The genetic profile and molecular subtypes of human pseudomyxoma peritonei and appendiceal mucinous neoplasms: a systematic review.

Pseudomyxoma peritonei (PMP) is a rare, progressive, slowly growing neoplastic condition which is poorly understood, with a 5-year progression-free survival rate as low as 48%. PMP is most commonly caused by appendiceal mucinous neoplasms (AMN), and understanding their genetic biology and pathogenicity may allow for the development of better novel systemic treatments to target key deleterious mutations and the implicated pathways. The primary aim of this systematic review was to identify the genetic profile of histologically confirmed human PMP or AMN samples. The secondary aim was to identify whether genetic marks could be used to predict patient survival. Ovid EMBASE, Ovid MEDLINE, PubMed, and Web of Science were searched to identify studies investigating the genetic profile of histologically-confirmed human PMP or AMN samples. We review findings of 46 studies totalling 2181 tumour samples. The most frequently identified somatic gene mutations in patients with PMP included KRAS (38-100%), GNAS (17-100%), and TP53 (5-23%); however, there were conflicting results of their effect on survival. Three studies identified molecular subtypes based on gene expression profiles classifying patients into oncogene-enriched, immune-enriched, and mixed molecular subtypes with prognostic value. This review summarises the current literature surrounding genetic aberrations in PMP and AMNs and their potential utility for targeted therapy. Given the recent advances in clinical trials to directly target KRAS and GNAS mutations in other cancers, we propose a rationale to explore these mutations in future pre-clinical studies in PMP with a view for a future clinical trial.

Prevalence and Risk Factors for Malignant Nodal Involvement in Early esophago-gastric Adenocarcinoma: Results from the Multicenter Retrospective Congress Study (endosCopic resectiON, esophaGectomy or Gastrectomy For Early Esophagogastric Cancers).

OBJECTIVE: The aim of this study was to quantify LNM risk and outcomes following treatment of early esophago-gastric (EG) adenocarcinoma. BACKGROUND: The standard of care for early T1N0 EG cancer is endoscopic resection (ER). Radical surgical resection is recommended for patients perceived to be at risk of lymph node metastasis (LNM). Current models to select organ-preserving vs. surgical treatment are inconsistent. METHODS: CONGRESS is a UK-based multicentre retrospective cohort study. Patients diagnosed with clinical or pathological T1N0 EG adenocarcinoma from 2015-2022 were included. Outcomes and rates of LNM were assessed. Cox regression was performed to assess the impact of prognostic and treatment factors on overall survival. RESULTS: 1,601 patients from 26 centres were included, with median follow-up 32 months(IQR 14-53). 1285/1612(80.3%) underwent ER, 497/1601(31.0%) underwent surgery. Overall rate of LNM was 13.5%. On ER staging, tumour depth (T1bsm2-3 17.6% vs. T1a 7.1%), lymphovascular invasion (17.2% vs. 12.6%), or signet cells (28.6% vs. 13.0%) were associated with LNM. In multivariable regression analysis, these were not significantly associated with LNM rates or survival. Adjusting for demographic and tumour variables, surgery after ER was associated with significant survival benefit, HR 0.33(0.15-0.77),P=0.010. CONCLUSION: This large multicentre dataset suggests that early EG adenocarcinoma is associated with significant risk of LNM. This data is representative of current real clinical practice with ER-based staging, and suggests previously held beliefs regarding reliability of predictive factors for LNM may need to be reconsidered. Further research to identify patients who may benefit from organ-preserving vs. surgical treatment is urgently required.

High proportion of PD-1 and CD39 positive CD8+ tissue resident T lymphocytes correlates with better clinical outcome in resected human oesophageal adenocarcinoma.

