東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Development and Applications of Topological Data Analysis for Biomedicine.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Development and Applications of Topological Data Analysis for Biomedicine./
作者:	Skaf, Yara.
面頁冊數:	1 online resource (157 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
標題:	Mathematics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30417803click for full text (PQDT)
ISBN:	9798379752989

Development and Applications of Topological Data Analysis for Biomedicine.
Skaf, Yara.

Development and Applications of Topological Data Analysis for Biomedicine. - 1 online resource (157 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--University of Florida, 2023.

Includes bibliographical references

Thousands of clinical factors define a unique phenotype for each patient, all of which contribute to the prognosis of that patient in different ways. This makes the problem of anticipating and altering the clinical course of individual patients a challenging one for healthcare professionals and computational algorithms alike, despite modern advances in medical care and predictive modeling. An improved ability to make such inferences would be of particular value in the setting of critical care, where patients tend to be complex, clinical course may shift rapidly, and timely intervention can be life-saving. Topological data analysis (TDA) is an approach uniquely suited to address this challenge. Grounded in the field of topology, a mathematical study of shape and connectivity, TDA accounts for properties limited to local subgroups within data more effectively than standard techniques. In conjunction with patient-level data sets, TDA could potentially facilitate construction of "patient-centered" models that are tailored to the unique behavior of phenotypic subpopulations. Despite its widespread use within the mathematical community and growing applications outside of it, including within the biomedical research community for disease subtyping, its potential for analysis of healthcare data remains largely unexplored.In this dissertation work, we aim to develop and demonstrate the potential of novel TDA tools for modeling patient populations in the setting of clinical applications, specifically in the context of COVID-19 outcomes prediction. Our central hypothesis is that topological modeling methods can provide additional insight into complex biomedical data that could not be gleaned through standard techniques alone. To test this hypothesis, we use a TDA algorithm called Mapper to build models of a population of COVID-19 patients using an electronic health records (EHR) data set on which preliminary analyses have identified several disparities that could benefit from further investigation by alternative methods. After implementing a number of modifications to the Mapper algorithm to adapt it for use on this type of data, we use this topological approach to conduct population-level exploratory analyses with an emphasis on identifying predictors of severe disease and characterizing phenotypic subtypes at increased risk of adverse outcomes such as major adverse cardiovascular events (MACE), mechanical ventilation, and death.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379752989Subjects--Topical Terms:

515831
Mathematics.
Subjects--Index Terms:

Electronic-health-recordsIndex Terms--Genre/Form:

542853
Electronic books.

Development and Applications of Topological Data Analysis for Biomedicine.
LDR:03857nmm a2200397K 4500 001 2361074
005 20231024102925.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379752989
035 $a (MiAaPQ)AAI30417803
035 $a AAI30417803
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Skaf, Yara. $3 3701725
245 1 0 $a Development and Applications of Topological Data Analysis for Biomedicine.
264 0 $c 2023
300 $a 1 online resource (157 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: 84-12, Section: B.
500 $a Advisor: Laubenbacher, Reinhard.
502 $a Thesis (Ph.D.)--University of Florida, 2023.
504 $a Includes bibliographical references
520 $a Thousands of clinical factors define a unique phenotype for each patient, all of which contribute to the prognosis of that patient in different ways. This makes the problem of anticipating and altering the clinical course of individual patients a challenging one for healthcare professionals and computational algorithms alike, despite modern advances in medical care and predictive modeling. An improved ability to make such inferences would be of particular value in the setting of critical care, where patients tend to be complex, clinical course may shift rapidly, and timely intervention can be life-saving. Topological data analysis (TDA) is an approach uniquely suited to address this challenge. Grounded in the field of topology, a mathematical study of shape and connectivity, TDA accounts for properties limited to local subgroups within data more effectively than standard techniques. In conjunction with patient-level data sets, TDA could potentially facilitate construction of "patient-centered" models that are tailored to the unique behavior of phenotypic subpopulations. Despite its widespread use within the mathematical community and growing applications outside of it, including within the biomedical research community for disease subtyping, its potential for analysis of healthcare data remains largely unexplored.In this dissertation work, we aim to develop and demonstrate the potential of novel TDA tools for modeling patient populations in the setting of clinical applications, specifically in the context of COVID-19 outcomes prediction. Our central hypothesis is that topological modeling methods can provide additional insight into complex biomedical data that could not be gleaned through standard techniques alone. To test this hypothesis, we use a TDA algorithm called Mapper to build models of a population of COVID-19 patients using an electronic health records (EHR) data set on which preliminary analyses have identified several disparities that could benefit from further investigation by alternative methods. After implementing a number of modifications to the Mapper algorithm to adapt it for use on this type of data, we use this topological approach to conduct population-level exploratory analyses with an emphasis on identifying predictors of severe disease and characterizing phenotypic subtypes at increased risk of adverse outcomes such as major adverse cardiovascular events (MACE), mechanical ventilation, and death.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Mathematics. $3 515831
650 4 $a Medicine. $3 641104
650 4 $a Bioinformatics. $3 553671
653 $a Electronic-health-records
653 $a Landmark-sampling
653 $a Mapper
653 $a Mathematical-modeling
653 $a Topological-data-analysis
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0405
690 $a 0564
690 $a 0715
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Florida. $b Mathematics. $3 3343201
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30417803 $z click for full text (PQDT)