Predicting Incident Adenocarcinoma of the Esophagus or Gastric Cardia Using Machine Learning of Electronic Health Records

Artificial intelligence to predict cancer risk, are we there yet? A comprehensive review across cancer types

Cancer remains the second leading cause of death worldwide, representing a substantial challenge to global health. Although traditional risk prediction models have played a crucial role in epidemiology of several cancer types, they have limitations especially in the ability to process complex and multidimensional data. In contrast, artificial intelligence (AI) approaches represent a promising solution to overcome this limitation. AI techniques have the potential to identify complex patterns and relationships in data that traditional methods might overlook, making them especially useful for handling large and heterogeneous datasets analysed in cancer research. This review first examines the current state of the art of AI techniques, highlighting their differences and suitability for various data types. Then, offers a comprehensive analysis of the literature, focusing on the application of AI approaches in nineteen cancer types (bladder cancer, breast cancer, cervical cancer, colorectal cancer, endometrial cancer, esophageal cancer, gastric cancer, gynaecological cancers, head and neck cancer, haematological cancers, kidney cancer, liver cancer, lung cancer, melanoma, ovarian cancer, pancreatic cancer, prostate cancer, thyroid cancer and overall cancer), evaluating the models, metrics, and exposure variables used. Finally, the review discusses the application of AI in the clinical practice, along with an assessment of its potential limitations and future directions.

Artificial intelligence methods applied to longitudinal data from electronic health records for prediction of cancer: a scoping review

BACKGROUND

Early detection and diagnosis of cancer are vital to improving outcomes for patients. Artificial intelligence (AI) models have shown promise in the early detection and diagnosis of cancer, but there is limited evidence on methods that fully exploit the longitudinal data stored within electronic health records (EHRs). This review aims to summarise methods currently utilised for prediction of cancer from longitudinal data and provides recommendations on how such models should be developed.

METHODS

The review was conducted following PRISMA-ScR guidance. Six databases (MEDLINE, EMBASE, Web of Science, IEEE Xplore, PubMed and SCOPUS) were searched for relevant records published before 2/2/2024. Search terms related to the concepts "artificial intelligence", "prediction", "health records", "longitudinal", and "cancer". Data were extracted relating to several areas of the articles: (1) publication details, (2) study characteristics, (3) input data, (4) model characteristics, (4) reproducibility, and (5) quality assessment using the PROBAST tool. Models were evaluated against a framework for terminology relating to reporting of cancer detection and risk prediction models.

RESULTS

Of 653 records screened, 33 were included in the review; 10 predicted risk of cancer, 18 performed either cancer detection or early detection, 4 predicted recurrence, and 1 predicted metastasis. The most common cancers predicted in the studies were colorectal (n = 9) and pancreatic cancer (n = 9). 16 studies used feature engineering to represent temporal data, with the most common features representing trends. 18 used deep learning models which take a direct sequential input, most commonly recurrent neural networks, but also including convolutional neural networks and transformers. Prediction windows and lead times varied greatly between studies, even for models predicting the same cancer. High risk of bias was found in 90% of the studies. This risk was often introduced due to inappropriate study design (n = 26) and sample size (n = 26).

CONCLUSION

This review highlights the breadth of approaches to cancer prediction from longitudinal data. We identify areas where reporting of methods could be improved, particularly regarding where in a patients' trajectory the model is applied. The review shows opportunities for further work, including comparison of these approaches and their applications in other cancers.

Artificial intelligence-aided data mining of medical records for cancer detection and screening

The application of artificial intelligence methods to electronic patient records paves the way for large-scale analysis of multimodal data. Such population-wide data describing deep phenotypes composed of thousands of features are now being leveraged to create data-driven algorithms, which in turn has led to improved methods for early cancer detection and screening. Remaining challenges include establishment of infrastructures for prospective testing of such methods, ways to assess biases given the data, and gathering of sufficiently large and diverse datasets that reflect disease heterogeneities across populations. This Review provides an overview of artificial intelligence methods designed to detect cancer early, including key aspects of concern (eg, the problem of data drift-when the underlying health-care data change over time), ethical aspects, and discrepancies between access to cancer screening in high-income countries versus low-income and middle-income countries.

Validation of an Epigenetic Prognostic Assay to Accurately Risk-Stratify Patients with Barrett's Esophagus

INTRODUCTION:

Esophageal adenocarcinoma (EAC) is the second-most lethal cancer in the United States, with Barrett esophagus (BE) being the strongest risk factor. Assessing the future risk of neoplastic progression in patients with BE is difficult; however, high-grade dysplasia (HGD) and early EAC are treatable by endoscopic eradication therapy (EET), with survival rates of 90%. Thus, it would be beneficial to develop a molecular assay to identify high-risk patients, who merit more frequent endoscopic surveillance or EET, as well as low-risk patients, who can avoid EET and undergo less frequent surveillance.

METHODS:

Deidentified endoscopic biopsies were acquired from 240 patients with BE at 6 centers and confirmed as future progressors or nonprogressors. Tissues were analyzed by a set of methylation-specific biomarker assays. Test performance was assessed in an independent validation set using 4 stratification levels: low risks, low-moderate risks, high-moderate risks, and high risks.

RESULTS:

Relative to patients in the low-risk group, high-risk patients were 15.2 times more likely to progress within 5 years to HGD or EAC. For patients in the high-risk category, the average risk of progressing to HGD or EAC within 5 years was 21.5%, 4-fold the BE population prevalence within 5 years, whereas low-risk patients had a progression risk of only 1.85%.

DISCUSSION:

This clinical assay, Esopredict, stratifies future neoplastic progression risk to identify higher-risk patients with BE who can benefit from EET or more frequent surveillance and lower-risk patients who can benefit from reduced surveillance.

Etiologic factors for Barrett's esophagus: toward countermeasures in Asia

INTRODUCTION

Over the past several decades, Europe and the United States have experienced a rapid increase in esophageal adenocarcinoma. Research and countermeasures against Barrett's esophagus, its precancerous lesion, are progressing. Because esophageal adenocarcinoma has an extremely poor prognosis when diagnosed in an advanced stage, recommendations for early cancer detection have been made based on the various proven etiological factors of Barrett's esophagus and the actual cancer risk of Barrett's esophagus. In recent years, there have been indications of an increase in esophageal adenocarcinoma in Japan, and a similar trend of cancer will occur shortly in other Asian countries. Consequently, Asian countries must implement similar countermeasures against Barrett's esophagus and esophageal adenocarcinoma, referencing the knowledge gained thus far in Europe and the United States.

AREAS COVERED

This review summarizes the latest findings on the etiologic factors of Barrett's esophagus and discusses the differences between Westerners and Asians. The current status of Barrett's esophagus in Japan and other Asian countries is also summarized.

EXPERT OPINION

The etiological factors and cancer incidence of Barrett's esophagus in Asia diverge somewhat from those observed in Europe and America. Therefore, it is imperative to implement measures that are tailored to the actual circumstances of Asian people.