Can we screen for pancreatic cancer? Identifying a sub-population of patients at high risk of subsequent diagnosis using machine learning techniques applied to primary care data

Abstract

Background Pancreatic cancer (PC) represents a substantial public health burden. Pancreatic cancer patients have very low survival due to the difficulty of identifying cancers early when the tumour is localised to the site of origin and treatable. Recent progress has been made in identifying biomarkers for PC in the blood and urine, but these cannot be used for population-based screening as this would be prohibitively expensive and potentially harmful. Methods We conducted a case-control study using prospectively-collected electronic health records from primary care individually-linked to cancer registrations. Our cases were comprised of 1,139 patients, aged 15–99 years, diagnosed with pancreatic cancer between January 1, 2005 and June 30, 2009. Each case was age-, sex- and diagnosis time-matched to four non-pancreatic (cancer patient) controls. Disease and prescription codes for the 24 months prior to diagnosis were used to identify 57 individual symptoms. Using a machine learning approach, we trained a logistic regression model on 75% of the data to predict patients who later developed PC and tested the model’s performance on the remaining 25%. Results We were able to identify 41.3% of patients < = 60 years at ‘high risk’ of developing pancreatic cancer up to 20 months prior to diagnosis with 72.5% sensitivity, 59% specificity and, 66% AUC. 43.2% of patients >60 years were similarly identified at 17 months, with 65% sensitivity, 57% specificity and, 61% AUC. We estimate that combining our algorithm with currently available biomarker tests could result in 30 older and 400 younger patients per cancer being identified as ‘potential patients’, and the earlier diagnosis of around 60% of tumours. Conclusion After further work this approach could be applied in the primary care setting and has the potential to be used alongside a non-invasive biomarker test to increase earlier diagnosis. This would result in a greater number of patients surviving this devastating disease.

Temporality of clinical factors associated with pancreatic cancer: a case-control study using linked electronic health records

“…The findings are evidence in support of developing PC risk-stratification strategies from routine medical records through the assessment of individuals’ demographic, comorbidity and lifestyle profile. When it comes to implementation in the clinical settings, the identified risk factors can be used as indication for primary care-based surveillance, if not serving as the first sieve in a multi-stage, targeted screening model [ 41 ], with a realistic expectation of identifying patients with “silent” non-cancerous pancreatic conditions in the process. Considering the well-documented probability of progression to PC from pancreatitis and cystic neoplasm [ 2 , 3 , 42 , 43 ], early detection of these patient groups and taking measures such as extirpation of cystic neoplasms or limitation of smoking and alcohol use [ 8 ], can be considered as a PC preventive strategy serving a broader goal.…”

Clinical Prediction Models for Pancreatic Cancer in General and At-Risk Populations: A Systematic Review

“…Eleven studies developed 12 models for individuals with gastrointestinal (and other) symptoms, or that included alarm symptoms within the model (23,25,30,31,(33)(34)(35)(36)44,45,53), and 10 included clinical risk factors and symptoms alone (range: 0.66-0.98) (Tables 3 and 4) (23,25,(33)(34)(35)(36)44,45). One study by De Icaza et al (31) included biomarkers and symptoms in addition to clinical risk factors (C-statistic not reported) (31).…”

Early Detection of Pancreatic Cancer

“…Only a handful of research studies have used ML to build predictive models with EHR data in this field. 11 , 15 , 16 These studies have demonstrated that by leveraging AI/ML and EHRs, subpopulations at high risk for PDAC can be identified 1 to 2 years before diagnosis. Such efforts also highlight specific challenges and opportunities for improving the secondary use of EHR data with AI and innovative data science solutions.…”