NLP-guided Video Thin-slicing for Automated Scoring of Non-Cognitive, Behavioral Performance Tasks

2021 ◽  
Author(s):  
Chee Wee Leong ◽  
Xianyang Chen ◽  
Vinay Basheerabad ◽  
Chong Min Lee ◽  
Patrick Houghton
PLoS ONE ◽  
2016 ◽  
Vol 11 (1) ◽  
pp. e0146356 ◽  
Author(s):  
Mi Li ◽  
Ning Zhong ◽  
Shengfu Lu ◽  
Gang Wang ◽  
Lei Feng ◽  
...  

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Leanne M. Williams ◽  
John T. Coman ◽  
Patrick C. Stetz ◽  
Nicole C. Walker ◽  
F. Andrew Kozel ◽  
...  

Abstract Background Although repetitive transcranial magnetic stimulation (‘TMS’) is becoming a gold standard treatment for pharmacoresistant depression, we lack neural target biomarkers for identifying who is most likely to respond to TMS and why. To address this gap in knowledge we evaluate neural targets defined by activation and functional connectivity of the dorsolateral prefrontal cortex-anchored cognitive control circuit, regions of the default mode network and attention circuit, and interactions with the subgenual anterior cingulate. We evaluate whether these targets and interactions between them change in a dose-dependent manner, whether changes in these neural targets correspond to changes in cognitive behavioral performance, and whether baseline and early change in neural target and cognitive behavioral performance predict subsequent symptom severity, suicidality, and quality of life outcomes. This study is designed as a pragmatic, mechanistic trial partnering with the National Clinical TMS Program of the Veteran’s Health Administration. Methods Target enrollment consists of 100 veterans with pharmacoresistant Major Depressive Disorder (MDD). All veterans will receive a clinical course of TMS and will be assessed at ‘baseline’ pre-TMS commencement, ‘first week’ after initiation of TMS (targeting five sessions) and ‘post-treatment’ at the completion of TMS (targeting 30 sessions). Veterans will be assessed using functional magnetic resonance imaging (fMRI), a cognitive behavioral performance battery, and established questionnaires. Multivariate linear mixed models will be used to assess whether neural targets change with TMS as a function of dose (Aim 1), whether extent and change of neural target relates to and predicts extent of behavioral performance (Aim 3), and whether extent of neural target change predicts improvement in symptom severity, suicidality, and quality of life (Aim 3). For all three aims, we will also assess the contribution of baseline moderators such as biological sex and age. Discussion To our knowledge, our study will be the first pragmatic, mechanistic observational trial to use fMRI imaging and cognitive-behavioral performance as biomarkers of TMS treatment response in pharmacoresistant MDD. The results of this trial will allow providers to select suitable candidates for TMS treatment and better predict treatment response by assessing circuit connectivity and cognitive-behavioral performance at baseline and during early treatment. Trial registration ClinicalTrials.gov NCT04663481, December 5th, 2020, retrospectively registered. The first veteran was enrolled October 30th, 2020.


Alcohol ◽  
2000 ◽  
Vol 20 (2) ◽  
pp. 187-192 ◽  
Author(s):  
E.Jon Popke ◽  
Sharon R Allen ◽  
Merle G Paule

Author(s):  
Peter W. Foltz

The ability to convey information through writing is a central component of real-world skills. However, assessing writing can be time consuming, limiting the timeliness of feedback. Automated scoring of writing has been shown to be effective across a number of applications. This chapter focuses on how automated scoring of writing has been extended to assessing and training of real-world skills in a range of content domains. It illustrates examples of how the technology is used and considerations for its implementation. The examples include 1) Formative feedback on writing quality, 2) scoring of content in student writing. 3) improving reading comprehension through summary writing, and 4) assessment of writing integrated in higher-level performance tasks in professional domains.


Author(s):  
Glenn Waller ◽  
Helen Cordery ◽  
Emma Corstorphine ◽  
Hendrik Hinrichsen ◽  
Rachel Lawson ◽  
...  

2017 ◽  
Vol 2 (1) ◽  
pp. 31-36
Author(s):  
Pascal Wabnitz ◽  
Michael Schulz ◽  
Michael Löhr ◽  
André Nienaber

2012 ◽  
Vol 11 (3) ◽  
pp. 118-126 ◽  
Author(s):  
Olive Emil Wetter ◽  
Jürgen Wegge ◽  
Klaus Jonas ◽  
Klaus-Helmut Schmidt

In most work contexts, several performance goals coexist, and conflicts between them and trade-offs can occur. Our paper is the first to contrast a dual goal for speed and accuracy with a single goal for speed on the same task. The Sternberg paradigm (Experiment 1, n = 57) and the d2 test (Experiment 2, n = 19) were used as performance tasks. Speed measures and errors revealed in both experiments that dual as well as single goals increase performance by enhancing memory scanning. However, the single speed goal triggered a speed-accuracy trade-off, favoring speed over accuracy, whereas this was not the case with the dual goal. In difficult trials, dual goals slowed down scanning processes again so that errors could be prevented. This new finding is particularly relevant for security domains, where both aspects have to be managed simultaneously.


Sign in / Sign up

Export Citation Format

Share Document