A Tool for Automatic Scoring of Spelling Performance

Themistocleous, Charalambos; Neophytou, Kyriaki; Rapp, Brenda; Tsapkini, Kyrana

doi:10.1044/2020_jslhr-20-00177

Cited by 14 publications

(9 citation statements)

References 34 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, such technologies have scarcely been tested in PPA. Two such examples include the automated analysis of spelling errors 38 and the automated analysis of two written works in a patient with svPPA. 12 In-depth analysis of written language can be time consuming, and therefore is not routinely incorporated into clinical practice.…”

Section: Discussionmentioning

confidence: 99%

Automated analysis of written language in the three variants of primary progressive aphasia

Josephy‐Hernandez

Rezaii

Jones

et al. 2023

Brain Communications

View full text Add to dashboard Cite

Despite the important role of written language in everyday life, abnormalities in functional written communication have been sparsely investigated in primary progressive aphasia. Prior studies have analyzed written language separately in each of the three variants of primary progressive aphasia – but have rarely compared them to each other or to spoken language. Manual analysis of written language can be a time-consuming process. We therefore developed a program which quantifies content units and total units in written or transcribed language samples. We analyzed written and spoken descriptions of the Western Aphasia Battery Picnic scene, based on a pre-defined content unit corpus. We calculated the ratio of content units to units as a measure of content density. Our cohort included 115 participants (20 controls for written, 20 controls spoken, 28 participants with nonfluent variant primary progressive aphasia, 30 logopenic variant, 17 semantic variant). Our program identified content units with a validity of 99.7% (95%CI 99.5-99.8). All patients wrote fewer units than controls (p<0.001). Patients with the logopenic variant (p=0.013) and the semantic variant (0.004) wrote fewer content units than controls. The content-unit-to-unit ratio was higher in the nonfluent and semantic variants than controls (p=0.019), but no different in the logopenic variant (p=0.962). Participants with the logopenic (p<0.001) and semantic (p=0.04) variants produced fewer content units in written compared to spoken descriptions. All variants produced fewer units in written samples compared to spoken (p<0.001). However, due to a relatively smaller decrease in written content units, we observed a larger content-unit-to-unit ratio in writing over speech (p<0.001). Written and spoken content units (r=0.5, p=0.009) and total units (r=0.64, p<0.001) were significantly correlated in patients with nonfluent variant, but this was not the case for logopenic or semantic. Considering all patients with primary progressive aphasia, fewer content units were produced in those with greater aphasia severity (Progressive Aphasia Severity Scale Sum of Boxes, r=-0.24, p=0.04) and dementia severity (Clinical Dementia Rating scale Sun of Boxes, r=-0.34, p=0.004). In conclusion, we observed reduced written content in patients with primary progressive aphasia compared to controls, with a preference for content over non-content units in patients with the nonfluent and semantic variants. We observed a similar “telegraphic” style in both language modalities in patients with the nonfluent variant. Lastly, we show how our program provides a time-efficient tool, which could enable feedback and tracking of writing as an important feature of language and cognition.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated analysis of written language in the three variants of primary progressive aphasia

Josephy‐Hernandez

Rezaii

Jones

et al. 2023

Brain Communications

View full text Add to dashboard Cite

show abstract

“…However, such technologies have scarcely been tested in PPA. Two such examples include the automated analysis of spelling errors 37 and the automated analysis of two written works in a patient with svPPA. 12 In-depth analysis of written language can be time-consuming, and therefore is not routinely incorporated into clinical practice.…”

Section: Discussionmentioning

confidence: 99%

Automated analysis of written language in the three variants of primary progressive aphasia

