Personalized medicine (PM) is the customization of healthcare, with medical decisions and practices tailored to the individual characteristics of a given patient and one of the great challenges for the 21st century. Chronic lymphocytic leukemia (CLL) is a malignancy of B lymphocytes and the most common adult leukemia in the West, mainly affecting the aged population and characterized by remarkable clinicobiological heterogeneity. The great majority (~85%) of patients with CLL do not require treatment upon diagnosis, however may later experience disease evolution and develop a need for therapy. Presently, it is not possible to predict with accuracy when this may happen, if at all. Hence, it is not paradoxical that CLL patient management has largely adopted a ‘watch and wait’ approach. For those patients developing a need for therapy, several therapeutic options are available, with varying efficacy and cost. On these grounds, essential pre-requisites for realizing PM in CLL are two-fold:
(i) robust prognosis at the time of diagnosis,
(ii) individualized therapeutic approach for each patient based on personalized prediction.
The potential impact of addressing these problems is multidimensional. (a) The prevalence of CLL in Europe is on the rise not least due to the aging of the population. Thus, inoculating novel statistical concepts for addressing both prognosis and personalized prediction will have significant impact in the context of CLL management and European health, in general. (b) From the healthcare professional’s perspective, robust prognostication may assist in the design of the follow-up strategy and the selection of the optimal treatment, increasing clinical efficacy while significantly reducing unwanted toxicities and costs, thus benefiting society at large. (c) Prognostic information can also assist the patient and his/her family in seeing the big picture and making the best decisions, hence improving their quality of life.
The overall objectives of CLLassify were:
(i) To improve prognostic assessment of CLL patients at the time of diagnosis. This may guide the physician to define the risk group the patient belongs to and, consequently, efficiently manage the follow-up.
(ii) To match individual patient characteristics with particular outcomes at any stage during the disease course, thus enabling personalized management of CLL. This relates to the ability to efficiently predict the pattern of disease course of the individual patient, including his/her response to different treatment modalities. Efficient prediction could reasonably be anticipated to empower clinical decision-making with various benefits related to prevention, efficient disease management, economy, etc.
