New Diagnostic Modality Combining Mass Spectrometry and Machine Learning for the Discrimination of Malignant Intraductal Papillary Mucinous Neoplasms.
Journal
Annals of surgical oncology
ISSN: 1534-4681
Titre abrégé: Ann Surg Oncol
Pays: United States
ID NLM: 9420840
Informations de publication
Date de publication:
May 2023
May 2023
Historique:
received:
13
10
2022
accepted:
09
12
2022
medline:
12
4
2023
pubmed:
8
1
2023
entrez:
7
1
2023
Statut:
ppublish
Résumé
An intraductal papillary mucinous neoplasm (IPMN) is a pancreatic tumor with malignant potential. Although we anticipate a sensitive method to diagnose the malignant conversion of IPMN, an effective strategy has not yet been established. The combination of probe electrospray ionization-mass spectrometry (PESI-MS) and machine learning provides a promising solution for this purpose. We prospectively analyzed 42 serum samples obtained from IPMN patients who underwent pancreatic resection between 2020 and 2021. Based on the postoperative pathological diagnosis, patients were classified into two groups: IPMN-low grade dysplasia (n = 17) and advanced-IPMN (n = 25). Serum samples were analyzed by PESI-MS, and the obtained mass spectral data were converted into continuous variables. These variables were used to discriminate advanced-IPMN from IPMN-low grade dysplasia by partial least square regression or support vector machine analysis. The areas under receiver operating characteristics curves were obtained to visualize the difference between the two groups. Partial least square regression successfully discriminated the two disease classes. From another standpoint, we selected 130 parameters from the entire dataset by PESI-MS, which were fed into the support vector machine. The diagnostic accuracy was 88.1%, and the area under the receiver operating characteristics curve was 0.924 by this method. Approximately 10 min were required to perform each method. PESI-MS combined with machine learning is an easy-to-use tool with the advantage of rapid on-site analysis. Here, we show the great potential of our system to diagnose the malignant conversion of IPMN, which would be a promising diagnostic tool in clinical settings.
Sections du résumé
BACKGROUND
BACKGROUND
An intraductal papillary mucinous neoplasm (IPMN) is a pancreatic tumor with malignant potential. Although we anticipate a sensitive method to diagnose the malignant conversion of IPMN, an effective strategy has not yet been established. The combination of probe electrospray ionization-mass spectrometry (PESI-MS) and machine learning provides a promising solution for this purpose.
METHODS
METHODS
We prospectively analyzed 42 serum samples obtained from IPMN patients who underwent pancreatic resection between 2020 and 2021. Based on the postoperative pathological diagnosis, patients were classified into two groups: IPMN-low grade dysplasia (n = 17) and advanced-IPMN (n = 25). Serum samples were analyzed by PESI-MS, and the obtained mass spectral data were converted into continuous variables. These variables were used to discriminate advanced-IPMN from IPMN-low grade dysplasia by partial least square regression or support vector machine analysis. The areas under receiver operating characteristics curves were obtained to visualize the difference between the two groups.
RESULTS
RESULTS
Partial least square regression successfully discriminated the two disease classes. From another standpoint, we selected 130 parameters from the entire dataset by PESI-MS, which were fed into the support vector machine. The diagnostic accuracy was 88.1%, and the area under the receiver operating characteristics curve was 0.924 by this method. Approximately 10 min were required to perform each method.
CONCLUSION
CONCLUSIONS
PESI-MS combined with machine learning is an easy-to-use tool with the advantage of rapid on-site analysis. Here, we show the great potential of our system to diagnose the malignant conversion of IPMN, which would be a promising diagnostic tool in clinical settings.
Identifiants
pubmed: 36611070
doi: 10.1245/s10434-022-13012-y
pii: 10.1245/s10434-022-13012-y
pmc: PMC10085898
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
3150-3157Subventions
Organisme : Japan Society for the Promotion of Science
ID : 22K16529
Informations de copyright
© 2023. The Author(s).
