東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Risk Prediction and Calibration with...

Ahuja, Yuri Vital.

Linked to FindBook

Google Book

Amazon

博客來

Risk Prediction and Calibration with Weak Supervision Using the Electronic Health Record.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Risk Prediction and Calibration with Weak Supervision Using the Electronic Health Record./
Author:	Ahuja, Yuri Vital.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	91 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-09, Section: B.
Contained By:	Dissertations Abstracts International82-09B.
Subject:	Bioinformatics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28262594
ISBN:	9798582570752

Risk Prediction and Calibration with Weak Supervision Using the Electronic Health Record.
Ahuja, Yuri Vital.

Risk Prediction and Calibration with Weak Supervision Using the Electronic Health Record. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 91 p.

Source: Dissertations Abstracts International, Volume: 82-09, Section: B.

Thesis (Ph.D.)--Harvard University, 2021.

This item must not be sold to any third party vendors.

Electronic health records (EHRs) promise unprecedented opportunities for in silico clinical and translational discovery ranging from disease risk prediction to survival analysis. However, the scarcity of reliable labels for many phenotypes has hampered efforts to effectively harness the EHR for these objectives. Many studies circumvent this problem via either chart review or rule-based electronic phenotyping, both of which necessitate significant expert labor. This problem is exacerbated when interest lies in phenotype event times - perhaps to evaluate the effect of a treatment decision on time to relapse. In this case, chart review involves reviewing potentially hundreds of notes over the course of a patient's record. Moreover, devising rules to ascertain the time of an event is far more complicated than determining the presence of a binary phenotype. When chart review and rule-based phenotyping are infeasible, studies often utilize billing codes such as International Classification of Diseases (ICD) codes as surrogates for true phenotype labels. However, many diseases tend to have imprecise codes that can bias or de-power the downstream study. Even when codes are reliable disease proxies, they often exhibit systematic temporal biases that hinder their use as event time surrogates. Thus, there is an ongoing need for reliable algorithms that can both identify the presence of a phenotype and estimate its temporal course using limited supervision.In chapter 1, we introduce surrogate-guided ensemble LDA (sureLDA), a weakly supervised phenotyping method that predicts binary patient-level phenotypes from EHR data without using any manual "gold-standard" labels. It accomplishes this by initializing priors for the target phenotypes using phenotype surrogate features, and then using these priors to guide the unsupervised topic modeling method Latent Dirichlet Allocation (LDA).In chapter 2, we introduce Semi-supervised Adaptive Markov Gaussian Embedding Process (SAMGEP), a semi-supervised method that predicts phenotype event times using EHR data and a limited number of gold-standard phenotype labels. It does so by mapping EHR features to embedding vectors, inferring from these patient-level embeddings, and fitting to these latter embeddings a Gaussian Process mixture model wherein the phenotype state follows a discretized Markov Process.Finally, in chapter 3 we introduce Semi-supervised Calibration of Risk with Noisy Event Times (SCORNET), a consistent, semi-supervised survival function estimator that calibrates the risk predictions of sureLDA, SAMGEP, and other phenotyping algorithms using a limited set of easy-to-compile current status labels. SCORNET effectively leverages weakly supervised risk predictors like sureLDA and SAMGEP to maximize efficient use of limited labeling resources for marginal survival estimation.

ISBN: 9798582570752Subjects--Topical Terms:

553671
Bioinformatics.
Subjects--Index Terms:

Electronic health record

Risk Prediction and Calibration with Weak Supervision Using the Electronic Health Record.
LDR:04078nmm a2200385 4500 001 2281974
005 20210927083509.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798582570752
035 $a (MiAaPQ)AAI28262594
035 $a AAI28262594
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ahuja, Yuri Vital. $0 (orcid)0000-0002-8528-0421 $3 3560689
245 1 0 $a Risk Prediction and Calibration with Weak Supervision Using the Electronic Health Record.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 91 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-09, Section: B.
500 $a Advisor: Cai, Tianxi.
502 $a Thesis (Ph.D.)--Harvard University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Electronic health records (EHRs) promise unprecedented opportunities for in silico clinical and translational discovery ranging from disease risk prediction to survival analysis. However, the scarcity of reliable labels for many phenotypes has hampered efforts to effectively harness the EHR for these objectives. Many studies circumvent this problem via either chart review or rule-based electronic phenotyping, both of which necessitate significant expert labor. This problem is exacerbated when interest lies in phenotype event times - perhaps to evaluate the effect of a treatment decision on time to relapse. In this case, chart review involves reviewing potentially hundreds of notes over the course of a patient's record. Moreover, devising rules to ascertain the time of an event is far more complicated than determining the presence of a binary phenotype. When chart review and rule-based phenotyping are infeasible, studies often utilize billing codes such as International Classification of Diseases (ICD) codes as surrogates for true phenotype labels. However, many diseases tend to have imprecise codes that can bias or de-power the downstream study. Even when codes are reliable disease proxies, they often exhibit systematic temporal biases that hinder their use as event time surrogates. Thus, there is an ongoing need for reliable algorithms that can both identify the presence of a phenotype and estimate its temporal course using limited supervision.In chapter 1, we introduce surrogate-guided ensemble LDA (sureLDA), a weakly supervised phenotyping method that predicts binary patient-level phenotypes from EHR data without using any manual "gold-standard" labels. It accomplishes this by initializing priors for the target phenotypes using phenotype surrogate features, and then using these priors to guide the unsupervised topic modeling method Latent Dirichlet Allocation (LDA).In chapter 2, we introduce Semi-supervised Adaptive Markov Gaussian Embedding Process (SAMGEP), a semi-supervised method that predicts phenotype event times using EHR data and a limited number of gold-standard phenotype labels. It does so by mapping EHR features to embedding vectors, inferring from these patient-level embeddings, and fitting to these latter embeddings a Gaussian Process mixture model wherein the phenotype state follows a discretized Markov Process.Finally, in chapter 3 we introduce Semi-supervised Calibration of Risk with Noisy Event Times (SCORNET), a consistent, semi-supervised survival function estimator that calibrates the risk predictions of sureLDA, SAMGEP, and other phenotyping algorithms using a limited set of easy-to-compile current status labels. SCORNET effectively leverages weakly supervised risk predictors like sureLDA and SAMGEP to maximize efficient use of limited labeling resources for marginal survival estimation.
590 $a School code: 0084.
650 4 $a Bioinformatics. $3 553671
650 4 $a Biostatistics. $3 1002712
650 4 $a Information technology. $3 532993
653 $a Electronic health record
653 $a Phenotype prediction
653 $a Phenotyping
653 $a Risk estimation
653 $a Semi-supervised learning
653 $a Survival analysis
690 $a 0715
690 $a 0308
690 $a 0489
710 2 $a Harvard University. $b Biostatistics. $3 2104931
773 0 $t Dissertations Abstracts International $g 82-09B.
790 $a 0084
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28262594