Machine learning to predict curative multidisciplinary team treatment decisions in oesophageal cancer

Current Role of Artificial Intelligence in the Management of Esophageal Cancer

Background/Objectives: Esophageal cancer (EC) represents a major global contributor to cancer-related mortality. The advent of artificial intelligence (AI), including machine learning, deep learning, and radiomics, holds promise for enhancing treatment decisions and predicting outcomes. The aim of this review is to present an overview of the current landscape and future perspectives of AI in the management of EC. Methods: A literature search was performed on MEDLINE using the following keywords: "Artificial Intelligence", "Esophageal cancer", "Barrett's esophagus", "Esophageal Adenocarcinoma", and "Esophageal Squamous cell carcinoma". All titles and abstracts were screened; the results included 41 studies. Results: Over the past five years, the number of studies focusing on the application of AI to the treatment and prognosis of EC has surged, leveraging increasingly larger datasets with external validation. The simultaneous incorporation in AI models of clinical factors and features from several imaging modalities displays improved predictive performance, which may enhance patient outcomes, based on direct personalized therapeutic options. However, clinicians and researchers must address existing limitations, conduct randomized controlled trials, and consider the ethical and legal aspects that arise to establish AI as a standard decision-support tool. Conclusions: AI applications may result in substantial advances in EC management, heralding a new era. Considering the complexity of EC as a clinical entity, the evolving potential of AI is anticipated to ameliorate patients' quality of life and survival rates.

Inter-rater variability in multidisciplinary team meetings of oesophageal and gastro-oesophageal junction cancer on staging, resectability and treatment recommendation: national retrospective multicentre study

BACKGROUND

There are differences in oesophageal cancer care across Sweden. According to national guidelines, all patients should be offered equal care, planned and administrated by regional multidisciplinary team meetings. The aim of the study was to investigate differences between regional multidisciplinary team meetings in Sweden regarding clinical staging and treatment recommendations for oesophageal cancer patients.

METHODS

All six Swedish regional multidisciplinary teams were each invited to retrospectively include ten consecutive oesophageal cancer cases. After anonymization, radiological investigations were presented, along with the original case-specific medical history, anew at the participating regional multidisciplinary team meetings. Estimation of clinical tumour node metastasis (TNM) classification and treatment recommendation (curative, palliative or best supportive care) were compared between multidisciplinary team meetings as well as with original assessments.

RESULTS

Five multidisciplinary teams participated and contributed a total of 50 cases presented to each multidisciplinary team. In estimations of cT-stage, the multidisciplinary teams were in total agreement in only eight of 50 cases (16%). For cN-stage, total agreement was seen in 17 of 50 cases (34%) and for cM-stage there was agreement in 34 cases (68%). For cT-stage, the overall summarized κ value was 0.57. For N-stage and M-stage the κ values were 0.66 and 0.78 respectively. Differences in appraisal were not associated with usage of positron emission tomography-computed tomography. In 15 of 50 cases (30%) the multidisciplinary teams disagreed on curative or palliative treatment.

CONCLUSION

The study shows differences in assessment of clinical TNM classification and treatment recommendations made at regional multidisciplinary team meetings. Increased interrater agreement on clinical TNM classification and management plans are essential to achieve more equal care for oesophageal cancer patients in Sweden.

Insights from explainable AI in oesophageal cancer team decisions

BACKGROUND

Clinician-led quality control into oncological decision-making is crucial for optimising patient care. Explainable artificial intelligence (XAI) techniques provide data-driven approaches to unravel how clinical variables influence this decision-making. We applied global XAI techniques to examine the impact of key clinical decision-drivers when mapped by a machine learning (ML) model, on the likelihood of receiving different oesophageal cancer (OC) treatment modalities by the multidisciplinary team (MDT).

METHODS

Retrospective analysis of 893 OC patients managed between 2010 and 2022 at our tertiary unit, used a random forests (RF) classifier to predict four possible treatment pathways as determined by the MDT: neoadjuvant chemotherapy followed by surgery (NACT + S), neoadjuvant chemoradiotherapy followed by surgery (NACRT + S), surgery-alone, and palliative management. Variable importance and partial dependence (PD) analyses then examined the influence of targeted high-ranking clinical variables within the ML model on treatment decisions as a surrogate model of the MDT decision-making dynamic.

RESULTS

Amongst guideline-variables known to determine treatments, such as Tumour-Node-Metastasis (TNM) staging, age also proved highly important to the RF model (16.1 % of total importance) on variable importance analysis. PD subsequently revealed that predicted probabilities for all treatment modalities change significantly after 75 years (p < 0.001). Likelihood of surgery-alone and palliative therapies increased for patients aged 75-85yrs but lowered for NACT/NACRT. Performance status divided patients into two clusters which influenced all predicted outcomes in conjunction with age.

CONCLUSION

XAI techniques delineate the relationship between clinical factors and OC treatment decisions. These techniques identify advanced age as heavily influencing decisions based on our model with a greater role in patients with specific tumour characteristics. This study methodology provides the means for exploring conscious/subconscious bias and interrogating inconsistencies in team-based decision-making within the era of AI-driven decision support.

Clinical decision support systems for multidisciplinary team decision-making in patients with solid cancer: Composition of an implementation model based on a scoping review

Generating guideline-based recommendations during multidisciplinary team (MDT) meetings in solid cancers is getting more complex due to increasing amount of information needed to follow the guidelines. Usage of clinical decision support systems (CDSSs) can simplify and optimize decision-making. However, CDSS implementation is lagging behind. Therefore, we aim to compose a CDSS implementation model. By performing a scoping review of the currently reported CDSSs for MDT decision-making we determined 102 barriers and 86 facilitators for CDSS implementation out of 44 papers describing 20 different CDSSs. The most frequently reported barriers and facilitators for CDSS implementation supporting MDT decision-making concerned CDSS maintenance (e.g. incorporating guideline updates), validity of recommendations and interoperability with electronic health records. Based on the identified barriers and facilitators, we composed a CDSS implementation model describing clinical utility, analytic validity and clinical validity to guide CDSS integration more successfully in the clinical workflow to support MDTs in the future.