On the prediction of Hodgkin lymphoma treatment response

• E. J. deAndrés-Galiana ^[1] ; J. L. Fernández-Martínez ^[1] ; O. Luaces ^[1] ; J. J. del Coz ^[1] ; R. Fernández ^[2] ; J. Solano ^[3] ; E. A. Nogués ^[3] ; Y. Zanabilli ^[5] ; J. M. Alonso ^[4] ; A. R. Payer ^[3] ; J. M. Vicente ^[6] ; J. Medina ^[5] ; F. Taboada ^[7] ; M. Vargas ^[8] ; C. Alarcón ^[5] ; M. Morán ^[5] ; A. González-Ordóñez ^[5] ; M. A. Palicio ^[8] ; S. Ortiz ^[8] ; C. Chamorro ^[1] ; S. Gonzalez ^[1] ; A. P. González-Rodríguez ^[3]
  1. [1] Universidad de Oviedo

     Universidad de Oviedo

     Oviedo, España

     
  2. [2] Hospital de Cabueñes

     Hospital de Cabueñes

     Gijón, España

     
  3. [3] Hospital Universitario Central de Asturias

     Hospital Universitario Central de Asturias

     Oviedo, España

     
  4. [4] Hospital Valle del Nalón

     Hospital Valle del Nalón

     Langreo, España

     
  5. [5] Hospital San Agustin
  6. [6] Hospital de Mieres
  7. [7] Hospital Cangas de Narcea
  8. [8] Hospital de Jarrio

  Mostrar afiliaciones +
• Localización: Clinical & translational oncology, ISSN 1699-048X, Vol. 17, Nº. 8 (August), 2015, págs. 612-619
• Idioma: inglés
• DOI: 10.1007/s12094-015-1285-z
• Texto completo no disponible (Saber más ...)
• Resumen

  • Purpose The cure rate in Hodgkin lymphoma is high, but the response along with treatment is still unpredictable and highly variable among patients. Detecting those patients who do not respond to treatment at early stages could bring improvements in their treatment. This research tries to identify the main biological prognostic variables currently gathered at diagnosis and design a simple machine learning methodology to help physicians improve the treatment response assessment.

    Methods We carried out a retrospective analysis of the response to treatment of a cohort of 263 Caucasians who were diagnosed with Hodgkin lymphoma in Asturias (Spain). For that purpose, we used a list of 35 clinical and biological variables that are currently measured at diagnosis before any treatment begins. To establish the list of most discriminatory prognostic variables for treatment response, we designed a machine learning approach based on two different feature selection methods (Fisher’s ratio and maximum percentile distance) and backwards recursive feature elimination using a nearest-neighbor classifier (k-NN). The weights of the k-NN classifier were optimized using different terms of the confusion matrix (true- and false-positive rates) to minimize risk in the decisions.

    Results and conclusions We found that the optimum strategy to predict treatment response in Hodgkin lymphoma consists in solving two different binary classification problems, discriminating first if the patient is in progressive disease; if not, then discerning among complete and partial remission. Serum ferritin turned to be the most discriminatory variable in predicting treatment response, followed by alanine aminotransferase and alkaline phosphatase. The importance of these prognostic variables suggests a close relationship between inflammation, iron overload, liver damage and the extension of the disease.