Machine learning approaches to diagnosis and laterality effects in semantic dementia discourse

Garrard, Peter; Rentoumi, Vassiliki; Gesierich, Benno; Miller, Bruce L.; Gorno‐Tempini, Maria Luisa

doi:10.1016/j.cortex.2013.05.008

Cited by 78 publications

(58 citation statements)

References 31 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, we introduce the n -gram model [35], which captures the pattern of the sequence of words in the language of the disease and healthy elderly groups. We emphasise that the machine learning approach has proven to be effective in clinical diagnostics [3, 12, 36, 37]. Our predictive models achieved a better Area Under the ROC Curve (AUC) in distinguishing the probable AD group from the healthy elderly group.…”

Section: Introductionmentioning

confidence: 97%

Predicting probable Alzheimer’s disease using linguistic deficits and biomarkers

et al. 2017

View full text Add to dashboard Cite

BackgroundThe manual diagnosis of neurodegenerative disorders such as Alzheimer’s disease (AD) and related Dementias has been a challenge. Currently, these disorders are diagnosed using specific clinical diagnostic criteria and neuropsychological examinations. The use of several Machine Learning algorithms to build automated diagnostic models using low-level linguistic features resulting from verbal utterances could aid diagnosis of patients with probable AD from a large population. For this purpose, we developed different Machine Learning models on the DementiaBank language transcript clinical dataset, consisting of 99 patients with probable AD and 99 healthy controls.ResultsOur models learned several syntactic, lexical, and n-gram linguistic biomarkers to distinguish the probable AD group from the healthy group. In contrast to the healthy group, we found that the probable AD patients had significantly less usage of syntactic components and significantly higher usage of lexical components in their language. Also, we observed a significant difference in the use of n-grams as the healthy group were able to identify and make sense of more objects in their n-grams than the probable AD group. As such, our best diagnostic model significantly distinguished the probable AD group from the healthy elderly group with a better Area Under the Receiving Operating Characteristics Curve (AUC) using the Support Vector Machines (SVM).ConclusionsExperimental and statistical evaluations suggest that using ML algorithms for learning linguistic biomarkers from the verbal utterances of elderly individuals could help the clinical diagnosis of probable AD. We emphasise that the best ML model for predicting the disease group combines significant syntactic, lexical and top n-gram features. However, there is a need to train the diagnostic models on larger datasets, which could lead to a better AUC and clinical diagnosis of probable AD.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1456-0) contains supplementary material, which is available to authorized users.

show abstract

Section: Introductionmentioning

confidence: 97%

Predicting probable Alzheimer’s disease using linguistic deficits and biomarkers

et al. 2017

View full text Add to dashboard Cite

show abstract

“…A closely related work to ours is Garrard et al (2013) research. The study used Naïve Bayes Gaussian (NBG) and Naïve Bayes multinomial (NBM) to classify textual descriptions into a Dementia group and a healthy elderly group.…”

Section: Related Workmentioning

confidence: 99%

Learning Predictive Linguistic Features for Alzheimer’s Disease and related Dementias using Verbal Utterances

Orimaye¹,

Wong²,

Golden³

2014

Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality

View full text Add to dashboard Cite

Early diagnosis of neurodegenerative disorders (ND) such as Alzheimer's disease (AD) and related Dementias is currently a challenge. Currently, AD can only be diagnosed by examining the patient's brain after death and Dementia is diagnosed typically through consensus using specific diagnostic criteria and extensive neuropsychological examinations with tools such as the Mini-Mental State Examination (MMSE) or the Montreal Cognitive Assessment (MoCA). In this paper, we use several Machine Learning (ML) algorithms to build diagnostic models using syntactic and lexical features resulting from verbal utterances of AD and related Dementia patients. We emphasize that the best diagnostic model distinguished the AD and related Dementias group from the healthy elderly group with 74% FMeasure using Support Vector Machines (SVM). Additionally, we perform several statistical tests to indicate the significance of the selected linguistic features. Our results show that syntactic and lexical features could be good indicative features for helping to diagnose AD and related Dementias.

show abstract

“…Sighting dominance, i.e. the eye that is consistently favored under monocular viewing, has traditionally been considered to be a robust individual trait [115]. However, Khan and Crawford [116,117] found that subjects altered ocular dominance as a function of horizontal gaze direction in a reaching task.…”

Section: Reviewmentioning

confidence: 99%

“…However, Khan and Crawford [116,117] found that subjects altered ocular dominance as a function of horizontal gaze direction in a reaching task. Notably, the alternating of ocular dominance depends on which hand is used to reach out and grasp the target [115,117]. …”

Section: Reviewmentioning

confidence: 99%

The optic chiasm: a turning point in the evolution of eye/hand coordination

Larsson

2013

Front Zool

View full text Add to dashboard Cite

The primate visual system has a uniquely high proportion of ipsilateral retinal projections, retinal ganglial cells that do not cross the midline in the optic chiasm. The general assumption is that this developed due to the selective advantage of accurate depth perception through stereopsis. Here, the hypothesis that the need for accurate eye-forelimb coordination substantially influenced the evolution of the primate visual system is presented. Evolutionary processes may change the direction of retinal ganglial cells. Crossing, or non-crossing, in the optic chiasm determines which hemisphere receives visual feedback in reaching tasks. Each hemisphere receives little tactile and proprioceptive information about the ipsilateral hand. The eye-forelimb hypothesis proposes that abundant ipsilateral retinal projections developed in the primate brain to synthesize, in a single hemisphere, visual, tactile, proprioceptive, and motor information about a given hand, and that this improved eye-hand coordination and optimized the size of the brain. If accurate eye-hand coordination was a major factor in the evolution of stereopsis, stereopsis is likely to be highly developed for activity in the area where the hands most often operate.The primate visual system is ideally suited for tasks within arm’s length and in the inferior visual field, where most manual activity takes place. Altering of ocular dominance in reaching tasks, reduced cross-modal cuing effects when arms are crossed, response of neurons in the primary motor cortex to viewed actions of a hand, multimodal neuron response to tactile as well as visual events, and extensive use of multimodal sensory information in reaching maneuvers support the premise that benefits of accurate limb control influenced the evolution of the primate visual system. The eye-forelimb hypothesis implies that evolutionary change toward hemidecussation in the optic chiasm provided parsimonious neural pathways in animals developing frontal vision and visually guided forelimbs, and also suggests a new perspective on vision convergence in prey and predatory animals.

show abstract

Machine learning approaches to diagnosis and laterality effects in semantic dementia discourse

Cited by 78 publications

References 31 publications

Predicting probable Alzheimer’s disease using linguistic deficits and biomarkers

Predicting probable Alzheimer’s disease using linguistic deficits and biomarkers

Learning Predictive Linguistic Features for Alzheimer’s Disease and related Dementias using Verbal Utterances

The optic chiasm: a turning point in the evolution of eye/hand coordination

Contact Info

Product

Resources

About