Treatment selection using prototyping in latent-space with application to depression treatment.

Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results,...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Akiva Kleinerman, Ariel Rosenfeld, David Benrimoh, Robert Fratila, Caitrin Armstrong, Joseph Mehltretter, Eliyahu Shneider, Amit Yaniv-Rosenfeld, Jordan Karp, Charles F Reynolds, Gustavo Turecki, Adam Kapelner
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/9f4016ee1eb14b8787c63c24a01141b2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9f4016ee1eb14b8787c63c24a01141b2
record_format dspace
spelling oai:doaj.org-article:9f4016ee1eb14b8787c63c24a01141b22021-12-02T20:13:15ZTreatment selection using prototyping in latent-space with application to depression treatment.1932-620310.1371/journal.pone.0258400https://doaj.org/article/9f4016ee1eb14b8787c63c24a01141b22021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0258400https://doaj.org/toc/1932-6203Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. In this article, we propose a novel deep learning-based treatment selection approach that is shown to strike a balance between the two paradigms using latent-space prototyping. Our approach is specifically tailored for domains in which effective prototypes and sub-groups of patients are assumed to exist, but groupings relevant to the training objective are not observable in the non-latent space. In an extensive evaluation, using both synthetic and Major Depressive Disorder (MDD) real-world clinical data describing 4754 MDD patients from clinical trials for depression treatment, we show that our approach favorably compares with state-of-the-art approaches. Specifically, the model produced an 8% absolute and 23% relative improvement over random treatment allocation. This is potentially clinically significant, given the large number of patients with MDD. Therefore, the model can bring about a much desired leap forward in the way depression is treated today.Akiva KleinermanAriel RosenfeldDavid BenrimohRobert FratilaCaitrin ArmstrongJoseph MehltretterEliyahu ShneiderAmit Yaniv-RosenfeldJordan KarpCharles F ReynoldsGustavo TureckiAdam KapelnerPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 11, p e0258400 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Akiva Kleinerman
Ariel Rosenfeld
David Benrimoh
Robert Fratila
Caitrin Armstrong
Joseph Mehltretter
Eliyahu Shneider
Amit Yaniv-Rosenfeld
Jordan Karp
Charles F Reynolds
Gustavo Turecki
Adam Kapelner
Treatment selection using prototyping in latent-space with application to depression treatment.
description Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. In this article, we propose a novel deep learning-based treatment selection approach that is shown to strike a balance between the two paradigms using latent-space prototyping. Our approach is specifically tailored for domains in which effective prototypes and sub-groups of patients are assumed to exist, but groupings relevant to the training objective are not observable in the non-latent space. In an extensive evaluation, using both synthetic and Major Depressive Disorder (MDD) real-world clinical data describing 4754 MDD patients from clinical trials for depression treatment, we show that our approach favorably compares with state-of-the-art approaches. Specifically, the model produced an 8% absolute and 23% relative improvement over random treatment allocation. This is potentially clinically significant, given the large number of patients with MDD. Therefore, the model can bring about a much desired leap forward in the way depression is treated today.
format article
author Akiva Kleinerman
Ariel Rosenfeld
David Benrimoh
Robert Fratila
Caitrin Armstrong
Joseph Mehltretter
Eliyahu Shneider
Amit Yaniv-Rosenfeld
Jordan Karp
Charles F Reynolds
Gustavo Turecki
Adam Kapelner
author_facet Akiva Kleinerman
Ariel Rosenfeld
David Benrimoh
Robert Fratila
Caitrin Armstrong
Joseph Mehltretter
Eliyahu Shneider
Amit Yaniv-Rosenfeld
Jordan Karp
Charles F Reynolds
Gustavo Turecki
Adam Kapelner
author_sort Akiva Kleinerman
title Treatment selection using prototyping in latent-space with application to depression treatment.
title_short Treatment selection using prototyping in latent-space with application to depression treatment.
title_full Treatment selection using prototyping in latent-space with application to depression treatment.
title_fullStr Treatment selection using prototyping in latent-space with application to depression treatment.
title_full_unstemmed Treatment selection using prototyping in latent-space with application to depression treatment.
title_sort treatment selection using prototyping in latent-space with application to depression treatment.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/9f4016ee1eb14b8787c63c24a01141b2
work_keys_str_mv AT akivakleinerman treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT arielrosenfeld treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT davidbenrimoh treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT robertfratila treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT caitrinarmstrong treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT josephmehltretter treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT eliyahushneider treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT amityanivrosenfeld treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT jordankarp treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT charlesfreynolds treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT gustavoturecki treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
AT adamkapelner treatmentselectionusingprototypinginlatentspacewithapplicationtodepressiontreatment
_version_ 1718374781590437888