Cargando…
Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype
We introduce data assimilation as a computational method that uses machine learning to combine data with human knowledge in the form of mechanistic models in order to forecast future states, to impute missing data from the past by smoothing, and to infer measurable and unmeasurable quantities that r...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6188514/ https://www.ncbi.nlm.nih.gov/pubmed/30312445 http://dx.doi.org/10.1093/jamia/ocy106 |
_version_ | 1783363196882518016 |
---|---|
author | Albers, David J Levine, Matthew E Stuart, Andrew Mamykina, Lena Gluckman, Bruce Hripcsak, George |
author_facet | Albers, David J Levine, Matthew E Stuart, Andrew Mamykina, Lena Gluckman, Bruce Hripcsak, George |
author_sort | Albers, David J |
collection | PubMed |
description | We introduce data assimilation as a computational method that uses machine learning to combine data with human knowledge in the form of mechanistic models in order to forecast future states, to impute missing data from the past by smoothing, and to infer measurable and unmeasurable quantities that represent clinically and scientifically important phenotypes. We demonstrate the advantages it affords in the context of type 2 diabetes by showing how data assimilation can be used to forecast future glucose values, to impute previously missing glucose values, and to infer type 2 diabetes phenotypes. At the heart of data assimilation is the mechanistic model, here an endocrine model. Such models can vary in complexity, contain testable hypotheses about important mechanics that govern the system (eg, nutrition’s effect on glucose), and, as such, constrain the model space, allowing for accurate estimation using very little data. |
format | Online Article Text |
id | pubmed-6188514 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-61885142018-10-19 Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype Albers, David J Levine, Matthew E Stuart, Andrew Mamykina, Lena Gluckman, Bruce Hripcsak, George J Am Med Inform Assoc Perspective We introduce data assimilation as a computational method that uses machine learning to combine data with human knowledge in the form of mechanistic models in order to forecast future states, to impute missing data from the past by smoothing, and to infer measurable and unmeasurable quantities that represent clinically and scientifically important phenotypes. We demonstrate the advantages it affords in the context of type 2 diabetes by showing how data assimilation can be used to forecast future glucose values, to impute previously missing glucose values, and to infer type 2 diabetes phenotypes. At the heart of data assimilation is the mechanistic model, here an endocrine model. Such models can vary in complexity, contain testable hypotheses about important mechanics that govern the system (eg, nutrition’s effect on glucose), and, as such, constrain the model space, allowing for accurate estimation using very little data. Oxford University Press 2018-10-12 /pmc/articles/PMC6188514/ /pubmed/30312445 http://dx.doi.org/10.1093/jamia/ocy106 Text en © The Author(s) 2018. Published by Oxford University Press on behalf of the American Medical Informatics Association. http://creativecommons.org/licenses/by-nc/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com |
spellingShingle | Perspective Albers, David J Levine, Matthew E Stuart, Andrew Mamykina, Lena Gluckman, Bruce Hripcsak, George Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype |
title | Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype |
title_full | Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype |
title_fullStr | Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype |
title_full_unstemmed | Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype |
title_short | Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype |
title_sort | mechanistic machine learning: how data assimilation leverages physiologic knowledge using bayesian inference to forecast the future, infer the present, and phenotype |
topic | Perspective |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6188514/ https://www.ncbi.nlm.nih.gov/pubmed/30312445 http://dx.doi.org/10.1093/jamia/ocy106 |
work_keys_str_mv | AT albersdavidj mechanisticmachinelearninghowdataassimilationleveragesphysiologicknowledgeusingbayesianinferencetoforecastthefutureinferthepresentandphenotype AT levinematthewe mechanisticmachinelearninghowdataassimilationleveragesphysiologicknowledgeusingbayesianinferencetoforecastthefutureinferthepresentandphenotype AT stuartandrew mechanisticmachinelearninghowdataassimilationleveragesphysiologicknowledgeusingbayesianinferencetoforecastthefutureinferthepresentandphenotype AT mamykinalena mechanisticmachinelearninghowdataassimilationleveragesphysiologicknowledgeusingbayesianinferencetoforecastthefutureinferthepresentandphenotype AT gluckmanbruce mechanisticmachinelearninghowdataassimilationleveragesphysiologicknowledgeusingbayesianinferencetoforecastthefutureinferthepresentandphenotype AT hripcsakgeorge mechanisticmachinelearninghowdataassimilationleveragesphysiologicknowledgeusingbayesianinferencetoforecastthefutureinferthepresentandphenotype |