OBJECTIVE: To understand the CD8+ tumour infiltrating lymphocyte (TIL) compartment of oesophageal adenocarcinoma (OAC) with regards to markers of lymphocyte exhaustion, tissue residency and to identify possible reasons behind differential responses to therapy. DESIGN: Tumour samples from 44 patients undergoing curative resection for OAC were assessed by flow cytometry for presence of antigen-experienced TILs and markers of activation and exhaustion. Populations of PD-1 and CD39 positive OAC TILs were sorted, and bulk RNA sequencing undertaken using a modified SmartSeq2 protocol. Flow cytometric assessment of functionality was completed. RESULTS: A higher proportion of antigen experienced CD8+ OAC TILs was associated with improved survival following surgery; while, high double positivity (DP) for PD-1 and CD39 among these TILs also correlated significantly with outcome. These DP TILs possess a minority population which is positive for the markers of exhaustion TIM3 and LAG3. Transcriptomic assessment of the PD-1 and CD39 DP TILs demonstrated enrichment for a tissue resident memory T lymphocyte (TRM) phenotype associated with improved survival in other cancers, reinforced by positivity for the canonical TRM marker CD103 by flow cytometry. This population demonstrated maintained functional capacity both in their transcriptomic profile, and on flow cytometric assessment, as well as preserved proliferative capacity. CONCLUSION: Resected OAC are variably infiltrated by PD-1 and CD39 DP TILs, an abundance of which among lymphocytes is associated with improved survival. This DP population has an increased, but still modest, frequency of TIM3 and LAG3 positivity compared to DN, and is in keeping with a functionally competent TRM phenotype.

Association of Upper Gastrointestinal Surgery of Great Britain and Ireland (AUGIS)/perioperative quality initiative (POQI) consensus statement on prehabilitation in oesophagogastric surgery.

BACKGROUND: Prehabilitation is safe, feasible and may improve a range of outcomes in patients with oesophago-gastric cancer (OGC). Recent studies have suggested the potential of prehabilitation to improve body composition, sarcopenia and physical fitness, reduce surgical complications and improve quality of life. Despite this, prehabilitation services are not offered throughout all OGC centres in the UK. Where prehabilitation is offered, delivery and definitions vary significantly, as do funding sources and access. METHODS: A professional association endorsed series of consensus meetings were conducted using a modified Delphi process developed by the Peri-Operative Quality Initiative (POQI) to identify and refine consensus statements relating to the development and delivery of prehabilitation services for OGC patients. Participants from a variety of disciplines were identified based on a track record of published studies in the field of prehabilitation and/or practice experience encompassing prehabilitation of OGC patients. Approval from the POQI board was obtained and independent supervision provided by POQI. RESULTS: A total of 20 statements were developed and agreed by 26 participants over a preliminary meeting and 2 semi-structured formal POQI meetings. Ten research themes were identified. In the case of one statement, consensus was not reached and the statement was recorded and developed into a research theme. A strong recommendation was made for the majority of the consensus statements (17 of 20). DISCUSSION: Consensus statements encompassing the interventions and outcomes of prehabilitation services in oesophago-gastric cancer surgery have been developed to inform the implementation of programmes.

The AUGIS Survival Predictor: Prediction of Long-Term and Conditional Survival After Esophagectomy Using Random Survival Forests.

OBJECTIVE: The aim of this study was to develop a predictive model for overall survival after esophagectomy using pre/postoperative clinical data and machine learning. SUMMARY BACKGROUND DATA: For patients with esophageal cancer, accurately predicting long-term survival after esophagectomy is challenging. This study investigated survival prediction after esophagectomy using a RandomSurvival Forest (RSF) model derived from routine data from a large, well-curated, national dataset. METHODS: Patients diagnosed with esophageal adenocarcinoma or squamous cell carcinoma between 2012 and 2018 in England and Wales who underwent an esophagectomy were included. Prediction models for overall survival were developed using the RSF method and Cox regression from 41 patient and disease characteristics. Calibration and discrimination (time-dependent area under the curve) were validated internally using bootstrap resampling. RESULTS: The study analyzed 6399 patients, with 2625 deaths during follow-up. Median follow-up was 41 months. Overall survival was 47.1% at 5 years. The final RSF model included 14 variables and had excellent discrimination with a 5-year time-dependent area under the receiver operator curve of 83.9% [95% confidence interval (CI) 82.6%-84.9%], compared to 82.3% (95% CI 81.1%-83.3%) for the Cox model. The most important variables were lymph node involvement, pT stage, circumferential resection margin involvement (tumor at < 1 mm from cut edge) and age. There was a wide range of survival estimates even within TNM staging groups, with quintiles of prediction within Stage 3b ranging from 12.2% to 44.7% survival at 5 years. CONCLUSIONS: An RSF model for long-term survival after esophagectomy exhibited excellent discrimination and well-calibrated predictions. At a patient level, it provides more accuracy than TNM staging alone and could help in the delivery of tailored treatment and follow-up.

