Enhancing physiologic simulations using supervised learning on coarse mesh solutions
Computational modelling of physical and biochemical processes has emerged as a means of evaluating medical devices, offering new insights that explain current performance, inform future designs and even enable personalized use. Yet resource limitations force one to compromise with reduced order comp...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Royal Society Publishing
2016
|
| Online Access: | http://hdl.handle.net/1721.1/102946 https://orcid.org/0000-0002-7832-7156 https://orcid.org/0000-0002-2890-2319 |
| _version_ | 1811084983873306624 |
|---|---|
| author | Kolandaivelu, Kumaran O'Brien, Caroline C. Shazly, Tarek Kolachalama, Vijaya Bhasker Edelman, Elazer R |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Kolandaivelu, Kumaran O'Brien, Caroline C. Shazly, Tarek Kolachalama, Vijaya Bhasker Edelman, Elazer R |
| author_sort | Kolandaivelu, Kumaran |
| collection | MIT |
| description | Computational modelling of physical and biochemical processes has emerged as a means of evaluating medical devices, offering new insights that explain current performance, inform future designs and even enable personalized use. Yet resource limitations force one to compromise with reduced order computational models and idealized assumptions that yield either qualitative descriptions or approximate, quantitative solutions to problems of interest. Considering endovascular drug delivery as an exemplary scenario, we used a supervised machine learning framework to process data generated from low fidelity coarse meshes and predict high fidelity solutions on refined mesh configurations. We considered two models simulating drug delivery to the arterial wall: (i) two-dimensional drug-coated balloons and (ii) three-dimensional drug-eluting stents. Simulations were performed on computational mesh configurations of increasing density. Supervised learners based on Gaussian process modelling were constructed from combinations of coarse mesh setting solutions of drug concentrations and nearest neighbourhood distance information as inputs, and higher fidelity mesh solutions as outputs. These learners were then used as computationally inexpensive surrogates to extend predictions using low fidelity information to higher levels of mesh refinement. The cross-validated, supervised learner-based predictions improved fidelity as compared with computational simulations performed at coarse level meshes—a result consistent across all outputs and computational models considered. Supervised learning on coarse mesh solutions can augment traditional physics-based modelling of complex physiologic phenomena. By obtaining efficient solutions at a fraction of the computational cost, this framework has the potential to transform how modelling approaches can be applied in the evaluation of medical technologies and their real-time administration in an increasingly personalized fashion. |
| first_indexed | 2024-09-23T13:01:08Z |
| format | Article |
| id | mit-1721.1/102946 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:01:08Z |
| publishDate | 2016 |
| publisher | Royal Society Publishing |
| record_format | dspace |
| spelling | mit-1721.1/1029462022-10-01T12:32:23Z Enhancing physiologic simulations using supervised learning on coarse mesh solutions Kolandaivelu, Kumaran O'Brien, Caroline C. Shazly, Tarek Kolachalama, Vijaya Bhasker Edelman, Elazer R Massachusetts Institute of Technology. Institute for Medical Engineering & Science Kolandaivelu, Kumaran O'Brien, Caroline C. Edelman, Elazer R. Kolachalama, Vijaya Bhasker Computational modelling of physical and biochemical processes has emerged as a means of evaluating medical devices, offering new insights that explain current performance, inform future designs and even enable personalized use. Yet resource limitations force one to compromise with reduced order computational models and idealized assumptions that yield either qualitative descriptions or approximate, quantitative solutions to problems of interest. Considering endovascular drug delivery as an exemplary scenario, we used a supervised machine learning framework to process data generated from low fidelity coarse meshes and predict high fidelity solutions on refined mesh configurations. We considered two models simulating drug delivery to the arterial wall: (i) two-dimensional drug-coated balloons and (ii) three-dimensional drug-eluting stents. Simulations were performed on computational mesh configurations of increasing density. Supervised learners based on Gaussian process modelling were constructed from combinations of coarse mesh setting solutions of drug concentrations and nearest neighbourhood distance information as inputs, and higher fidelity mesh solutions as outputs. These learners were then used as computationally inexpensive surrogates to extend predictions using low fidelity information to higher levels of mesh refinement. The cross-validated, supervised learner-based predictions improved fidelity as compared with computational simulations performed at coarse level meshes—a result consistent across all outputs and computational models considered. Supervised learning on coarse mesh solutions can augment traditional physics-based modelling of complex physiologic phenomena. By obtaining efficient solutions at a fraction of the computational cost, this framework has the potential to transform how modelling approaches can be applied in the evaluation of medical technologies and their real-time administration in an increasingly personalized fashion. United States. Dept. of Health and Human Services/National Institutes of Health. (U.S.) (P20RR016461) American Heart Association (12FTF12080241) Charles Stark Draper Laboratory (CSDL-29414-005, CSDL-29889-001, CSDL-30716-005 & CSDL-30736-003) 2016-06-03T18:43:50Z 2016-06-03T18:43:50Z 2015-02 2014-09 Article http://purl.org/eprint/type/JournalArticle 1742-5689 1742-5662 http://hdl.handle.net/1721.1/102946 Kolandaivelu, Kumaran, Caroline C. O’Brien, Tarek Shazly, Elazer R. Edelman, and Vijaya B. Kolachalama. “Enhancing Physiologic Simulations Using Supervised Learning on Coarse Mesh Solutions.” Journal of The Royal Society Interface 12, no. 104 (February 4, 2015): 20141073–20141073. https://orcid.org/0000-0002-7832-7156 https://orcid.org/0000-0002-2890-2319 en_US http://dx.doi.org/10.1098/rsif.2014.1073 Journal of The Royal Society Interface Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/ application/pdf Royal Society Publishing The Royal Society |
| spellingShingle | Kolandaivelu, Kumaran O'Brien, Caroline C. Shazly, Tarek Kolachalama, Vijaya Bhasker Edelman, Elazer R Enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| title | Enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| title_full | Enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| title_fullStr | Enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| title_full_unstemmed | Enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| title_short | Enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| title_sort | enhancing physiologic simulations using supervised learning on coarse mesh solutions |
| url | http://hdl.handle.net/1721.1/102946 https://orcid.org/0000-0002-7832-7156 https://orcid.org/0000-0002-2890-2319 |
| work_keys_str_mv | AT kolandaivelukumaran enhancingphysiologicsimulationsusingsupervisedlearningoncoarsemeshsolutions AT obriencarolinec enhancingphysiologicsimulationsusingsupervisedlearningoncoarsemeshsolutions AT shazlytarek enhancingphysiologicsimulationsusingsupervisedlearningoncoarsemeshsolutions AT kolachalamavijayabhasker enhancingphysiologicsimulationsusingsupervisedlearningoncoarsemeshsolutions AT edelmanelazerr enhancingphysiologicsimulationsusingsupervisedlearningoncoarsemeshsolutions |