Primary central chondrosarcoma of long bone, limb girdle and trunk: Analysis of 174 cases by numerical scoring on histology.

The aims of this study were: (i) to elucidate clinicopathological characteristics of pcCHS of long bones (L), limb girdles (LG) and trunk (T) in Japan; (ii) to investigate predictive pathological findings for outcome of pcCHS of L, LG and T, objectively; and (iii) to elucidate a discrepancy of grade between biopsy and resected specimens. Clinicopathological profiles of 174 pcCHS (79 male, 95 female), of L, LG, and T were retrieved. For each case, a numerical score was given to 18 pathological findings. The average age was 50.5 years (15-80 years). Frequently involved sites were femur, humerus, pelvis and rib. The 5-year and 10-year disease-specific survival (DSS) rates [follow-up: 1-258 months (average 65.5)] were 87.0% and 80.4%, respectively. By Cox hazards analysis on pathological findings, age, sex and location, histologically higher grade and older age were unfavorable predictors, and calcification was a favorable predictor in DSS. The histological grade of resected specimen was higher than that of biopsy in 37.7% (26/69 cases). In conclusion, higher histological grade and older age were predictors for poor, but calcification was for good prognosis. Because there was a discrepancy in grade between biopsy and resected specimens, comprehensive evaluation is necessary before definitive operation for pcCHS.

An approach to predict the risk of glaucoma development by integrating different attribute data.

Primary open-angle glaucoma (POAG) is one of the major causes of blindness worldwide and considered to be influenced by inherited and environmental factors. Recently, we demonstrated a genome-wide association study for the susceptibility to POAG by comparing patients and controls. In addition, the serum cytokine levels, which are affected by environmental and postnatal factors, could be also obtained in patients as well as in controls, simultaneously. Here, in order to predict the effective diagnosis of POAG, we developed an "integration approach" using different attribute data which were integrated simply with several machine learning methods and random sampling. Two data sets were prepared for this study. The one is the "training data set", which consisted of 42 POAG and 42 controls. The other is the "test data set" consisted of 73 POAG and 52 controls. We first examined for genotype and cytokine data using the training data set with general machine learning methods. After the integration approach was applied, we obtained the stable accuracy, using the support vector machine method with the radial basis function. Although our approach was based on well-known machine learning methods and a simple process, we demonstrated that the integration with two kinds of attributes, genotype and cytokines, was effective and helpful in diagnostic prediction of POAG.