Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer

Abstract

Pancreatic ductal adenocarcinoma (PDAC) is the third most lethal cancer in the United States, with a 5-year life expectancy of 11%. Most symptoms manifest at an advanced stage of the disease when surgery is no longer appropriate. The dire prognosis of PDAC warrants new strategies to improve the outcomes of patients, and early detection has garnered significant attention. However, early detection of PDAC is most often incidental, emphasizing the importance of developing new early detection screening strategies. Due to the low incidence of the disease in the general population, much of the focus for screening has turned to individuals at high risk of PDAC. This enriches the screening population and balances the risks associated with pancreas interventions. The cancers that are found in these high-risk individuals by MRI and/or EUS screening show favorable 73% 5-year overall survival. Even with the emphasis on screening in enriched high-risk populations, only a minority of incident cancers are detected this way. One strategy to improve early detection outcomes is to integrate artificial intelligence (AI) into biomarker discovery and risk models. This expert review summarizes recent publications that have developed AI algorithms for the applications of risk stratification of PDAC using radiomics and electronic health records. Furthermore, this review illustrates the current uses of radiomics and biomarkers in AI for early detection of PDAC. Finally, various challenges and potential solutions are highlighted regarding the use of AI in medicine for early detection purposes.

Keywords

Pancreatic cancer / artificial intelligence / early detection / risk prediction

References

[1] Park W,O'Reilly EM.Pancreatic cancer: a review.JAMA2021;326:851-62

[2] Rahib L,Aizenberg R,Fleshman JM.Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States.Cancer Res2014;74:2913-21

[3] National cancer institute. SEER cancer statistics review (CSR) 1975-2015. Available from: https://seer.cancer.gov/archive/csr/1975_2015/ [Last accessed on 17 Mar 2023]

[4] Kleeff J,Apte M.Pancreatic cancer.Nat Rev Dis Primers2016;2:16022

[5] Poruk KE,Adler DG.Screening for pancreatic cancer: why, how, and who?.Ann Surg2013;257:17-26 PMCID:PMC4113008

[6] Zwanenburg A,Abdalah MA.The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping.Radiology2020;295:328-38 PMCID:PMC7193906

[7] McCulloch WS. A logical calculus of the ideas immanent in nervous activity. Available from: https://www.cs.cmu.edu/~./epxing/Class/10715/reading/McCulloch.and.Pitts.pdf [Last accessed on 17 Mar 2023]

[8] Meyers PH.Automated computer analysis of radiographic images.Arch Environ Health1964;8:774-5

[9] Giger ML,MacMahon H.Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields.Med Phys1988;15:158-66

[10] Gross GW,Greco-Hunt V.Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs.Invest Radiol1990;25:1017-23

[11] Lambin P,Leijenaar R.Radiomics: extracting more information from medical images using advanced feature analysis.Eur J Cancer2012;48:441-6 PMCID:PMC4533986

[12] Katzen J.A review of computer aided detection in mammography.Clin Imaging2018;52:305-9

[13] O'Connor JP,Adams JE.Imaging biomarker roadmap for cancer studies.Nat Rev Clin Oncol2017;14:169-86 PMCID:PMC5378302

[14] National cancer institute. Cancer stat facts: pancreatic cancer. Available from: https://seer.cancer.gov/statfacts/html/pancreas.html [Last accessed on 17 Mar 2023]

[15] Dbouk M,Brand RE.The multicenter cancer of pancreas screening study: impact on stage and survival.J Clin Oncol2022;40:3257-66 PMCID:PMC9553376

[16] Canto MI,Yeo CJ.Surgical outcomes after pancreatic resection of screening-detected lesions in individuals at high risk for developing pancreatic cancer.J Gastrointest Surg2020;24:1101-10 PMCID:PMC6908777

[17] U.S. Census Bureau. Available from: https://www.census.gov/quickfacts/fact/table/US/PST045221 [Last accessed on 17 Mar 2023]

[18] Owens DK,Krist AH.Screening for pancreatic cancer: us preventive services task force reaffirmation recommendation statement.JAMA2019;322:438-44

[19] Srivastava S,Borowsky AD.Cancer overdiagnosis: a biological challenge and clinical dilemma.Nat Rev Cancer2019;19:349-58 PMCID:PMC8819710

[20] Canto MI,Schulick RD.Risk of neoplastic progression in individuals at high risk for pancreatic cancer undergoing long-term surveillance.Gastroenterology2018;155:740-751.e2 PMCID:PMC6120797

[21] Reni M,Balzano G.Carbohydrate antigen 19-9 change during chemotherapy for advanced pancreatic adenocarcinoma.Cancer2009;115:2630-9

[22] Goonetilleke KS.Systematic review of carbohydrate antigen (CA 19-9) as a biochemical marker in the diagnosis of pancreatic cancer.Eur J Surg Oncol2007;33:266-70

[23] Kim G.Assessing risk of breast cancer: a review of risk prediction models.J Breast Imaging2021;3:144-55 PMCID:PMC7980704

