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

Data Driven Models in Time Series He...

He, Rosemary Yuan,

Linked to FindBook

Google Book

Amazon

博客來

Data Driven Models in Time Series Health Records and Medical Imaging /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Data Driven Models in Time Series Health Records and Medical Imaging // Rosemary Yuan He.
Author:	He, Rosemary Yuan,
Description:	1 electronic resource (142 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
Contained By:	Dissertations Abstracts International86-11B.
Subject:	Neurosciences. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32041535
ISBN:	9798315742166

Data Driven Models in Time Series Health Records and Medical Imaging /
He, Rosemary Yuan,

Data Driven Models in Time Series Health Records and Medical Imaging /Rosemary Yuan He. - 1 electronic resource (142 pages)

Source: Dissertations Abstracts International, Volume: 86-11, Section: B.

With a large increase in the adoption of electronic health records, researchers have access to an unprecedented amount of health data on a patient-specific level, ranging from vitals every hour to medical images over a decade. Among these, time series data have been of particular interest to researchers as it is informative of disease progression, but difficult to model as its underlying distribution can be highly complex. On the other hand, machine learning models have been adopted across a wide range of tasks due to their ability to model non-linear relationships, rapid growth in computational power and decline in cost. However, machine learning applications in medical datasets face a set of unique challenges that decrease robustness and performance in off-the-shelf methods. As such, developing domain-specific algorithms to address these difficulties and improve model performance becomes crucial in successfully building and deploying these models in healthcare. In this dissertation, I describe my work in developing machine learning and generative AI methods for prediction, forecasting, and generative modeling specifically in the medical domain, using time series structured clinical data and longitudinal 3D medical images.

English

ISBN: 9798315742166Subjects--Topical Terms:

588700
Neurosciences.
Subjects--Index Terms:

Alzheimer's disease

Data Driven Models in Time Series Health Records and Medical Imaging /
LDR:02789nmm a22004573i 4500 001 2435700
005 20251009122916.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798315742166
035 $a (MiAaPQD)AAI32041535
035 $a AAI32041535
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a He, Rosemary Yuan, $e author. $3 3826092
245 1 0 $a Data Driven Models in Time Series Health Records and Medical Imaging / $c Rosemary Yuan He.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (142 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
500 $a Advisors: Eskin, Eleazar; Tward, Daniel Committee members: Chiang, Jeffrey N.; Zhou, Bolei; Sankararaman, Sriram.
502 $b Ph.D. $c University of California, Los Angeles $d 2025.
520 $a With a large increase in the adoption of electronic health records, researchers have access to an unprecedented amount of health data on a patient-specific level, ranging from vitals every hour to medical images over a decade. Among these, time series data have been of particular interest to researchers as it is informative of disease progression, but difficult to model as its underlying distribution can be highly complex. On the other hand, machine learning models have been adopted across a wide range of tasks due to their ability to model non-linear relationships, rapid growth in computational power and decline in cost. However, machine learning applications in medical datasets face a set of unique challenges that decrease robustness and performance in off-the-shelf methods. As such, developing domain-specific algorithms to address these difficulties and improve model performance becomes crucial in successfully building and deploying these models in healthcare. In this dissertation, I describe my work in developing machine learning and generative AI methods for prediction, forecasting, and generative modeling specifically in the medical domain, using time series structured clinical data and longitudinal 3D medical images.
546 $a English
590 $a School code: 0031
650 4 $a Neurosciences. $3 588700
650 4 $a Computer science. $3 523869
650 4 $a Bioinformatics. $3 553671
650 4 $a Medical imaging. $3 3172799
653 $a Alzheimer's disease
653 $a Disease modeling
653 $a Electronic health records
653 $a Generative modeling
690 $a 0800
690 $a 0984
690 $a 0574
690 $a 0317
690 $a 0715
710 2 $a University of California, Los Angeles. $b Computer Science 0201. $e degree granting institution. $3 3816290
720 1 $a Eskin, Eleazar $e degree supervisor.
720 1 $a Tward, Daniel $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-11B.
790 $a 0031
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32041535