A 'Mini Linguistic State Examination' to classify primary progressive aphasia

Abstract

There are few available methods for qualitatively evaluating patients with primary progressive aphasia. Commonly adopted approaches are time-consuming, of limited accuracy or designed to assess different patient populations. This paper introduces a new clinical test-the Mini Linguistic State Examination-which was designed uniquely to enable a clinician to assess and subclassify both classical and mixed presentations of primary progressive aphasia. The adoption of a novel assessment method (error classification) greatly amplifies the clinical information that can be derived from a set of standard linguistic tasks and allows a five-dimensional profile to be defined. Fifty-four patients and 30 matched controls were recruited. Five domains of language competence (motor speech, phonology, semantics, syntax and working memory) were assessed using a sequence of 11 distinct linguistic assays. A random forest classification was used to assess the diagnostic accuracy for predicting primary progressive aphasia subtypes and create a decision tree as a guide to clinical classification. The random forest prediction model was 96% accurate overall (92% for the logopenic variant, 93% for the semantic variant and 98% for the non-fluent variant). The derived decision tree produced a correct classification of 91% of participants whose data were not included in the training set. The Mini Linguistic State Examination is a new cognitive test incorporating a novel and powerful, yet straightforward, approach to scoring. Rigorous assessment of its diagnostic accuracy confirmed excellent matching of primary progressive aphasia syndromes to clinical gold standard diagnoses. Adoption of the Mini Linguistic State Examination by clinicians will have a decisive impact on the consistency and uniformity with which patients can be described clinically. It will also facilitate screening for cohort-based research, including future therapeutic trials, and is suitable for describing, quantifying and monitoring language deficits in other brain disorders.

Keywords: frontotemporal dementia; primary progressive aphasia; random forest classifier.

Graphical Abstract

Figure 1

MLSE domain scores (A–E) and total score (F) grouped by diagnosis. The boxes represent IQRs, horizontal lines the medians and error bars the minimum and maximum values excluding outliers. The latter are represented by the symbols ‘circle’ (values which are between 1.5 and 3.0 times the IQR below the first quartile or above the third) and ‘asterisk’ (values which are >3.0 times the IQR below the first quartile or above the third).

Figure 2

MLSE results. Mean percentage scores with error bars showing standard deviations in five linguistic domains grouped by PPA subtype and healthy controls. lvPPA, logopenic variant PPA; nfvPPA, non-fluent variant PPA; svPPA, semantic variant PPA.

Figure 3

Domain accuracies. Independent ROC curves demonstrating the accuracy of all five linguistic domains for each PPA subtype.

Figure 4

MLSE diagnostic decision tree. On the scores of the five linguistic domains to classify PPA subtypes from the out-of-sample data, this decision tree yielded correct classifications of 91% (31/34 participants—9 lvPPA, 7 svPPA, 7, nfvPPA, 11 controls). lvPPA, logopenic variant PPA; nfvPPA, non-fluent variant PPA; svPPA, semantic variant PPA.