Thinking through the multimodal treatment of localized oesophageal cancer: the point of view of the surgeon.

PURPOSE OF REVIEW: This review examines current developments and controversies in the multimodal management of oesophageal cancer, with an emphasis on surgical dilemmas and outcomes from the surgeon's perspective. RECENT FINDINGS: Despite the advancement of oncological neoadjuvant treatments, there is still no consensus on what regimen is superior. The majority of patients may still fail to respond to neoadjuvant therapy and suffer potential harm without any survival advantage as a result. In patients who do not respond, adjuvant therapy is still often recommended after surgery despite any evidence for its benefit. We examine the implications of different regimens and treatment approaches for both squamous cell cancer and adenocarcinoma of the oesophagus. SUMMARY: The efficacy of neoadjuvant treatment is highly variable and likely relates to variability of tumour biology. Ongoing work to identify responders, or optimize treatment on an individual patient, should increase the efficacy of multimodal therapy and improve patient outcomes.

Cardiopulmonary exercise testing has greater prognostic value than sarcopenia in oesophago-gastric cancer patients undergoing neoadjuvant therapy and surgical resection.

BACKGROUND: Sarcopenia (low skeletal muscle mass), myosteatosis (low skeletal muscle radiation-attenuation) and fitness are independently associated with postoperative outcomes in oesophago-gastric cancer. This study aimed to investigate (1) the effect of neoadjuvant therapy (NAT) on sarcopenia, myosteatosis and cardiopulmonary exercise testing (CPET), (2) the relationship between these parameters, and (3) their association with postoperative morbidity and survival. METHODS: Body composition analysis used single slice computed tomography (CT) images from chest (superior to aortic arch) and abdominal CT scans (third lumbar vertebrae). Oxygen uptake at anaerobic threshold (VO2 at AT) and at peak exercise (VO2 Peak) were measured using CPET. Measurements were performed before and after NAT and an adjusted regression model assessed their association. RESULTS: Of the 184 patients recruited, 100 underwent surgical resection. Following NAT skeletal muscle mass, radiation-attenuation and fitness reduced significantly (p < 0.001). When adjusted for age, sex, and body mass index, only pectoralis muscle mass was associated with VO2 Peak (p = 0.001). VO2 at AT and Peak were associated with 1-year survival, while neither sarcopenia nor myosteatosis were associated with morbidity or survival. CONCLUSION: Skeletal muscle and CPET variables reduced following NAT and were positively associated with each other. Cardiorespiratory function significantly contributes to short-term survival after oesophago-gastric cancer surgery.

Consensus recommendations for the standardized histopathological evaluation and reporting after radical oesophago-gastrectomy (HERO consensus).

BACKGROUND: Variation in the approach, radicality, and quality of gastroesophageal surgery impacts patient outcomes. Pathological outcomes such as lymph node yield are routinely used as surrogate markers of surgical quality, but are subject to significant variations in histopathological evaluation and reporting. A multi-society consensus group was convened to develop evidence-based recommendations for the standardized assessment of gastroesophageal cancer specimens. METHODS: A consensus group comprised of surgeons, pathologists, and oncologists was convened on behalf of the Association of Upper Gastrointestinal Surgery of Great Britain & Ireland. Literature was reviewed for 17 key questions. Draft recommendations were voted upon via an anonymous Delphi process. Consensus was considered achieved where >70% of participants were in agreement. RESULTS: Consensus was achieved on 18 statements for all 17 questions. Twelve strong recommendations regarding preparation and assessment of lymph nodes, margins, and reporting methods were made. Importantly, there was 100% agreement that the all specimens should be reported using the Royal College of Pathologists Guidelines as the minimum acceptable dataset. In addition, two weak recommendations regarding method and duration of specimen fixation were made. Four topics lacked sufficient evidence and no recommendation was made. CONCLUSIONS: These consensus recommendations provide explicit guidance for gastroesophageal cancer specimen preparation and assessment, to provide maximum benefit for patient care and standardize reporting to allow benchmarking and improvement of surgical quality.

