Abstract

The main aim of this study was to model the effectiveness of multiple myeloma (MM) therapy using machine learning, which was based on the analysis of various methods of MM treatment, a number of prognostic factors and their results in the daily routine clinical practice of medical centers in European countries. The present study was retrospective, non-interventional, multicenter. A structured database of MM patients provided by the Oncology Information service (O.I.s.) was used for the study. Registration took place in medical institutions in eight countries: Austria, Belgium, Switzerland, Germany, Spain, France, Greece and Great Britain. In total, 57% of men and 43% of women were analyzed in the base of 6074 patients with MM. The median age was 71 years. The median follow-up time along the lines was 387 days. High-risk cytogenetics are represented in 15% of cases. The efficacy endpoint was the best response to each line of therapy, as measured by time to death (TTD) as an indirect indicator of overall survival and time to next treatment (TTNT) as an indirect indicator of progression-free survival. The median TTD and TTNT were 730 and 399 days respectively. After a multi-step selection process, characteristics with the greatest importance for the therapy prognosis were selected: age at the beginning of therapy, line of therapy, time after MM verification, ECOG (Eastern Cooperative Oncology Group), cytogenetic risk, transplant eligibible or not, TTNT after the previous line of therapy, therapy regimen. To continue the study it is necessary to analyze literature data and compare with real practice. Also analysis and comparison with Russian data on the treatment of patients with MM is required. The analysis of the presented data provides a basis for modeling a tool for assessing the effectiveness of MM therapy (prognosis of TTD and TTNT) for each patient, based on a number of prognostic factors and the results of routine clinical practice in various medical centers in European countries.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.