Data-Driven Differential Diagnosis of Dementia Using Multiclass Disease State Index Classifier

Abstract

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.

Detecting Amyloid Positivity in Elderly With Increased Risk of Cognitive Decline

“…DSI is a supervised machine learning method developed at the VTT Technical Research Centre of Finland (Mattila et al, 2011). Its accuracy is comparable to other methods such as logistic regression, support vector machines, and Bayes inference (Mattila et al, 2011), and it has been successful in modeling MCI progression (Hall et al, 2015) and discriminating between dementia types (Koikkalainen et al, 2016;Tolonen et al, 2018). DSI classifies individuals into Aβ positive and negative based on a population with known Aβ status (training population).…”

Gait Disturbances are Associated with Increased Cognitive Impairment and Cerebrospinal Fluid Tau Levels in a Memory Clinic Cohort

“…An early and accurate diagnosis is essential to provide appropriate care, information, and inclusion to clinical trials. However, diagnosing correctly can be difficult due to overlapping symptoms, comorbid pathologies, and relatively general diagnostic guidelines [3]. Biomarkers are of increasing importance and improve diagnosis accuracy, but are not always available [4].…”

Selection of memory clinic patients for CSF biomarker assessment can be restricted to a quarter of cases by using computerized decision support, without compromising diagnostic accuracy

“…Our stepwise approach meets all these requirements; well-known CSF values are https://doi.org/10.1371/journal.pone.0226784.g003 simulated in a simple way and the tool provides a suggestion on the usefulness of CSF testing. We used the DSI classifier, an existing, validated machine learning algorithm [10,12]. The DSI classifier has a graphical counterpart which makes interpretation of results to clinicians more transparent (an example is shown in Fig 3), tolerates missing data (no imputation needed), and gives information about the confidence of the classification.…”

“…All variables are corrected for age and sex [32]. Due to the design of DSI, there is no need to impute data or exclude cases with incomplete data, as only available data are used [10].…”

“…The latter had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.' types of dementia [9,10]. The DSI classifier can achieve high probability of correct diagnosis even without CSF biomarkers, by using an optimal combination of tests [11,12].…”