ObjectivesUsing the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes.SettingA regional cancer centre in Australia.ParticipantsDisease-specific data from a purpose-built cancer registry (Evaluation of Cancer Outcomes (ECO)) from 869 patients were used to predict survival at 6, 12 and 24 months. The model was validated with data from a further 94 patients, and results compared to the assessment of five specialist oncologists. Machine-learning prediction using ECO data was compared with that using EAR and a model combining ECO and EAR data.Primary and secondary outcome measuresSurvival prediction accuracy in terms of the area under the receiver operating characteristic curve (AUC).ResultsThe ECO model yielded AUCs of 0.87 (95% CI 0.848 to 0.890) at 6 months, 0.796 (95% CI 0.774 to 0.823) at 12 months and 0.764 (95% CI 0.737 to 0.789) at 24 months. Each was slightly better than the performance of the clinician panel. The model performed consistently across a range of cancers, including rare cancers. Combining ECO and EAR data yielded better prediction than the ECO-based model (AUCs ranging from 0.757 to 0.997 for 6 months, AUCs from 0.689 to 0.988 for 12 months and AUCs from 0.713 to 0.973 for 24 months). The best prediction was for genitourinary, head and neck, lung, skin, and upper gastrointestinal tumours.ConclusionsMachine learning applied to information from a disease-specific (cancer) database and the EAR can be used to predict clinical outcomes. Importantly, the approach described made use of digital data that is already routinely collected but underexploited by clinical health systems.
Introduction: Cancer-related mortality rates are higher in rural areas compared with urban regions. Whether there are corresponding geographical variations in radiotherapy utilisation rates (RURs) is the subject of this study. Methods: RURs for the regional centre of Geelong and rural areas of the Barwon South Western Region were calculated using a population-based database (2009). Results: Lower RURs were observed for rural patients compared with the Geelong region for prostate cancer (15.7% vs 25.8%, P = 0.02), rectal cancer (32.8% vs 44.7%, P = 0.11), lymphoma (9.4% vs 26.2%, P = 0.05), and all cancers overall (25.6% vs 28.9%, P = 0.06). This lower rate was significant in men (rural, 19.9%; Geelong, 28.3%; P = 0.00) but not in women (rural, 33.6%; Geelong, 29.7%; P = 0.88). Time from diagnosis to radiotherapy was not significantly different for patients from the two regions. Tumour staging within the rural and Geelong regions was not significantly different for the major tumour streams of rectal, prostate and lung cancer (P = 0.61, P = 0.79, P = 0.43, respectively). A higher proportion of tumours were unstaged or unstageable in the rural region for lung (44% vs 18%, P < 0.01) and prostate (73% vs 57%, P < 0.01) cancer. Conclusion: Lower RURs were observed in our rural region. Differences found within tumour streams and in men suggest a complexity of relationships that will require further study.
Reasons for presentation to ED would be multifactorial and include complex cases with coexisting symptoms making diagnosis difficult. The general public appear to have a low level of awareness of alternative primary care services or difficulty accessing such information. Some of the changes towards reducing the number of patients presenting to ED will include patient education.
The Evaluation of Cancer Outcomes study is an important initiative that collects information about newly diagnosed cases of cancer more detailed than is currently collected by the Cancer Council of Victoria. Future studies will build on this base dataset and provide valuable insight into the regional and rural experience of treatment pathways after diagnosis. More work is needed to bring more services to our rural patients, or more education is needed to encourage the recording of tumour staging.
Our study confirmed improved survival outcomes for patients of higher socio-economic status and younger age. Future research to explain the unexpected survival benefit in patients who lived in more remote areas should examine factors including the correlation between geographical residence and eventual treatment facility as well as compare the BSWR care model to other regions' approaches.
Summary Current treatments for metastatic breast cancer are not associated with significant survival benefits despite response rates of over 50%. High-dose therapy with autologous bone marrow transplantation (ABMT) has been investigated, particularly in North America, and prolonged survival in up to 25% of women has been reported, but with a significant treatment-related mortality. However, in patients with haematological malignancies undergoing autologous transplantation, haematopoietic reconstruction is significantly quicker and mortality lower than with ABMT, when peripheral blood progenitor cells (PBPCs) are used. In 32 women with metastatic breast cancer, we investigated the feasibility of PBPC mobilisation with high-dose cyclophosphamide and granulocyte colony-stimulating factor (G-CSF) after 12 weeks' infusional induction chemotherapy and the subsequent efficacy of the haematopoietic reconstitution after conditioning with melphalan and either etoposide or thiotepa. PBPC mobilisation was successful in 28/32 (88%) patients, and there was a rapid posttransplantation haematopoietic recovery: median time to neutrophils >0.5 x l091 -1 was 14 days and to platelets >20 x 109 1 was 10 days. There was no procedure-related mortality, and the major morbidity was mucositis (WHO grade 3-4) in 18/32 patients (56%). In a patient group of which the majority had very poor prognostic features, the median survival from start of induction chemotherapy was 15 months. Thus, PBPC mobilisation and support of high-dose chemotherapy is feasible after infusional induction chemotherapy for patients with metastatic breast cancer, although the optimum drug combination has not yet been determined.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.