An omics-based machine learning approach to predict diabetes progression: a RHAPSODY study

Conclusions/interpretationUsing machine learning approaches, we show that insulin requirement risk can be modestly well predicted by predominantly clinical variables. Inclusion of molecular markers improves the prognostic performance beyond that of clinical variables by up to 5%. Such prognostic models could be useful for identifying people with diabetes at high risk of progressing quickly to treatment intensification.Data availabilitySummary statistics of lipidomic, proteomic and metabolomic data are available from a Shiny dashboard athttps://rhapdata-app.vital-it.ch.Graphical Abstract
Source: Diabetologia - Category: Endocrinology Source Type: research