Interpretation of microbiota-based diagnostics by explaining individual classifier decisions
Abstract Background The human microbiota is associated with various disease states and holds a great promise for non-invasive diagnostics. However, microbiota data is challenging for traditional diagnostic approaches: It is high-dimensional, sparse and comprises of high inter-personal variation. Sta...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2017-10-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-017-1843-1 |
| _version_ | 1828452247761059840 |
|---|---|
| author | A. Eck L. M. Zintgraf E. F. J. de Groot T. G. J. de Meij T. S. Cohen P. H. M. Savelkoul M. Welling A. E. Budding |
| author_facet | A. Eck L. M. Zintgraf E. F. J. de Groot T. G. J. de Meij T. S. Cohen P. H. M. Savelkoul M. Welling A. E. Budding |
| author_sort | A. Eck |
| collection | DOAJ |
| description | Abstract Background The human microbiota is associated with various disease states and holds a great promise for non-invasive diagnostics. However, microbiota data is challenging for traditional diagnostic approaches: It is high-dimensional, sparse and comprises of high inter-personal variation. State of the art machine learning tools are therefore needed to achieve this goal. While these tools have the ability to learn from complex data and interpret patterns therein that cannot be identified by humans, they often operate as black boxes, offering no insight into their decision-making process. In most cases, it is difficult to represent the learning of a classifier in a comprehensible way, which makes them prone to be mistrusted, or even misused, in a clinical environment. In this study, we aim to elucidate microbiota-based classifier decisions in a biologically meaningful context to allow their interpretation. Results We applied a method for explanation of classifier decisions on two microbiota datasets of increasing complexity: gut versus skin microbiota samples, and inflammatory bowel disease versus healthy gut microbiota samples. The algorithm simulates bacterial species as being unknown to a pre-trained classifier, and measures its effect on the outcome. Consequently, each patient is assigned a unique quantitative estimation of which species in their microbiota defined the classification of their sample. The algorithm was able to explain the classifier decisions well, demonstrated by our validation method, and the explanations were biologically consistent with recent microbiota findings. Conclusions Application of a method for explaining individual classifier decisions for complex microbiota analysis proved feasible and opens perspectives on personalized therapy. Providing an explanation to support a microbiota-based diagnosis could guide decisions of clinical microbiologists, and has the potential to increase their confidence in the outcome of such decision support systems. This may facilitate the development of new diagnostic applications. |
| first_indexed | 2024-12-10T23:50:31Z |
| format | Article |
| id | doaj.art-d09a95c586394441b872c5a33748c612 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-10T23:50:31Z |
| publishDate | 2017-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-d09a95c586394441b872c5a33748c6122022-12-22T01:28:47ZengBMCBMC Bioinformatics1471-21052017-10-0118111310.1186/s12859-017-1843-1Interpretation of microbiota-based diagnostics by explaining individual classifier decisionsA. Eck0L. M. Zintgraf1E. F. J. de Groot2T. G. J. de Meij3T. S. Cohen4P. H. M. Savelkoul5M. Welling6A. E. Budding7Department of Medical Microbiology and Infection Control, VU University medical centerInformatics Institute, University of AmsterdamDepartment of Gastroenterology and Hepatology, VU University medical centerDepartment of Pediatric Gastroenterology, VU University medical centerInformatics Institute, University of AmsterdamDepartment of Medical Microbiology and Infection Control, VU University medical centerInformatics Institute, University of AmsterdamDepartment of Medical Microbiology and Infection Control, VU University medical centerAbstract Background The human microbiota is associated with various disease states and holds a great promise for non-invasive diagnostics. However, microbiota data is challenging for traditional diagnostic approaches: It is high-dimensional, sparse and comprises of high inter-personal variation. State of the art machine learning tools are therefore needed to achieve this goal. While these tools have the ability to learn from complex data and interpret patterns therein that cannot be identified by humans, they often operate as black boxes, offering no insight into their decision-making process. In most cases, it is difficult to represent the learning of a classifier in a comprehensible way, which makes them prone to be mistrusted, or even misused, in a clinical environment. In this study, we aim to elucidate microbiota-based classifier decisions in a biologically meaningful context to allow their interpretation. Results We applied a method for explanation of classifier decisions on two microbiota datasets of increasing complexity: gut versus skin microbiota samples, and inflammatory bowel disease versus healthy gut microbiota samples. The algorithm simulates bacterial species as being unknown to a pre-trained classifier, and measures its effect on the outcome. Consequently, each patient is assigned a unique quantitative estimation of which species in their microbiota defined the classification of their sample. The algorithm was able to explain the classifier decisions well, demonstrated by our validation method, and the explanations were biologically consistent with recent microbiota findings. Conclusions Application of a method for explaining individual classifier decisions for complex microbiota analysis proved feasible and opens perspectives on personalized therapy. Providing an explanation to support a microbiota-based diagnosis could guide decisions of clinical microbiologists, and has the potential to increase their confidence in the outcome of such decision support systems. This may facilitate the development of new diagnostic applications.http://link.springer.com/article/10.1186/s12859-017-1843-1MicrobiotaInflammatory bowel disease (IBD)Supervised classificationIS-proMachine learning |
| spellingShingle | A. Eck L. M. Zintgraf E. F. J. de Groot T. G. J. de Meij T. S. Cohen P. H. M. Savelkoul M. Welling A. E. Budding Interpretation of microbiota-based diagnostics by explaining individual classifier decisions BMC Bioinformatics Microbiota Inflammatory bowel disease (IBD) Supervised classification IS-pro Machine learning |
| title | Interpretation of microbiota-based diagnostics by explaining individual classifier decisions |
| title_full | Interpretation of microbiota-based diagnostics by explaining individual classifier decisions |
| title_fullStr | Interpretation of microbiota-based diagnostics by explaining individual classifier decisions |
| title_full_unstemmed | Interpretation of microbiota-based diagnostics by explaining individual classifier decisions |
| title_short | Interpretation of microbiota-based diagnostics by explaining individual classifier decisions |
| title_sort | interpretation of microbiota based diagnostics by explaining individual classifier decisions |
| topic | Microbiota Inflammatory bowel disease (IBD) Supervised classification IS-pro Machine learning |
| url | http://link.springer.com/article/10.1186/s12859-017-1843-1 |
| work_keys_str_mv | AT aeck interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT lmzintgraf interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT efjdegroot interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT tgjdemeij interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT tscohen interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT phmsavelkoul interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT mwelling interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions AT aebudding interpretationofmicrobiotabaseddiagnosticsbyexplainingindividualclassifierdecisions |