Josephy‐Hernandez

Rezaii

Jones

et al. 2022

Preprint

View full text Add to dashboard Cite

Despite the important role of written language in everyday life, abnormalities in functional written communication have been sparsely investigated in Primary Progressive Aphasia (PPA). Prior studies have analyzed written language separately in the three variants of PPA - nonfluent (nfvPPA), logopenic (lvPPA), and semantic (svPPA) - but have rarely compared them to each other or to spoken language. Manual analysis of written language can be a time-consuming process. We developed a program which uses a language parser and quantifies content units (CU) and total units (U) in written language samples. The program was used to analyze written and spoken descriptions of the WAB Picnic scene, based on a pre-defined CU corpus. We then calculated the ratio of CU to U (CU/U Ratio) as a measure of content density. Our cohort included 115 participants (20 control participants for written, 20 control participants for spoken, 28 participants with nfvPPA, 30 with lvPPA, and 17 with svPPA). We compared written language between patients with PPA and control participants and written to spoken language in patients with the three variants of PPA. Finally, we analyzed CU and U in relation to the Progressive Aphasia Severity Scale Sum of Boxes and the Clinical Dementia Rating Sum of Boxes. Our program identified CU with a validity of 99.7% (95%CI 99.5 to 99.8) compared to manual annotation of the samples. All patients with PPA wrote fewer total units than controls (p<0.001). Patients with lvPPA (p=0.013) and svPPA (0.004) wrote fewer CU than controls. The CU/U Ratio was higher in nfvPPA and svPPA than controls (p=0.019 in both cases), but no different between lvPPA patients and controls (p=0.962). Participants with lvPPA (p<0.001) and svPPA (p=0.04) produced fewer CU in written samples compared to spoken. A two-way ANOVA showed all groups produced fewer units in written samples compared to spoken (p<0.001). However, the decrease in written CU compared to spoken was smaller than the decrease in written units compared to spoken in participants with PPA, resulting in a larger written CU/U Ratio when compared to spoken language (p<0.001). nfvPPA patients produced correlated written and spoken CU (R=0.5, p=0.009) and total units (R=0.64, p<0.001), but this was not the case for lvPPA or svPPA. Considering all PPA patients, fewer CU were produced in those with greater aphasia severity (PASS SoB, R=-0.24, p=0.04) and dementia severity (CDR SoB, R=-0.34, p=0.004). In conclusion, we observed reduced written content in patients with PPA compared to controls, with a preference for content over non-content units in patients with nfvPPA and svPPA. When comparing written to spoken language, we observed a similar "telegraphic" style in both modalities in patients with nfvPPA, which was different from patients with svPPA and lvPPA, who use significantly less non-content units in writing than in speech. Lastly, we show how our program provides a time-efficient tool, which could enable feedback and tracking of writing as an important feature of language and cognition.

show abstract

“…or primary memory deficits. Differential diagnosis was based on three types of evidence: neuropsychological and language testing, MRI, and clinical assessment, according to criteria in Gorno-Tempini et al (2011) (see also Neophytou et al, 2019 ; Themistocleous et al, 2020 ). Demographic and clinical information for the participants is reported in Table 1 .…”

Section: Methodsmentioning

confidence: 99%

Selective Functional Network Changes Following tDCS-Augmented Language Treatment in Primary Progressive Aphasia

Tao

Ficek²,

Wang

et al. 2021

Front. Aging Neurosci.

Self Cite

View full text Add to dashboard Cite

ObjectiveTranscranial direct current stimulation (tDCS) has shown promising results when used as an adjunct to behavioral training in neurodegenerative diseases. However, the underlying neural mechanisms are not understood and neuroimaging evidence from pre/post treatment has been sparse. In this study, we examined tDCS-induced neural changes in a language intervention study for primary progressive aphasia (PPA), a neurodegenerative syndrome with language impairment as the primary clinical presentation. Anodal tDCS was applied to the left inferior frontal gyrus (LIFG). To evaluate the hypothesis that tDCS promotes system segregation, analysis focused on understanding tDCS-induced changes in the brain-wide functional network connectivity of the targeted LIFG.MethodsResting-state fMRI data were obtained from 32 participants with PPA before and after receiving a written naming therapy, accompanied either by tDCS or sham stimulation. We focused on evaluating changes in the global connectivity of the stimulated LIFG-triangularis (LIFG-tri) region given its important role in lexical processing. Global connectivity was indexed by the graph-theoretic measure participation coefficient (PC) which quantifies a region’s level of system segregation. The values before and after treatment were compared for each condition (tDCS or Sham) as well as with age-matched healthy controls (n = 19).ResultsHigher global connectivity of the LIFG-tri before treatment was associated with greater dementia severity. After treatment, the tDCS group showed a significant decrease in global connectivity whereas the Sham group’s did not change, suggesting specific neural effects induced by tDCS. Further examination revealed that the decrease was driven by reduced connectivity between the LIFG-tri and regions outside the perisylvian language area, consistent with the hypothesis that tDCS enhances the segregation of the language system and improves processing efficiency. Additionally, we found that these effects were specific to the LIFG-tri and not observed in other control regions.ConclusionTDCS-augmented language therapy in PPA increased the functional segregation of the language system, a normalization of the hyper-connectivity observed before treatment. These findings add to our understanding of the nature of tDCS-induced neural changes in disease treatment and have applications for validating treatment efficacy and designing future tDCS and other non-invasive brain stimulation (NIBS) treatments.

show abstract

A Tool for Automatic Scoring of Spelling Performance

Cited by 14 publications

References 34 publications

Automated analysis of written language in the three variants of primary progressive aphasia

Automated analysis of written language in the three variants of primary progressive aphasia

Automated analysis of written language in the three variants of primary progressive aphasia

Selective Functional Network Changes Following tDCS-Augmented Language Treatment in Primary Progressive Aphasia

Contact Info

Product

Resources

About