Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions

We conducted a feasibility analysis to determine the quality of data that could be collected ambiently during routine clinical conversations. We used inexpensive, consumer-grade hardware to record unstructured dialogue and open-source software tools to quantify and model face, voice (acoustic and la...

Full description

Bibliographic Details
Main Authors: Daniel S. Barron, Stephen Heisig, Carla Agurto, Raquel Norel, Brittany Quagan, Albert Powers, Michael L. Birnbaum, Todd Constable, Guillermo Cecchi, John H. Krystal
Format: Article
Language:English
Published: Ubiquity Press 2022-01-01
Series:Computational Psychiatry
Subjects:
Online Access:https://cpsyjournal.org/articles/78
_version_ 1811259610148896768
author Daniel S. Barron
Stephen Heisig
Carla Agurto
Raquel Norel
Brittany Quagan
Albert Powers
Michael L. Birnbaum
Todd Constable
Guillermo Cecchi
John H. Krystal
author_facet Daniel S. Barron
Stephen Heisig
Carla Agurto
Raquel Norel
Brittany Quagan
Albert Powers
Michael L. Birnbaum
Todd Constable
Guillermo Cecchi
John H. Krystal
author_sort Daniel S. Barron
collection DOAJ
description We conducted a feasibility analysis to determine the quality of data that could be collected ambiently during routine clinical conversations. We used inexpensive, consumer-grade hardware to record unstructured dialogue and open-source software tools to quantify and model face, voice (acoustic and language) and movement features. We used an external validation set to perform proof-of-concept predictive analyses and show that clinically relevant measures can be produced without a restrictive protocol.
first_indexed 2024-04-12T18:34:16Z
format Article
id doaj.art-8e1168b23fd54936b24970cbf8f0be68
institution Directory Open Access Journal
issn 2379-6227
language English
last_indexed 2024-04-12T18:34:16Z
publishDate 2022-01-01
publisher Ubiquity Press
record_format Article
series Computational Psychiatry
spelling doaj.art-8e1168b23fd54936b24970cbf8f0be682022-12-22T03:21:00ZengUbiquity PressComputational Psychiatry2379-62272022-01-016110.5334/cpsy.7864Feasibility Analysis of Phenotype Quantification from Unstructured Clinical InteractionsDaniel S. Barron0Stephen Heisig1Carla Agurto2Raquel Norel3Brittany Quagan4Albert Powers5Michael L. Birnbaum6Todd Constable7Guillermo Cecchi8John H. Krystal9Department of Psychiatry, Yale University, New Haven, CT; Department of Psychiatry, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA; Department of Anesthesiology and Pain Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MADepartment of Neurology, Icahn School of Medicine, Mt. Sinai, NYT.J. Watson IBM Research Laboratory, Yorktown Heights, NYT.J. Watson IBM Research Laboratory, Yorktown Heights, NYDepartment of Psychiatry, Yale University, New Haven, CTDepartment of Psychiatry, Yale University, New Haven, CTDepartment of Psychiatric Research, The Zucker Hillside Hospital, Northwell Health, Glen Oaks, NYDepartment of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT; Department of Neurosurgery, Yale School of Medicine, New Haven, CT 06520T.J. Watson IBM Research Laboratory, Yorktown Heights, NYDepartment of Psychiatry, Yale University, New Haven, CTWe conducted a feasibility analysis to determine the quality of data that could be collected ambiently during routine clinical conversations. We used inexpensive, consumer-grade hardware to record unstructured dialogue and open-source software tools to quantify and model face, voice (acoustic and language) and movement features. We used an external validation set to perform proof-of-concept predictive analyses and show that clinically relevant measures can be produced without a restrictive protocol.https://cpsyjournal.org/articles/78digital phenotypeconversationvoicefacial featureacoustic
spellingShingle Daniel S. Barron
Stephen Heisig
Carla Agurto
Raquel Norel
Brittany Quagan
Albert Powers
Michael L. Birnbaum
Todd Constable
Guillermo Cecchi
John H. Krystal
Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions
Computational Psychiatry
digital phenotype
conversation
voice
facial feature
acoustic
title Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions
title_full Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions
title_fullStr Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions
title_full_unstemmed Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions
title_short Feasibility Analysis of Phenotype Quantification from Unstructured Clinical Interactions
title_sort feasibility analysis of phenotype quantification from unstructured clinical interactions
topic digital phenotype
conversation
voice
facial feature
acoustic
url https://cpsyjournal.org/articles/78
work_keys_str_mv AT danielsbarron feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT stephenheisig feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT carlaagurto feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT raquelnorel feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT brittanyquagan feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT albertpowers feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT michaellbirnbaum feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT toddconstable feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT guillermocecchi feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions
AT johnhkrystal feasibilityanalysisofphenotypequantificationfromunstructuredclinicalinteractions