[24] Alhazmi A,Makrami A.Application of artificial intelligence and machine learning for prediction of oral cancer risk.J Oral Pathol Med2021;50:444-50

[25] Yeh MC,Yang HC,Wang HH.Artificial intelligence-based prediction of lung cancer risk using nonimaging electronic medical records: deep learning approach.J Med Internet Res2021;23:e26256

[26] Kakileti ST,Manjunath G,Dekker A.Personalized risk prediction for breast cancer pre-screening using artificial intelligence and thermal radiomics.Artif Intell Med2020;105:101854

[27] Yin H,Yang X.Research trends of artificial intelligence in pancreatic cancer: a bibliometric analysis.Front Oncol2022;12:973999 PMCID:PMC9380440

[28] Jordan MI.Machine learning: trends, perspectives, and prospects.Science2015;349:255-60

[29] Schmidhuber J.Deep learning in neural networks: an overview.Neural Netw2015;61:85-117

[30] Brown T,Ryder N. Language models are few-shot learners. Available from: https://papers.nips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html [Last accessed on 17 Mar 2023]

[31] LeCun Y,Hinton G.Deep learning.Nature2015;521:436-44

[32] Alzubaidi L,Humaidi AJ.Review of deep learning: concepts, CNN architectures, challenges, applications, future directions.J Big Data2021;8:53 PMCID:PMC8010506

[33] Chari ST.Detecting early pancreatic cancer: problems and prospects.Semin Oncol2007;34:284-94 PMCID:PMC2680914

[34] Petersen GM.Familial pancreatic cancer.Semin Oncol2016;43:548-53 PMCID:PMC5234085

[35] Becker AE,Frucht H.Pancreatic ductal adenocarcinoma: risk factors, screening, and early detection.World J Gastroenterol2014;20:11182-98 PMCID:PMC4145757

[36] Chari ST,Matrisian LM.Early detection initiative: a randomized controlled trial of algorithm-based screening in patients with new onset hyperglycemia and diabetes for early detection of pancreatic ductal adenocarcinoma.Contemp Clin Trials2022;113:106659 PMCID:PMC8844106

[37] Permuth JB,Vyas S.The Florida pancreas collaborative next-generation biobank: infrastructure to reduce disparities and improve survival for a diverse cohort of patients with pancreatic cancer.Cancers2021;13:809 PMCID:PMC7919015

[38] Boursi B,Giantonio BJ.A clinical prediction model to assess risk for pancreatic cancer among patients with new-onset diabetes.Gastroenterology2017;152:840-850.e3 PMCID:PMC5337138

[39] Boursi B,Giantonio BJ.A clinical prediction model to assess risk for pancreatic cancer among patients with prediabetes.Eur J Gastroenterol Hepatol2022;34:33-8 PMCID:PMC8286263

[40] Muhammad W,Nartowt B.Pancreatic cancer prediction through an artificial neural network.Front Artif Intell2019;2:2

[41] Qureshi TA,Wachsman AM.Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images.Cancer Biomark2022;33:211-7 PMCID:PMC9255993

[42] Chen W,Zhou Y,Jeon CY.Prediction of pancreatic cancer based on imaging features in patients with duct abnormalities.Pancreas2020;49:413-9 PMCID:PMC7444654

[43] Mukherjee S,Khasawneh H.Radiomics-based machine-learning models can detect pancreatic cancer on prediagnostic computed tomography scans at a substantial lead time before clinical diagnosis.Gastroenterology2022;163:1435-1446.e3

[44] Permuth JB,Balarunathan Y.Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms.Oncotarget2016;7:85785-97 PMCID:PMC5349874

[45] Polk SL,McGettigan MJ.Multiphase computed tomography radiomics of pancreatic intraductal papillary mucinous neoplasms to predict malignancy.World J Gastroenterol2020;26:3458-71 PMCID:PMC7327792

[46] Tobaly D,Sartoris R.CT-based radiomics analysis to predict malignancy in patients with intraductal papillary mucinous neoplasm (IPMN) of the pancreas.Cancers2020;12:3089 PMCID:PMC7690711

[47] Kuwahara T,Mizuno N.Usefulness of deep learning analysis for the diagnosis of malignancy in intraductal papillary mucinous neoplasms of the pancreas.Clin Transl Gastroenterol2019;10:1-8 PMCID:PMC6602761

[48] Hanania AN,Feng Z.Quantitative imaging to evaluate malignant potential of IPMNs.Oncotarget2016;7:85776-84 PMCID:PMC5349873

[49] Momeni-Boroujeni A,Somma J.Computer-assisted cytologic diagnosis in pancreatic FNA: an application of neural networks to image analysis.Cancer Cytopathol2017;125:926-33

[50] Chen PT,Wang P.Pancreatic cancer detection on CT scans with deep learning: a nationwide population-based study.Radiology2023;306:172-82

