BackgroundMultidisciplinary team (MDT) meetings are used to optimise expert decision-making about treatment options, but such expertise is not digitally transferable between centres. To help standardise medical decision-making, we developed a machine learning model designed to predict MDT decisions about adjuvant breast cancer treatments.MethodsWe analysed MDT decisions regarding adjuvant systemic therapy for 1065 breast cancer cases over eight years. Machine learning classifiers with and without bootstrap aggregation were correlated with MDT decisions (recommended, not recommended, or discussable) regarding adjuvant cytotoxic, endocrine and biologic/targeted therapies, then tested for predictability using stratified ten-fold cross-validations. The predictions so derived were duly compared with those based on published (ESMO and NCCN) cancer guidelines.ResultsMachine learning more accurately predicted adjuvant chemotherapy MDT decisions than did simple application of guidelines. No differences were found between MDT- vs. ESMO/NCCN- based decisions to prescribe either adjuvant endocrine (97%, p = 0.44/0.74) or biologic/targeted therapies (98%, p = 0.82/0.59). In contrast, significant discrepancies were evident between MDT- and guideline-based decisions to prescribe chemotherapy (87%, p < 0.01, representing 43% and 53% variations from ESMO/NCCN guidelines, respectively). Using ten-fold cross-validation, the best classifiers achieved areas under the receiver operating characteristic curve (AUC) of 0.940 for chemotherapy (95% C.I., 0.922—0.958), 0.899 for the endocrine therapy (95% C.I., 0.880—0.918), and 0.977 for trastuzumab therapy (95% C.I., 0.955—0.999) respectively. Overall, bootstrap aggregated classifiers performed better among all evaluated machine learning models.ConclusionsA machine learning approach based on clinicopathologic characteristics can predict MDT decisions about adjuvant breast cancer drug therapies. The discrepancy between MDT- and guideline-based decisions regarding adjuvant chemotherapy implies that certain non-clincopathologic criteria, such as patient preference and resource availability, are factored into clinical decision-making by local experts but not captured by guidelines.Electronic supplementary materialThe online version of this article (doi:10.1186/s12885-016-2972-z) contains supplementary material, which is available to authorized users.

Vast amounts of clinically relevant text-based variables lie undiscovered and unexploited in electronic medical records (EMR). To exploit this untapped resource, and thus facilitate the discovery of informative covariates from unstructured clinical narratives, we have built a novel computational pipeline termed Text-based Exploratory Pattern Analyser for Prognosticator and Associator discovery (TEPAPA). This pipeline combines semantic-free natural language processing (NLP), regular expression induction, and statistical association testing to identify conserved text patterns associated with outcome variables of clinical interest. When we applied TEPAPA to a cohort of head and neck squamous cell carcinoma patients, plausible concepts known to be correlated with human papilloma virus (HPV) status were identified from the EMR text, including site of primary disease, tumour stage, pathologic characteristics, and treatment modalities. Similarly, correlates of other variables (including gender, nodal status, recurrent disease, smoking and alcohol status) were also reliably recovered. Using highly-associated patterns as covariates, a patient’s HPV status was classifiable using a bootstrap analysis with a mean area under the ROC curve of 0.861, suggesting its predictive utility in supporting EMR-based phenotyping tasks. These data support using this integrative approach to efficiently identify disease-associated factors from unstructured EMR narratives, and thus to efficiently generate testable hypotheses.

Aim: To review the expected increasing demand for cancer services among low and middle-income countries (LMICs) in the Asia-Pacific (APAC), and to describe ways in which Australia and New Zealand (ANZ) can provide support to improve cancer outcomes in our region. Methods:We first review the current and projected incidence of cancer within the APAC between 2018 and 2040, and the estimated demand for chemotherapy, radiotherapy and surgery. We then explore potential ways in which ANZ can increase regional collaborations to improve cancer outcomes. Results:We identify 6 ways that ANZ can collaborate with LMICs to improve cancer care in the APAC through the ANZ Regional Oncology Collaboration Strategy: 1. Increasing education and institutional collaborations in the APAC region through incountry training, twinning partnerships, observerships and formalised training programs in order to increase cancer care quality and capacity. 2. Promoting and assisting in the establishment and maintenance of population-based cancer registries in LMICs. 3. Increasing research capacity in LMICs through collaboration and promoting high quality global oncology research within ANZ. 4. Engaging and training Australian and New Zealand clinicians in global oncology, increasing awareness of this important career path, and increasing health policy engagement. 5. Increasing web-based endeavours through virtual tumour boards, web-based advocacy platforms and web-based teaching programs. 6. Continuing to leverage for funding through professional bodies, government, industry, not-for-profit organisations and local hospital funds. Conclusion:We propose the creation of an Australian and New Zealand Interest Group to provide formalised and sustained collaboration between researchers, clinicians and stakeholders.