Using AI to predict breast cancer recurrence and guide treatment decisions
| ISRCTN | ISRCTN12901516 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN12901516 |
- Submission date
- 05/02/2025
- Registration date
- 07/02/2025
- Last edited
- 06/02/2025
- Recruitment status
- Recruiting
- Overall study status
- Ongoing
- Condition category
- Cancer
Plain English Summary
Background and study aims
Breast cancer recurrence remains a significant concern for patients and clinicians alike. Current prediction methods, although robust, can be complex and may not fully support individualized treatment decision-making. To improve personalized care, an artificial intelligence-clinical decision support system (AI-CDSS) has been developed to predict the risk of breast cancer recurrence using patient-specific clinical and pathological data. This system is intended to assist clinicians in discussing prognosis and treatment options with patients. The primary aim of this study is to evaluate whether the use of AI-CDSS in treatment planning improves patient satisfaction and confidence in treatment decisions. Secondary aims include assessing the impact of the tool on patients’ understanding of their recurrence risk, decisional conflict, and quality of life.
Who can participate?
Adult patients (aged 18 years or older) newly diagnosed with early-stage breast cancer who are facing treatment decisions (e.g., choice of surgical approach, adjuvant therapy options) are eligible for participation.
What does the study involve?
Participants will be randomly assigned to one of two groups:
• Intervention Group: Patients receive treatment planning that is guided by the AI-CDSS. In this arm, clinicians use the AI tool to generate a personalized recurrence risk prediction that informs the treatment discussion.
• Control Group: Patients receive standard treatment planning without the aid of the AI-CDSS.
Following the treatment consultation, all participants will complete a series of survey questionnaires assessing satisfaction with the decision-making process, understanding of recurrence risk, confidence in the chosen treatment, and quality of life. Surveys will be administered at baseline (pre-consultation) and at follow-up time points (1 month, 3 months, and 6 months after treatment initiation).
What are the possible benefits and risks of participating?
Participation in this study offers meaningful benefits. Intervention group participants gain access to AI-generated personalized recurrence risk assessments and treatment insights for their care planning. Additionally, all participants contribute valuable feedback that helps enhance decision-support tools for future breast cancer care. There are no risks associated with participation in this study, as patient care will continue to be guided by established clinical judgment and standards, with the AI tool serving solely to support—not replace—the decision-making process.
Where is the study run from?
The study is being conducted at Tri-Service General Hospital, which has agreed to implement and test this new technology.
When is the study starting and how long is it expected to run for?
December 2024 to October 2025
Who is funding the study?
Tri-Service General Hospital
Who is the main contact?
Dr. Hung-Sheng Shang, iamkeith@mail.ndmctsgh.edu.tw
Contact information
Public, Scientific, Principal Investigator
No. 161, Sec. 6, Minquan E. Rd., Neihu Dist., Division of Clinical Pathology, TSGH, NDMC
Taipei City
11490
Taiwan
 ORCID ID |
0000-0002-4831-1866 |
|---|---|
| Phone | +886 920713130 |
| iamkeith@mail.ndmctsgh.edu.tw |
Study information
| Study design | Randomized controlled trial |
|---|---|
| Primary study design | Interventional |
| Secondary study design | Randomised controlled trial |
| Study setting(s) | Hospital, Internet/virtual |
| Study type | Efficacy |
| Participant information sheet | 46797_PIS.pdf |
| Scientific title | Impact of an artificial intelligence-clinical decision support system on patient satisfaction and confidence in treatment decision-making for breast cancer recurrence prediction: a randomized controlled trial |
| Study acronym | Breast Recurrence Intelligent Decision Guidance Engine (BRIDGE) |
| Study hypothesis | Primary Hypothesis: The AI-CDSS will significantly improve patient satisfaction and confidence in treatment decision-making at baseline, 1, 3, and 6 months post-consultation compared to standard care. Secondary Hypothesis: The AI-CDSS will enhance patients’ understanding of their recurrence risk, reduce decisional conflict, and improve quality of life, as measured at baseline, 1, 3, and 6 months after the consultation. |
| Ethics approval(s) |
Approved 31/12/2024, Institutional Review Board of Tri-Service General Hospital (No.325, Sec.2, Cheng-Kung Rd. Neihu, Taipei City, 114202, Taiwan; +88687923311 ext 17763; tsghirb@ndmctsgh.edu.tw), ref: B202005044 |