[51] Zhang S,Tang D.A deep learning-based segmentation system for rapid onsite cytologic pathology evaluation of pancreatic masses: a retrospective, multicenter, diagnostic study.EBioMedicine2022;80:104022 PMCID:PMC9079232

[52] Kartal E,Molina-Montes E.A faecal microbiota signature with high specificity for pancreatic cancer.Gut2022;71:1359-72 PMCID:PMC9185815

[53] Zaid M,Dogra P.Imaging-based subtypes of pancreatic ductal adenocarcinoma exhibit differential growth and metabolic patterns in the pre-diagnostic period: implications for early detection.Front Oncol2020;10:596931 PMCID:PMC7738633

[54] Pannala R,Bamlet WR,Petersen GM.Prevalence and clinical profile of pancreatic cancer-associated diabetes mellitus.Gastroenterology2008;134:981-7 PMCID:PMC2323514

[55] Sharma A,Levy MJ,Chari ST.Fasting blood glucose levels provide estimate of duration and progression of pancreatic cancer before diagnosis.Gastroenterology2018;155:490-500.e2 PMCID:PMC6067966

[56] Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. Radiomics in medical imaging-“how-to” guide and critical reflection.Insights Imaging2020;11:91 PMCID:PMC7423816

[57] Forghani R,Chatterjee A,Reinhold C.Radiomics and artificial intelligence for biomarker and prediction model development in oncology.Comput Struct Biotechnol J2019;17:995-1008 PMCID:PMC6667772

[58] Kang JD,Costa AF.Factors associated with missed and misinterpreted cases of pancreatic ductal adenocarcinoma.Eur Radiol2021;31:2422-32

[59] Laffan TA,Klein AP.Prevalence of unsuspected pancreatic cysts on MDCT.AJR Am J Roentgenol2008;191:802-7 PMCID:PMC2692243

[60] Sharib JM,Swords DS.Surgical overtreatment of pancreatic intraductal papillary mucinous neoplasms: do the 2017 International Consensus Guidelines improve clinical decision making?.Surgery2018;164:1178-84

[61] Hines OJ.Pancreatic surgery.Curr Opin Gastroenterol2005;21:568-72

[62] Chen J,Lu Y,Zhou H.Diagnostic accuracy of endoscopic ultrasound-guided fine-needle aspiration for solid pancreatic lesion: a systematic review.J Cancer Res Clin Oncol2012;138:1433-41

[63] Hayashi T,Yoshida M.Rapid on-site evaluation by endosonographer during endoscopic ultrasound-guided fine needle aspiration for pancreatic solid masses.J Gastroenterol Hepatol2013;28:656-63

[64] Alston E,Eltoum IA.Atypical cytologic diagnostic category in EUS-FNA of the pancreas: follow-up, outcomes, and predictive models.Cancer Cytopathol2014;122:428-34

[65] Savoy AD,Woodward TA.Can endosonographers evaluate on-site cytologic adequacy? A comparison with cytotechnologists.Gastrointest Endosc2007;65:953-7

[66] Del Castillo E,Chung M.The microbiomes of pancreatic and duodenum tissue overlap and are highly subject specific but differ between pancreatic cancer and noncancer subjects.Cancer Epidemiol Biomarkers Prev2019;28:370-83 PMCID:PMC6363867

[67] Sheller MJ,Reina GA.Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data.Sci Rep2020;10:12598 PMCID:PMC7387485

[68] Rieke N,Li W.The future of digital health with federated learning.NPJ Digit Med2020;3:119 PMCID:PMC7490367

[69] Brisimi TS,Mela T,Paschalidis IC.Federated learning of predictive models from federated Electronic Health Records.Int J Med Inform2018;112:59-67 PMCID:PMC5836813

[70] Qayyum A,Ahtazaz Ahsan M,Qadir J.Collaborative Federated Learning for Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge.IEEE Open J Comput Soc2022;3:172-84

[71] Maitra A. A clinical validation center for early detection of pancreatic cancer. Available from: https://grantome.com/grant/NIH/U01-CA200468-02 [Last accessed on 17 Mar 2023]

[72] Koay EJ,Cristini V.A visually apparent and quantifiable ct imaging feature identifies biophysical subtypes of pancreatic ductal adenocarcinoma.Clin Cancer Res2018;24:5883-94 PMCID:PMC6279613

[73] Price WN.Privacy in the age of medical big data.Nat Med2019;25:37-43 PMCID:PMC6376961

[74] Grote T.On the ethics of algorithmic decision-making in healthcare.J Med Ethics2020;46:205-11 PMCID:PMC7042960

[75] van de Sande D,Smit JM.Developing, implementing and governing artificial intelligence in medicine: a step-by-step approach to prevent an artificial intelligence winter.BMJ Health Care Inform2022;29:e100495 PMCID:PMC8860016

[76] Kim DW,Kim KW,Park SH.Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers.Korean J Radiol2019;20:405-10 PMCID:PMC6389801

[77] Norgeot B,Beaulieu-Jones BK.Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist.Nat Med2020;26:1320-4 PMCID:PMC7538196