國立虎尾科技大學 |

Uncovering Strategies for Personalized Treatment Selection Using Large Language Models.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Uncovering Strategies for Personalized Treatment Selection Using Large Language Models./
Author:	Miao, Brenda.
Description:	1 online resource (168 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
Contained By:	Dissertations Abstracts International85-12A.
Subject:	Bioinformatics. -
Online resource:	click for full text (PQDT)
ISBN:	9798382813813

Uncovering Strategies for Personalized Treatment Selection Using Large Language Models.
Miao, Brenda.

Uncovering Strategies for Personalized Treatment Selection Using Large Language Models. - 1 online resource (168 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: A.

Thesis (Ph.D.)--University of California, San Francisco, 2024.

Includes bibliographical references

Healthcare data has never been so accessible to patients and physicians, from smartphones and other remote monitoring devices to improved access for patients to their own Electronic Medical Record (EMR) history and clinical notes. Despite the ubiquity of healthcare data collection and distribution, there remains a significant gap in understanding the impacts of this data on clinical care. Insights from these digital health tools and downstream clinical decision-making processes are often only captured in medical notes, which are complex, sparse, unstructured, and difficult to model even with traditional deep learning methods. Only recently have large language models (LLMs) emerged that are capable of zero- or few-shot clinical language, without the need for large, manually annotated datasets. In this dissertation, I develop methods to adapt LLMs to healthcare tasks, particularly for identifying points of actionable insights for both digital and pharmaceutical therapeutics. These approaches demonstrate the ways in which digital health products can impact clinical care, as well as provide methods to identify reasons for medication class switching that consider the complexities of patient care beyond lab values and diagnosis codes. While careful, rigorous research is needed to ensure that these approaches are effective in facilitating patient care improvements and to reduce any potential for harm, the rapid pace of language model development provides an extraordinary opportunity to transform clinical practice. These new methods allow us to take an unprecedented look at the conversations, decisions, and medical expertise captured in billions of clinical notes and other clinical text, and to learn from this shared knowledge to accelerate medical research, improve clinical guidelines, and personalize patient care.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382813813Subjects--Topical Terms:

583857
Bioinformatics.
Subjects--Index Terms:

Clinical text processingIndex Terms--Genre/Form:

554714
Electronic books.

Uncovering Strategies for Personalized Treatment Selection Using Large Language Models.
LDR:03370ntm a22004217 4500 001 1146538
005 20240812064639.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382813813
035 $a (MiAaPQ)AAI31242717
035 $a AAI31242717
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Miao, Brenda. $3 1471941
245 1 0 $a Uncovering Strategies for Personalized Treatment Selection Using Large Language Models.
264 0 $c 2024
300 $a 1 online resource (168 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: 85-12, Section: A.
500 $a Includes supplementary digital materials.
500 $a Advisor: Butte, Atul.
502 $a Thesis (Ph.D.)--University of California, San Francisco, 2024.
504 $a Includes bibliographical references
520 $a Healthcare data has never been so accessible to patients and physicians, from smartphones and other remote monitoring devices to improved access for patients to their own Electronic Medical Record (EMR) history and clinical notes. Despite the ubiquity of healthcare data collection and distribution, there remains a significant gap in understanding the impacts of this data on clinical care. Insights from these digital health tools and downstream clinical decision-making processes are often only captured in medical notes, which are complex, sparse, unstructured, and difficult to model even with traditional deep learning methods. Only recently have large language models (LLMs) emerged that are capable of zero- or few-shot clinical language, without the need for large, manually annotated datasets. In this dissertation, I develop methods to adapt LLMs to healthcare tasks, particularly for identifying points of actionable insights for both digital and pharmaceutical therapeutics. These approaches demonstrate the ways in which digital health products can impact clinical care, as well as provide methods to identify reasons for medication class switching that consider the complexities of patient care beyond lab values and diagnosis codes. While careful, rigorous research is needed to ensure that these approaches are effective in facilitating patient care improvements and to reduce any potential for harm, the rapid pace of language model development provides an extraordinary opportunity to transform clinical practice. These new methods allow us to take an unprecedented look at the conversations, decisions, and medical expertise captured in billions of clinical notes and other clinical text, and to learn from this shared knowledge to accelerate medical research, improve clinical guidelines, and personalize patient care.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Bioinformatics. $3 583857
650 4 $a Computer science. $3 573171
650 4 $a Language. $3 571568
653 $a Clinical text processing
653 $a Large language models
653 $a Treatment strategy optimization
653 $a Electronic Medical Record history
653 $a Deep learning methods
655 7 $a Electronic books. $2 local $3 554714
690 $a 0715
690 $a 0984
690 $a 0679
690 $a 0769
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, San Francisco. $b Biological and Medical Informatics. $3 1193289
773 0 $t Dissertations Abstracts International $g 85-12A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31242717 $z click for full text (PQDT)