Biomarkers.

Background: The increasing dementia prevalence and potential introduction of disease-modifying therapies (DMTs) highlight the need for efficient diagnostic pathways. Clear recommendations to guide the choice of diagnostic tests are lacking and may vary depending on different clinical scenarios. We used a data-driven approach to identify efficient and effective stepwise diagnostic testing for three clinical scenarios: 1) syndrome diagnosis, 2) etiological diagnosis, 3) potential eligibility for DMT.

Method: We used data from two memory clinic cohorts (ADC, PredictND), including 504 patients with dementia (302 Alzheimer's disease, 107 frontotemporal dementia, 35 vascular dementia, 60 dementia with Lewy bodies), 191 patients with mild cognitive impairment, and 188 cognitively healthy controls (CN). Tests included digital cognitive screening (cCOG), neuropsychological and functional assessment (NP), MRI with automated quantification, and CSF biomarkers. Sequential testing followed a predetermined order (Figure 1). Subsequent tests were conducted if the diagnosis remained uncertain. Diagnostic certainty was ascertained through a data-driven clinical decision support system (CDSS) that generated a disease state index probability score (DSI, 0-1), indicating the probability of each diagnosis. Diagnosis was confirmed if the DSI exceeded a predefined threshold, set based on sensitivity/specificity cutoffs relevant for each clinical scenario and step. We assessed correct diagnoses and the need for additional testing at each step.

Result: For syndrome diagnosis, stepwise testing (cCOG, NP, MRI) accurately identified 71% of the patients, with NP needed in 42%, and MRI in 31%. For etiological diagnosis, starting with cognitive testing to rule out dementia resulted in the need for MRI in 84% of cases, including 91% of dementia patients and 25% CN. Subsequent MRI reduced CSF required to 29%, ultimately diagnosing 81% of patients with 71% accuracy. In determining DMT eligibility, stepwise testing (cCOG, NP, MRI) correctly identified 91% of potential eligible patients for confirmatory CSF testing, while only 51% of ineligible patients.

Conclusion: Depending on the setting, alternative diagnostic pathways are accurate and efficient. As such, a data-driven tool can assist clinicians in selecting tests of added value across different clinical contexts. This becomes especially important with DMT availability, where the need for more efficient diagnostic pathways is crucial to maintain accessibility and affordability of diagnoses.