Uses and opportunities for machine learning in hypertension research
Background: Artificial intelligence (AI) promises to provide useful information to clinicians specializing in hypertension. Already, there are some significant AI applications on large validated data sets. Methods and results: This review presents the use of AI to predict clinical outcomes in big da...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-06-01
|
| Series: | International Journal of Cardiology. Hypertension |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590086220300045 |
| _version_ | 1818878931243106304 |
|---|---|
| author | Dhammika Amaratunga Javier Cabrera Davit Sargsyan John B. Kostis Stavros Zinonos William J. Kostis |
| author_facet | Dhammika Amaratunga Javier Cabrera Davit Sargsyan John B. Kostis Stavros Zinonos William J. Kostis |
| author_sort | Dhammika Amaratunga |
| collection | DOAJ |
| description | Background: Artificial intelligence (AI) promises to provide useful information to clinicians specializing in hypertension. Already, there are some significant AI applications on large validated data sets. Methods and results: This review presents the use of AI to predict clinical outcomes in big data i.e. data with high volume, variety, veracity, velocity and value. Four examples are included in this review. In the first example, deep learning and support vector machine (SVM) predicted the occurrence of cardiovascular events with 56%–57% accuracy. In the second example, in a data base of 378,256 patients, a neural network algorithm predicted the occurrence of cardiovascular events during 10 year follow up with sensitivity (68%) and specificity (71%). In the third example, a machine learning algorithm classified 1,504,437 patients on the presence or absence of hypertension with 51% sensitivity, 99% specificity and area under the curve 87%. In example four, wearable biosensors and portable devices were used in assessing a person's risk of developing hypertension using photoplethysmography to separate persons who were at risk of developing hypertension with sensitivity higher than 80% and positive predictive value higher than 90%. The results of the above studies were adjusted for demographics and the traditional risk factors for atherosclerotic disease. Conclusion: These examples describe the use of artificial intelligence methods in the field of hypertension. |
| first_indexed | 2024-12-19T14:22:01Z |
| format | Article |
| id | doaj.art-9d00875f50bf4457b13e937480ef572f |
| institution | Directory Open Access Journal |
| issn | 2590-0862 |
| language | English |
| last_indexed | 2024-12-19T14:22:01Z |
| publishDate | 2020-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Cardiology. Hypertension |
| spelling | doaj.art-9d00875f50bf4457b13e937480ef572f2022-12-21T20:17:45ZengElsevierInternational Journal of Cardiology. Hypertension2590-08622020-06-015100027Uses and opportunities for machine learning in hypertension researchDhammika Amaratunga0Javier Cabrera1Davit Sargsyan2John B. Kostis3Stavros Zinonos4William J. Kostis5Cardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ 08901, USADepartment of Statistics, Rutgers University, Piscataway, NJ 08854, USACardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ 08901, USACardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ 08901, USA; Corresponding author. Cardiovascular Institute Rutgers Robert Wood Johnson Medical School 125 Paterson Street, CAB-4180A New Brunswick, NJ. 08901, USA.Cardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ 08901, USACardiovascular Institute, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ 08901, USABackground: Artificial intelligence (AI) promises to provide useful information to clinicians specializing in hypertension. Already, there are some significant AI applications on large validated data sets. Methods and results: This review presents the use of AI to predict clinical outcomes in big data i.e. data with high volume, variety, veracity, velocity and value. Four examples are included in this review. In the first example, deep learning and support vector machine (SVM) predicted the occurrence of cardiovascular events with 56%–57% accuracy. In the second example, in a data base of 378,256 patients, a neural network algorithm predicted the occurrence of cardiovascular events during 10 year follow up with sensitivity (68%) and specificity (71%). In the third example, a machine learning algorithm classified 1,504,437 patients on the presence or absence of hypertension with 51% sensitivity, 99% specificity and area under the curve 87%. In example four, wearable biosensors and portable devices were used in assessing a person's risk of developing hypertension using photoplethysmography to separate persons who were at risk of developing hypertension with sensitivity higher than 80% and positive predictive value higher than 90%. The results of the above studies were adjusted for demographics and the traditional risk factors for atherosclerotic disease. Conclusion: These examples describe the use of artificial intelligence methods in the field of hypertension.http://www.sciencedirect.com/science/article/pii/S2590086220300045Machine learningDeep neural networksHypertensionDisease managementPersonalized disease network |
| spellingShingle | Dhammika Amaratunga Javier Cabrera Davit Sargsyan John B. Kostis Stavros Zinonos William J. Kostis Uses and opportunities for machine learning in hypertension research International Journal of Cardiology. Hypertension Machine learning Deep neural networks Hypertension Disease management Personalized disease network |
| title | Uses and opportunities for machine learning in hypertension research |
| title_full | Uses and opportunities for machine learning in hypertension research |
| title_fullStr | Uses and opportunities for machine learning in hypertension research |
| title_full_unstemmed | Uses and opportunities for machine learning in hypertension research |
| title_short | Uses and opportunities for machine learning in hypertension research |
| title_sort | uses and opportunities for machine learning in hypertension research |
| topic | Machine learning Deep neural networks Hypertension Disease management Personalized disease network |
| url | http://www.sciencedirect.com/science/article/pii/S2590086220300045 |
| work_keys_str_mv | AT dhammikaamaratunga usesandopportunitiesformachinelearninginhypertensionresearch AT javiercabrera usesandopportunitiesformachinelearninginhypertensionresearch AT davitsargsyan usesandopportunitiesformachinelearninginhypertensionresearch AT johnbkostis usesandopportunitiesformachinelearninginhypertensionresearch AT stavroszinonos usesandopportunitiesformachinelearninginhypertensionresearch AT williamjkostis usesandopportunitiesformachinelearninginhypertensionresearch |