Immune activation by DNA damage predicts response to chemotherapy and survival in oesophageal adenocarcinoma.

OBJECTIVE: Current strategies to guide selection of neoadjuvant therapy in oesophageal adenocarcinoma (OAC) are inadequate. We assessed the ability of a DNA damage immune response (DDIR) assay to predict response following neoadjuvant chemotherapy in OAC. DESIGN: Transcriptional profiling of 273 formalin-fixed paraffin-embedded prechemotherapy endoscopic OAC biopsies was performed. All patients were treated with platinum-based neoadjuvant chemotherapy and resection between 2003 and 2014 at four centres in the Oesophageal Cancer Clinical and Molecular Stratification consortium. CD8 and programmed death ligand 1 (PD-L1) immunohistochemical staining was assessed in matched resection specimens from 126 cases. Kaplan-Meier and Cox proportional hazards regression analysis were applied according to DDIR status for recurrence-free survival (RFS) and overall survival (OS). RESULTS: A total of 66 OAC samples (24%) were DDIR positive with the remaining 207 samples (76%) being DDIR negative. DDIR assay positivity was associated with improved RFS (HR: 0.61; 95% CI 0.38 to 0.98; p=0.042) and OS (HR: 0.52; 95% CI 0.31 to 0.88; p=0.015) following multivariate analysis. DDIR-positive patients had a higher pathological response rate (p=0.033), lower nodal burden (p=0.026) and reduced circumferential margin involvement (p=0.007). No difference in OS was observed according to DDIR status in an independent surgery-alone dataset.DDIR-positive OAC tumours were also associated with the presence of CD8+ lymphocytes (intratumoural: p<0.001; stromal: p=0.026) as well as PD-L1 expression (intratumoural: p=0.047; stromal: p=0.025). CONCLUSION: The DDIR assay is strongly predictive of benefit from DNA-damaging neoadjuvant chemotherapy followed by surgical resection and is associated with a proinflammatory microenvironment in OAC.

Quantitative proteomic profiling of primary cancer-associated fibroblasts in oesophageal adenocarcinoma.

BACKGROUND: Cancer-associated fibroblasts (CAFs) form the major stromal component of the tumour microenvironment (TME). The present study aimed to examine the proteomic profiles of CAFs vs. normal fibroblasts (NOFs) from patients with oesophageal adenocarcinoma to gain insight into their pro-oncogenic phenotype. METHODS: CAFs/NOFs from four patients were sub-cultured and analysed using quantitative proteomics. Differentially expressed proteins (DEPs) were subjected to bioinformatics and compared with published proteomics and transcriptomics  datasets. RESULTS: Principal component analysis of all profiled proteins showed that CAFs had high heterogeneity and clustered separately from NOFs. Bioinformatics interrogation of the DEPs demonstrated inhibition of adhesion of epithelial cells, adhesion of connective tissue cells and cell death of fibroblast cell lines in CAFs vs. NOFs (p < 0.0001). KEGG pathway analysis showed a significant enrichment of the insulin-signalling pathway (p = 0.03). Gene ontology terms related with myofibroblast phenotype, metabolism, cell adhesion/migration, hypoxia/oxidative stress, angiogenesis, immune/inflammatory response were enriched in CAFs vs. NOFs. Nestin, a stem-cell marker up-regulated in CAFs vs. NOFs, was confirmed to be expressed in the TME with immunohistochemistry. CONCLUSIONS: The identified pathways and participating proteins may provide novel insight on the tumour-promoting properties of CAFs and unravel novel adjuvant therapeutic targets in the TME.

