Intricacies of human–AI interaction in dynamic decision-making for precision oncology
Abstract AI decision support systems can assist clinicians in planning adaptive treatment strategies that can dynamically react to individuals’ cancer progression for effective personalized care. However, AI’s imperfections can lead to suboptimal therapeutics if clinicians over or under rely on AI....
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55259-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571544737415168 |
|---|---|
| author | Dipesh Niraula Kyle C. Cuneo Ivo D. Dinov Brian D. Gonzalez Jamalina B. Jamaluddin Jionghua Judy Jin Yi Luo Martha M. Matuszak Randall K. Ten Haken Alex K. Bryant Thomas J. Dilling Michael P. Dykstra Jessica M. Frakes Casey L. Liveringhouse Sean R. Miller Matthew N. Mills Russell F. Palm Samuel N. Regan Anupam Rishi Javier F. Torres-Roca Hsiang-Hsuan Michael Yu Issam El Naqa |
| author_facet | Dipesh Niraula Kyle C. Cuneo Ivo D. Dinov Brian D. Gonzalez Jamalina B. Jamaluddin Jionghua Judy Jin Yi Luo Martha M. Matuszak Randall K. Ten Haken Alex K. Bryant Thomas J. Dilling Michael P. Dykstra Jessica M. Frakes Casey L. Liveringhouse Sean R. Miller Matthew N. Mills Russell F. Palm Samuel N. Regan Anupam Rishi Javier F. Torres-Roca Hsiang-Hsuan Michael Yu Issam El Naqa |
| author_sort | Dipesh Niraula |
| collection | DOAJ |
| description | Abstract AI decision support systems can assist clinicians in planning adaptive treatment strategies that can dynamically react to individuals’ cancer progression for effective personalized care. However, AI’s imperfections can lead to suboptimal therapeutics if clinicians over or under rely on AI. To investigate such collaborative decision-making process, we conducted a Human–AI interaction study on response-adaptive radiotherapy for non-small cell lung cancer and hepatocellular carcinoma. We investigated two levels of collaborative behavior: model-agnostic and model-specific; and found that Human–AI interaction is multifactorial and depends on the complex interrelationship between prior knowledge and preferences, patient’s state, disease site, treatment modality, model transparency, and AI’s learned behavior and biases. In summary, some clinicians may disregard AI recommendations due to skepticism; others will critically analyze AI recommendations on a case-by-case basis; clinicians will adjust their decisions if they find AI recommendations beneficial to patients; and clinician will disregard AI recommendations if deemed harmful or suboptimal and seek alternatives. |
| format | Article |
| id | doaj-art-c3e69f7c45664848a67f3543fa0641a0 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-c3e69f7c45664848a67f3543fa0641a02025-02-02T12:33:30ZengNature PortfolioNature Communications2041-17232025-01-0116111910.1038/s41467-024-55259-xIntricacies of human–AI interaction in dynamic decision-making for precision oncologyDipesh Niraula0Kyle C. Cuneo1Ivo D. Dinov2Brian D. Gonzalez3Jamalina B. Jamaluddin4Jionghua Judy Jin5Yi Luo6Martha M. Matuszak7Randall K. Ten Haken8Alex K. Bryant9Thomas J. Dilling10Michael P. Dykstra11Jessica M. Frakes12Casey L. Liveringhouse13Sean R. Miller14Matthew N. Mills15Russell F. Palm16Samuel N. Regan17Anupam Rishi18Javier F. Torres-Roca19Hsiang-Hsuan Michael Yu20Issam El Naqa21Department of Machine Learning, Moffitt Cancer CenterDepartment of Radiation Oncology, University of MichiganDepartment of Health Behavior and Biological Sciences, University of MichiganDepartment of Health Outcomes and Behavior, Moffitt Cancer CenterDepartment of Nuclear Engineering and Radiological Sciences, Moffitt Cancer CenterDepartment of Industrial and Operations Engineering, University of MichiganDepartment of Machine Learning, Moffitt Cancer CenterDepartment of Radiation Oncology, University of MichiganDepartment of Radiation Oncology, University of MichiganDepartment of Radiation Oncology, University of MichiganDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, University of MichiganDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, University of MichiganDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, University of MichiganDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Radiation Oncology, H. Lee Moffitt Cancer Center & Research InstituteDepartment of Machine Learning, Moffitt Cancer CenterAbstract AI decision support systems can assist clinicians in planning adaptive treatment strategies that can dynamically react to individuals’ cancer progression for effective personalized care. However, AI’s imperfections can lead to suboptimal therapeutics if clinicians over or under rely on AI. To investigate such collaborative decision-making process, we conducted a Human–AI interaction study on response-adaptive radiotherapy for non-small cell lung cancer and hepatocellular carcinoma. We investigated two levels of collaborative behavior: model-agnostic and model-specific; and found that Human–AI interaction is multifactorial and depends on the complex interrelationship between prior knowledge and preferences, patient’s state, disease site, treatment modality, model transparency, and AI’s learned behavior and biases. In summary, some clinicians may disregard AI recommendations due to skepticism; others will critically analyze AI recommendations on a case-by-case basis; clinicians will adjust their decisions if they find AI recommendations beneficial to patients; and clinician will disregard AI recommendations if deemed harmful or suboptimal and seek alternatives.https://doi.org/10.1038/s41467-024-55259-x |
| spellingShingle | Dipesh Niraula Kyle C. Cuneo Ivo D. Dinov Brian D. Gonzalez Jamalina B. Jamaluddin Jionghua Judy Jin Yi Luo Martha M. Matuszak Randall K. Ten Haken Alex K. Bryant Thomas J. Dilling Michael P. Dykstra Jessica M. Frakes Casey L. Liveringhouse Sean R. Miller Matthew N. Mills Russell F. Palm Samuel N. Regan Anupam Rishi Javier F. Torres-Roca Hsiang-Hsuan Michael Yu Issam El Naqa Intricacies of human–AI interaction in dynamic decision-making for precision oncology Nature Communications |
| title | Intricacies of human–AI interaction in dynamic decision-making for precision oncology |
| title_full | Intricacies of human–AI interaction in dynamic decision-making for precision oncology |
| title_fullStr | Intricacies of human–AI interaction in dynamic decision-making for precision oncology |
| title_full_unstemmed | Intricacies of human–AI interaction in dynamic decision-making for precision oncology |
| title_short | Intricacies of human–AI interaction in dynamic decision-making for precision oncology |
| title_sort | intricacies of human ai interaction in dynamic decision making for precision oncology |
| url | https://doi.org/10.1038/s41467-024-55259-x |
| work_keys_str_mv | AT dipeshniraula intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT kyleccuneo intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT ivoddinov intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT briandgonzalez intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT jamalinabjamaluddin intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT jionghuajudyjin intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT yiluo intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT marthammatuszak intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT randallktenhaken intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT alexkbryant intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT thomasjdilling intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT michaelpdykstra intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT jessicamfrakes intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT caseylliveringhouse intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT seanrmiller intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT matthewnmills intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT russellfpalm intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT samuelnregan intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT anupamrishi intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT javierftorresroca intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT hsianghsuanmichaelyu intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology AT issamelnaqa intricaciesofhumanaiinteractionindynamicdecisionmakingforprecisiononcology |