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

An ensemble approach to predicting h...

Nilles, Ester Kim.

FindBook

Google Book

Amazon

博客來

An ensemble approach to predicting health outcomes.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	An ensemble approach to predicting health outcomes./
作者:	Nilles, Ester Kim.
面頁冊數:	95 p.
附註:	Source: Dissertation Abstracts International, Volume: 75-01(E), Section: B.
Contained By:	Dissertation Abstracts International75-01B(E).
標題:	Biostatistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3596551
ISBN:	9781303433580

An ensemble approach to predicting health outcomes.
Nilles, Ester Kim.

An ensemble approach to predicting health outcomes. - 95 p.

Source: Dissertation Abstracts International, Volume: 75-01(E), Section: B.

Thesis (Ph.D.)--The Florida State University, 2013.

Heart disease and premature birth continue to be the leading cause of mortality and neonatal mortality in large parts of the world. They are also estimated to have the highest medical expenditures in the United States. Early detection of heart disease incidence plays a critical role in preserving heart health, and identifying pregnancies at high risk of premature birth is highly valuable information for early interventions. The past few decades, identification of patients at high health risk have been based on logistic regression or Cox proportional hazards models. In more recent years, machine learning models have grown in popularity within the medical field for their superior predictive and classification performances over the classical statistical models. However, their performances in heart disease and premature birth predictions have been comparable and inconclusive, leaving the question of which model most accurately reflects the data difficult to resolve.

ISBN: 9781303433580Subjects--Topical Terms:

1002712
Biostatistics.

An ensemble approach to predicting health outcomes.
LDR:02941nmm a2200313 4500 001 2070193
005 20160531113957.5
008 170521s2013 ||||||||||||||||| ||eng d
020 $a 9781303433580
035 $a (MiAaPQ)AAI3596551
035 $a AAI3596551
040 $a MiAaPQ $c MiAaPQ
100 1 $a Nilles, Ester Kim. $3 3185232
245 1 3 $a An ensemble approach to predicting health outcomes.
300 $a 95 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-01(E), Section: B.
500 $a Advisers: Dan McGee; Jinfeng Zhang.
502 $a Thesis (Ph.D.)--The Florida State University, 2013.
520 $a Heart disease and premature birth continue to be the leading cause of mortality and neonatal mortality in large parts of the world. They are also estimated to have the highest medical expenditures in the United States. Early detection of heart disease incidence plays a critical role in preserving heart health, and identifying pregnancies at high risk of premature birth is highly valuable information for early interventions. The past few decades, identification of patients at high health risk have been based on logistic regression or Cox proportional hazards models. In more recent years, machine learning models have grown in popularity within the medical field for their superior predictive and classification performances over the classical statistical models. However, their performances in heart disease and premature birth predictions have been comparable and inconclusive, leaving the question of which model most accurately reflects the data difficult to resolve.
520 $a Our aim is to incorporate information learned by different models into one final model that will generate superior predictive performances. We first compare the widely used machine learning models---the multilayer perceptron network, k-nearest neighbor and support vector machine---to the statistical models logistic regression and Cox proportional hazards. Then the individual models are combined into one in an ensemble approach, also referred to as ensemble modeling. The proposed approaches include SSE-weighted, AUC-weighted, logistic and flexible naive Bayes.
520 $a The individual models are unique and capture different aspects of the data, but as expected, no individual one outperforms any other. The ensemble approach is an easily computed method that eliminates the need to select one model, integrates the strengths of different models, and generates optimal performances. Particularly in cases where the risk factors associated to an outcome are elusive, such as in premature birth, the ensemble models significantly improve their prediction.
590 $a School code: 0071.
650 4 $a Biostatistics. $3 1002712
650 4 $a Statistics. $3 517247
650 4 $a Public health. $3 534748
690 $a 0308
690 $a 0463
690 $a 0573
710 2 $a The Florida State University. $b Statistics. $3 3185231
773 0 $t Dissertation Abstracts International $g 75-01B(E).
790 $a 0071
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3596551