Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study
BackgroundSmartphones and wearables are revolutionizing the assessment of cognitive and motor function in neurological disorders, allowing for objective, frequent, and remote data collection. However, these assessments typically provide a plethora of sensor-derived measures (...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-11-01
|
| Series: | JMIR Formative Research |
| Online Access: | https://formative.jmir.org/2024/1/e60673 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850192725329051648 |
|---|---|
| author | Matthew Scaramozza Aurélie Ruet Patrizia A Chiesa Laïtissia Ahamada Emmanuel Bartholomé Loïc Carment Julie Charre-Morin Gautier Cosne Léa Diouf Christine C Guo Adrien Juraver Christoph M Kanzler Angelos Karatsidis Claudia Mazzà Joaquin Penalver-Andres Marta Ruiz Aurore Saubusse Gabrielle Simoneau Alf Scotland Zhaonan Sun Minao Tang Johan van Beek Lauren Zajac Shibeshih Belachew Bruno Brochet Nolan Campbell |
| author_facet | Matthew Scaramozza Aurélie Ruet Patrizia A Chiesa Laïtissia Ahamada Emmanuel Bartholomé Loïc Carment Julie Charre-Morin Gautier Cosne Léa Diouf Christine C Guo Adrien Juraver Christoph M Kanzler Angelos Karatsidis Claudia Mazzà Joaquin Penalver-Andres Marta Ruiz Aurore Saubusse Gabrielle Simoneau Alf Scotland Zhaonan Sun Minao Tang Johan van Beek Lauren Zajac Shibeshih Belachew Bruno Brochet Nolan Campbell |
| author_sort | Matthew Scaramozza |
| collection | DOAJ |
| description |
BackgroundSmartphones and wearables are revolutionizing the assessment of cognitive and motor function in neurological disorders, allowing for objective, frequent, and remote data collection. However, these assessments typically provide a plethora of sensor-derived measures (SDMs), and selecting the most suitable measure for a given context of use is a challenging, often overlooked problem.
ObjectiveThis analysis aims to develop and apply an SDM selection framework, including automated data quality checks and the evaluation of statistical properties, to identify robust SDMs that describe the cognitive and motor function of people with multiple sclerosis (MS).
MethodsThe proposed framework was applied to data from a cross-sectional study involving 85 people with MS and 68 healthy participants who underwent in-clinic supervised and remote unsupervised smartphone-based assessments. The assessment provided high-quality recordings from cognitive, manual dexterity, and mobility tests, from which 47 SDMs, based on established literature, were extracted using previously developed and publicly available algorithms. These SDMs were first separately and then jointly screened for bias and normality by 2 expert assessors. Selected SDMs were then analyzed to establish their reliability, using an intraclass correlation coefficient and minimal detectable change at 95% CI. The convergence of selected SDMs with in-clinic MS functional measures and patient-reported outcomes was also evaluated.
ResultsA total of 16 (34%) of the 47 SDMs passed the selection framework. All selected SDMs demonstrated moderate-to-good reliability in remote settings (intraclass correlation coefficient 0.5-0.85; minimal detectable change at 95% CI 19%-35%). Selected SDMs extracted from the smartphone-based cognitive test demonstrated good-to-excellent correlation (Spearman correlation coefficient, |ρ|>0.75) with the in-clinic Symbol Digit Modalities Test and fair correlation with Expanded Disability Status Scale (EDSS) scores (0.25≤|ρ|<0.5). SDMs extracted from the manual dexterity tests showed either fair correlation (0.25≤|ρ|<0.5) or were not correlated (|ρ|<0.25) with the in-clinic 9-hole peg test and EDSS scores. Most selected SDMs from mobility tests showed fair correlation with the in-clinic timed 25-foot walk test and fair to moderate-to-good correlation (0.5<|ρ|≤0.75) with EDSS scores. SDM correlations with relevant patient-reported outcomes varied by functional domain, ranging from not correlated (cognitive test SDMs) to good-to-excellent correlation (|ρ|>0.75) for mobility test SDMs. Overall, correlations were similar when smartphone-based tests were performed in a clinic or remotely.
