AI-initiated second opinions: a framework for advanced caries treatment planning
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
AI-initiated second opinions : a framework for advanced caries treatment planning. / Dascalu, Tudor; Ramezanzade, Shaqayeq; Bakhshandeh, Azam; Bjørndal, Lars; Ibragimov, Bulat.
In: BMC Oral Health, Vol. 24, No. 1, 772, 2024.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - AI-initiated second opinions
T2 - a framework for advanced caries treatment planning
AU - Dascalu, Tudor
AU - Ramezanzade, Shaqayeq
AU - Bakhshandeh, Azam
AU - Bjørndal, Lars
AU - Ibragimov, Bulat
N1 - Publisher Copyright: © The Author(s) 2024.
PY - 2024
Y1 - 2024
N2 - Integrating artificial intelligence (AI) into medical and dental applications can be challenging due to clinicians’ distrust of computer predictions and the potential risks associated with erroneous outputs. We introduce the idea of using AI to trigger second opinions in cases where there is a disagreement between the clinician and the algorithm. By keeping the AI prediction hidden throughout the diagnostic process, we minimize the risks associated with distrust and erroneous predictions, relying solely on human predictions. The experiment involved 3 experienced dentists, 25 dental students, and 290 patients treated for advanced caries across 6 centers. We developed an AI model to predict pulp status following advanced caries treatment. Clinicians were asked to perform the same prediction without the assistance of the AI model. The second opinion framework was tested in a 1000-trial simulation. The average F1-score of the clinicians increased significantly from 0.586 to 0.645.
AB - Integrating artificial intelligence (AI) into medical and dental applications can be challenging due to clinicians’ distrust of computer predictions and the potential risks associated with erroneous outputs. We introduce the idea of using AI to trigger second opinions in cases where there is a disagreement between the clinician and the algorithm. By keeping the AI prediction hidden throughout the diagnostic process, we minimize the risks associated with distrust and erroneous predictions, relying solely on human predictions. The experiment involved 3 experienced dentists, 25 dental students, and 290 patients treated for advanced caries across 6 centers. We developed an AI model to predict pulp status following advanced caries treatment. Clinicians were asked to perform the same prediction without the assistance of the AI model. The second opinion framework was tested in a 1000-trial simulation. The average F1-score of the clinicians increased significantly from 0.586 to 0.645.
KW - Artificial intelligence
KW - CAD
KW - Caries
KW - Computer vision/convolutional neural networks
U2 - 10.1186/s12903-024-04551-9
DO - 10.1186/s12903-024-04551-9
M3 - Journal article
C2 - 38987714
AN - SCOPUS:85198120319
VL - 24
JO - BMC Oral Health
JF - BMC Oral Health
SN - 1472-6831
IS - 1
M1 - 772
ER -
ID: 398633548