國立虎尾科技大學 |

Understanding Cognitive and Psychopathological Variability : = The Role of Individual Differences in Machine Learning Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Understanding Cognitive and Psychopathological Variability :/
Reminder of title:	The Role of Individual Differences in Machine Learning Applications.
Author:	Porter, Alexis Grace.
Description:	1 online resource (187 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
Subject:	Medical imaging. -
Online resource:	click for full text (PQDT)
ISBN:	9798382757803

Understanding Cognitive and Psychopathological Variability : = The Role of Individual Differences in Machine Learning Applications.
Porter, Alexis Grace.

Understanding Cognitive and Psychopathological Variability :The Role of Individual Differences in Machine Learning Applications. - 1 online resource (187 pages)

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

Thesis (Ph.D.)--Northwestern University, 2024.

Includes bibliographical references

The study of psychiatric disorders often involves tracking changes in brain function as it relates to symptoms. While research has found significant differences in functional network organization as it relates to various clinical outcomes, the exact neural biomarkers that contribute to symptom severity is often inconsistent. Prior research has shown that methodological considerations in sample size, motion artifacts, and increasing data quantity at the individual level can lead to substantial improvements in reliability. In Chapter 1, I provide a brief overview on existing work surrounding different methodological approaches that improve prediction of behavioral variables from brain network data. In the next three chapters, I describe research projects that aimed to use different cutting-edge approaches to improve machine learning prediction of behavior. In Chapter 2, I tested whether machine learning classification can improve our understanding of how brain networks are altered during tasks by using an individual specific approach. I found that individual focused approaches can uncover robust features of brain states, including features obscured in cross-subject analyses. In Chapter 3 I asked whether prediction of Schizophrenia Spectrum Disorders could be improved by joining together different neuroimaging modalities. I conducted a meta-analysis and systematic review of the existing literature and found no significant evidence for an advantage of multimodal relative to unimodal imaging approaches. However, this result could have been driven by biased effect sizes, particularly highlighting the need for improvements in data quality and quantity. In Chapter 4 I sought to test whether the prediction of clinical (especially psychosis) and cognitive measures from brain network data could be improved by either using person-specific parcellations or extended amounts of data from each participant. I found that increasing the quantity of data at the individual level exhibited significant improvements at predicting clinical and cognitive measures compared to resting state models, with only smaller scale effects associated with individual parcellations. Finally, in Chapter 5 I provide a brief general discussion to highlight the contributions of this work and future directions.

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

Mode of access: World Wide Web

ISBN: 9798382757803Subjects--Topical Terms:

1180167
Medical imaging.
Subjects--Index Terms:

Cognitive measuresIndex Terms--Genre/Form:

554714
Electronic books.

Understanding Cognitive and Psychopathological Variability : = The Role of Individual Differences in Machine Learning Applications.
LDR:03783ntm a22004217 4500 001 1148045
005 20240916070011.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382757803
035 $a (MiAaPQ)AAI31239665
035 $a AAI31239665
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Porter, Alexis Grace. $3 1473923
245 1 0 $a Understanding Cognitive and Psychopathological Variability : $b The Role of Individual Differences in Machine Learning Applications.
264 0 $c 2024
300 $a 1 online resource (187 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: B.
500 $a Advisor: Gratton, Caterina.
502 $a Thesis (Ph.D.)--Northwestern University, 2024.
504 $a Includes bibliographical references
520 $a The study of psychiatric disorders often involves tracking changes in brain function as it relates to symptoms. While research has found significant differences in functional network organization as it relates to various clinical outcomes, the exact neural biomarkers that contribute to symptom severity is often inconsistent. Prior research has shown that methodological considerations in sample size, motion artifacts, and increasing data quantity at the individual level can lead to substantial improvements in reliability. In Chapter 1, I provide a brief overview on existing work surrounding different methodological approaches that improve prediction of behavioral variables from brain network data. In the next three chapters, I describe research projects that aimed to use different cutting-edge approaches to improve machine learning prediction of behavior. In Chapter 2, I tested whether machine learning classification can improve our understanding of how brain networks are altered during tasks by using an individual specific approach. I found that individual focused approaches can uncover robust features of brain states, including features obscured in cross-subject analyses. In Chapter 3 I asked whether prediction of Schizophrenia Spectrum Disorders could be improved by joining together different neuroimaging modalities. I conducted a meta-analysis and systematic review of the existing literature and found no significant evidence for an advantage of multimodal relative to unimodal imaging approaches. However, this result could have been driven by biased effect sizes, particularly highlighting the need for improvements in data quality and quantity. In Chapter 4 I sought to test whether the prediction of clinical (especially psychosis) and cognitive measures from brain network data could be improved by either using person-specific parcellations or extended amounts of data from each participant. I found that increasing the quantity of data at the individual level exhibited significant improvements at predicting clinical and cognitive measures compared to resting state models, with only smaller scale effects associated with individual parcellations. Finally, in Chapter 5 I provide a brief general discussion to highlight the contributions of this work and future directions.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Medical imaging. $3 1180167
650 4 $a Computer science. $3 573171
650 4 $a Neurosciences. $3 593561
650 4 $a Cognitive psychology. $3 556029
653 $a Cognitive measures
653 $a Psychosis
653 $a Clinical outcomes
653 $a Individual differences
653 $a Machine learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0633
690 $a 0984
690 $a 0574
690 $a 0800
690 $a 0317
710 2 $a Northwestern University. $b Psychology. $3 1186776
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31239665 $z click for full text (PQDT)