Breast cancer risk prediction in African women using Random Forest Classifier.

INTRODUCTION: One of the most important steps in combating breast cancer is early and accurate diagnosis. Unfortunately, breast cancer is asymptomatic at the early stage, although some symptoms are presented at a later time, but at symptomatic stage treatment could be complicated or even become impossible thereby leading to death. Proper risk assessment is hence very important in reducing mortality. Some computational techniques have been developed for breast cancer risk assessment in the developed world, but such techniques do not work well in Africa because of the difference in risk profiles of African women e.g. later menarche, low drug abuse and low smoking rate. AIM: In this work, we propose a bespoke risk prediction model for African women using Random Forest Classifier (RFC) machine learning technique. METHODS: A total of 180 subjects were studied out of which 90 were confirmed cases of breast cancer and 90 were benign. Twenty-five risk factors were included, for example, smoking, alcohol intake, occupational hazards and age at menopause. Four approaches were empirically used in the feature selection, these are the use of Chi-Square, mutual information gain, Spearman correlation and the entire features. RFC algorithm was used to develop the prediction model. RESULTS: We found that family history of breast cancer, dense breast, deliberate abortion, age at first child, fruit intake and regular exercise are predictors of breast cancer. The RFC model gave an accuracy of 91.67%, sensitivity of 87.10%, specificity of 96.55% and Area under curve (AUC) of 92% when all the risk factors were included in the model while an accuracy of 96.67%, sensitivity of 93.75%, specificity of 100% and AUC of 97% were obtained when correlation-selected features were included in the model. The Chi-Square selected features gave the best performance with 98.33% accuracy, 100% sensitivity, 96.55 specificity and 98% AUC. Mutual information gain selected feature gave the same results as Chi-Square selected features. CONCLUSION: Random Forest Classifier has a good potential at predicting the risk of breast cancer in African women. The study helped to identify the risk factors of breast cancer in African women. This is a valuable information which can help African women to pay attention to those risk factors with the intention of reducing the incidence of breast cancer in Africa.

Association between scripture memorization and brain atrophy using magnetic resonance imaging.

We investigated the association between scripture memorization and brain tissue using magnetic resonance imaging techniques. Participants comprised 63 healthy adults between the ages of 35 and 80 years old with no neurological or psychological disorders. Of these, 19 had completely memorized the Quran, 28 had partially memorized parts of Quran while 16, the control group, had not committed the Quran into their memory. White matter, grey matter and cerebrospinal fluid volumes were calculated. The brain tissue volumes of those who memorized the entire Quran and those who memorized only a small portion were compared with the control group using one­way ANOVA implemented in SPSS. There was no significant effect of age between the three groups (p>0.50). The group who completely memorized the Quran had larger grey matter and white matter volumes than the control group. Our results showed that those who memorized scripture had more brain tissues preserved compared with those who had not memorized scripture. These findings suggest that engaging our brains by memorizing scripture may increase brain health.

Potential effect of skull thickening on the associations between cognition and brain atrophy in ageing.

BACKGROUND: intracranial volume (ICV) is commonly used as a marker of premorbid brain size in neuroimaging studies as it is thought to remain fixed throughout adulthood. However, inner skull table thickening would encroach on ICV and could mask actual brain atrophy. OBJECTIVE: we investigated the effect that thickening might have on the associations between brain atrophy and cognition. METHODS: the sample comprised 57 non-demented older adults who underwent structural brain MRI at mean age 72.7 ± 0.7 years and were assessed on cognitive ability at mean age 11 and 73 years. Principal component analysis was used to derive factors of general cognitive ability (g), information processing speed and memory from the recorded cognitive ability data. The total brain tissue volume and ICV with (estimated original ICV) and without (current ICV) adjusting for the effects of inner table skull thickening were measured. General linear modelling was used to test for associations. RESULTS: all cognitive ability variables were significantly (P < 0.01) associated with percentage total brain volume in ICV measured without adjusting for skull thickening (g: η(2) = 0.177, speed: η(2) = 0.264 and memory: η(2) = 0.132). After accounting for skull thickening, only speed was significantly associated with percentage total brain volume in ICV (η(2) = 0.085, P = 0.034), not g or memory. CONCLUSIONS: not accounting for skull thickening when computing ICV can distort the association between brain atrophy and cognitive ability in old age. Larger samples are required to determine the true effect.