Advertisement

Primary Care Datasets for Early Lung Cancer Detection: An AI Led Approach

Conference paper
  • 262 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12721)

Abstract

Cancer is one of the most common and serious medical conditions, with significant challenges in the detection of cancer originating from the non-specific nature of symptoms and very low prevalence. For general practitioners (GPs), this can be particularly important, as they are the primary contact for patients for most medical conditions. This places high significance on using the data available to a GP to design decision support tools that will aid GPs in detecting cancer as early as possible. With pathology data being one of the datasets available in the GP electronic medical record (EMR), our work targets this type of data in an attempt to incorporate an early cancer detection tool in existing GP practices. We focus on utilizing full blood count pathology results to design features that can be used in an early cancer detection model 3 to 6 months ahead of standard diagnosis. This research focuses initially on lung cancer but can be extended to other types of cancer. Additional challenges are present in this type of data due to the irregular and infrequent nature of doing pathology tests, which are also considered in designing the AI solution. Our findings demonstrate that hematological measures from pathology data are a suitable choice for a cancer detection tool that can deliver early cancer diagnosis up to 6 months ahead for up to 8 out of 10 patients, in a way that is easily incorporated in current GP practice.

Keywords

Early lung cancer detection Primary care data Explainable AI 

References

  1. 1.
    Hamilton, W.: The CAPER studies: five case-control studies aimed at identifying and quantifying the risk of cancer in symptomatic primary care patients. Br. J. Cancer 101, S80–S86 (2009)CrossRefGoogle Scholar
  2. 2.
    Hippisley-Cox, J., Coupland, C.: Identifying patients with suspected lung cancer in primary care: derivation and validation of an algorithm. Br. J. Gen. Pract. 61(592), e715–e723 (2011)CrossRefGoogle Scholar
  3. 3.
    Corner, J., Hopkinson, J., Fitzsimmons, D., et al.: Is late diagnosis of lung cancer inevitable? Interview study of patients’ recollections of symptoms before diagnosis. Thorax 60, 314–319 (2005)CrossRefGoogle Scholar
  4. 4.
    Iyen-Omofoman, B., et al.: Using socio-demographic and early clinical features in general practice to identify people with lung cancer earlier. Thorax 68(5), 451–459 (2013)CrossRefGoogle Scholar
  5. 5.
    Hannah, T.P., et al.: Mortality due to cancer treatment delay: systematic review and meta-analysis. BMJ 371, m4087 (2020)CrossRefGoogle Scholar
  6. 6.
    Bailey, S.E.R., Ukoumunne, O.C., Shephard, E., Hamilton, W.: How useful is thrombocytosis in predicting an underlying cancer in primary care? A systematic review. Fam. Pract. 34(1), 4–10 (2017)CrossRefGoogle Scholar
  7. 7.
    Bailey, S.E.R., Ukoumunne, O.C., Shephard, E.A., Hamilton, W.: Clinical relevance of thrombocytosis in primary care: a prospective cohort study of cancer incidence using English electronic medical records and cancer registry data. Br. J. Gen. Pract. 67(659), e405–e413 (2017)CrossRefGoogle Scholar
  8. 8.
    Shapley, M., Mansell, G., Jordan, J.L., Jordan, K.P.: Positive predictive values of ≥5% in primary care for cancer: systematic review. Br. J. Gen. Pract. 60(578), e366–e377 (2010)CrossRefGoogle Scholar
  9. 9.
    Bjerager, M., Palshof, T., Dahl, R., et al.: Delay in diagnosis of lung cancer in general practice. Br. J. Gen. Pract. 56, 863–868 (2006) Google Scholar
  10. 10.
    World Health Organization: Cancer Fact Sheets. https://www.who.int/news-room/fact-sheets/detail/cancer
  11. 11.
    Victoria Cancer Council: I-PACED (Implementing Pathways for Cancer Early Diagnosis). https://www.cancervic.org.au/downloads/resources/factsheets/AL1720_OCP_I-PACED_Lung_FINAL.pdf
  12. 12.
    ten Haaf, K., et al.: Risk prediction models for selection of lung cancer screening candidates: a retrospective validation study. PLoS Med. 14(4), e1002277 (2017)CrossRefGoogle Scholar
  13. 13.
    O’Dowd, E.L., et al.: What characteristics of primary care and patients are associated with early death in patients with lung cancer in the UK? Thorax 70(2), 161–168 (2015)CrossRefGoogle Scholar
  14. 14.
    Weller, D.P., Peake, M.D., Field, J.K.: Presentation of lung cancer in primary care. NPJ Prim. Care Respir. Med. 29(1), 1–5 (2019)CrossRefGoogle Scholar
  15. 15.
    Goldstein, B.A., et al.: Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review. J. Am. Med. Inform. Assoc. 24(1), 198–208 (2017)CrossRefGoogle Scholar
  16. 16.
    Schmidt-Hansen, M., et al.: Lung cancer in symptomatic patients presenting in primary care: a systematic review of risk prediction tools. Br. J. Gen. Pract. 67(659), e396–e404 (2017)CrossRefGoogle Scholar
  17. 17.
    Bradley, S.H., Martyn, P.T.K., Richard, D.N.: Recognizing lung cancer in primary care. Adv. Ther. 36(1), 19–30 (2019)CrossRefGoogle Scholar
  18. 18.
    NPS MedicineWise Annual Report 2019–20. https://www.nps.org.au/about-us/reports-evaluation

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.School of Computing and Information SystemsThe University of MelbourneMelbourneAustralia
  2. 2.Department of General Practice and Centre for Cancer Research, Medicine, Dentistry and Health SciencesThe University of MelbourneMelbourneAustralia
  3. 3.Victorian Comprehensive Cancer CentreMelbourneAustralia
  4. 4.Department of Family Medicine, School of MedicinePontificia Universidad Católica de ChileSantiagoChile

Personalised recommendations