Importance of risk factor management in diabetic patients and reduction in Stage B heart failure

BACKGROUND: A number of studies have demonstrated the presence of a diabetic cardiomyopathy, increasing the risk of heart failure development in this population. Improvements in present-day risk factor control may have modified the risk of diabetes-associated cardiomyopathy.

AIM: We sought to determine the contemporary impact of diabetes mellitus (DM) on the prevalence of cardiomyopathy in at-risk patients with and without adjustment for risk factor control.

DESIGN: A cross-sectional study in a population at risk for heart failure.

METHODS: Those with diabetes were compared to those with other cardiovascular risk factors, unmatched, matched for age and gender and then matched for age, gender, body mass index, systolic blood pressure and low density lipoprotein cholesterol.

RESULTS: In total, 1399 patients enrolled in the St Vincent's Screening to Prevent Heart Failure (STOP-HF) cohort were included. About 543 participants had an established history of DM. In the whole sample, Stage B heart failure (asymptomatic cardiomyopathy) was not found more frequently among the diabetic cohort compared to those without diabetes [113 (20.8%) vs. 154 (18.0%), P = 0.22], even when matched for age and gender. When controlling for these risk factors and risk factor control Stage B was found to be more prevalent in those with diabetes [88 (22.2%)] compared to those without diabetes [65 (16.4%), P = 0.048].

CONCLUSION: In this cohort of patients with established risk factors for Stage B heart failure superior risk factor management among the diabetic population appears to dilute the independent diabetic insult to left ventricular structure and function, underlining the importance and benefit of effective risk factor control in this population on cardiovascular outcomes.

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.