Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans
Objective: Accurate prediction of abdominal aortic aneurysm (AAA) growth in an individual can allow personalised stratification of surveillance intervals and better inform the timing for surgery. The authors recently described the novel significant association between flow mediated dilatation (FMD)...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2018-01-01
|
| Series: | EJVES Short Reports |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405655318300094 |
| _version_ | 1819072623503474688 |
|---|---|
| author | R. Lee D. Jarchi R. Perera A. Jones I. Cassimjee A. Handa D.A. Clifton K. Bellamkonda F. Woodgate N. Killough N. Maistry A. Chandrashekar C.R. Darby A. Halliday L.J. Hands P. Lintott T.R. Magee A. Northeast J. Perkins E. Sideso |
| author_facet | R. Lee D. Jarchi R. Perera A. Jones I. Cassimjee A. Handa D.A. Clifton K. Bellamkonda F. Woodgate N. Killough N. Maistry A. Chandrashekar C.R. Darby A. Halliday L.J. Hands P. Lintott T.R. Magee A. Northeast J. Perkins E. Sideso |
| author_sort | R. Lee |
| collection | DOAJ |
| description | Objective: Accurate prediction of abdominal aortic aneurysm (AAA) growth in an individual can allow personalised stratification of surveillance intervals and better inform the timing for surgery. The authors recently described the novel significant association between flow mediated dilatation (FMD) and future AAA growth. The feasibility of predicting future AAA growth was explored in individual patients using a set of benchmark machine learning techniques. Methods: The Oxford Abdominal Aortic Aneurysm Study (OxAAA) prospectively recruited AAA patients undergoing the routine NHS management pathway. In addition to the AAA diameter, FMD was systemically measured in these patients. A benchmark machine learning technique (non-linear Kernel support vector regression) was applied to predict future AAA growth in individual patients, using their baseline FMD and AAA diameter as input variables. Results: Prospective growth data were recorded at 12 months (360 ± 49 days) in 94 patients. Of these, growth data were further recorded at 24 months (718 ± 81 days) in 79 patients. The average growth in AAA diameter was 3.4% at 12 months, and 2.8% per year at 24 months. The algorithm predicted the individual's AAA diameter to within 2 mm error in 85% and 71% of patients at 12 and 24 months. Conclusions: The data highlight the utility of FMD as a biomarker for AAA and the value of machine learning techniques for AAA research in the new era of precision medicine. Keywords: Abdominal aortic aneurysm, Aneurysm progression, Machine learning, Biomarker, Flow mediated dilatation |
| first_indexed | 2024-12-21T17:40:40Z |
| format | Article |
| id | doaj.art-d4ed64f438ca4ae8875017357b2c677f |
| institution | Directory Open Access Journal |
| issn | 2405-6553 |
| language | English |
| last_indexed | 2024-12-21T17:40:40Z |
| publishDate | 2018-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EJVES Short Reports |
| spelling | doaj.art-d4ed64f438ca4ae8875017357b2c677f2022-12-21T18:55:38ZengElsevierEJVES Short Reports2405-65532018-01-01392428Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in HumansR. Lee0D. Jarchi1R. Perera2A. Jones3I. Cassimjee4A. Handa5D.A. Clifton6K. BellamkondaF. WoodgateN. KilloughN. MaistryA. ChandrashekarC.R. DarbyA. HallidayL.J. HandsP. LintottT.R. MageeA. NortheastJ. PerkinsE. SidesoNuffield Department of Surgical Sciences, University of Oxford, Oxford, UK; Corresponding author.Department of Engineering Science, University of Oxford, Oxford, UKNuffield Department of Primary Care Health, University of Oxford, Oxford, UKNuffield Department of Surgical Sciences, University of Oxford, Oxford, UKNuffield Department of Surgical Sciences, University of Oxford, Oxford, UKNuffield Department of Surgical Sciences, University of Oxford, Oxford, UKNuffield Department of Primary Care Health, University of Oxford, Oxford, UKObjective: Accurate prediction of abdominal aortic aneurysm (AAA) growth in an individual can allow personalised stratification of surveillance intervals and better inform the timing for surgery. The authors recently described the novel significant association between flow mediated dilatation (FMD) and future AAA growth. The feasibility of predicting future AAA growth was explored in individual patients using a set of benchmark machine learning techniques. Methods: The Oxford Abdominal Aortic Aneurysm Study (OxAAA) prospectively recruited AAA patients undergoing the routine NHS management pathway. In addition to the AAA diameter, FMD was systemically measured in these patients. A benchmark machine learning technique (non-linear Kernel support vector regression) was applied to predict future AAA growth in individual patients, using their baseline FMD and AAA diameter as input variables. Results: Prospective growth data were recorded at 12 months (360 ± 49 days) in 94 patients. Of these, growth data were further recorded at 24 months (718 ± 81 days) in 79 patients. The average growth in AAA diameter was 3.4% at 12 months, and 2.8% per year at 24 months. The algorithm predicted the individual's AAA diameter to within 2 mm error in 85% and 71% of patients at 12 and 24 months. Conclusions: The data highlight the utility of FMD as a biomarker for AAA and the value of machine learning techniques for AAA research in the new era of precision medicine. Keywords: Abdominal aortic aneurysm, Aneurysm progression, Machine learning, Biomarker, Flow mediated dilatationhttp://www.sciencedirect.com/science/article/pii/S2405655318300094 |
| spellingShingle | R. Lee D. Jarchi R. Perera A. Jones I. Cassimjee A. Handa D.A. Clifton K. Bellamkonda F. Woodgate N. Killough N. Maistry A. Chandrashekar C.R. Darby A. Halliday L.J. Hands P. Lintott T.R. Magee A. Northeast J. Perkins E. Sideso Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans EJVES Short Reports |
| title | Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans |
| title_full | Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans |
| title_fullStr | Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans |
| title_full_unstemmed | Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans |
| title_short | Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in Humans |
| title_sort | applied machine learning for the prediction of growth of abdominal aortic aneurysm in humans |
| url | http://www.sciencedirect.com/science/article/pii/S2405655318300094 |
| work_keys_str_mv | AT rlee appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT djarchi appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT rperera appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT ajones appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT icassimjee appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT ahanda appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT daclifton appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT kbellamkonda appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT fwoodgate appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT nkillough appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT nmaistry appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT achandrashekar appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT crdarby appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT ahalliday appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT ljhands appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT plintott appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT trmagee appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT anortheast appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT jperkins appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans AT esideso appliedmachinelearningforthepredictionofgrowthofabdominalaorticaneurysminhumans |