Data science and cardiovascular risk

Janis Marc Nolde

doi:10.26182/khc9-3f24

Data science and cardiovascular risk

Janis Marc Nolde

UWA Medical School

Research output: Thesis › Doctoral Thesis › peer-review

146 Downloads (Pure)

Abstract

Projects investigating cardiovascular risk associated with hypertension, sympathetic nervous activity and metabolic risk factors were analysed by a range of Data Scientific means. In Part I of the thesis, biostatistical methods were implemented and statistical inference reported as part of several projects. In Part II, automated data and signal extraction, processing, labelling and utilisation was investigated and adequate tools developed. Part III describes the utilisation of machine learning models in a clinical context for the diagnosis of a cardiometabolic condition. In conclusion, the vast range of data scientific approaches in an increasingly digitally transformed scientific landscape became overt.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	The University of Western Australia
Supervisors/Advisors	Schlaich, Markus, Supervisor Mian, Ajmal, Supervisor Frost, Shaun, Supervisor
Award date	26 Apr 2023
DOIs	https://doi.org/10.26182/khc9-3f24
Publication status	Unpublished - 2022

Access to Document

10.26182/khc9-3f24

THESIS - DOCTOR OF PHILOSOPHY - NOLDE Janis Marc - 2022
This work is protected by Copyright. You may print or download ONE copy of this document for the purpose of your own non-commercial research or study. Any other use requires permission from the copyright owner. The Copyright Act requires you to attribute any copyright works you quote or paraphrase.

8 Article

Catheter-Based Renal Denervation: 9-Year Follow-Up Data on Safety and Blood Pressure Reduction in Patients with Resistant Hypertension
Sesa-Ashton, G., Nolde, J. M., Muente, I., Carnagarin, R., Lee, R., Macefield, V. G., Dawood, T., Sata, Y., Lambert, E. A., Lambert, G. W., Walton, A., Kiuchi, M. G., Esler, M. D. & Schlaich, M. P., 1 Apr 2023, In: Hypertension. 80, 4, p. 811-819 9 p.
Research output: Contribution to journal › Article › peer-review
54 Citations (Scopus)
Autoencoded deep features for semi-automatic, weakly supervised physiological signal labelling
Nolde, J. M., Carnagarin, R., Lugo-Gavidia, L. M., Azzam, O., Kiuchi, M. G., Robinson, S., Mian, A. & Schlaich, M. P., Apr 2022, In: Computers in Biology and Medicine. 143, 105294.
Research output: Contribution to journal › Article › peer-review
2 Citations (Scopus)
Automatic data extraction from 24 hour blood pressure measurement reports of a large multicenter clinical trial
Nolde, J. M., Mian, A., Schlaich, L., Chan, J., Lugo-Gavidia, L. M., Barrie, N., Gopal, V., Hillis, G. S., Chow, C. K. & Schlaich, M. P., Feb 2022, In: Computer Methods and Programs in Biomedicine. 214, 106588.
Research output: Contribution to journal › Article › peer-review
3 Citations (Scopus)

Cite this

@phdthesis{70119a1d4a534990a397bfc913109df9,

title = "Data science and cardiovascular risk",

abstract = "Projects investigating cardiovascular risk associated with hypertension, sympathetic nervous activity and metabolic risk factors were analysed by a range of Data Scientific means. In Part I of the thesis, biostatistical methods were implemented and statistical inference reported as part of several projects. In Part II, automated data and signal extraction, processing, labelling and utilisation was investigated and adequate tools developed. Part III describes the utilisation of machine learning models in a clinical context for the diagnosis of a cardiometabolic condition. In conclusion, the vast range of data scientific approaches in an increasingly digitally transformed scientific landscape became overt.",

keywords = "Data Science, Machine Learning, Hypertension, Cardiovascular Risk, Biostatistics",

author = "Nolde, {Janis Marc}",

year = "2022",

doi = "10.26182/khc9-3f24",

language = "English",

school = "The University of Western Australia",

}

TY - BOOK

T1 - Data science and cardiovascular risk

AU - Nolde, Janis Marc

PY - 2022

Y1 - 2022

N2 - Projects investigating cardiovascular risk associated with hypertension, sympathetic nervous activity and metabolic risk factors were analysed by a range of Data Scientific means. In Part I of the thesis, biostatistical methods were implemented and statistical inference reported as part of several projects. In Part II, automated data and signal extraction, processing, labelling and utilisation was investigated and adequate tools developed. Part III describes the utilisation of machine learning models in a clinical context for the diagnosis of a cardiometabolic condition. In conclusion, the vast range of data scientific approaches in an increasingly digitally transformed scientific landscape became overt.

AB - Projects investigating cardiovascular risk associated with hypertension, sympathetic nervous activity and metabolic risk factors were analysed by a range of Data Scientific means. In Part I of the thesis, biostatistical methods were implemented and statistical inference reported as part of several projects. In Part II, automated data and signal extraction, processing, labelling and utilisation was investigated and adequate tools developed. Part III describes the utilisation of machine learning models in a clinical context for the diagnosis of a cardiometabolic condition. In conclusion, the vast range of data scientific approaches in an increasingly digitally transformed scientific landscape became overt.

KW - Data Science

KW - Machine Learning

KW - Hypertension

KW - Cardiovascular Risk

KW - Biostatistics

U2 - 10.26182/khc9-3f24

DO - 10.26182/khc9-3f24

M3 - Doctoral Thesis

ER -

Data science and cardiovascular risk

Abstract

Access to Document

Fingerprint

Research output

Catheter-Based Renal Denervation: 9-Year Follow-Up Data on Safety and Blood Pressure Reduction in Patients with Resistant Hypertension

Autoencoded deep features for semi-automatic, weakly supervised physiological signal labelling

Automatic data extraction from 24 hour blood pressure measurement reports of a large multicenter clinical trial

Cite this