Tumour infiltrating lymphocytes correlate with improved survival in patients with oesophageal adenocarcinoma.

BACKGROUND: Oesophageal adenocarcinoma (OAC) is increasingly common in the west, and survival remains poor at 10-15 % at 5 years. Immune responses are increasingly implicated as a determining factor of tumour progression. The ability of lymphocytes to recognise tumour antigens provides a mechanism for a host immune attack against cancer providing a potential treatment strategy. MATERIALS AND METHODS: Tumour infiltrating lymphocytes (TILs: CD3+, CD4+, CD8+ and FOXp3+) were assessed by immunohistochemistry using tissue microarrays in a contemporary and homogeneous cohort of OAC patients (n = 128) undergoing curative treatment. RESULTS: Multivariate analysis identified three independent prognostic factors for improved cancer-specific survival (CSS): increased CD8+ TILs (p = 0.003), completeness of resection (p < 0.0001) and lower pathological N stage (p < 0.0001). Independent prognostic factors for favourable disease-free survival included surgery-only treatment (p = 0.015), completeness of resection (p = 0.001), increased CD8+ TILs (p < 0.0001) and reduced pathological N stage (p < 0.0001). Higher levels of TILs in the pathological specimen were associated with significant pathological response to neoadjuvant chemotherapy (NAC). On multivariate analysis increased levels of CD4+ (p = 0.017) and CD8+ TILs (p = 0.005) were associated with significant local tumour regression and lymph node downstaging, respectively. DISCUSSION: Our results establish an association of TILs and survival in OAC, as seen in other solid tumours, and identify particular TIL subsets that are present at higher levels in patients who responded to NAC compared to non-responders. These findings highlight potential therapeutic strategies in EAC based on utilising the host immunological response and highlight the immune responses biomarker potential.

Cancer-associated fibroblasts predict poor outcome and promote periostin-dependent invasion in oesophageal adenocarcinoma.

Interactions between cancer cells and cancer-associated fibroblasts (CAFs) play an important role in tumour development and progression. In this study we investigated the functional role of CAFs in oesophageal adenocarcinoma (EAC). We used immunochemistry to analyse a cohort of 183 EAC patients for CAF markers related to disease mortality. We characterized CAFs and normal oesophageal fibroblasts (NOFs) using western blotting, immunofluorescence and gel contraction. Transwell assays, 3D organotypic culture and xenograft models were used to examine the effects on EAC cell function and to dissect molecular mechanisms regulating invasion. Most EACs (93%) contained CAFs with a myofibroblastic (α-SMA-positive) phenotype, which correlated significantly with poor survival [p = 0.016; HR 7. 1 (1.7-29.4)]. Primary CAFs isolated from EACs have a contractile, myofibroblastic phenotype and promote EAC cell invasion in vitro (Transwell assays, p ≤ 0.05; organotypic culture, p < 0.001) and in vivo (p ≤ 0.05). In vitro, this pro-invasive effect is modulated through the matricellular protein periostin. Periostin is secreted by CAFs and acts as a ligand for EAC cell integrins αvß3 and αvß5, promoting activation of the PI3kinase-Akt pathway. In patient samples, periostin expression at the tumour cell-stromal interface correlates with poor overall and disease-free survival. Our study highlights the importance of the tumour stroma in EAC progression. Paracrine interaction between CAF-secreted periostin and EAC-expressed integrins results in PI3 kinase-Akt activation and increased tumour cell invasion. Most EACs contain a myofibroblastic CAF-rich stroma; this may explain the aggressive, highly infiltrative nature of the disease, and suggests that stromal targeting may produce therapeutic benefit in EAC patients.

The relevance of the Siewert classification in the era of multimodal therapy for adenocarcinoma of the gastro-oesophageal junction.