ConclusionsReported results highlight that smartphone-based assessments are suitable tools to remotely obtain high-quality SDMs of cognitive and motor function in people with MS. The presented SDM selection framework promises to increase the interpretability and standardization of smartphone-based SDMs in people with MS, paving the way for their future use in interventional trials. |
| format | Article |
| id | doaj-art-0831e3ea94c0408fbce33db1b59a1650 |
| institution | OA Journals |
| issn | 2561-326X |
| language | English |
| publishDate | 2024-11-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Formative Research |
| spelling | doaj-art-0831e3ea94c0408fbce33db1b59a16502025-08-20T02:14:27ZengJMIR PublicationsJMIR Formative Research2561-326X2024-11-018e6067310.2196/60673Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept StudyMatthew Scaramozzahttps://orcid.org/0000-0003-3738-459XAurélie Ruethttps://orcid.org/0000-0002-0020-8739Patrizia A Chiesahttps://orcid.org/0000-0002-1606-9008Laïtissia Ahamadahttps://orcid.org/0009-0006-4296-0706Emmanuel Bartholoméhttps://orcid.org/0009-0007-1370-8197Loïc Carmenthttps://orcid.org/0000-0002-1358-2877Julie Charre-Morinhttps://orcid.org/0009-0005-3116-6630Gautier Cosnehttps://orcid.org/0009-0009-5802-1414Léa Dioufhttps://orcid.org/0009-0005-6109-0817Christine C Guohttps://orcid.org/0000-0003-1530-0172Adrien Juraverhttps://orcid.org/0009-0004-4251-9609Christoph M Kanzlerhttps://orcid.org/0000-0003-1214-8347Angelos Karatsidishttps://orcid.org/0000-0001-6474-9377Claudia Mazzàhttps://orcid.org/0000-0002-5215-1746Joaquin Penalver-Andreshttps://orcid.org/0000-0001-8181-7538Marta Ruizhttps://orcid.org/0009-0007-7744-4207Aurore Saubussehttps://orcid.org/0009-0001-0180-2844Gabrielle Simoneauhttps://orcid.org/0000-0001-9310-6274Alf Scotlandhttps://orcid.org/0000-0001-9590-8617Zhaonan Sunhttps://orcid.org/0000-0001-5333-4387Minao Tanghttps://orcid.org/0009-0003-3007-6874Johan van Beekhttps://orcid.org/0000-0002-5641-0004Lauren Zajachttps://orcid.org/0000-0002-1642-4284Shibeshih Belachewhttps://orcid.org/0000-0003-3976-1950Bruno Brochethttps://orcid.org/0000-0003-3824-2796Nolan Campbellhttps://orcid.org/0009-0005-2746-5531 BackgroundSmartphones and wearables are revolutionizing the assessment of cognitive and motor function in neurological disorders, allowing for objective, frequent, and remote data collection. However, these assessments typically provide a plethora of sensor-derived measures (SDMs), and selecting the most suitable measure for a given context of use is a challenging, often overlooked problem. ObjectiveThis analysis aims to develop and apply an SDM selection framework, including automated data quality checks and the evaluation of statistical properties, to identify robust SDMs that describe the cognitive and motor function of people with multiple sclerosis (MS). MethodsThe proposed framework was applied to data from a cross-sectional study involving 85 people with MS and 68 healthy participants who underwent in-clinic supervised and remote unsupervised smartphone-based assessments. The assessment provided high-quality recordings from cognitive, manual dexterity, and mobility tests, from which 47 SDMs, based on established literature, were extracted using previously developed and publicly available algorithms. These SDMs were first separately and then jointly screened for bias and normality by 2 expert assessors. Selected SDMs were then analyzed to establish their reliability, using an intraclass correlation coefficient and minimal detectable change at 95% CI. The convergence of selected SDMs with in-clinic MS functional measures and patient-reported outcomes was also evaluated. ResultsA total of 16 (34%) of the 47 SDMs passed the selection framework. All selected SDMs demonstrated moderate-to-good reliability in remote settings (intraclass correlation coefficient 0.5-0.85; minimal detectable change at 95% CI 19%-35%). Selected SDMs extracted from the smartphone-based cognitive test demonstrated good-to-excellent correlation (Spearman correlation coefficient, |ρ|>0.75) with the in-clinic Symbol Digit Modalities Test and fair correlation with Expanded Disability Status Scale (EDSS) scores (0.25≤|ρ|<0.5). SDMs extracted from the manual dexterity tests showed either fair correlation (0.25≤|ρ|<0.5) or were not correlated (|ρ|<0.25) with the in-clinic 9-hole peg test and EDSS scores. Most selected SDMs from mobility tests showed fair correlation with the in-clinic timed 25-foot walk test and fair to moderate-to-good correlation (0.5<|ρ|≤0.75) with EDSS scores. SDM correlations with relevant patient-reported outcomes varied by functional domain, ranging from not correlated (cognitive test SDMs) to good-to-excellent correlation (|ρ|>0.75) for mobility test SDMs. Overall, correlations were similar when smartphone-based tests were performed in a clinic or remotely. ConclusionsReported results highlight that smartphone-based assessments are suitable tools to remotely obtain high-quality SDMs of cognitive and motor function in people with MS. The presented SDM selection framework promises to increase the interpretability and standardization of smartphone-based SDMs in people with MS, paving the way for their future use in interventional trials.https://formative.jmir.org/2024/1/e60673 |
| spellingShingle | Matthew Scaramozza Aurélie Ruet Patrizia A Chiesa Laïtissia Ahamada Emmanuel Bartholomé Loïc Carment Julie Charre-Morin Gautier Cosne Léa Diouf Christine C Guo Adrien Juraver Christoph M Kanzler Angelos Karatsidis Claudia Mazzà Joaquin Penalver-Andres Marta Ruiz Aurore Saubusse Gabrielle Simoneau Alf Scotland Zhaonan Sun Minao Tang Johan van Beek Lauren Zajac Shibeshih Belachew Bruno Brochet Nolan Campbell Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study JMIR Formative Research |
| title | Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study |
| title_full | Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study |
| title_fullStr | Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study |
| title_full_unstemmed | Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study |
| title_short | Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study |
| title_sort | sensor derived measures of motor and cognitive functions in people with multiple sclerosis using unsupervised smartphone based assessments proof of concept study |
| url | https://formative.jmir.org/2024/1/e60673 |
| work_keys_str_mv | AT matthewscaramozza sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT aurelieruet sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT patriziaachiesa sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT laitissiaahamada sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT emmanuelbartholome sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT loiccarment sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT juliecharremorin sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT gautiercosne sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT leadiouf sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT christinecguo sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT adrienjuraver sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT christophmkanzler sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT angeloskaratsidis sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT claudiamazza sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT joaquinpenalverandres sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT martaruiz sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT auroresaubusse sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT gabriellesimoneau sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT alfscotland sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT zhaonansun sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT minaotang sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT johanvanbeek sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT laurenzajac sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT shibeshihbelachew sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT brunobrochet sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy AT nolancampbell sensorderivedmeasuresofmotorandcognitivefunctionsinpeoplewithmultiplesclerosisusingunsupervisedsmartphonebasedassessmentsproofofconceptstudy |