Impact of a clinical decision support tool on prediction of progression in early-stage dementia: a prospective validation study.
Alzheimer’s disease
CDSS
Computer-assisted
Conversion
Dementia
Mild cognitive impairment
Progression
Subjective cognitive decline
Journal
Alzheimer's research & therapy
ISSN: 1758-9193
Titre abrégé: Alzheimers Res Ther
Pays: England
ID NLM: 101511643
Informations de publication
Date de publication:
20 03 2019
20 03 2019
Historique:
received:
21
11
2018
accepted:
11
03
2019
entrez:
22
3
2019
pubmed:
22
3
2019
medline:
31
3
2020
Statut:
epublish
Résumé
In clinical practice, it is often difficult to predict which patients with cognitive complaints or impairment will progress or remain stable. We assessed the impact of using a clinical decision support system, the PredictND tool, to predict progression in patients with subjective cognitive decline (SCD) and mild cognitive impairment (MCI) in memory clinics. In this prospective multicenter study, we included 429 patients with SCD (n = 230) and MCI (n = 199) (female 54%, age 67 ± 9, MMSE 28 ± 2) and followed them for at least 12 months. Based on all available patient baseline data (demographics, cognitive tests, cerebrospinal fluid biomarkers, and MRI), the PredictND tool provides a comprehensive overview of the data and a classification defining the likelihood of progression. At baseline, a clinician defined an expected follow-up diagnosis and estimated the level of confidence in their prediction using a visual analogue scale (VAS, 0-100%), first without and subsequently with the PredictND tool. As outcome measure, we defined clinical progression as progression from SCD to MCI or dementia, and from MCI to dementia. Correspondence between the expected and the actual clinical progression at follow-up defined the prognostic accuracy. After a mean follow-up time of 1.7 ± 0.4 years, 21 (9%) SCD and 63 (32%) MCI had progressed. When using the PredictND tool, the overall prognostic accuracy was unaffected (0.4%, 95%CI - 3.0%; + 3.9%; p = 0.79). However, restricting the analysis to patients with more certain classifications (n = 203), we found an increase of 3% in the accuracy (95%CI - 0.6%; + 6.5%; p = 0.11). Furthermore, for this subgroup, the tool alone showed a statistically significant increase in the prognostic accuracy compared to the evaluation without tool (6.4%, 95%CI 2.1%; 10.7%; p = 0.004). Specifically, the negative predictive value was high. Moreover, confidence in the prediction increased significantly (∆VAS = 4%, p < .0001). Adding the PredictND tool to the clinical evaluation increased clinicians' confidence. Furthermore, the results indicate that the tool has the potential to improve prediction of progression for patients with more certain classifications.
Sections du résumé
BACKGROUND
In clinical practice, it is often difficult to predict which patients with cognitive complaints or impairment will progress or remain stable. We assessed the impact of using a clinical decision support system, the PredictND tool, to predict progression in patients with subjective cognitive decline (SCD) and mild cognitive impairment (MCI) in memory clinics.
METHODS
In this prospective multicenter study, we included 429 patients with SCD (n = 230) and MCI (n = 199) (female 54%, age 67 ± 9, MMSE 28 ± 2) and followed them for at least 12 months. Based on all available patient baseline data (demographics, cognitive tests, cerebrospinal fluid biomarkers, and MRI), the PredictND tool provides a comprehensive overview of the data and a classification defining the likelihood of progression. At baseline, a clinician defined an expected follow-up diagnosis and estimated the level of confidence in their prediction using a visual analogue scale (VAS, 0-100%), first without and subsequently with the PredictND tool. As outcome measure, we defined clinical progression as progression from SCD to MCI or dementia, and from MCI to dementia. Correspondence between the expected and the actual clinical progression at follow-up defined the prognostic accuracy.
RESULTS
After a mean follow-up time of 1.7 ± 0.4 years, 21 (9%) SCD and 63 (32%) MCI had progressed. When using the PredictND tool, the overall prognostic accuracy was unaffected (0.4%, 95%CI - 3.0%; + 3.9%; p = 0.79). However, restricting the analysis to patients with more certain classifications (n = 203), we found an increase of 3% in the accuracy (95%CI - 0.6%; + 6.5%; p = 0.11). Furthermore, for this subgroup, the tool alone showed a statistically significant increase in the prognostic accuracy compared to the evaluation without tool (6.4%, 95%CI 2.1%; 10.7%; p = 0.004). Specifically, the negative predictive value was high. Moreover, confidence in the prediction increased significantly (∆VAS = 4%, p < .0001).