INTRODUCTION: The Siewert classification has been used to plan treatment for tumours of the gastro-oesophageal junction since its proposal in the 1980s. The purpose of this study was to assess its continued relevance by evaluating whether there were differences in the biology and clinical characteristics of adenocarcinomas by Siewert type, in a contemporary cohort of patients, in whom the majority had received neoadjuvant chemotherapy. METHODS: A prospective database was reviewed for all patients who underwent resection from 2005 to 2011 and analysed with regard to Siewert classification determined from the pathological specimen, treatment and clinicopathological outcomes. RESULTS: Two hundred and sixteen patients underwent oesophagogastric resection: 133 for type I, 51 for type II and 33 for type III tumours. 135 Patients (62.5%) received neoadjuvant chemotherapy with no difference between groups. There were no significant differences in age, sex, pT stage, pN stage, pM stage, ASA, or inpatient complications between patients with adenocarcinoma based on their Siewert classification. There was a significant increase in maximum tumour diameter (P = 0.023), perineural invasion (P = 0.021) and vascular invasion (P = 0.020), associated with more distal tumours (Type III > Type II > Type I). Median overall survival was significantly shorter for more distal tumours (Type I: 4.96 years vs. Type II: 3.3 years vs. Type III: 2.64 years; P = 0.04). The surgical approach did not influence survival. CONCLUSION: In the era of multi-modal treatment pathological Siewert tumour type is of prognostic value, as patients with Type III disease are likely to have larger and more aggressive tumours that lead to worse outcomes.

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.

Cardiopulmonary exercise variables and their association with postoperative morbidity and mortality after major oesophagogastric cancer surgery-a multicentre observational study.

Background: Outcomes after oesophagogastric cancer surgery remain poor. Cardiopulmonary exercise testing (CPET) used for risk stratification before oesophagogastric cancer surgery is based on conflicting evidence. This study explores the relationship between CPET and postoperative outcomes, specifically for patients undergoing neoadjuvant treatment. Methods: Patients undergoing oesophagogastric cancer resection and CPET (pre- or post-neoadjuvant treatment, or both) were retrospectively enrolled into a multicentre pooled cohort study. Oxygen uptake at peak exercise (VO2 peak) was compared with 1-yr postoperative survival. Secondary analyses explored relationships between patient characteristics, tumour pathology characteristics, CPET variables (absolute, relative to weight, ideal body weight, and body surface area), and postoperative outcomes (morbidity, 1-yr and 3-yr survival) were assessed using logistic regression analyses. Results: Seven UK centres recruited 611 patients completing a 3-yr postoperative follow-up period. Oesophagectomy was undertaken in 475 patients (78%). Major complications occurred in 25%, with 18% 1-yr and 43% 3-yr mortality. No association between VO2 peak or other selected CPET variables and 1-yr survival was observed in the overall cohort. In the overall cohort, the anaerobic threshold relative to ideal body weight was associated with 3-yr survival (P=0.013). Tumour characteristics (ypT/ypN/tumour regression/lymphovascular invasion/resection margin; P<0.001) and Clavien-Dindo ≥3a (P<0.001) were associated with 1-yr and 3-yr survival. On subgroup analyses, pre-neoadjuvant treatment CPET; anaerobic threshold (absolute; P=0.024, relative to ideal body weight; P=0.001, body surface area; P=0.009) and VE/VCO2 at anaerobic threshold (P=0.026) were associated with 3-yr survival. No other CPET variables (pre- or post-neoadjuvant treatment) were associated with survival. Conclusions: VO2 peak was not associated with 1-yr survival after oesophagogastric cancer resection. Tumour characteristics and major complications were associated with survival; however, only some selected pre-neoadjuvant treatment CPET variables were associated with 3-yr survival. CPET in this cohort of patients demonstrates limited outcome predictive precision. Clinical trial registration: NCT03637647.

The Oesophageal Cancer Multidisciplinary Team: Can Machine Learning Assist Decision-Making?

