A machine learning tool for identifying non-metastatic colorectal cancer in primary care

Elinor Nemlander; Marcela Ewing; Eliya Abedi; Jan Hasselström; Annika Sjövall; Axel C Carlsson; Andreas Rosenblad

doi:10.1016/j.ejca.2023.01.011

A machine learning tool for identifying non-metastatic colorectal cancer in primary care

Eur J Cancer. 2023 Mar:182:100-106. doi: 10.1016/j.ejca.2023.01.011. Epub 2023 Jan 20.

Authors

Elinor Nemlander¹, Marcela Ewing², Eliya Abedi¹, Jan Hasselström¹, Annika Sjövall³, Axel C Carlsson⁴, Andreas Rosenblad⁵

Affiliations

¹ Department of Neurobiology, Care Sciences and Society, Division of Family Medicine and Primary Care, Karolinska Institutet, Solna, Sweden; Academic Primary Health Care Centre, Region Stockholm, Stockholm, Sweden.
² Institute of Medicine, Department of Community Medicine and Public Health, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
³ Division of Coloproctology, Department of Pelvic Cancer, Karolinska University Hospital, Stockholm, Sweden; Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden.
⁴ Department of Neurobiology, Care Sciences and Society, Division of Family Medicine and Primary Care, Karolinska Institutet, Solna, Sweden; Academic Primary Health Care Centre, Region Stockholm, Stockholm, Sweden. Electronic address: axel.carlsson@ki.se.
⁵ Department of Neurobiology, Care Sciences and Society, Division of Family Medicine and Primary Care, Karolinska Institutet, Solna, Sweden; Regional Cancer Centre Stockholm-Gotland, Region Stockholm, Stockholm, Sweden; Department of Medical Sciences, Division of Clinical Diabetology and Metabolism, Uppsala University, Uppsala, Sweden.

PMID: 36758474
DOI: 10.1016/j.ejca.2023.01.011

Abstract

Background: Primary health care (PHC) is often the first point of contact when diagnosing colorectal cancer (CRC). Human limitations in processing large amounts of information warrant the use of machine learning as a diagnostic prediction tool for CRC.

Aim: To develop a predictive model for identifying non-metastatic CRC (NMCRC) among PHC patients using diagnostic data analysed with machine learning.

Design and setting: A case-control study containing data on PHC visits for 542 patients >18 years old diagnosed with NMCRC in the Västra Götaland Region, Sweden, during 2011, and 2,139 matched controls.

Method: Stochastic gradient boosting (SGB) was used to construct a model for predicting the presence of NMCRC based on diagnostic codes from PHC consultations during the year before the date of cancer diagnosis and the total number of consultations. Variables with a normalised relative influence (NRI) >1% were considered having an important contribution to the model. Risks of having NMCRC were calculated using odds ratios of marginal effects.

Results: Of the 361 variables used as predictors in the stochastic gradient boosting model, 184 had non-zero influence, with 16 variables having NRI >1% and a combined NRI of 63.3%. Variables representing anaemia and bleeding had a combined NRI of 27.6%. The model had a sensitivity of 73.3% and a specificity of 83.5%. Change in bowel habit had the highest odds ratios of marginal effects at 28.8.

Conclusion: Machine learning is useful for identifying variables of importance for predicting NMCRC in PHC. Malignant diagnoses may be hidden behind benign symptoms such as haemorrhoids.

Keywords: Artificial intelligence; Cancer detection; Family practice; Gradient boosting; Normalised relative influence; Prediction.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adolescent
Anemia*
Case-Control Studies
Colorectal Neoplasms* / pathology
Humans
Machine Learning
Primary Health Care