東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Advancing Temporal Modeling and Hete...

Meng, Yiwen.

Linked to FindBook

Google Book

Amazon

博客來

Advancing Temporal Modeling and Heterogeneous Data Analysis for Digital Health.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Advancing Temporal Modeling and Heterogeneous Data Analysis for Digital Health./
Author:	Meng, Yiwen.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	153 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-06, Section: B.
Contained By:	Dissertations Abstracts International82-06B.
Subject:	Bioengineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28258218
ISBN:	9798698588030

Advancing Temporal Modeling and Heterogeneous Data Analysis for Digital Health.
Meng, Yiwen.

Advancing Temporal Modeling and Heterogeneous Data Analysis for Digital Health. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 153 p.

Source: Dissertations Abstracts International, Volume: 82-06, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2020.

This item must not be sold to any third party vendors.

Recent development in electronic medical devices or systems has realized the effective collection and documentation of patients' health in real time. To date, the potential clinical impact of this healthcare data has not been fully realized. Specifically, patients' health data is heterogenous and sparse in nature, as it is composed of various modalities and is collected on different scales. In addition, processing this data efficiently in a temporal manner to take advantage of its sequential structure remains a barrier for medical records. This dissertation attempts to overcome these challenges by developing machine learning models to classify patient reported outcome (PRO) scores from activity tracker data and predict depression diagnoses based on data from patients' historical electronic health records (EHR). A temporal model based on hidden Markov models (HMM) is first proposed to classify PRO scores in various categories from human vital signs collected from Fitbit activity trackers. This approach is able to combine various vital signs on difference scales in a single model that tracks changes in PRO scores over time. Second, several end-to-end machine learning models were built to aggregate multimodal EHR data in a single model. A novel hierarchical embedding method achieved superior performance for predicting depression diagnosis, which lays a foundation for addressing the heterogeneity and sparsity of EHR data. Third, an innovative bidirectional sequence learning model with a transformer architecture was developed for representation learning on high dimensional EHR data, demonstrating significantly improved performance over the traditional forward-only method. Finally, methods to improve the interpretability of the aforementioned models have been developed, which is a critical step before clinical deployment. Relative feature importance factors are determined for each vital sign collected from the Fitbit and attention weights are found for each data modality in the sequential EHR data. Extensive experiments and results have demonstrated the effectiveness of these proposed methods. This dissertation provides methodologies that advance modeling and understanding of digital health datasets, which lays the foundation to construct clinical decision support systems in this domain which could potentially lead to early disease detection and intervention.

ISBN: 9798698588030Subjects--Topical Terms:

657580
Bioengineering.
Subjects--Index Terms:

Deep learning

Advancing Temporal Modeling and Heterogeneous Data Analysis for Digital Health.
LDR:03788nmm a2200445 4500 001 2278448
005 20210628075030.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798698588030
035 $a (MiAaPQ)AAI28258218
035 $a AAI28258218
040 $a MiAaPQ $c MiAaPQ
100 1 $a Meng, Yiwen. $3 3556823
245 1 0 $a Advancing Temporal Modeling and Heterogeneous Data Analysis for Digital Health.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 153 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-06, Section: B.
500 $a Advisor: Arnold, Corey W.;Speier, William F.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Recent development in electronic medical devices or systems has realized the effective collection and documentation of patients' health in real time. To date, the potential clinical impact of this healthcare data has not been fully realized. Specifically, patients' health data is heterogenous and sparse in nature, as it is composed of various modalities and is collected on different scales. In addition, processing this data efficiently in a temporal manner to take advantage of its sequential structure remains a barrier for medical records. This dissertation attempts to overcome these challenges by developing machine learning models to classify patient reported outcome (PRO) scores from activity tracker data and predict depression diagnoses based on data from patients' historical electronic health records (EHR). A temporal model based on hidden Markov models (HMM) is first proposed to classify PRO scores in various categories from human vital signs collected from Fitbit activity trackers. This approach is able to combine various vital signs on difference scales in a single model that tracks changes in PRO scores over time. Second, several end-to-end machine learning models were built to aggregate multimodal EHR data in a single model. A novel hierarchical embedding method achieved superior performance for predicting depression diagnosis, which lays a foundation for addressing the heterogeneity and sparsity of EHR data. Third, an innovative bidirectional sequence learning model with a transformer architecture was developed for representation learning on high dimensional EHR data, demonstrating significantly improved performance over the traditional forward-only method. Finally, methods to improve the interpretability of the aforementioned models have been developed, which is a critical step before clinical deployment. Relative feature importance factors are determined for each vital sign collected from the Fitbit and attention weights are found for each data modality in the sequential EHR data. Extensive experiments and results have demonstrated the effectiveness of these proposed methods. This dissertation provides methodologies that advance modeling and understanding of digital health datasets, which lays the foundation to construct clinical decision support systems in this domain which could potentially lead to early disease detection and intervention.
590 $a School code: 0031.
650 4 $a Bioengineering. $3 657580
650 4 $a Bioinformatics. $3 553671
650 4 $a Public health. $3 534748
650 4 $a Information technology. $3 532993
650 4 $a Health care management. $3 2122906
653 $a Deep learning
653 $a Digital health
653 $a Electronic health records
653 $a Machine learning
653 $a Temporal modeling
653 $a Fitbit activity trackers
653 $a Depression
653 $a Early disease detection
653 $a Disease intervention
690 $a 0202
690 $a 0715
690 $a 0489
690 $a 0769
690 $a 0573
710 2 $a University of California, Los Angeles. $b Biomedical Engineering 0289. $3 2098711
773 0 $t Dissertations Abstracts International $g 82-06B.
790 $a 0031
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28258218