A data-driven framework for selecting and validating digital health metrics: use-case in neurological sensorimotor impairments.

Diagnostic markers Multiple sclerosis Neurological disorders Predictive markers Prognostic markers

Journal

NPJ digital medicine
ISSN: 2398-6352
Titre abrégé: NPJ Digit Med
Pays: England
ID NLM: 101731738

Informations de publication

Date de publication:
2020
Historique:
received: 20 12 2019
accepted: 28 04 2020
entrez: 13 6 2020
pubmed: 13 6 2020
medline: 13 6 2020
Statut: epublish

Résumé

Digital health metrics promise to advance the understanding of impaired body functions, for example in neurological disorders. However, their clinical integration is challenged by an insufficient validation of the many existing and often abstract metrics. Here, we propose a data-driven framework to select and validate a clinically relevant core set of digital health metrics extracted from a technology-aided assessment. As an exemplary use-case, the framework is applied to the Virtual Peg Insertion Test (VPIT), a technology-aided assessment of upper limb sensorimotor impairments. The framework builds on a use-case-specific pathophysiological motivation of metrics, models demographic confounds, and evaluates the most important clinimetric properties (discriminant validity, structural validity, reliability, measurement error, learning effects). Applied to 77 metrics of the VPIT collected from 120 neurologically intact and 89 affected individuals, the framework allowed selecting 10 clinically relevant core metrics. These assessed the severity of multiple sensorimotor impairments in a valid, reliable, and informative manner. These metrics provided added clinical value by detecting impairments in neurological subjects that did not show any deficits according to conventional scales, and by covering sensorimotor impairments of the arm and hand with a single assessment. The proposed framework provides a transparent, step-by-step selection procedure based on clinically relevant evidence. This creates an interesting alternative to established selection algorithms that optimize mathematical loss functions and are not always intuitive to retrace. This could help addressing the insufficient clinical integration of digital health metrics. For the VPIT, it allowed establishing validated core metrics, paving the way for their integration into neurorehabilitation trials.

Identifiants

pubmed: 32529042
doi: 10.1038/s41746-020-0286-7
pii: 286
pmc: PMC7260375
doi:

Types de publication

Journal Article

Langues

eng

Pagination

80

Informations de copyright

© The Author(s) 2020.

Déclaration de conflit d'intérêts

Competing interestsThe authors declare no competing interests.

