Impact of a clinical decision support tool on prediction of progression in early-stage dementia: a prospective validation study

Abstract

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.

Keywords: Alzheimer’s disease; CDSS; Computer-assisted; Conversion; Dementia; Mild cognitive impairment; Progression; Subjective cognitive decline.

Fig. 1

Flow diagram of the study

Fig. 2

Disease state fingerprints from the PredictND tool. a A 46-year-old male with a family history of early-onset dementia and 1 year of word-finding problems, loss of initiative, and subjective complaints of affected memory and sleep. Aβ42, 1059 ng/L; total tau, 201 ng/L; and P-tau, 43 ng/L. Diagnosed with SCD at baseline. The DSI value (0.06) predicted a stable condition and increased the clinician’s confidence from a VAS score of 55% to 80% in the prediction of stable SCD. After the 18-month follow-up, the diagnosis was still stable SCD. b A 76-year-old female with mild forgetfulness for words and names during the last 2 years. Normal daily function. MMSE, 30; CERAD learning, 21/30; and CERAD recall, 1/10. Diagnosed with MCI at baseline. The DSI value (0.51) did not indicate a clear stable or progressive condition. The clinician without tool predicted the follow-up diagnosis to be stable MCI, whereas the clinician with tool predicted the patient to progress to AD dementia. The diagnosis at 24-month follow-up was MCI, but after the end of the project at a 3-year follow-up visit, the patient was diagnosed with AD dementia. c A 74-year-old male with memory problems for events and names, loss of initiative, and orientation. Aβ42, 358 ng/L; total tau, 370 ng/L; and P-tau, 50 ng/L. Diagnosed with amnestic MCI at baseline. The DSI value (0.78) predicted progression and increased the clinician’s confidence in the prediction of progression to dementia by 30% on the VAS scale. After the 12-month follow-up, the patient had progressed to AD dementia

Fig. 3

The number of changed predictions after application of the PredictND tool, stratified by DSI values. DSI disease state index