Clinical decision support systems (CDSSs) hold potential for the differential diagnosis of neurodegenerative diseases. We developed a novel CDSS, the PredictND tool, designed for differential diagnosis of different types of dementia. It combines information obtained from multiple diagnostic tests such as neuropsychological tests, MRI and cerebrospinal fluid samples. Here we evaluated how the classifier used in it performs in differentiating between controls with subjective cognitive decline, dementia due to Alzheimer’s disease, vascular dementia, frontotemporal lobar degeneration and dementia with Lewy bodies. We used the multiclass Disease State Index classifier, which is the classifier used by the PredictND tool, to differentiate between controls and patients with the four different types of dementia. The multiclass Disease State Index classifier is an extension of a previously developed two-class Disease State Index classifier. As the two-class Disease State Index classifier, the multiclass Disease State Index classifier also offers a visualization of its decision making process, which makes it especially suitable for medical decision support where interpretability of the results is highly important. A subset of the Amsterdam Dementia cohort, consisting of 504 patients (age 65 ± 8 years, 44% females) with data from neuropsychological tests, cerebrospinal fluid samples and both automatic and visual MRI quantifications, was used for the evaluation. The Disease State Index classifier was highly accurate in separating the five classes from each other (balanced accuracy 82.3%). Accuracy was highest for vascular dementia and lowest for dementia with Lewy bodies. For the 50% of patients for which the classifier was most confident on the classification the balanced accuracy was 93.6%. Data-driven CDSSs can be of aid in differential diagnosis in clinical practice. The decision support system tested in this study was highly accurate in separating the different dementias and controls from each other. In addition to the predicted class, it also provides a confidence measure for the classification.

Objectives. To study whether visual MRI rating scales used in diagnostics of cognitive disorders can be estimated computationally and to compare the visual rating scales with their computed counterparts in differential diagnostics. Methods. A set of volumetry and voxel-based morphometry imaging biomarkers was extracted from T1-weighted and FLAIR images. A regression model was developed for estimating visual rating scale values from a combination of imaging biomarkers. We studied three visual rating scales: medial temporal lobe atrophy (MTA), global cortical atrophy (GCA) and white matter hyperintensities (WMHs) measured by the Fazekas scale. Images and visual ratings from the Amsterdam Dementia Cohort (ADC) (N=513) were used to develop the models and cross validate them. The PredictND (N=672) and ADNI (N=752) cohorts were used for independent validation to test generalizability. Results. The correlation coefficients between visual and computed rating scale values were 0.83/0.78 (MTA-Left), 0.83/0.79 (MTA-Right), 0.64/0.64 (GCA) and 0.76/0.75 (Fazekas) in ADC/PredictND cohorts. When performance in differential diagnostics was studied for the main types of dementia, the highest balanced accuracy, 0.75-0.86, was observed for separating different dementias from cognitively normal subjects using computed GCA. The lowest accuracy of about 0.5 for all the visual and computed scales was observed for the differentiation between Alzheimer's disease and frontotemporal lobar degeneration. Computed scales produced higher balanced accuracies than visual scales for MTA and GCA (statistically significant). 2 Conclusions. MTA, GCA and WMHs can be reliably estimated automatically helping to provide consistent imaging biomarkers for diagnosing cognitive disorders, even among less-experienced readers.

BackgroundDiagnosing frontotemporal dementia may be challenging. New methods for analysis of regional brain atrophy patterns on magnetic resonance imaging (MRI) could add to the diagnostic assessment. Therefore, we aimed to develop automated imaging biomarkers for differentiating frontotemporal dementia subtypes from other diagnostic groups, and from one another.MethodsIn this retrospective multicenter cohort study, we included 1213 patients (age 67 ± 9, 48% females) from two memory clinic cohorts: 116 frontotemporal dementia, 341 Alzheimer's disease, 66 Dementia with Lewy bodies, 40 vascular dementia, 104 other dementias, 229 mild cognitive impairment, and 317 subjective cognitive decline. Three MRI atrophy biomarkers were derived from the normalized volumes of automatically segmented cortical regions: 1) the anterior vs. posterior index, 2) the asymmetry index, and 3) the temporal pole left index. We used the following performance metrics: area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. To account for the low prevalence of frontotemporal dementia we pursued a high specificity of 95%. Cross-validation was used in assessing the performance. The generalizability was assessed in an independent cohort (n = 200).ResultsThe anterior vs. posterior index performed with an AUC of 83% for differentiation of frontotemporal dementia from all other diagnostic groups (Sensitivity = 59%, Specificity = 95%, positive likelihood ratio = 11.8, negative likelihood ratio = 0.4). The asymmetry index showed highest performance for separation of primary progressive aphasia and behavioral variant frontotemporal dementia (AUC = 85%, Sensitivity = 79%, Specificity = 92%, positive likelihood ratio = 9.9, negative likelihood ratio = 0.2), whereas the temporal pole left index was specific for detection of semantic variant primary progressive aphasia (AUC = 85%, Sensitivity = 82%, Specificity = 80%, positive likelihood ratio = 4.1, negative likelihood ratio = 0.2). The validation cohort provided corresponding results for the anterior vs. posterior index and temporal pole left index.ConclusionThis study presents three quantitative MRI biomarkers, which could provide additional information to the diagnostic assessment and assist clinicians in diagnosing frontotemporal dementia.