-cancer liver tissues cut from surgically extracted specimens were analyzed using PESI-MS. Mass spectra obtained by PESI-MS were classified into cancer or non-cancer groups by using logistic regression, a kind of machine learning. Next, to identify the exact molecules responsible for the difference between CRLM and non-cancerous tissues, we performed liquid chromatography-electrospray ionization-MS (LC-ESI-MS), which visualizes sample molecular composition in more detail. This diagnostic system distinguished CRLM from non-cancer liver parenchyma with an accuracy rate of 99.5%. The area under the receiver operating characteristic curve reached 0.9999. LC-ESI-MS analysis showed higher ion intensities of phosphatidylcholine and phosphatidylethanolamine in CRLM than in non-cancer liver parenchyma (P < 0.01, respectively). The proportion of phospholipids categorized as monounsaturated fatty acids was higher in CRLM (37.2%) than in non-cancer liver parenchyma (10.7%; P < 0.01). The combination of PESI-MS and machine learning distinguished CRLM from non-cancer tissue with high accuracy. Phospholipids categorized as monounsaturated fatty acids contributed to the difference between CRLM and normal parenchyma and might also be a useful diagnostic biomarker and therapeutic target for CRLM.
Sections du résumé
BACKGROUND
BACKGROUND
Probe electrospray ionization-mass spectrometry (PESI-MS) can rapidly visualize mass spectra of small, surgically obtained tissue samples, and is a promising novel diagnostic tool when combined with machine learning which discriminates malignant spectrum patterns from others. The present study was performed to evaluate the utility of this device for rapid diagnosis of colorectal liver metastasis (CRLM).
METHODS
METHODS
A prospectively planned study using retrospectively obtained tissues was performed. In total, 103 CRLM samples and 80 non-cancer liver tissues cut from surgically extracted specimens were analyzed using PESI-MS. Mass spectra obtained by PESI-MS were classified into cancer or non-cancer groups by using logistic regression, a kind of machine learning. Next, to identify the exact molecules responsible for the difference between CRLM and non-cancerous tissues, we performed liquid chromatography-electrospray ionization-MS (LC-ESI-MS), which visualizes sample molecular composition in more detail.
RESULTS
RESULTS
This diagnostic system distinguished CRLM from non-cancer liver parenchyma with an accuracy rate of 99.5%. The area under the receiver operating characteristic curve reached 0.9999. LC-ESI-MS analysis showed higher ion intensities of phosphatidylcholine and phosphatidylethanolamine in CRLM than in non-cancer liver parenchyma (P < 0.01, respectively). The proportion of phospholipids categorized as monounsaturated fatty acids was higher in CRLM (37.2%) than in non-cancer liver parenchyma (10.7%; P < 0.01).
CONCLUSION
CONCLUSIONS
The combination of PESI-MS and machine learning distinguished CRLM from non-cancer tissue with high accuracy. Phospholipids categorized as monounsaturated fatty acids contributed to the difference between CRLM and normal parenchyma and might also be a useful diagnostic biomarker and therapeutic target for CRLM.
Identifiants
pubmed: 33691644
doi: 10.1186/s12885-021-08001-5
pii: 10.1186/s12885-021-08001-5
pmc: PMC7945316
doi:
Types de publication
Journal Article
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
262Références
BMC Cancer. 2018 Jan 15;18(1):78
pubmed: 29334918
Cancer Sci. 2013 Oct;104(10):1295-302
pubmed: 23815430
Anal Biochem. 2013 Oct 1;441(1):32-7
pubmed: 23851340
J Chromatogr B Analyt Technol Biomed Life Sci. 2007 Aug;855(1):98-103
pubmed: 17369111
Oral Oncol. 2017 Dec;75:111-119
pubmed: 29224807
J Gastrointest Surg. 2005 Nov;9(8):1148-53; discussion 1153-4
pubmed: 16269386
PLoS One. 2012;7(3):e33823
pubmed: 22457791
Ann Surg. 2015 Sep;262(3):476-85; discussion 483-5
pubmed: 26258316
Int J Mol Sci. 2016 Nov 28;17(12):
pubmed: 27916803
Ann Oncol. 2016 Aug;27(8):1386-422
pubmed: 27380959
Mass Spectrom Rev. 2018 Mar;37(2):107-138
pubmed: 27276657
Anal Chem. 2013 Mar 5;85(5):2860-6
pubmed: 23347294
Lipids. 1968 Mar;3(2):129-35
pubmed: 17805900
Surg Oncol. 2007 Jul;16(1):33-45
pubmed: 17544654
J Clin Pathol. 2006 Mar;59(3):334
pubmed: 16505290
Clin Chem. 2018 Apr;64(4):628-630
pubmed: 29378688
Br J Surg. 2020 May;107(6):632-635
pubmed: 32246473
Ann Surg. 2014 Mar;259(3):543-8
pubmed: 23732261
World J Surg. 2016 Jan;40(1):190-7
pubmed: 26470698
Sci Rep. 2014 Aug 05;4:5959
pubmed: 25091112
J Sep Sci. 2016 Jan;39(1):38-50
pubmed: 26394722
Bioinformatics. 2005 Aug 1;21(15):3301-7
pubmed: 15905277
J Clin Pathol. 2006 Apr;59(4):352-4
pubmed: 16489181
J Vis Exp. 2020 Feb 19;(156):
pubmed: 32150163
Mol Cancer Res. 2011 Nov;9(11):1551-61
pubmed: 21954435
Br J Surg. 2012 Sep;99(9):1271-7
pubmed: 22829436
Sci Transl Med. 2013 Jul 17;5(194):194ra93
pubmed: 23863833
Am J Surg. 2019 Nov;218(5):887-893
pubmed: 30712864
Metabolomics. 2018 Feb 27;14(4):38
pubmed: 30830369
Asian Pac J Cancer Prev. 2018 May 26;19(5):1287-1293
pubmed: 29802561