The shape of cancer relapse: Topological data analysis predicts recurrence in paediatric acute lymphoblastic leukaemia

Abstract

Although children and adolescents with acute lymphoblastic leukaemia (ALL) have high survival rates, approximately 15-20% of patients relapse. Risk of relapse is routinely estimated at diagnosis by biological factors, including flow cytometry data. This high-dimensional data is typically manually assessed by projecting it onto a subset of biomarkers. Cell density and “empty spaces” in 2D projections of the data, i.e. regions devoid of cells, are then used for qualitative assessment. Here, we use topological data analysis (TDA), which quantifies shapes, including empty spaces, in data, to analyse pre-treatment ALL datasets with known patient outcomes. We combine these fully unsupervised analyses with Machine Learning (ML) to identify significant shape characteristics and demonstrate that they accurately predict risk of relapse, particularly for patients previously classified as ‘low risk’. We independently confirm the predictive power of CD10, CD20, CD38, and CD45 as biomarkers for ALL diagnosis. Based on our analyses, we propose three increasingly detailed prognostic pipelines for analysing flow cytometry data from ALL patients depending on technical and technological availability: 1. Visual inspection of specific biological features in biparametric projections of the data; 2. Computation of quantitative topological descriptors of such projections; 3. A combined analysis, using TDA and ML, in the four-parameter space defined by CD10, CD20, CD38 and CD45. Our analyses readily extend to other haematological malignancies.

Computational flow cytometry immunophenotyping at diagnosis is unable to predict relapse in childhood B-cell Acute Lymphoblastic Leukemia

“…Similar constraints apply to an earlier work by our own group that included 56 patients to identify differences in expression 16 . Finally, we recently published a framework that uses topological data analysis for feature extraction and includes a classifier that reached high accuracy and AUC with an increased number of patients (N = 96) 17 . This study meets the criterion of moving beyond the conventional feature engineering in FC and the preliminary results encourage the search for differences in immunophenotype of relapsing patients by means of more 16 complex methods.…”

“…Good et al 15 compiled data from 54 patients and developed a classifier that organized cells based on developmental stage and achieved a high accuracy in relapse prediction 15 . Two additional preliminary works from our group complete this landscape 16,17 , one based on percentile differences of marker expression and the other on topological data analysis.…”