Abstract
Leukemia epitomizes the class of highly complex diseases that new technologies aim to tackle by using large sets of single-cell-level information. Achieving such a goal depends critically not only on experimental techniques but also on approaches to interpret the data. A most pressing issue is to identify the salient quantitative features of the disease from the resulting massive amounts of information. Here, I show that the entropies of cell-population distributions on specific multidimensional molecular and morphological landscapes provide a set of measures for the precise characterization of normal and pathological states, such as those corresponding to healthy individuals and acute myeloid leukemia (AML) patients. I provide a systematic procedure to identify the specific landscapes and illustrate how, applied to cell samples from peripheral blood and bone marrow aspirates, this characterization accurately diagnoses AML from just flow cytometry data. The methodology can generally be applied to other types of cell populations and establishes a straightforward link between the traditional statistical thermodynamics methodology and biomedical applications.
- Received 3 February 2014
DOI:https://doi.org/10.1103/PhysRevX.4.021038
This article is available under the terms of the Creative Commons Attribution 3.0 License. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.
Published by the American Physical Society
Viewpoint
Diagnosing Leukemia Through Entropy
Published 28 May 2014
Measurements of the entropy of immune cell distributions can provide a reliable tool for the diagnosis of acute myeloid leukemia.
See more in Physics
Popular Summary
Complex diseases often require measurements of multiple molecular factors at the level of single cells. Current technologies, such as flow cytometry, allow for the simultaneous quantification of many morphological and molecular properties of diseases. Cytometric analysis of acute myeloid leukemia, for example, is a powerful technique but one that is associated with extremely large quantities of data. A central aspect of all data-intensive approaches is identifying the relevant quantitative features of the diseases from massive amounts of information.
We show, in this study, that entropy, as traditionally used in statistical physics, provides a measure for the precise diagnosis of leukemia. Cell populations from blood and bone marrow are characterized by their entropies in multidimensional landscapes constructed from the distributions of their single-cell morphological and molecular attributes. We make diagnoses by comparing how much the cell population distribution of an individual deviates from prototypical leukemia and normal maximum-entropy distributions. We use this approach to perfectly diagnose leukemia in a blind test set of 179 patients, based solely on flow cytometry data of blood and bone marrow cell populations. Our entropy-based methodology performed better than traditional machine learning algorithms in the Molecular Classification of Acute Myeloid Leukaemia Challenge co-sponsored by Columbia University, the National Institutes of Health, and IBM.
We have shown that it is possible to characterize both leukemic and normal cell populations in terms of average distributions of morphological and molecular properties, establishing a straightforward link between statistical thermodynamics and biomedical applications. We anticipate that these results will usher in the use of sophisticated statistical physics methodologies to tackle medical problems.