國立虎尾科技大學 |

Generalizable Risk Predictive Deep Learning Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Generalizable Risk Predictive Deep Learning Models./
作者:	Amrollahi, Fatemeh.
面頁冊數:	1 online resource (109 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-07, Section: A.
Contained By:	Dissertations Abstracts International85-07A.
標題:	Information science. -
電子資源:	click for full text (PQDT)
ISBN:	9798381426465

Generalizable Risk Predictive Deep Learning Models.
Amrollahi, Fatemeh.

Generalizable Risk Predictive Deep Learning Models. - 1 online resource (109 pages)

Source: Dissertations Abstracts International, Volume: 85-07, Section: A.

Thesis (Ph.D.)--University of California, San Diego, 2023.

Includes bibliographical references

The broad adoption of Electronic Health Records (EHRs) accelerated the development and usage of Machine learning (ML) and Deep learning (DL) algorithms in clinical settings. The potential uses of ML and DL algorithms to augment clinical decision-making in domains such as forecasting disease onset and progression, predicting response to treatments, and optimization of treatment protocols are growing. While most existing ML/DL models are trained on single-centered data, multi-center datasets are becoming increasingly available. However, curation of such datasets is often time-consuming and lags behind shifts in disease prevalence and changes in workflow practices, which are known to cause data distribution shifts and degradation in ML/DL model performance.In addition, data privacy concerns and patient confidentiality regulations continue to pose a major barrier to multicenter EHR data access. In this work, we developed algorithms to enable DL models to transfer their knowledge across institutional boundaries and learn from new episodes of patient care without forgetting previously learned patterns. We validated and compared our methods in the context of early prediction of sepsis using data across four geographically distinct healthcare systems. We explore several methods to enhance the generalizability of DL models. We focus on three areas: Continual Learning, Federated Learning, and Generative Adversarial Networks (GANs), introducing new algorithms within each area and comparing their performance against state-of-the-art models. We have validated and compared these methods in one of the most challenging tasks for biomedical researchers: predicting the onset of sepsis in intensive care units.

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

Mode of access: World Wide Web

ISBN: 9798381426465Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

Continual LearningIndex Terms--Genre/Form:

554714
Electronic books.

Generalizable Risk Predictive Deep Learning Models.
LDR:03045ntm a22003737 4500 001 1147346
005 20240909100803.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381426465
035 $a (MiAaPQ)AAI30818863
035 $a AAI30818863
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Amrollahi, Fatemeh. $3 1473051
245 1 0 $a Generalizable Risk Predictive Deep Learning Models.
264 0 $c 2023
300 $a 1 online resource (109 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: 85-07, Section: A.
500 $a Advisor: Nemati, Shamim.
502 $a Thesis (Ph.D.)--University of California, San Diego, 2023.
504 $a Includes bibliographical references
520 $a The broad adoption of Electronic Health Records (EHRs) accelerated the development and usage of Machine learning (ML) and Deep learning (DL) algorithms in clinical settings. The potential uses of ML and DL algorithms to augment clinical decision-making in domains such as forecasting disease onset and progression, predicting response to treatments, and optimization of treatment protocols are growing. While most existing ML/DL models are trained on single-centered data, multi-center datasets are becoming increasingly available. However, curation of such datasets is often time-consuming and lags behind shifts in disease prevalence and changes in workflow practices, which are known to cause data distribution shifts and degradation in ML/DL model performance.In addition, data privacy concerns and patient confidentiality regulations continue to pose a major barrier to multicenter EHR data access. In this work, we developed algorithms to enable DL models to transfer their knowledge across institutional boundaries and learn from new episodes of patient care without forgetting previously learned patterns. We validated and compared our methods in the context of early prediction of sepsis using data across four geographically distinct healthcare systems. We explore several methods to enhance the generalizability of DL models. We focus on three areas: Continual Learning, Federated Learning, and Generative Adversarial Networks (GANs), introducing new algorithms within each area and comparing their performance against state-of-the-art models. We have validated and compared these methods in one of the most challenging tasks for biomedical researchers: predicting the onset of sepsis in intensive care units.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information science. $3 561178
650 4 $a Bioinformatics. $3 583857
653 $a Continual Learning
653 $a Federated Learning
653 $a Generative Adversarial Networks
653 $a Deep learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0715
690 $a 0723
710 2 $a University of California, San Diego. $b Bioinformatics and Systems Biology. $3 1473052
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-07A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30818863 $z click for full text (PQDT)