3 August 2011 in British Journal of Nutrition
The increase in the prevalence of obesity in recent years has prompted research into alternative methods of modulating body weight and body fat. The last decade has reflected this with a surge in studies investigating the potential of green tea as a natural agent of weight loss, with a view to confirming and elucidating the mechanisms underlying its effect on the body. Currently, it is widely believed that the polyphenolic components present in green tea have an anti-obesogenic effect on fat homeostasis, by increasing thermogenesis or reducing fat absorption among other ways. The data published to date, however, are inconsistent, with numerous putative modes of action suggested therein. While several unimodal mechanisms have been postulated, a more plausible explanation of the observed results might involve a multimodal approach. Such a mechanism is suggested here, involving simultaneous inhibition of the enzymes catechol-O-methyltransferase, acetyl-CoA carboxylase, fatty acid synthase and impeding absorption of fat via the gut. An evaluation of the available evidence supports a role of green tea in weight loss; however the extent of the effects obtained is still subject to debate, and requires more objective quantification in future research.
23 January 2023 in Journal of Gastrointestinal Surgery
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.
12 July 2023 in European Journal of Surgical Oncology
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. 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. 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). 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.
23 October 2014 in Case Reports in Neurology
Deep brain stimulation (DBS) is approved for idiopathic Parkinson's disease (IPD) but has a poor evidence base in Parkinson-plus syndromes such as multiple system atrophy (MSA). We describe the clinical and neuropathological findings in a man who was initially diagnosed with IPD, in whom DBS was unsuccessful, and in whom MSA was unexpectedly diagnosed at a subsequent autopsy. This case report highlights that DBS is often unsuccessful in MSA and also demonstrates that MSA can masquerade as IPD, which may explain treatment failure in a small group of patients apparently suffering from Parkinson's disease. Additionally, it also presents a case with an unusually long duration of disease prior to death, comparable only to a handful of other cases in the literature.
5 August 2024 in Computers in Biology and Medicine
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). 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. 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. 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.
10 December 2025 in Computers in Biology and Medicine
Oesophageal cancer (OC) causes significant morbidity and mortality. Multiple treatment regimens are available, and multidisciplinary team (MDT) decisions over which to offer are complex, multi-faceted and subject to logistical constraints and human factors. A machine learning (ML) model-based clinical decision support system (CDSS) for OC has been developed, trained on historical treatment decisions. However, clinician trust in such systems is not yet established. This study surveyed clinicians in OC MDTs in the UK and Ireland to investigate which clinical and sociodemographic factors influence conscious decision-making in OC, comparing their relative subjective importance to those derived from the ML model (reflecting previous real-world practice). It also sought to explore clinicians' views on the potential use of artificial intelligence-based CDSSs in OC. There was agreement between clinicians and the model in many of the most influential factors in decision making, although age and gender had greater influence on the model than their conscious importance to clinicians would support. Clinicians identified a wide range of additional clinical and holistic factors outside the current model which factor into their decision-making, including further investigations, symptoms, nutrition and social factors. The prospect of utilising an ML CDSS in future received generally positive feedback, although opinions varied widely. However, barriers to implementation were identified, including concerns around perceived clinician superiority over ML CDSSs, patient individuality, transparency and safeguarding, the need for evidence, and additional input requirements. As ML CDSSs are increasingly offered in practice, clinicians' reservations must be addressed and their need for transparency and evidence met.