Références

Mult Scler Relat Disord. 2019 Sep;34:119-127
pubmed: 31255988
Am J Phys Med Rehabil. 2005 Sep;84(9):719-23
pubmed: 16141752
Neural Comput. 2003 Nov;15(11):2619-42
pubmed: 14577856
Brain. 2000 May;123 ( Pt 5):940-53
pubmed: 10775539
J Neurol Sci. 2006 Jul 15;246(1-2):117-22
pubmed: 16678208
Brain. 2001 Feb;124(Pt 2):299-309
pubmed: 11157557
Neurorehabil Neural Repair. 2008 Jan-Feb;22(1):50-63
pubmed: 17626223
Conf Proc IEEE Eng Med Biol Soc. 2012;2012:4776-9
pubmed: 23366996
Neurorehabil Neural Repair. 2002 Sep;16(3):232-40
pubmed: 12234086
Neurorehabil Neural Repair. 2010 Feb;24(2):178-87
pubmed: 19794134
Clin Interv Aging. 2017 Apr 06;12:635-643
pubmed: 28435235
Arch Phys Med Rehabil. 2015 Oct;96(10):1845-9
pubmed: 26143054
NPJ Digit Med. 2019;2:
pubmed: 31119198
Neurorehabil Neural Repair. 2012 Nov-Dec;26(9):1106-15
pubmed: 22647879
Int J MS Care. 2013 Fall;15(3):146-58
pubmed: 24453777
PLoS Med. 2017 Nov 16;14(11):e1002447
pubmed: 29145404
J Neurol Sci. 2014 Dec 15;347(1-2):341-4
pubmed: 25439167
Clin Neurophysiol. 2017 Oct;128(10):1858-1871
pubmed: 28826016
PLoS One. 2017 Mar 22;12(3):e0173674
pubmed: 28329000
J Neuroeng Rehabil. 2014 Apr 18;11:67
pubmed: 24745972
J Clin Epidemiol. 2014 Jul;67(7):745-53
pubmed: 24582946
Exp Brain Res. 1993;95(1):131-43
pubmed: 8405245
Stroke. 2014 Jan;45(1):200-4
pubmed: 24335224
Clin Neurophysiol. 2003 May;114(5):915-29
pubmed: 12738439
Arch Phys Med Rehabil. 2002 Aug;83(8):1145-50
pubmed: 12161838
Arch Phys Med Rehabil. 2014 Jun;95(6):1184-200
pubmed: 24631802
Trials. 2016 Sep 13;17(1):449
pubmed: 27618914
Neurorehabil Neural Repair. 2009 Oct;23(8):855-61
pubmed: 19531607
J Clin Epidemiol. 1999 Oct;52(10):935-42
pubmed: 10513756
NPJ Digit Med. 2019 Dec 12;2:126
pubmed: 31872066
IEEE Int Conf Rehabil Robot. 2011;2011:5975348
pubmed: 22275552
Stroke. 2010 Oct;41(10):2303-8
pubmed: 20814001
Front Neurol. 2010 Dec 17;1:149
pubmed: 21206767
J Anim Ecol. 2006 Sep;75(5):1182-9
pubmed: 16922854
Mov Disord. 2001 May;16(3):469-80
pubmed: 11391741
Int J Stroke. 2019 Oct;14(8):783-791
pubmed: 31510885
J Clin Epidemiol. 2006 Oct;59(10):1033-9
pubmed: 16980142
Arch Phys Med Rehabil. 1999 Jul;80(7):766-72
pubmed: 10414760
Nature. 1998 Aug 20;394(6695):780-4
pubmed: 9723616
PLoS One. 2010 Dec 20;5(12):e15032
pubmed: 21188140
Neurorehabil Neural Repair. 2017 Sep;31(9):784-792
pubmed: 28934918
Brain Res. 2012 May 3;1452:96-107
pubmed: 22464180
BMC Med. 2019 Oct 29;17(1):195
pubmed: 31665002
J Neuroeng Rehabil. 2015 Dec 09;12:112
pubmed: 26651329
J Neuroeng Rehabil. 2004 Dec 14;1(1):11
pubmed: 15679937
J Neurosci. 2002 Sep 15;22(18):8297-304
pubmed: 12223584
PLoS One. 2018 Jan 2;13(1):e0189275
pubmed: 29293512
Neurorehabil Neural Repair. 2011 Jun;25(5 Suppl):6S-20S
pubmed: 21613534
Exp Brain Res. 1992;90(2):393-8
pubmed: 1397153
Dev Med Child Neurol. 1999 Mar;41(3):166-75
pubmed: 10210249
Neurology. 1983 Nov;33(11):1444-52
pubmed: 6685237
IEEE Int Conf Rehabil Robot. 2019 Jun;2019:392-397
pubmed: 31374661
Stroke. 2019 Mar;50(3):718-727
pubmed: 30776997
PLoS One. 2014 Oct 20;9(10):e106136
pubmed: 25329712
J Physiol. 2011 Dec 1;589(Pt 23):5603-12
pubmed: 21878519
J Neuroeng Rehabil. 2015 Aug 12;12:66
pubmed: 26265327
Clin Interv Aging. 2012;7:499-507
pubmed: 23226011
Neurorehabil Neural Repair. 2010 Jul-Aug;24(6):528-41
pubmed: 20233965
Front Neurol. 2019 Jun 25;10:567
pubmed: 31293493
Sci Rep. 2018 Feb 1;8(1):2110
pubmed: 29391520
Neurorehabil Neural Repair. 2009 Jun;23(5):435-40
pubmed: 19261767
Mult Scler. 2018 Dec;24(14):1792-1794
pubmed: 30411655
J Neurosci. 1985 Jul;5(7):1688-703
pubmed: 4020415
Brain. 2001 Apr;124(Pt 4):720-30
pubmed: 11287372
NPJ Digit Med. 2018 Jan 15;1:20175
pubmed: 31304349
Arch Phys Med Rehabil. 2017 Mar;98(3):456-462
pubmed: 27519928
J Neuroeng Rehabil. 2014 Sep 12;11:137
pubmed: 25217124
Exp Brain Res. 1991;84(2):434-8
pubmed: 2065750
J Neuroeng Rehabil. 2019 Apr 29;16(1):53
pubmed: 31036003
Psychometrika. 1965 Jun;30:179-85
pubmed: 14306381
Qual Life Res. 2001;10(7):571-8
pubmed: 11822790
Brain. 2005 Jan;128(Pt 1):64-74
pubmed: 15471902
J Hand Ther. 2013 Apr-Jun;26(2):104-14;quiz 115
pubmed: 22975740
J Exp Psychol. 1954 Jun;47(6):381-91
pubmed: 13174710
Brain. 2019 Jan 1;142(1):15-22
pubmed: 30535098
Nat Rev Neurosci. 2004 Jul;5(7):532-46
pubmed: 15208695
IEEE Trans Biomed Eng. 2012 Aug;59(8):2126-36
pubmed: 22180502
Trends Ecol Evol. 2009 Mar;24(3):127-35
pubmed: 19185386
J Neuroeng Rehabil. 2014 Mar 25;11:43
pubmed: 24666888
Stroke. 2001 Jun;32(6):1279-84
pubmed: 11387487
Gait Posture. 2014;40(1):11-9
pubmed: 24768525
BMC Med. 2019 Jul 17;17(1):143
pubmed: 31311603
Neurorehabil Neural Repair. 2011 Jun;25(5 Suppl):21S-32S
pubmed: 21613535
Exp Brain Res. 2006 Nov;175(4):676-88
pubmed: 16835793
Neurorehabil Neural Repair. 2017 Jun;31(6):521-529
pubmed: 28506146
Am J Occup Ther. 1985 Jun;39(6):386-91
pubmed: 3160243
IEEE Int Conf Rehabil Robot. 2013 Jun;2013:6650494
pubmed: 24187309
Acta Psychol (Amst). 2011 Sep;138(1):126-34
pubmed: 21684505
Bone Joint Res. 2015 Sep;4(9):152-3
pubmed: 26392591
Med Eng Phys. 2018 Mar;53:13-31
pubmed: 29361407
J Neuroeng Rehabil. 2016 Jan 22;13:8
pubmed: 26801395
J Neuroeng Rehabil. 2014 Apr 02;11:47
pubmed: 24693877
Front Hum Neurosci. 2017 Feb 24;11:82
pubmed: 28286474
J Neuroeng Rehabil. 2009 Apr 13;6:10
pubmed: 19364396
PLoS One. 2016 May 06;11(5):e0154792
pubmed: 27152853
Int J Rehabil Res. 2004 Sep;27(3):253-6
pubmed: 15319698
Qual Life Res. 2018 May;27(5):1147-1157
pubmed: 29435801
Bioinformatics. 2007 Oct 1;23(19):2507-17
pubmed: 17720704
NPJ Digit Med. 2019 May 13;2:38
pubmed: 31304384

