國立虎尾科技大學 |

Methods and Systems for Targeted Evaluations of Clinical Machine Learning Models on the Deployment Population.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Methods and Systems for Targeted Evaluations of Clinical Machine Learning Models on the Deployment Population./
Author:	Corbin, Conor Kirkham.
Description:	1 online resource (159 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: A.
Contained By:	Dissertations Abstracts International85-11A.
Subject:	Infections. -
Online resource:	click for full text (PQDT)
ISBN:	9798382646435

Methods and Systems for Targeted Evaluations of Clinical Machine Learning Models on the Deployment Population.
Corbin, Conor Kirkham.

Methods and Systems for Targeted Evaluations of Clinical Machine Learning Models on the Deployment Population. - 1 online resource (159 pages)

Source: Dissertations Abstracts International, Volume: 85-11, Section: A.

Thesis (Ph.D.)--Stanford University, 2023.

Includes bibliographical references

The development of clinical machine learning applications frequently follows a sequential path from ideation to deployment - where each step is only considered after completion of the prior. A common consequence is that the distribution of data used to validate a model and permit eventual translation (the evaluation population) fails to reflect the distribution of data on which the model is served (the deployment population). In this dissertation I discuss methods and systems for enabling targeted evaluations of clinical machine learning models on the deployment population. I detail the implications of label selection (censoring) on the evaluation of binary classifiers, showing that traditional weighted estimators from causal inference literature recover performance over the deployment population when selection probabilities are properly specified. I emphasize the importance of silent prospective evaluations of machine learning models to appraise performance in the intended production environment. Silent trial evaluations require integrated deployment infrastructure with modern electronic medical record vendors - for which I develop and blueprint. I finally discuss the implications of feedback effects, where use of deployed models induce differences between the deployment population and the population that is prospectively observed. I provide a taxonomy of feedback effects, and recommend feedback aware model monitoring strategies. Instead of following a linear path from model ideation, to development and eventual deployment, researchers and machine learning practitioners should first consider the deployment population,and use it to contextualize model development and evaluation throughout its entire life-cycle.

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

Mode of access: World Wide Web

ISBN: 9798382646435Subjects--Topical Terms:

882242
Infections.
Index Terms--Genre/Form:

554714
Electronic books.

Methods and Systems for Targeted Evaluations of Clinical Machine Learning Models on the Deployment Population.
LDR:03129ntm a22004097 4500 001 1151209
005 20241104055828.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798382646435
035 $a (MiAaPQ)AAI31049662
035 $a (MiAaPQ)STANFORDhg979cs4589
035 $a AAI31049662
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Corbin, Conor Kirkham. $3 1477932
245 1 0 $a Methods and Systems for Targeted Evaluations of Clinical Machine Learning Models on the Deployment Population.
264 0 $c 2023
300 $a 1 online resource (159 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: 85-11, Section: A.
500 $a Advisor: Chen, Jonathan.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
504 $a Includes bibliographical references
520 $a The development of clinical machine learning applications frequently follows a sequential path from ideation to deployment - where each step is only considered after completion of the prior. A common consequence is that the distribution of data used to validate a model and permit eventual translation (the evaluation population) fails to reflect the distribution of data on which the model is served (the deployment population). In this dissertation I discuss methods and systems for enabling targeted evaluations of clinical machine learning models on the deployment population. I detail the implications of label selection (censoring) on the evaluation of binary classifiers, showing that traditional weighted estimators from causal inference literature recover performance over the deployment population when selection probabilities are properly specified. I emphasize the importance of silent prospective evaluations of machine learning models to appraise performance in the intended production environment. Silent trial evaluations require integrated deployment infrastructure with modern electronic medical record vendors - for which I develop and blueprint. I finally discuss the implications of feedback effects, where use of deployed models induce differences between the deployment population and the population that is prospectively observed. I provide a taxonomy of feedback effects, and recommend feedback aware model monitoring strategies. Instead of following a linear path from model ideation, to development and eventual deployment, researchers and machine learning practitioners should first consider the deployment population,and use it to contextualize model development and evaluation throughout its entire life-cycle.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Infections. $3 882242
650 4 $a Medical records. $3 683485
650 4 $a Patients. $3 963142
650 4 $a Electronic health records. $3 1467061
650 4 $a Hemoglobin. $3 647413
650 4 $a Sensitivity analysis. $3 1465552
650 4 $a Demographics. $3 1004800
650 4 $a Antibiotics. $3 582863
650 4 $a Leukocytes. $3 1477933
650 4 $a Medical research. $2 bicssc $3 809476
650 4 $a Linear programming. $3 528157
650 4 $a Potassium. $3 1372559
650 4 $a Blood. $3 790457
650 4 $a Creatinine. $3 1045778
650 4 $a Demography. $3 527764
650 4 $a Information science. $3 561178
650 4 $a Medicine. $3 644133
650 4 $a Pharmaceutical sciences. $3 1180569
650 4 $a Sociology. $3 551705
650 4 $a Statistics. $3 556824
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0938
690 $a 0769
690 $a 0723
690 $a 0564
690 $a 0572
690 $a 0626
690 $a 0463
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stanford University. $3 1184533
773 0 $t Dissertations Abstracts International $g 85-11A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31049662 $z click for full text (PQDT)