Références
Werner J, Fritz S, Büchler MW. Intraductal papillary mucinous neoplasms of the pancreas—a surgical disease. Nat Rev Gastroenterol Hepatol. 2012;9(5):253–9.
doi: 10.1038/nrgastro.2012.31
pubmed: 22392299
Tanaka M. Clinical management and surgical decision-making of IPMN of the pancreas. Methods Mol Biol. 2019;1882:9–22.
doi: 10.1007/978-1-4939-8879-2_2
pubmed: 30378040
Adsay V, Mino-Kenudson M, Furukawa T, et al. Pathologic evaluation and reporting of intraductal papillary mucinous neoplasms of the pancreas and other tumoral intraepithelial neoplasms of pancreatobiliary tract: recommendations of verona consensus meeting. Ann Surg. 2016;263(1):162–77.
doi: 10.1097/SLA.0000000000001173
pubmed: 25775066
Klöppel G, Solcia E, Longnecker DS. Histological typing of tumours of the exocrine pancreas. Cham: Springer; 1996.
doi: 10.1007/978-3-642-61024-0
Marchegiani G, Andrianello S, Pollini T, et al. “Trivial” cysts redefine the risk of cancer in presumed branch-duct intraductal papillary mucinous neoplasms of the pancreas: a potential target for follow-up discontinuation? Am J Gastroenterol. 2019;114(10):1678–84.
doi: 10.14309/ajg.0000000000000378
pubmed: 31449158
Facciorusso A, Crinò SF, Ramai D, et al. Association between pancreatic intraductal papillary mucinous neoplasms and extrapancreatic malignancies: a systematic review with meta-analysis. Eur J Surg Oncol J Eur Soc Surg Oncol Br Assoc Surg Oncol. 2022;48(3):632–9.
Baiocchi GL, Molfino S, Frittoli B, et al. Increased risk of second malignancy in pancreatic intraductal papillary mucinous tumors: review of the literature. World J Gastroenterol. 2015;21(23):7313–9.
doi: 10.3748/wjg.v21.i23.7313
pubmed: 26109820
pmcid: 4476895
Pugliese L, Keskin M, Maisonneuve P, et al. Increased incidence of extrapancreatic neoplasms in patients with IPMN: fact or fiction? A critical systematic review. Pancreatol Off J Int Assoc Pancreatol (IAP). 2015;15(3):209–16.
doi: 10.1016/j.pan.2015.03.007
Basturk O, Esposito I, Fukushim N. Pancreatic intraductal papillary mucinous neoplasm. In: WHO classification of tumors. WHO classification of tumors. Digestive system tumors. Lyon: IARC Press; 2019. p. 310–8.
Tanaka M, Fernández-Del Castillo C, Kamisawa T, et al. Revisions of international consensus Fukuoka guidelines for the management of IPMN of the pancreas. Pancreatol Off J Int Assoc Pancreatol (IAP). 2017;17(5):738–53.
doi: 10.1016/j.pan.2017.07.007
Shimizu Y, Hijioka S, Hirono S, et al. New model for predicting malignancy in patients with intraductal papillary mucinous neoplasm. Ann Surg. 2020;272(1):155–62.
doi: 10.1097/SLA.0000000000003108
pubmed: 30499803
Marchegiani G, Andrianello S, Borin A, et al. Systematic review, meta-analysis, and a high-volume center experience supporting the new role of mural nodules proposed by the updated 2017 international guidelines on IPMN of the pancreas. Surgery. 2018;163(6):1272–9.
doi: 10.1016/j.surg.2018.01.009
pubmed: 29454468
Crippa S, Fogliati A, Valente R, et al. A tug-of-war in intraductal papillary mucinous neoplasms management: comparison between 2017 International and 2018 European guidelines. Dig Liver Dis. 2021;53(8):998–1003.
doi: 10.1016/j.dld.2021.03.009
pubmed: 33846103
Hiraoka K, Nishidate K, Mori K, Asakawa D, Suzuki S. Development of probe electrospray using a solid needle. Rapid Commun Mass Spectrom. 2007;21(18):3139–44.
doi: 10.1002/rcm.3201
pubmed: 17708527
Yoshimura K, Chen LC, Asakawa D, Hiraoka K, Takeda S. Physical properties of the probe electrospray ionization (PESI) needle applied to the biological samples. J Mass Spectrom. 2009;44(6):978–85.
doi: 10.1002/jms.1576
pubmed: 19306264
Iwano T, Yoshimura K, Inoue S, et al. Breast cancer diagnosis based on lipid profiling by probe electrospray ionization mass spectrometry. Br J Surg. 2020;107(6):632–5.
doi: 10.1002/bjs.11613
pubmed: 32246473
pmcid: 7216899
Saito R, Yoshimura K, Shoda K, et al. Diagnostic significance of plasma lipid markers and machine learning-based algorithm for gastric cancer. Oncol Lett. 2021;21(5):405.
doi: 10.3892/ol.2021.12666
pubmed: 33841566
pmcid: 8020384
Kiritani S, Yoshimura K, Arita J, et al. A new rapid diagnostic system with ambient mass spectrometry and machine learning for colorectal liver metastasis. BMC Cancer. 2021;21(1):262.
