Comparison of two representatives of bone tumor classifications

This study compares the histological method versus the Memorial Sloan Kettering Cancer Center (MSKCC) method for categorizing cancer types using Machine Language algorithms. Its objective is to assess the potential of a newly introduced approach (MSKCC) for oncology classification. Development in computing algorithms has advanced systematic disease classification ability. These algorithms help clinical professionals make appropriate diagnoses and design rapid-responding treatment procedures. Bone tumors are uncommon oncological diseases, showing an encouraging five-year survival rate of ~70%. The histological classification method for Bone tumors follows the conventional sorting out criteria, depending on tumor location, patient age and grade, among other factors. Recently, MSKCC has launched a new simplified oncology classification based on a homogenized diagnosis after incorporating feedback from public tumor associations and consortia. The MSKCC system simplifies classification in hard-to-classify heterogenous tumors and addresses a pressing and evolving need of accurate diagnosis. We aimed to evaluate whether the MSKCC classification resulted in similar categorization of cancers that were conventionally classified using the histological method. In this comparative analysis, we concluded that the MSKCC method possessed the classifying power equivalent to the histological method with the added advantage of much-simplified categorization. This new method to classify cancers can lead to improved cancer treatment strategies for favorable outcomes.