Machine learning and artificial intelligence approaches to the analysis of physical activity from wearables and biosensors in clinical trials: applications of clustering and prediction of clinical outcomes
| dc.contributor.author | Vlajnic, Vanja M., author | |
| dc.contributor.author | Simske, Steve, advisor | |
| dc.contributor.author | Miller, Erika, committee member | |
| dc.contributor.author | Cale, Jim, committee member | |
| dc.contributor.author | Reisfeld, Bradley, committee member | |
| dc.date.accessioned | 2022-08-29T10:17:06Z | |
| dc.date.available | 2022-08-29T10:17:06Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | As human demographics continue to trend toward elderly, especially in advanced economies, the treatment of illness becomes more salient. Across many therapeutic areas, researchers examine potential treatments while incorporating novel technologies in an effort to prolong the years in which quality of life is achieved for patients around the world. In the area of cardiovascular disease, wearable and biosensor data is becoming increasingly used in order to compliment data traditionally collected from clinical trials. This work discusses a series of analytical approaches for the analysis of data from recent clinical trials in which accelerometry data from wearable devices were analyzed using clustering approaches (K-means and consensus clustering) and survival analyses (Cox proportional hazards and random survival forest) for the purposes of clustering patients and assessing their baseline clinical characteristics as well as for the prediction of clinical outcomes. Unique clinical phenotypes were identified within the patient aggregations as part of the clustering analyses. Furthermore, models were created with improved predictive accuracy for clinical outcomes of interest in the heart failure space. Taken collectively, the results from these analyses and the analytical approaches therein can be used to assess whether heterogeneous clinical subgroups of patients exist as well as further guide the clinical development programs. | |
| dc.format.medium | born digital | |
| dc.format.medium | doctoral dissertations | |
| dc.identifier | Vlajnic_colostate_0053A_17275.pdf | |
| dc.identifier.uri | https://hdl.handle.net/10217/235687 | |
| dc.language | English | |
| dc.language.iso | eng | |
| dc.publisher | Colorado State University. Libraries | |
| dc.relation.ispartof | 2020- | |
| dc.rights | Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright. | |
| dc.subject | clinical trials | |
| dc.subject | machine learning | |
| dc.subject | wearables | |
| dc.subject | heart failure | |
| dc.subject | biosensors | |
| dc.subject | statistical learning | |
| dc.title | Machine learning and artificial intelligence approaches to the analysis of physical activity from wearables and biosensors in clinical trials: applications of clustering and prediction of clinical outcomes | |
| dc.type | Text | |
| dcterms.rights.dpla | This Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). | |
| thesis.degree.discipline | Systems Engineering | |
| thesis.degree.grantor | Colorado State University | |
| thesis.degree.level | Doctoral | |
| thesis.degree.name | Doctor of Philosophy (Ph.D.) |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Vlajnic_colostate_0053A_17275.pdf
- Size:
- 1.59 MB
- Format:
- Adobe Portable Document Format