Statin use and breast cancer survival: a nationwide cohort study in Scotland

Background: Preclinical evidence suggests that statins could delay cancer progression. Previous epidemiological findings have been inconsistent and some have been limited by small sample sizes, as well as certain time-related biases. This study aimed to investigate whether breast cancer patients who were exposed to statins had reduced breast cancer-specific mortality. Methods: We conducted a retrospective cohort study of 15,140 newly diagnosed invasive breast cancer patients diagnosed from 2009 to 2012 within the Scottish Cancer Registry. Dispensed medication usage was obtained from linkages to the Scottish Prescribing Information System and breast cancer-specific deaths were identified from National Records of Scotland Death Records. Using time-dependent Cox regression models, hazard ratios (HR) and 95 % confidence intervals (CI) were calculated for the association between post-diagnostic exposure to statins (including simvastatin) and breast cancer-specific mortality. Adjustments were made for a range of potential confounders including age at diagnosis, year of diagnosis, cancer stage, grade, cancer treatments received, comorbidities, socioeconomic status and use of aspirin. Results: A total of 1,190 breast cancer-specific deaths occurred up to January 2015. Overall, after adjustment for potential confounders, there was no evidence of an association between statin use and breast cancer-specific death (adjusted HR 0.93, 95 % CI 0.77, 1.12). No significant associations were observed in dose–response analyses or in analysis of all-cause mortality. For simvastatin use specifically, a weak non-significant reduction in breast cancer-specific mortality was observed compared to non-users (adjusted HR 0.89, 95 % CI 0.73, 1.08). Statin use before diagnosis was weakly associated with a reduction in breast cancer-specific mortality (adjusted HR 0.85, 95 % CI 0.74, 0.98). Conclusion: Overall, we found little evidence of a protective association between post-diagnostic statin use and cancer-specific mortality in a large nation-wide cohort of breast cancer patients. These findings will help inform the decision whether to conduct randomised controlled trials of statins as an adjuvant treatment in breast cancer.

Statin use and survival in colorectal cancer: Results from a population-based cohort study and an updated systematic review and meta-analysis

BACKGROUND: The aim of this study was to investigate the association between statin use and survival in a population-based colorectal cancer (CRC) cohort and perform an updated meta-analysis to quantify the magnitude of any association.

METHODS: A cohort of 8391 patients with newly diagnosed Dukes' A-C CRC (2009-2012) was identified from the Scottish Cancer Registry. This cohort was linked to the Prescribing Information System and the National Records of Scotland Death Records (until January 2015) to identify 1064 colorectal cancer-specific deaths. Adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) for cancer-specific mortality by statin use were calculated using time dependent Cox regression models. The systematic review included relevant studies published before January 2016. Meta-analysis techniques were used to derive combined HRs for associations between statin use and cancer-specific and overall mortality.

RESULTS: In the Scottish cohort, statin use before diagnosis (HR=0.84, 95% CI 0.75-0.94), but not after (HR=0.90, 95% CI 0.77-1.05), was associated with significantly improved cancer-specific mortality. The systematic review identified 15 relevant studies. In the meta-analysis, there was consistent (I(2)=0%,heterogeneity P=0.57) evidence of a reduction in cancer-specific mortality with statin use before diagnosis in 6 studies (n=86,622, pooled HR=0.82, 95% CI 0.79-0.86) but this association was less apparent and more heterogeneous (I(2)=67%,heterogeneity P=0.03) with statin use after diagnosis in 4 studies (n=19,152, pooled HR=0.84, 95% CI 0.68-1.04).

CONCLUSION: In a Scottish CRC cohort and updated meta-analysis there was some evidence that statin use was associated with improved survival. However, these associations were weak in magnitude and, particularly for post-diagnosis use, varied markedly between studies.

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.