AI Assistance for Cognitive Overload

Overseen By Victoria Xu

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: UNC Lineberger Comprehensive Cancer Center

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 1

10 Participants Needed

Trial Summary

What is the purpose of this trial?

The goal of this study is to explore cognitive burden perceptions among physicians in relation to case report writing. Furthermore, this study evaluates the use of artificial intelligence (AI) assistance as a tool to reduce cognitive burden among providers preparing and submitting case reports. If an AI-tool is helpful in this setting, it may potentially help increase reporting of rare medical events and thereby improve the evidence base for care of these patient populations. This study will occur at a single time point which is expected to last approximately 2 hours. This session will include reviewing two rare tumor cases and then writing a clinical vignette with and without AI assistance.

Do I need to stop taking my current medications for this trial?

The trial information does not specify whether you need to stop taking your current medications. It seems unlikely since the study focuses on cognitive tasks and AI assistance, not on medication effects.

What data supports the effectiveness of the treatment Artificial Intelligence for cognitive overload?

Research suggests that artificial intelligence (AI) can help reduce the mental and work burden on healthcare professionals, potentially leading to less burnout and better care. This indicates that AI might be effective in managing cognitive overload by easing the mental demands on individuals. ^{1 2 3 4 5}

Is AI generally safe for use in healthcare settings?

AI has been shown to improve patient safety by predicting and preventing adverse events like drug reactions and diagnostic errors. Studies suggest that AI can help reduce harm in healthcare, indicating it is generally safe when used properly. ^{6 7 8 9 10}

How does the AI Assistance for Cognitive Overload treatment differ from other treatments for cognitive overload?

This treatment is unique because it uses AI to detect and respond to information overload by adjusting the amount of information presented to the user, which is different from traditional methods that may not dynamically adapt to the user's cognitive state. ^{11 12 13 14 15}

Research Team

Shivani Sud

Principal Investigator

UNC Lineberger Comprehensive Cancer Center

Eligibility Criteria

This trial is for physicians, medical students, or postdoctoral students. It's designed to see if AI can help reduce the mental effort they use when writing about rare tumor cases.

Inclusion Criteria

The subject is a physician, medical student, or postdoctoral student.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

1 week

Single Session

Participants review two rare tumor cases and write a clinical vignette with and without AI assistance

2 hours

1 visit (in-person)

Follow-up

Participants are monitored for cognitive workload and perceived cognitive load using NASA-TLX and SUS

1 week

Treatment Details

Interventions

• Artificial Intelligence

Trial Overview The study tests whether artificial intelligence (AI) assistance can ease cognitive workload during the preparation and submission of case reports on rare tumors by comparing report writing with and without AI help.

Participant Groups

Group I: Case Report with Artificial Intelligence Experimental Treatment 1 Intervention

Medical students, resident physicians, or attending physicians report rare cases with using Artificial Intelligence.

Group II: Case Report without Artificial Intelligence Active Control 1 Intervention

Medical students, resident physicians, or attending physicians report rare cases without using Artificial Intelligence.

Who Is Running the Clinical Trial?

UNC Lineberger Comprehensive Cancer Center

Lead Sponsor

Trials

377

Recruited

95,900+

References

1. England pubmed.ncbi.nlm.nih.gov

Investigating the cognitive capacity constraints of an ICU care team using a systems engineering approach. [2022]

2. United States pubmed.ncbi.nlm.nih.gov

Comparing cognitive load levels among family members of the critically ill exposed to electronic decision aids. [2020]

3. United States pubmed.ncbi.nlm.nih.gov

How can artificial intelligence decrease cognitive and work burden for front line practitioners? [2023]

4. England pubmed.ncbi.nlm.nih.gov

Assessing workload in neuropsychology: An illustration with the Tower of Hanoi test. [2019]

5. England pubmed.ncbi.nlm.nih.gov

The effect of multitasking on the communication skill and clinical skills of medical students. [2018]

6. England pubmed.ncbi.nlm.nih.gov

The potential of artificial intelligence to improve patient safety: a scoping review. [2021]

7. Netherlands pubmed.ncbi.nlm.nih.gov

Contribution of human factors for the review of automatically detected ADE. [2017]

8. Netherlands pubmed.ncbi.nlm.nih.gov

Human factors engineering for computer-supported identification and prevention of adverse drug events. [2017]

9. United States pubmed.ncbi.nlm.nih.gov

Conclusion: You need human factors engineering expertise to see design hazards that are hiding in "plain sight!". [2019]

10. Netherlands pubmed.ncbi.nlm.nih.gov

Assessment of mental workload based on multi-physiological signals. [2021]

11. United States pubmed.ncbi.nlm.nih.gov

Are the limits of the mind expandable? [2019]

12. United States pubmed.ncbi.nlm.nih.gov

Operator functional state classification using multiple psychophysiological features in an air traffic control task. [2017]

13. United States pubmed.ncbi.nlm.nih.gov

Detecting and Responding to Information Overload With an Adaptive User Interface. [2022]

14. Netherlands pubmed.ncbi.nlm.nih.gov

What is the relationship between mental workload factors and cognitive load types? [2012]

15. United States pubmed.ncbi.nlm.nih.gov

Double trade-off curves with different cognitive processing combinations: testing the cancellation axiom of mental workload measurement theory. [2017]