Towards a Precision Medicine Approach Based on Machine Learning for Tailoring Medical Treatment in Alkaptonuria

Abstract

ApreciseKUre is a multi-purpose digital platform facilitating data collection, integration and analysis for patients affected by Alkaptonuria (AKU), an ultra-rare autosomal recessive genetic disease. It includes genetic, biochemical, histopathological, clinical, therapeutic resources and quality of life scores that can be shared among registered researchers and clinicians in order to create a Precision Medicine Ecosystem (PME). The combination of machine learning application to analyse and re-interpret data available in the ApreciseKUre shows the potential direct benefits to achieve patient stratification and the consequent tailoring of care and treatments to a specific subgroup of patients. In this study, we have developed a tool able to investigate the most suitable treatment for AKU patients in accordance with their Quality of Life scores, which indicates changes in health status before/after the assumption of a specific class of drugs. This fact highlights the necessity of development of patient databases for rare diseases, like ApreciseKUre. We believe this is not limited to the study of AKU, but it represents a proof of principle study that could be applied to other rare diseases, allowing data management, analysis, and interpretation.

Keywords: QoL scores; alkaptonuria; data analysis; machine learning; precision medicine; rare disease.

Figure 1

Workflow scheme represented by two stages, ’Quality of Life (QoL) scores prediction’ in the top and ’Correlation between QoL scores and drugs’ in the bottom.

Figure 2

Dense results of the Fisher’s exact test. For each QoL score, a first level of pie charts is shown, representing the psycho-physical state of the patients (from red to cyan, corresponding to progressively better health conditions); the area of each circle is proportional to the number of patients for which the information about that QoL score is available. A second level of pie charts, then, shows the impact of drugs on that particular QoL score, with the same conventions as before. As a reference, we also show three benchmark circles whose sizes correspond to the case where the number of patients is 150, 100 and 50, respectively.