A Decision Support System For Detecting Stage In Hodgkin Lymphoma Patients Using Artificial Neural Network and Optimization Algorithms

Hodgkin-type lymphoma is a disease with unique histological, immunophenotypic, and clinical features. This occurs in nearly 30% of all lymphomas. Its treatable high. However, the treatment plan specified after stage risk status are determined. For this reason, it an important process for doctors to decide on correctly. Some data used decision patient's history, detailed physical examination, laboratory findings, imaging methods bone marrow biopsy results. Hybrid FDG-PET other method medical world. diagnosis, evaluation response given treatment, staging restaging process. radiation-based. Therefore has possibility producing undesirable results future. In study, artificial intelligence-based computer-assisted support system done reduce number radiation exposure. Data were obtained from NCBI-GEO dataset. The these data, which contains missing values, handled two ways. Firstly, samples values initial deleted Then, trained “trainlm” function neural network architecture. reducing error value estimates important. this, architecture retrained bee colony algorithm, particle swarm optimization algorithm invasive weed respectively. Secondly, same operations performed again dataset containing values. As result training, maximum performance was algorithms 1,45547E+14 1,23103E+14 average rates,