| Condition | Breast cancer |
| Intervention | This randomized controlled trial evaluates the impact of an artificial intelligence-clinical decision support system (AI-CDSS) on breast cancer treatment planning. Participants are randomly assigned using a computer-generated sequence to ensure balanced allocation and reduce selection bias. The total duration of the intervention spans the initial treatment planning consultation, with follow-up assessments extending for six months. In the Intervention Group, clinicians integrate the AI-CDSS into the treatment planning consultation. The system processes patient-specific clinical data to generate personalized risk predictions for breast cancer recurrence and to propose tailored treatment recommendations. These AI-generated outputs facilitate shared decision-making between the clinician and the patient. Follow-up questionnaires are administered at baseline (pre-consultation) and 1, 3, and 6 months post-consultation to evaluate outcomes such as patient satisfaction, understanding of recurrence risk, decisional conflict, and overall quality of life. In the Control Group, participants receive treatment planning and counseling based solely on conventional clinical protocols, without the assistance of the AI-CDSS. Follow-up assessments in this arm are conducted at the same time points (baseline, 1, 3, and 6 months post-consultation) to directly compare the outcomes between the two study arms. |
| Intervention type | Other |
| Primary outcome measure | Patient satisfaction and confidence in treatment decision-making will be measured using the Satisfaction with Decision Scale (SWD) at baseline (pre-consultation) and 1, 3, and 6 months after the treatment consultation |
| Secondary outcome measures | The following secondary outcomes will be evaluated using validated questionnaires administered at baseline, 1, 3, and 6 months after the treatment consultation: 1. Patient understanding of recurrence risk measured using the Fear of Progression Questionnaire-12 (FoP-Q-12), to determine how well patients comprehend their individualized breast cancer recurrence risk 2. Decisional conflict measured using the Decisional Conflict Scale (DCS), which evaluates factors such as clarity of options and ease of decision-making 3. Quality of life measured using the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire (EORTC QLQ-C30) |
| Overall study start date | 20/12/2024 |
| Overall study end date | 15/10/2025 |
Eligibility
| Participant type(s) | Patient |
|---|---|
| Age group | Adult |
| Lower age limit | 18 Years |
| Sex | Female |
| Target number of participants | 200 |
| Participant inclusion criteria | 1. Female patients aged 18 years or older 2. Newly diagnosed with early-stage (Stage 0–II) breast cancer 3. Eligible for multiple treatment options (e.g., surgical and adjuvant therapies) |
| Participant exclusion criteria | 1. Previous history of invasive cancer or breast cancer recurrence 2. Patients whose tumors are hormone receptor-negative or show HER2 overexpression on immunohistochemical staining 3. Cognitive or language barriers that preclude completing the surveys 4. Patients who are enrolled in other interventional trials that might interfere with the study outcomes |
| Recruitment start date | 01/03/2025 |
| Recruitment end date | 30/09/2025 |
Locations
Countries of recruitment
- Taiwan
Study participating centre
Taipei City
114202
Taiwan
Sponsor information
Hospital/treatment centre
No. 325, Sec. 2, Chenggong Rd., Neihu Dist.
Taipei City
114202
Taiwan
| Phone | +886 287923311 |
|---|---|
| medr@mail.ndmctsgh.edu.tw | |
| Website | https://www.tsgh.ndmctsgh.edu.tw/ |
"ROR" |
https://ror.org/007h4qe29 |
Funders
Funder type
Hospital/treatment centre
Private sector organisation / Other non-profit organizations
- Alternative name(s)
- Sānjun Zongyīyuàn, Tri-Service General Hospital, Taiwan, TSGH
- Location
- Taiwan
Results and Publications
| Intention to publish date | 31/12/2025 |
|---|---|
| Individual participant data (IPD) Intention to share | Yes |
| IPD sharing plan summary | Published as a supplement to the results publication |
| Publication and dissemination plan | Planned publication in a peer-reviewed journal |
| IPD sharing plan | The datasets generated and/or analysed during the current study will be published as a supplement to the results publication |
Study outputs
| Output type | Details | Date created | Date added | Peer reviewed? | Patient-facing? |
|---|---|---|---|---|---|
| Participant information sheet | 06/02/2025 | No | Yes |
Additional files
Editorial Notes
05/02/2025: Study's existence confirmed by the Institutional Review Board of Tri-Service General Hospital.
