Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task
Conventional neuropsychological tests do not represent the complex and dynamic situations encountered in daily life. Immersive virtual reality simulations can be used to simulate dynamic and interactive situations in a controlled setting. Adding eye tracking to such simulations may provide highly de...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022004959 |
| _version_ | 1818006617856147456 |
|---|---|
| author | Veerle H.E.W. Brouwer Sjoerd Stuit Alex Hoogerbrugge Antonia F. Ten Brink Isabel K. Gosselt Stefan Van der Stigchel Tanja C.W. Nijboer |
| author_facet | Veerle H.E.W. Brouwer Sjoerd Stuit Alex Hoogerbrugge Antonia F. Ten Brink Isabel K. Gosselt Stefan Van der Stigchel Tanja C.W. Nijboer |
| author_sort | Veerle H.E.W. Brouwer |
| collection | DOAJ |
| description | Conventional neuropsychological tests do not represent the complex and dynamic situations encountered in daily life. Immersive virtual reality simulations can be used to simulate dynamic and interactive situations in a controlled setting. Adding eye tracking to such simulations may provide highly detailed outcome measures, and has great potential for neuropsychological assessment. Here, participants (83 stroke patients and 103 healthy controls) we instructed to find either 3 or 7 items from a shopping list in a virtual super market environment while eye movements were being recorded. Using Logistic Regression and Support Vector Machine models, we aimed to predict the task of the participant and whether they belonged to the stroke or the control group. With a limited number of eye movement features, our models achieved an average Area Under the Curve (AUC) of .76 in predicting whether each participant was assigned a short or long shopping list (3 or 7 items). Identifying participant as either stroke patients and controls led to an AUC of .64. In both classification tasks, the frequency with which aisles were revisited was the most dissociating feature. As such, eye movement data obtained from a virtual reality simulation contain a rich set of signatures for detecting cognitive deficits, opening the door to potential clinical applications. |
| first_indexed | 2024-04-14T05:03:40Z |
| format | Article |
| id | doaj.art-66e8378ae07447c8bcf5eec3e1493c32 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-14T05:03:40Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-66e8378ae07447c8bcf5eec3e1493c322022-12-22T02:10:50ZengElsevierHeliyon2405-84402022-04-0184e09207Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality taskVeerle H.E.W. Brouwer0Sjoerd Stuit1Alex Hoogerbrugge2Antonia F. Ten Brink3Isabel K. Gosselt4Stefan Van der Stigchel5Tanja C.W. Nijboer6Department of Experimental Psychology, Helmholtz Institute, Utrecht University, Heidelberglaan 1, 3584 CS, Utrecht, NetherlandsDepartment of Experimental Psychology, Helmholtz Institute, Utrecht University, Heidelberglaan 1, 3584 CS, Utrecht, NetherlandsDepartment of Experimental Psychology, Helmholtz Institute, Utrecht University, Heidelberglaan 1, 3584 CS, Utrecht, NetherlandsDepartment of Experimental Psychology, Helmholtz Institute, Utrecht University, Heidelberglaan 1, 3584 CS, Utrecht, NetherlandsCenter of Excellence for Rehabilitation Medicine, UMC Utrecht Brain Center, University Medical Center Utrecht, De Hoogstraat Rehabilitation, Heidelberglaan 100, 3584 CX, Utrecht, NetherlandsDepartment of Experimental Psychology, Helmholtz Institute, Utrecht University, Heidelberglaan 1, 3584 CS, Utrecht, NetherlandsDepartment of Experimental Psychology, Helmholtz Institute, Utrecht University, Heidelberglaan 1, 3584 CS, Utrecht, Netherlands; Center of Excellence for Rehabilitation Medicine, UMC Utrecht Brain Center, University Medical Center Utrecht, De Hoogstraat Rehabilitation, Heidelberglaan 100, 3584 CX, Utrecht, Netherlands; Department of Rehabilitation, Physical Therapy Science & Sports, UMC Utrecht Brain Center, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, Netherlands; Corresponding author.Conventional neuropsychological tests do not represent the complex and dynamic situations encountered in daily life. Immersive virtual reality simulations can be used to simulate dynamic and interactive situations in a controlled setting. Adding eye tracking to such simulations may provide highly detailed outcome measures, and has great potential for neuropsychological assessment. Here, participants (83 stroke patients and 103 healthy controls) we instructed to find either 3 or 7 items from a shopping list in a virtual super market environment while eye movements were being recorded. Using Logistic Regression and Support Vector Machine models, we aimed to predict the task of the participant and whether they belonged to the stroke or the control group. With a limited number of eye movement features, our models achieved an average Area Under the Curve (AUC) of .76 in predicting whether each participant was assigned a short or long shopping list (3 or 7 items). Identifying participant as either stroke patients and controls led to an AUC of .64. In both classification tasks, the frequency with which aisles were revisited was the most dissociating feature. As such, eye movement data obtained from a virtual reality simulation contain a rich set of signatures for detecting cognitive deficits, opening the door to potential clinical applications.http://www.sciencedirect.com/science/article/pii/S2405844022004959StrokeCognitive assessmentVirtual realityEye trackingMachine learning |
| spellingShingle | Veerle H.E.W. Brouwer Sjoerd Stuit Alex Hoogerbrugge Antonia F. Ten Brink Isabel K. Gosselt Stefan Van der Stigchel Tanja C.W. Nijboer Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task Heliyon Stroke Cognitive assessment Virtual reality Eye tracking Machine learning |
| title | Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task |
| title_full | Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task |
| title_fullStr | Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task |
| title_full_unstemmed | Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task |
| title_short | Applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task |
| title_sort | applying machine learning to dissociate between stroke patients and healthy controls using eye movement features obtained from a virtual reality task |
| topic | Stroke Cognitive assessment Virtual reality Eye tracking Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022004959 |
| work_keys_str_mv | AT veerlehewbrouwer applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask AT sjoerdstuit applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask AT alexhoogerbrugge applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask AT antoniaftenbrink applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask AT isabelkgosselt applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask AT stefanvanderstigchel applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask AT tanjacwnijboer applyingmachinelearningtodissociatebetweenstrokepatientsandhealthycontrolsusingeyemovementfeaturesobtainedfromavirtualrealitytask |