CONCLUSIONS
Adding the PredictND tool to the clinical evaluation increased clinicians' confidence. Furthermore, the results indicate that the tool has the potential to improve prediction of progression for patients with more certain classifications.
Identifiants
pubmed: 30894218
doi: 10.1186/s13195-019-0482-3
pii: 10.1186/s13195-019-0482-3
pmc: PMC6425602
doi:
Types de publication
Journal Article
Multicenter Study
Research Support, Non-U.S. Gov't
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
25Subventions
Organisme : European Commission
ID : 611005
Pays : International
Organisme : European Commission
ID : 601055
Pays : International
Organisme : European Commission
ID : 224328
Pays : International
Organisme : European Commission
ID : 611005
Pays : International
Références
Int Psychogeriatr. 2006 Mar;18(1):151-62
pubmed: 16403246
Neuroimage Clin. 2016 Mar 05;11:435-449
pubmed: 27104138
Neuroimage. 2015 May 1;111:562-79
pubmed: 25652394
PLoS One. 2011;6(7):e21896
pubmed: 21814561
Alzheimers Dement. 2011 May;7(3):270-9
pubmed: 21514249
AJR Am J Roentgenol. 1987 Aug;149(2):351-6
pubmed: 3496763
Eur Radiol. 2017 Aug;27(8):3372-3382
pubmed: 27986990
Alzheimers Dement. 2017 Mar;13(3):285-295
pubmed: 28341066
Radiology. 2013 Feb;266(2):583-91
pubmed: 23232293
Curr Alzheimer Res. 2015;12(1):69-79
pubmed: 25523428
Eur Neurol. 1996;36(5):268-72
pubmed: 8864706
Neurobiol Aging. 2011 Dec;32(12):2322.e19-27
pubmed: 20594615
Neurodegener Dis. 2014;13(2-3):200-2
pubmed: 23969422
Neurology. 2013 Mar 19;80(12):1124-32
pubmed: 23446677
PLoS One. 2014 Aug 20;9(8):e105542
pubmed: 25141298
Lancet Neurol. 2009 Jul;8(7):619-27
pubmed: 19523877
Alzheimers Dement (Amst). 2018 Oct 08;10:726-736
pubmed: 30619929
J Alzheimers Dis. 2012;32(4):969-79
pubmed: 22890102
Alzheimers Dement. 2014 Nov;10(6):844-52
pubmed: 24798886
Lancet Neurol. 2013 Feb;12(2):207-16
pubmed: 23332364
Neurology. 1998 Dec;51(6):1546-54
pubmed: 9855500
Acta Psychiatr Scand. 2014 Dec;130(6):439-51
pubmed: 25219393
PLoS One. 2013;8(2):e55246
pubmed: 23424625
JAMA Neurol. 2017 Dec 1;74(12):1481-1491
pubmed: 29049480
J Alzheimers Dis. 2015;44(1):79-92
pubmed: 25201784
J Alzheimers Dis. 2015;50(1):261-70
pubmed: 26577521
Neurology. 1993 Feb;43(2):250-60
pubmed: 8094895
Front Aging Neurosci. 2018 Apr 25;10:111
pubmed: 29922145
Alzheimers Dement (N Y). 2017 May 10;3(3):305-313
pubmed: 29067337
IEEE Trans Biomed Eng. 2012 Jan;59(1):234-40
pubmed: 21990325
Dement Geriatr Cogn Disord. 2012;34(5-6):344-50
pubmed: 23222123
Alzheimers Dement. 2013 Sep;9(5):481-7
pubmed: 23232269
J Alzheimers Dis. 2014;41(3):685-708
pubmed: 24718104
Alzheimers Dement (N Y). 2017 May 09;3(3):301-304
pubmed: 29067336
Curr Opin Neurol. 2017 Aug;30(4):371-379
pubmed: 28520598
Neurology. 2005 Dec 27;65(12):1863-72
pubmed: 16237129
J Neurol Neurosurg Psychiatry. 2012 Nov;83(11):1038-40
pubmed: 22566596
Neurobiol Aging. 2012 Jul;33(7):1203-14
pubmed: 21159408
Dement Geriatr Cogn Disord. 2010;29(4):325-34
pubmed: 20389074
Acta Psychiatr Scand. 2009 Apr;119(4):252-65
pubmed: 19236314
Alzheimers Dement. 2011 May;7(3):263-9
pubmed: 21514250
J Alzheimers Dis. 2011;27(1):163-76
pubmed: 21799247
Alzheimers Res Ther. 2016 Dec 9;8(1):51
pubmed: 27931251