CoChat
Sign Up
Cited by 141Artificial Intelligence in Healthcare and EducationRadiology practices and educationAI in cancer detection

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Can incorrect artificial intelligence (AI) results impact radiologists, and if so, what can we do about it? A multi-reader pilot study of lung cancer detection with chest radiography

Open access
Bernstein, Michael H., Atalay, Michael K., Dibble, Elizabeth H., Maxwell, Aaron W. P., Karam, Adib R., Agarwal, Saurabh, Ward, Robert C., Healey, Terrance T., Baird, Grayson L.·2023·European Radiology
DOI 10.1007/s00330-023-09747-1PMC PMC10235827
Open this paper in CoChat — free accountOpen PDF

Abstract

Objective: To examine whether incorrect AI results impact radiologist performance, and if so, whether human factors can be optimized to reduce error. Methods: Multi-reader design, 6 radiologists interpreted 90 identical chest radiographs (follow-up CT needed: yes/no) on four occasions (09/20–01/22). No AI result was provided for session 1. Sham AI results were provided for sessions 2–4, and AI for 12 cases were manipulated to be incorrect (8 false positives (FP), 4 false negatives (FN)) (0.87 ROC-AUC). In the Delete AI (No Box) condition, radiologists were told AI results would not be saved for the evaluation. In Keep AI (No Box) and Keep AI (Box), radiologists were told results would be saved. In Keep AI (Box), the ostensible AI program visually outlined the region of suspicion. AI results were constant between conditions. Results: Relative to the No AI condition (FN = 2.7%, FP = 51.4%), FN and FPs were higher in the Keep AI (No Box) (FN = 33.0%, FP = 86.0%), Delete AI (No Box) (FN = 26.7%, FP = 80.5%), and Keep AI (Box) (FN = to 20.7%, FP = 80.5%) conditions (all p s < 0.05). FNs were higher in the Keep AI (No Box) condition (33.0%) than in the Keep AI (Box) condition (20.7%) (p = 0.04). FPs were higher in the Keep AI (No Box) (86.0%) condition than in the Delete AI (No Box) condition (80.5%) (p = 0.03). Conclusion: Incorrect AI causes radiologists to make incorrect follow-up decisions when they were correct without AI. This effect is mitigated when radiologists believe AI will be deleted from the patient’s file or a box is provided around the region of interest. Clinical relevance statement: When AI is wrong, radiologists make more errors than they would have without AI. Based on human factors psychology, our manuscript provides evidence for two AI implementation strategies that reduce the deleterious effects of incorrect AI. Key Points: • When AI provided incorrect results, false negative and false positive rates among the radiologists increased. • False positives decreased when AI results were deleted, versus kept, in the patient’s record. • False negatives and false positives decreased when AI visually outlined the region of suspicion.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s00330-023-09747-1

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Study flow chart. Overall experimental procedure is displayed. The order of Keep AI (No Box) and Delete AI (No Box) was counterbalanced such that n = 3 participated in Keep AI (No Box) first, and n = 2 participated in Delete AI (No Box) first
Fig. 1 Study flow chart. Overall experimental procedure is displayed. The order of Keep AI (No Box) and Delete AI (No Box) was counterbalanced such that n = 3 participated in Keep AI (No Box) first, and n = 2 participated in Delete AI (No Box) firstCC BY · PubMed Central
Fig. 2 Procedural overview. A brief description of the major procedural elements within each session is shown
Fig. 2 Procedural overview. A brief description of the major procedural elements within each session is shownCC BY · PubMed Central
Fig. 3 False negatives (incorrect AI feedback) by experimental condition. False negative percent (y-axis) is shown for the No AI (red), Keep AI (No Box) (brown), Delete AI (No Box) (green), and Keep AI (Box) (blue) conditions (x-axis). Mean (circle) and 95% confidence intervals are displayed. Results display the four conditions for the 4 cases where AI provided false negative feedback
Fig. 3 False negatives (incorrect AI feedback) by experimental condition. False negative percent (y-axis) is shown for the No AI (red), Keep AI (No Box) (brown), Delete AI (No Box) (green), and Keep AI (Box) (blue) conditions (x-axis). Mean (circle) and 95% confidence intervals are displayed. Results display the four conditions for the 4 cases where AI provided false negative feedbackCC BY · PubMed Central
Fig. 4 False positives (incorrect AI feedback) by experimental condition. False positive percent (y-axis) is shown for the No AI (red), Keep AI (No Box) (brown), Delete AI (No Box) (green), and Keep AI (Box) (blue) conditions (x-axis). Mean (circle) and 95% confidence intervals are displayed. Results display the four conditions for the 8 cases where AI provided false positive feedback
Fig. 4 False positives (incorrect AI feedback) by experimental condition. False positive percent (y-axis) is shown for the No AI (red), Keep AI (No Box) (brown), Delete AI (No Box) (green), and Keep AI (Box) (blue) conditions (x-axis). Mean (circle) and 95% confidence intervals are displayed. Results display the four conditions for the 8 cases where AI provided false positive feedbackCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 19 references

Research works printed but not linked: 2

  1. Hundall C (2021) Thinking about AI? Available via https://www.acr.org/Practice-Management-Quality-Informatics/ACR-Bulletin/Articles/June-2021/Thinking-About-AI. Accessed 30 Mar 2022
  2. Walton D (2010) Appeal to expert opinion: arguments from authority. Penn State Press

Cited by

Sorted by citations

Items 101–141 of 141

Related

See all

Metadata

Authors
Bernstein, M. H., Atalay, M. K., Dibble, E. H., Maxwell, A. W. P., Karam, A. R., Agarwal, S., Ward, R. C., Healey, T. T., & Baird, G. L.
Affiliations
Brown University (US)
Corresponding author
Bernstein, Michael H.
ORCID
Venue
European Radiology
Publisher
Springer Science and Business Media LLC
Published
2023-06-02
Volume
33
Issue
11
Pages
8263-8269
ISSN
  • 0938-7994 (ISSN-L)
  • 1432-1084
DOI
10.1007/s00330-023-09747-1
PMC
PMC10235827
OpenAlex
W4379095447
Cited by
140
References
19
Citations by year
2026: 42 · 2025: 59 · 2024: 35 · 2023: 4
FWCI
5.59
Type
journal article
Language
en
Open access
Licence
Locations
  • European Radiology (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiology practices and education
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
Keywords
lung cancer detection, chest radiography, radiologist performance, false positives, false-negative results, AI implementation strategy, human factors, trustworthy AI
MeSH terms
Radiologists, Artificial Intelligence, Humans, Lung Neoplasms, Pilot Projects, Radiography, Retrospective Studies

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review