doi: 10.1186/s12885-021-08001-5
pubmed: 33691644
pmcid: 7945316
Ashizawa K, Yoshimura K, Johno H, et al. Construction of mass spectra database and diagnosis algorithm for head and neck squamous cell carcinoma. Oral Oncol. 2017;75:111–9.
doi: 10.1016/j.oraloncology.2017.11.008
pubmed: 29224807
Iwano T, Yoshimura K, Watanabe G, et al. High-performance collective biomarker from liquid biopsy for diagnosis of pancreatic cancer based on mass spectrometry and machine learning. J Cancer. 2021;12(24):7477–87.
doi: 10.7150/jca.63244
pubmed: 35003367
pmcid: 8734412
Takeda S, Yoshimura K, Tanihata H. Sample preparation for probe electrospray ionization mass spectrometry. J Vis Exp. 2019. https://doi.org/10.3791/59942 .
doi: 10.3791/59942
pubmed: 31424445
Ghosh T, Zhang W, Ghosh D, Kechris K. Predictive modeling for metabolomics data. Methods Mol Biol. 2020;2104:313–36.
doi: 10.1007/978-1-0716-0239-3_16
pubmed: 31953824
pmcid: 7423323
Macklin A, Khan S, Kislinger T. Recent advances in mass spectrometry based clinical proteomics: applications to cancer research. Clin Proteomics. 2020;17:17.
doi: 10.1186/s12014-020-09283-w
pubmed: 32489335
pmcid: 7247207
Banerjee S. Empowering clinical diagnostics with mass spectrometry. ACS Omega. 2020;5(5):2041–8.
doi: 10.1021/acsomega.9b03764
pubmed: 32064364
pmcid: 7016904
de Figueiredo Junior AG, Serafim PVP, de Melo AA, et al. Analysis of the lipid profile in patients with colorectal cancer in advanced stages. Asian Pac J Cancer Prev. 2018;19(5):1287–93.
pubmed: 29802561
Brown HM, Pirro V, Cooks RG. From DESI to the MasSpec Pen: ambient ionization mass spectrometry for tissue analysis and intrasurgical cancer diagnosis. Clin Chem. 2018;64(4):628–30.
doi: 10.1373/clinchem.2017.281923
pubmed: 29378688
Prasetyanti PR, Medema JP. Intra-tumor heterogeneity from a cancer stem cell perspective. Mol Cancer. 2017;16(1):41.
doi: 10.1186/s12943-017-0600-4
pubmed: 28209166
pmcid: 5314464
Huang S, Cai N, Pacheco PP, Narrandes S, Wang Y, Xu W. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics. 2018;15(1):41–51.
pubmed: 29275361
Moler EJ, Chow ML, Mian IS. Analysis of molecular profile data using generative and discriminative methods. Physiol Genomics. 2000;4(2):109–26.
doi: 10.1152/physiolgenomics.2000.4.2.109
pubmed: 11120872
Segal NH, Pavlidis P, Noble WS, et al. Classification of clear-cell sarcoma as a subtype of melanoma by genomic profiling. J Clin Oncol Off J Am Soc Clin Oncol. 2003;21(9):1775–81.
doi: 10.1200/JCO.2003.10.108
Jia Z. Controlling the overfitting of heritability in genomic selection through cross validation. Sci Rep. 2017;7(1):13678.
doi: 10.1038/s41598-017-14070-z
pubmed: 29057969
pmcid: 5651917
Wishart DS, Guo A, Oler E, et al. HMDB 5.0: the human metabolome database for 2022. Nucleic Acids Res. 2022;50(D1):D622–31.
doi: 10.1093/nar/gkab1062
pubmed: 34986597
Tande AJ, Platz EA, Folsom AR. The metabolic syndrome is associated with reduced risk of prostate cancer. Am J Epidemiol. 2006;164(11):1094–102.
doi: 10.1093/aje/kwj320
pubmed: 16968859
Furberg AS, Veierød MB, Wilsgaard T, Bernstein L, Thune I. Serum high-density lipoprotein cholesterol, metabolic profile, and breast cancer risk. J Nat Cancer Inst. 2004;96(15):1152–60.
doi: 10.1093/jnci/djh216
pubmed: 15292387
Cust AE, Kaaks R, Friedenreich C, et al. Metabolic syndrome, plasma lipid, lipoprotein and glucose levels, and endometrial cancer risk in the European prospective investigation into cancer and nutrition (EPIC). Endocr Relat Cancer. 2007;14(3):755–67.
doi: 10.1677/ERC-07-0132
pubmed: 17914105