2018
DOI: 10.1016/j.jelectrocard.2018.08.007
|View full text |Cite
|
Sign up to set email alerts
|

Automation bias in medicine: The influence of automated diagnoses on interpreter accuracy and uncertainty when reading electrocardiograms

Abstract: Incorrect ADs reduce the interpreter's diagnostic accuracy indicating an automation bias. Non-CFs tend to agree more with the ADs in comparison to CFs, hence less expert physicians are more effected by automation bias. Incorrect ADs reduce the interpreter's confidence and also reduces the predictive power of confidence for predicting accuracy (even more so for non-CFs). Whilst a statistically significant model was developed, it is difficult to predict interpretation accuracy using machine learning on basic fea… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
43
1
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 74 publications
(46 citation statements)
references
References 16 publications
1
43
1
1
Order By: Relevance
“…Such an algorithm could be implemented into a computerised ECG machine and a certainty index could be displayed alongside the suggested diagnosis. Other ways to help counter automation bias could include the use of touch-screen technology to provide a more user-friendly interface and provide prompts alongside a clinical decision tool to augment decision making [16].…”
Section: Discussionmentioning
confidence: 99%
“…Such an algorithm could be implemented into a computerised ECG machine and a certainty index could be displayed alongside the suggested diagnosis. Other ways to help counter automation bias could include the use of touch-screen technology to provide a more user-friendly interface and provide prompts alongside a clinical decision tool to augment decision making [16].…”
Section: Discussionmentioning
confidence: 99%
“…Once ADMS have the ability to make qualitative decisions, the risk of giving power to ADMS to judge what is our 'real' self and deciding what we really want, our autonomy is jeopardized, our capacities are blocked and we are less free. 3 To protect our freedom from ADMS taking control of who we are and what we do, we must retain the exercise of self-realization. Through self-understanding and self-reflection, ADMS remain as tools performing specific tasks that we, as self-reflecting humans, have decided will contribute towards the autonomous exercise of our self-realization.…”
Section: Freedom 31 An Exercise Conceptmentioning
confidence: 99%
“…It exists when humans over-rely on automation to complete a task complacently because it requires minimal effort or they believe the ADMS have superior intelligence. [3](44) An ADMS outcome would be accepted without validating against data bias, what is not taken into account, and the prediction's optimization constraints. The psychological status bestowed on ADMS contributes to complacency bias.…”
Section: Biasmentioning
confidence: 99%
See 1 more Smart Citation
“…Data fusion can also be applied to implantable devices to generate data telemetry systems [36] with patient profiles [37]. Decision trees [38], support vector machine, neural networks [39], uncertainty index [40] and hybrid intelligent systems consisting of fuzzy logic and genetic algorithms [41] have been employed as classification approaches for data fusion in medicine. Decision tree classifiers were used to build a classification model in the form of a tree from the patient biomarker data [42].…”
Section: Introductionmentioning
confidence: 99%