English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Strategy training is a multidisciplinary rehabilitation approach that teachesskills to reduce disability among those with cognitive impairments following astroke. Strategy training has been shown in randomized, controlled clinicaltrials to be a more feasible and efficacious intervention for promotingindependence than traditional rehabilitation approaches. A standardizedfidelity assessment is used to measure adherence to treatment principles byexamining guided and directed verbal cues in video recordings of rehabilitationsessions. Although the fidelity assessment for detecting guided and directedverbal cues is valid and feasible for single-site studies, it can become laborintensive, time consuming, and expensive in large, multi-site pragmatic trials.To address this challenge to widespread strategy training implementation, weleveraged natural language processing (NLP) techniques to automate the strategytraining fidelity assessment, i.e., to automatically identify guided anddirected verbal cues from video recordings of rehabilitation sessions. Wedeveloped a rule-based NLP algorithm, a long-short term memory (LSTM) model,and a bidirectional encoder representation from transformers (BERT) model forthis task. The best performance was achieved by the BERT model with a 0.8075F1-score. This BERT model was verified on an external validation datasetcollected from a separate major regional health system and achieved an F1 scoreof 0.8259, which shows that the BERT model generalizes well. The findings fromthis study hold widespread promise in psychology and rehabilitationintervention research and practice.

Automated Fidelity Assessment for Strategy Training in Inpatient Rehabilitation using Natural Language Processing