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

Deep Learning, Multi-Staged Machine ...

Michigan Technological University., Mathematical Sciences.

FindBook

Google Book

Amazon

博客來

Deep Learning, Multi-Staged Machine Learning, and Reinforcement Learning to Improve Cardiac Resynchronization Therapy.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Learning, Multi-Staged Machine Learning, and Reinforcement Learning to Improve Cardiac Resynchronization Therapy./
作者:	Larsen, Kristoffer A.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	65 p.
附註:	Source: Masters Abstracts International, Volume: 85-11.
Contained By:	Masters Abstracts International85-11.
標題:	Statistics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31144640
ISBN:	9798382599960

Deep Learning, Multi-Staged Machine Learning, and Reinforcement Learning to Improve Cardiac Resynchronization Therapy.
Larsen, Kristoffer A.

Deep Learning, Multi-Staged Machine Learning, and Reinforcement Learning to Improve Cardiac Resynchronization Therapy. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 65 p.

Source: Masters Abstracts International, Volume: 85-11.

Thesis (M.S.)--Michigan Technological University, 2024.

In Chapter one, we discussed the clinical background of cardiac resynchronization therapy (CRT) and the current issues towards patient response. Moreover, we considered previous machine learning (ML) and deep learning (DL) methods to improve the decision-making process, both standard supervised learning and multi-stage learning. Finally, we introduced the dataset which will be used in the following Chapters.{A0}In Chapter two, we developed a multi-input fusion DL model which utilizes SPECT MPI polar maps images and tabular data in the form of clinical features, ECG parameters, and derived SPECT MPI parameters. Using transfer learning (TL) to train the image component model via VGG16, while using a standard multilayer perceptron for the tabular component trended towards improve over current guidelines and conventional statistical ML. Additionally, Grad-CAM is employed to provide explainability in the DL model's decision making with respect to the polar map inputs.{A0}In Chapter three, we constructed a multi-stage ML model which splits the CRT decision making process into two stages: 1) Clinical and ECG parameter stage 2) SPECT MPI stage. Using the staged data, the model attempts to form a decision using only the first stage; however, if the uncertainty is too high, the model will then consider the addition of the second stage of data. A multi-stage framework provides more clinical interpretability and a more accurate modeling process for clinicians where multiple sequential decisions are assessed weighing associated costs.{A0}In Chapter four, we created a multi-stage DL model using similar data staging. The model is constructed in two parts: 1) A deep autoencoder which processes the staged data into fixed length data embedding. The second stage data is treated as missing-not-at-random data when at the first initial stage. 2) A deep reinforcement learning (RL) agent works upon the processed embeddings to perform sequential decision making. The RL agent was trained with volumetric differences in blood ejection as a reward to learn the optimal policy to recommend CRT on a per-patient level. The multi-stage DL model is flexible for unstructured inputs, such as images, and can easily introduce domain specific knowledge in the form of rewards.{A0}

ISBN: 9798382599960Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Cardiac resynchronization therapy

Deep Learning, Multi-Staged Machine Learning, and Reinforcement Learning to Improve Cardiac Resynchronization Therapy.
LDR:03477nmm a2200385 4500 001 2398584
005 20240812064712.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798382599960
035 $a (MiAaPQ)AAI31144640
035 $a AAI31144640
040 $a MiAaPQ $c MiAaPQ
100 1 $a Larsen, Kristoffer A. $3 3768502
245 1 0 $a Deep Learning, Multi-Staged Machine Learning, and Reinforcement Learning to Improve Cardiac Resynchronization Therapy.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 65 p.
500 $a Source: Masters Abstracts International, Volume: 85-11.
500 $a Advisor: Sha, Qiuying;Zhou, Weihua.
502 $a Thesis (M.S.)--Michigan Technological University, 2024.
520 $a In Chapter one, we discussed the clinical background of cardiac resynchronization therapy (CRT) and the current issues towards patient response. Moreover, we considered previous machine learning (ML) and deep learning (DL) methods to improve the decision-making process, both standard supervised learning and multi-stage learning. Finally, we introduced the dataset which will be used in the following Chapters.{A0}In Chapter two, we developed a multi-input fusion DL model which utilizes SPECT MPI polar maps images and tabular data in the form of clinical features, ECG parameters, and derived SPECT MPI parameters. Using transfer learning (TL) to train the image component model via VGG16, while using a standard multilayer perceptron for the tabular component trended towards improve over current guidelines and conventional statistical ML. Additionally, Grad-CAM is employed to provide explainability in the DL model's decision making with respect to the polar map inputs.{A0}In Chapter three, we constructed a multi-stage ML model which splits the CRT decision making process into two stages: 1) Clinical and ECG parameter stage 2) SPECT MPI stage. Using the staged data, the model attempts to form a decision using only the first stage; however, if the uncertainty is too high, the model will then consider the addition of the second stage of data. A multi-stage framework provides more clinical interpretability and a more accurate modeling process for clinicians where multiple sequential decisions are assessed weighing associated costs.{A0}In Chapter four, we created a multi-stage DL model using similar data staging. The model is constructed in two parts: 1) A deep autoencoder which processes the staged data into fixed length data embedding. The second stage data is treated as missing-not-at-random data when at the first initial stage. 2) A deep reinforcement learning (RL) agent works upon the processed embeddings to perform sequential decision making. The RL agent was trained with volumetric differences in blood ejection as a reward to learn the optimal policy to recommend CRT on a per-patient level. The multi-stage DL model is flexible for unstructured inputs, such as images, and can easily introduce domain specific knowledge in the form of rewards.{A0}
590 $a School code: 0129.
650 4 $a Statistics. $3 517247
650 4 $a Therapy. $3 3343697
653 $a Cardiac resynchronization therapy
653 $a Deep learning
653 $a Machine learning
653 $a Multi-stage learning
653 $a SPECT MPI
690 $a 0463
690 $a 0212
690 $a 0800
710 2 $a Michigan Technological University. $b Mathematical Sciences. $3 2096669
773 0 $t Masters Abstracts International $g 85-11.
790 $a 0129
791 $a M.S.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31144640