The use of an integrated dataset along with a SVM classifier rather than a Bayesian classifier has benefits in terms of the classification accuracy of HRCT images acquired with more than one scanner. This finding is of relevance in studies involving large number of images, as is the case in a multicenter trial with different scanners.

No abstract

We propose the use of a context-sensitive support vector machine (csSVM) to enhance the performance of a conventional support vector machine (SVM) for identifying diffuse interstitial lung disease (DILD) in high-resolution computerized tomography (HRCT) images. Nine hundred rectangular regions of interest (ROIs), each 20 × 20 pixels in size and consisting of 150 ROIs representing six regional disease patterns (normal, ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation), were marked by two experienced radiologists using consensus HRCT images of various DILD. Twenty-one textual and shape features were evaluated to characterize the ROIs. The csSVM classified an ROI by simultaneously using the decision value of each class and information from the neighboring ROIs, such as neighboring region feature distances and class differences. Sequential forward-selection was used to select the relevant features. To validate our results, we used 900 ROIs with fivefold cross-validation and 84 whole lung images categorized by a radiologist. The accuracy of the proposed method for ROI and whole lung classification (89.88 ± 0.02%, and 60.30 ± 13.95%, respectively) was significantly higher than that provided by the conventional SVM classifier (87.39 ± 0.02%, and 57.69 ± 13.31%, respectively; paired t test, p < 0.01, and p < 0.01, respectively). We conclude that our csSVM provides better overall quantification of DILD.

Prolonging survival in good health is a fundamental societal goal. However, the leading determinants of disability-free survival in healthy older people have not been well established. Data from ASPREE, a bi-national placebo-controlled trial of aspirin with 4.7 years median follow-up, was analysed. At enrolment, participants were healthy and without prior cardiovascular events, dementia or persistent physical disability. Disability-free survival outcome was defined as absence of dementia, persistent disability or death. Selection of potential predictors from amongst 25 biomedical, psychosocial and lifestyle variables including recognized geriatric risk factors, utilizing a machine-learning approach. Separate models were developed for men and women. The selected predictors were evaluated in a multivariable Cox proportional hazards model and validated internally by bootstrapping. We included 19,114 Australian and US participants aged ≥65 years (median 74 years, IQR 71.6–77.7). Common predictors of a worse prognosis in both sexes included higher age, lower Modified Mini-Mental State Examination score, lower gait speed, lower grip strength and abnormal (low or elevated) body mass index. Additional risk factors for men included current smoking, and abnormal eGFR. In women, diabetes and depression were additional predictors. The biased-corrected areas under the receiver operating characteristic curves for the final prognostic models at 5 years were 0.72 for men and 0.75 for women. Final models showed good calibration between the observed and predicted risks. We developed a prediction model in which age, cognitive function and gait speed were the strongest predictors of disability-free survival in healthy older people.Trial registrationClinicaltrials.gov (NCT01038583)