BACKGROUND: The complexity of the upper gastrointestinal (UGI) multidisciplinary team (MDT) is continually growing, leading to rising clinician workload, time pressures, and demands. This increases heterogeneity or 'noise' within decision-making for patients with oesophageal cancer (OC) and may lead to inconsistent treatment decisions. In recent decades, the application of artificial intelligence (AI) and more specifically the branch of machine learning (ML) has led to a paradigm shift in the perceived utility of statistical modelling within healthcare. Within oesophageal cancer (OC) care, ML techniques have already been applied with early success to the analyses of histological samples and radiology imaging; however, it has not yet been applied to the MDT itself where such models are likely to benefit from incorporating information-rich, diverse datasets to increase predictive model accuracy. METHODS: This review discusses the current role the MDT plays in modern UGI cancer care as well as the utilisation of ML techniques to date using histological and radiological data to predict treatment response, prognostication, nodal disease evaluation, and even resectability within OC. RESULTS: The review finds that an emerging body of evidence is growing in support of ML tools within multiple domains relevant to decision-making within OC including automated histological analysis and radiomics. However, to date, no specific application has been directed to the MDT itself which routinely assimilates this information. CONCLUSIONS: The authors feel the UGI MDT offers an information-rich, diverse array of data from which ML offers the potential to standardise, automate, and produce more consistent, data-driven MDT decisions.

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

BACKGROUND: Rising workflow pressures within the oesophageal cancer (OC) multidisciplinary team (MDT) can lead to variability in decision-making, and health inequality. Machine learning (ML) offers a potential automated data-driven approach to address inconsistency and standardize care. The aim of this experimental pilot study was to develop ML models able to predict curative OC MDT treatment decisions and determine the relative importance of underlying decision-critical variables. METHODS: Retrospective complete-case analysis of oesophagectomy patients ± neoadjuvant chemotherapy (NACT) or chemoradiotherapy (NACRT) between 2010 and 2020. Established ML algorithms (Multinomial Logistic regression (MLR), Random Forests (RF), Extreme Gradient Boosting (XGB)) and Decision Tree (DT) were used to train models predicting OC MDT treatment decisions: surgery (S), NACT + S or NACRT + S. Performance metrics included Area Under the Curve (AUC), Accuracy, Kappa, LogLoss, F1 and Precision -Recall AUC. Variable importance was calculated for each model. RESULTS: We identified 399 cases with a male-to-female ratio of 3.6:1 and median age of 66.1yrs (range 32-83). MLR outperformed RF, XGB and DT across performance metrics (mean AUC of 0.793 [±0.045] vs 0.757 [±0.068], 0.740 [±0.042], and 0.709 [±0.021] respectively). Variable importance analysis identified age as a major factor in the decision to offer surgery alone or NACT + S across models (p < 0.05). CONCLUSIONS: ML techniques can use limited feature-sets to predict curative UGI MDT treatment decisions. Explainable Artificial Intelligence methods provide insight into decision-critical variables, highlighting underlying subconscious biases in cancer care decision-making. Such models may allow prioritization of caseload, improve efficiency, and offer data-driven decision-assistance to MDTs in the future.

Review: Targeting EZH2 in neuroblastoma.

Neuroblastoma is one of the commonest extra-cranial pediatric tumors, and accounts for over 15% of all childhood cancer mortality. Risk stratification for children with neuroblastoma is based on age, stage, histology, and tumor cytogenetics. The majority of patients are considered to have high-risk neuroblastoma, for which the long-term survival is less than 50%. Current treatments combine surgical resection, chemotherapy, stem cell transplantation, radiotherapy, anti-GD2 based immunotherapy as well as the differentiating agent isotretinoin. Despite the intensive multimodal therapies applied, there are high relapse rates, and recurrent disease is often resistant to further therapy. Enhancer of Zeste Homolog 2 (EZH2), a catalytic subunit of Polycomb Repressive Complex 2 (PRC2), is a histone methyltransferase that represses transcription through trimethylation of lysine residue K27 on histone H3 (H3K27me3). It is responsible for epigenetic repression of transcription, making EZH2 an essential regulator for cell differentiation. Overexpression of EZH2 has been shown to promote tumorigenesis, cancer cell proliferation and prevent tumor cells from differentiating in a number of cancers. Therefore, research has been ongoing for the past decade, developing treatments that target EZH2 in neuroblastoma. This review summarises the role of EZH2 in neuroblastoma and evaluates the latest research findings on the therapeutic potential of targeting EZH2 in the treatment of neuroblastoma.