Classification of Control and Neurodegenerative Disease Subjects Using Tree Based Classifiers

Background: The medical researchers are developing different non-invasive methods for early detection of Neurodegenerative Diseases (NDDs) when pharmacological interventions are still possible to further prevent the disease progression. The NDDs are associated with the degradation in the complex gait dynamicsand motor activity. The classification ofgait data using machine learning techniques can assist the physiciansfor early diagnosis of the neural disorder when clinical manifestation of the diseases is not yet apparent. Aims: The present study was undertaken to classify the control and NDD subjects using decision trees based classifiers (Random Forest (RF), J48 and REPTree).Methodology:The data used in the study comprises of 16 control, 20 Huntington’s Disease (HD), 15 Parkinson’s Disease (PD), and 13 Amyotrophic Lateral Sclerosis (ALS) subjects, which were taken from publicly available database from Physionet. The age range of control subjects was 20-74, HD subjects was 36-70, PD subjects was 44-80, and ALS subjects was 29-71. There were 13 attributes associated with the data. Important features/attributes of the data were selected using correlation feature selection -subset evaluation (cfs) method. Three tree based machine learning algorithms (RF, J48 and REPTree) were used to classify the control and NDD subjects. The performance of classifiers were evaluated using Precision, Recall, F-Measure, MAE and RMSE.Results:In order to evaluate the performance of tree based classifiers, two different settings of data i.e. complete features and selected featureswere used. In classifying control vs HD subjects, RF provides the robust separation with classification accuracy of 84.79% using complete features and 83.94% using selected features. While in classifying control vs PD subjects, and control vs ALS subjects, RF also provides the best separation with classification accuracy of 86.51% and 94.95% respectively using complete features and 85.19% and 93.64% respectively using selected features.Conclusion:The variability analysis of physiological signals provides a valuable non-invasive tool for quantifying the system of dynamics of healthy subjects and to examine the alternations in the controlling mechanism of these systems with aging and disease. It is concluded that selected features encode adequate information about neural control of the gait. Moreover,the selected featuresalong with tree based machine learning algorithms can play a vital for early detection of NDDs, when pharmacological interventions are still possible

7-Month-Old Infant with Cushing's Disease

Cushing's disease in children is not rare but in infants it is quite rare and an important medical condition needing proper line of investigations and management options. Craniopharyngioma as a cause of Cushing's disease is well reported and practical inference of the condition is of clinical importance. Craniopharyngioma generally affects children at 5 - 10 years of age and is rarely seen in infancy. It usually manifests as endocrinological deficits such as short stature, delayed puberty, and obesity. We report the case of a 7 months old infant who presented with obesity and Cushing's disease associated with Craniopharyngioma

Brain Abscess in children

To find out the clinical presentation, radiological characteristics, various underlying predisposing conditions and causative organisms of brain abscess in children in our setup. Descriptive study. The Children's Hospital and the Institute of Child Health, Lahore, over two years from September 2001 to August 2003. All children [<16 years] presenting with brain abscess were included to study demographic, clinical and radiological features. In addition, attempts were made to find out underlying predisposing conditions and causative organisms. Twenty-five children with brain abscess were managed over 2 years. The mean age was 7.8 years [range 9 months to 16 years]. Male to female ratio was 2.1:1. Most patients [43%] presented with 4 weeks history of illness, with mean duration of illness at presentation of 29.3 days. Main presenting complaints were fever [72%], vomiting [48%], headache [44%] and convulsions [32%]. Five patients [20%] had papilledema at presentation, another 4 [16%] had paresis/paralysis and 3 [12%] had cranial nerve palsies. Majority [64%] had solitary abscess, located in parietal, temporal, frontal and occipital lobes in order of frequency. No underlying predisposing condition was identified in 8 [32%] cases; while 8 [32%] had cyanotic congenital heart disease, 5 [20%] patients had otic infection [mastoiditis], 2 [8%] were postoperative cases and one each developed brain abscess secondary to ventriculo-peritoneal [VP] shunt infection and pulmonary tuberculosis. Causative organisms were isolated in 40% cases, which included Staphylococcus aureus, Staphylococcus epidermidis, Streptococcal species, Klebsiella, E.coli and Proteus. Awareness of predisposing factors, early recognition of clinical features and understanding of the prevalent microbial profile is imperative for better management of children with brain abscess