Auteurs

Christoph M Kanzler (CM)

Rehabilitation Engineering Laboratory, Institute of Robotics and Intelligent Systems, Department of Health Sciences and Technology, ETH Zurich, Switzerland.

Mike D Rinderknecht (MD)

Rehabilitation Engineering Laboratory, Institute of Robotics and Intelligent Systems, Department of Health Sciences and Technology, ETH Zurich, Switzerland.

Anne Schwarz (A)

Division of Vascular Neurology and Rehabilitation, Department of Neurology, University Hospital and University of Zürich, Zurich, Switzerland.
Cereneo Center for Neurology and Rehabilitation, Vitznau, Switzerland.

Ilse Lamers (I)

REVAL, Rehabilitation Research Center, BIOMED, Biomedical Research Institute, Faculty of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium.
Rehabilitation and MS Center, Pelt, Belgium.

Cynthia Gagnon (C)

School of Rehabilitation, Faculty of Medicine and Health Sciences, Université de Sherbrooke, Québec, Canada.

Jeremia P O Held (JPO)

Division of Vascular Neurology and Rehabilitation, Department of Neurology, University Hospital and University of Zürich, Zurich, Switzerland.
Cereneo Center for Neurology and Rehabilitation, Vitznau, Switzerland.

Peter Feys (P)

REVAL, Rehabilitation Research Center, BIOMED, Biomedical Research Institute, Faculty of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium.

Andreas R Luft (AR)

Division of Vascular Neurology and Rehabilitation, Department of Neurology, University Hospital and University of Zürich, Zurich, Switzerland.
Cereneo Center for Neurology and Rehabilitation, Vitznau, Switzerland.

Roger Gassert (R)

Rehabilitation Engineering Laboratory, Institute of Robotics and Intelligent Systems, Department of Health Sciences and Technology, ETH Zurich, Switzerland.

Olivier Lambercy (O)

Rehabilitation Engineering Laboratory, Institute of Robotics and Intelligent Systems, Department of Health Sciences and Technology, ETH Zurich, Switzerland.

Classifications MeSH