Computer vision detects covert voluntary facial movements in unresponsive brain injury patients

Abstract Background Many brain injury patients who appear unresponsive retain subtle, purposeful motor behaviors, signaling capacity for recovery. We hypothesized that low-amplitude movements precede larger-amplitude voluntary movements detectable by clinicians after acute brain injury. To test this...

Full description

Saved in:
Bibliographic Details
Main Authors: Xi Cheng, Sujith Swarna, Jermaine Robertson, Nathaniel A. Cleri, Jordan R. Saadon, Chiemeka Uwakwe, Yindong Hua, Seyed Morsal Mosallami Aghili, Cassie Wang, Robert S. Kleyner, Xuwen Zheng, Ariana Forohar, John Servider, Kurt Butler, Chao Chen, Jordane Dimidschstein, Petar M. Djurić, Charles B. Mikell, Sima Mofakham
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Communications Medicine
Online Access:https://doi.org/10.1038/s43856-025-01042-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226023398277120
author Xi Cheng
Sujith Swarna
Jermaine Robertson
Nathaniel A. Cleri
Jordan R. Saadon
Chiemeka Uwakwe
Yindong Hua
Seyed Morsal Mosallami Aghili
Cassie Wang
Robert S. Kleyner
Xuwen Zheng
Ariana Forohar
John Servider
Kurt Butler
Chao Chen
Jordane Dimidschstein
Petar M. Djurić
Charles B. Mikell
Sima Mofakham
author_facet Xi Cheng
Sujith Swarna
Jermaine Robertson
Nathaniel A. Cleri
Jordan R. Saadon
Chiemeka Uwakwe
Yindong Hua
Seyed Morsal Mosallami Aghili
Cassie Wang
Robert S. Kleyner
Xuwen Zheng
Ariana Forohar
John Servider
Kurt Butler
Chao Chen
Jordane Dimidschstein
Petar M. Djurić
Charles B. Mikell
Sima Mofakham
author_sort Xi Cheng
collection DOAJ
description Abstract Background Many brain injury patients who appear unresponsive retain subtle, purposeful motor behaviors, signaling capacity for recovery. We hypothesized that low-amplitude movements precede larger-amplitude voluntary movements detectable by clinicians after acute brain injury. To test this hypothesis, we developed a novel, as far as we are aware, computer vision-based tool (SeeMe) that detects and quantifies low-amplitude facial movements in response to auditory commands. Methods We enrolled 16 healthy volunteers and 37 comatose acute brain injury patients (Glasgow Coma Scale ≤8) aged 18–85 with no prior neurological diagnoses. We measured facial movements to command assessed using SeeMe and compared them to clinicians’ exams. The primary outcome was the detection of facial movement in response to auditory commands. To assess comprehension, we tested whether movements were specific to command type (i.e., eye-opening to open your eyes and not stick out your tongue) with a machine learning-based classifier. Results Here we show that SeeMe detects eye-opening in comatose patients 4.1 days earlier than clinicians. SeeMe also detects eye-opening in more comatose patients (30/36, 85.7%) than clinical examination (25/36, 71.4%). In patients without an obscuring endotracheal tube, SeeMe detects mouth movements in 16/17 (94.1%) patients. The amplitude and number of SeeMe-detected responses correlate with clinical outcome at discharge. Using our classifier, eye-opening is specific (81%) to the command open your eyes. Conclusion Acute brain injury patients have low-amplitude movements before overt movements. Thus, many covertly conscious patients may have motor behavior currently undetected by clinicians.
format Article
id doaj-art-dd3b6ca7b6624cb6a1269104527bbe76
institution Kabale University
issn 2730-664X
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Communications Medicine
spelling doaj-art-dd3b6ca7b6624cb6a1269104527bbe762025-08-24T11:47:41ZengNature PortfolioCommunications Medicine2730-664X2025-08-01511910.1038/s43856-025-01042-yComputer vision detects covert voluntary facial movements in unresponsive brain injury patientsXi Cheng0Sujith Swarna1Jermaine Robertson2Nathaniel A. Cleri3Jordan R. Saadon4Chiemeka Uwakwe5Yindong Hua6Seyed Morsal Mosallami Aghili7Cassie Wang8Robert S. Kleyner9Xuwen Zheng10Ariana Forohar11John Servider12Kurt Butler13Chao Chen14Jordane Dimidschstein15Petar M. Djurić16Charles B. Mikell17Sima Mofakham18Department of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Electrical and Computer Engineering, Stony Brook UniversityDepartment of Biomedical Informatics, Stony Brook UniversityStanley Center for Psychiatric Research, Broad Institute of Harvard and MITDepartment of Electrical and Computer Engineering, Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityDepartment of Neurosurgery, Renaissance School of Medicine at Stony Brook UniversityAbstract Background Many brain injury patients who appear unresponsive retain subtle, purposeful motor behaviors, signaling capacity for recovery. We hypothesized that low-amplitude movements precede larger-amplitude voluntary movements detectable by clinicians after acute brain injury. To test this hypothesis, we developed a novel, as far as we are aware, computer vision-based tool (SeeMe) that detects and quantifies low-amplitude facial movements in response to auditory commands. Methods We enrolled 16 healthy volunteers and 37 comatose acute brain injury patients (Glasgow Coma Scale ≤8) aged 18–85 with no prior neurological diagnoses. We measured facial movements to command assessed using SeeMe and compared them to clinicians’ exams. The primary outcome was the detection of facial movement in response to auditory commands. To assess comprehension, we tested whether movements were specific to command type (i.e., eye-opening to open your eyes and not stick out your tongue) with a machine learning-based classifier. Results Here we show that SeeMe detects eye-opening in comatose patients 4.1 days earlier than clinicians. SeeMe also detects eye-opening in more comatose patients (30/36, 85.7%) than clinical examination (25/36, 71.4%). In patients without an obscuring endotracheal tube, SeeMe detects mouth movements in 16/17 (94.1%) patients. The amplitude and number of SeeMe-detected responses correlate with clinical outcome at discharge. Using our classifier, eye-opening is specific (81%) to the command open your eyes. Conclusion Acute brain injury patients have low-amplitude movements before overt movements. Thus, many covertly conscious patients may have motor behavior currently undetected by clinicians.https://doi.org/10.1038/s43856-025-01042-y
spellingShingle Xi Cheng
Sujith Swarna
Jermaine Robertson
Nathaniel A. Cleri
Jordan R. Saadon
Chiemeka Uwakwe
Yindong Hua
Seyed Morsal Mosallami Aghili
Cassie Wang
Robert S. Kleyner
Xuwen Zheng
Ariana Forohar
John Servider
Kurt Butler
Chao Chen
Jordane Dimidschstein
Petar M. Djurić
Charles B. Mikell
Sima Mofakham
Computer vision detects covert voluntary facial movements in unresponsive brain injury patients
Communications Medicine
title Computer vision detects covert voluntary facial movements in unresponsive brain injury patients
title_full Computer vision detects covert voluntary facial movements in unresponsive brain injury patients
title_fullStr Computer vision detects covert voluntary facial movements in unresponsive brain injury patients
title_full_unstemmed Computer vision detects covert voluntary facial movements in unresponsive brain injury patients
title_short Computer vision detects covert voluntary facial movements in unresponsive brain injury patients
title_sort computer vision detects covert voluntary facial movements in unresponsive brain injury patients
url https://doi.org/10.1038/s43856-025-01042-y
work_keys_str_mv AT xicheng computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT sujithswarna computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT jermainerobertson computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT nathanielacleri computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT jordanrsaadon computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT chiemekauwakwe computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT yindonghua computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT seyedmorsalmosallamiaghili computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT cassiewang computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT robertskleyner computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT xuwenzheng computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT arianaforohar computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT johnservider computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT kurtbutler computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT chaochen computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT jordanedimidschstein computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT petarmdjuric computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT charlesbmikell computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients
AT simamofakham computervisiondetectscovertvoluntaryfacialmovementsinunresponsivebraininjurypatients