The Role of Artificial Intelligence in Early Cancer Diagnosis

Abstract

Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are key challenges. In addition, there are concerns about limited diagnostic workforces, particularly in light of the COVID-19 pandemic, placing a strain on pathology and radiology services. In this review, we discuss how artificial intelligence algorithms could assist clinicians in (1) screening asymptomatic patients at risk of cancer, (2) investigating and triaging symptomatic patients, and (3) more effectively diagnosing cancer recurrence. We provide an overview of the main artificial intelligence approaches, including historical models such as logistic regression, as well as deep learning and neural networks, and highlight their early diagnosis applications. Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can be utilised to diagnose cancer. We also discuss the potential clinical implications for artificial intelligence algorithms, including an overview of models currently used in clinical practice. Finally, we discuss the potential limitations and pitfalls, including ethical concerns, resource demands, data security and reporting standards.

A radiomics-based decision support tool improves lung cancer diagnosis in combination with the Herder score in large lung nodules

“…Many radiomics models for nodule classification have been developed in recent years. 16 , 17 , 18 , 19 , 20 , 21 , 22 Baldwin et al. validated a lung nodule convolutional neural network (LN-CNN) in 1187 patients with 5–15 mm nodules, achieving an AUC of 89.6%.…”

Artificial Intelligence and Machine Learning in Cancer Research: A Systematic and Thematic Analysis of the Top 100 Cited Articles Indexed in Scopus Database

“… 152 In particular, early detection of cancer through the adoption of AI and ML stands as one of the innovations of the 21st century that can significantly help control the prevalence of cancer globally. 153 …”

Artificial Intelligence in Lung Cancer Imaging: Unfolding the Future

“…Based on this evidence, the United States Centers for Medicare & Medicaid Services (CMS) established that patients aged 55–77 with a 30-pack-year smoking history are eligible for CT screening programs, although new guidelines suggest that the target populations should be expanded further [ 33 , 34 ]. In 2006, the European Union approved a position statement in support of a risk-based implementation of LDCT lung cancer screening [ 35 ]; however, population-scale screening programs are lacking and, in clinical practice, only a small proportion of eligible patients are screened, due to the excessive workload and difficulties in documenting actual tobacco exposure [ 36 , 37 , 38 ]. AI techniques can allow for processing and integrating large volumes of data and extracting meaningful information to direct the screening decision process [ 39 ].…”