Abstract PS1-02-20: Feasibility of Implementing a Novel Dietary Assessment Platform for Breast Cancer Patients: A Kaiser Permanente Pilot Study

Abstract Background: Breast cancer has one of the highest 5-year survival rates among cancers, with over 4 million survivors in the U.S. Studies suggest that adherence to a healthy diet can reduce morbidity and mortality risk in this population. However, dietary assessment is often overlooked in routine care due to limitations of existing tools. Traditional methods such as 24-hour recalls and food frequency questionnaires are time-consuming and burdensome, particularly for patients undergoing treatment. Diet ID™ is an online, image-based dietary assessment tool that uses Diet Quality Photo Navigation—a patented visual pattern recognition algorithm. Participants compare food photos representing different dietary patterns and select the one that best reflects their typical diet over the past month. The tool generates comprehensive nutritional profiles, and a Healthy Eating Index (HEI) score. This study aims to evaluate the feasibility of using the Diet ID™ platform to assess diet quality in breast cancer patients within a large integrated healthcare system. Methods: Eligible participants were women diagnosed with any stage of breast cancer within the past 24 months and receiving care at Kaiser Permanente San Francisco or Oakland. Recruitment is being conducted via email across three planned waves spaced three months apart, with the first wave launched in April 2025. Participants complete the Diet ID™ assessment online, with responses linked to electronic health records to capture additional demographic and clinical data. Feasibility metrics include recruitment yield, completion rates, and time to completion. Descriptive analyses summarize participant characteristics and HEI score distributions. Results: In the first wave, 1,349 potentially eligible patients were identified. After excluding 324 (24%) for reasons such as language preference, cognitive impairment, and lack of email, 1,021 were invited via email. Of those invited, 328 (32%) enrolled, with 93% completing the assessment in full. While enrollees were similar in age to invitees (mean = 58.9 vs. 60.7 years), White participants were overrepresented (62.8% enrolled vs. 47.0% invited) and Black/African American (5.8% vs. 13.7%), Asian/PI (18.6% vs. 23.4%), and Hispanic (6.4% vs. 8.0%) participants were underrepresented. Stage III/IV patients were also less likely to enroll (5.4% vs. 8.0%). Among 304 participants with complete dietary data, HEI scores ranged from 17 to 98 (mean ≈ 83, standard deviation ≈ 18) and were strongly right-skewed. Participants under age 50 were more common in the lowest HEI tertile (38%) than in the highest (27%). White participants were more likely to be in the top tertile (67% vs. 59% in the lowest), while Black/African American (5% vs. 9%) and Asian/PI (13% vs. 20%) participants were less represented. Higher HEI scores were linked to lower BMI: normal weight was more common in the top tertile (54% vs. 36%), while obesity was less prevalent (12% vs. 26%). Overall, about 15% of participants felt the tool did not accurately capture their diet, but dissatisfaction was more common in the lowest tertile (30%) compared to the highest (7%). Most participants found the tool quick (<5 minutes) and easy to use, with high acceptability (∼85%). Results from the July and October waves will be included in the final analysis and presented at the conference. Conclusions: Preliminary findings suggest that Diet ID™ is a feasible and acceptable tool for assessing diet quality among breast cancer patients in clinical care. Early results show meaningful variation in diet quality and expected associations with BMI. However, the strong right skew in HEI scores highlights the need to assess the tool’s sensitivity to lower-quality diets. Ongoing data collection and follow-up will inform its broader use in dietary surveillance and survivorship care. Citation Format: I. J. Ergas, C. Mindemann, J. Roh, D. Lia, L. Raymond, V. Shim, S. Siegel, M. Kwan, L. Kushi, R. Zwerling Baltrushes. Feasibility of Implementing a Novel Dietary Assessment Platform for Breast Cancer Patients: A Kaiser Permanente Pilot Study [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS1-02-20.

Authors

Institutions

Publication Details

Journal
Clinical Cancer Research
Published
2026-02-17
DOI
https://doi.org/10.1158/1557-3265.sabcs25-ps1-02-20
Primary Topic
Nutritional Studies and Diet
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Abstract PS1-02-20: Feasibility of Implementing a Novel Dietary Assessment Platform for Breast Cancer Patients: A Kaiser Permanente Pilot Study

Marilyn L. Kwan, R. Zwerling Baltrushes, V. Shim, D. Lia et al.
Clinical Cancer Research
Nutritional Studies and Diet
article

Abstract PS1-02-20: Feasibility of Implementing a Novel Dietary Assessment Platform for Breast Cancer Patients: A Kaiser Permanente Pilot Study

Marilyn L. Kwan, R. Zwerling Baltrushes, V. Shim, D. Lia, S. Siegel, L. Kushi, I. J. Ergas, L. Raymond, J. Roh, C. Mindemann
article en

Abstract

Abstract Background: Breast cancer has one of the highest 5-year survival rates among cancers, with over 4 million survivors in the U.S. Studies suggest that adherence to a healthy diet can reduce morbidity and mortality risk in this population. However, dietary assessment is often overlooked in routine care due to limitations of existing tools. Traditional methods such as 24-hour recalls and food frequency questionnaires are time-consuming and burdensome, particularly for patients undergoing treatment. Diet ID™ is an online, image-based dietary assessment tool that uses Diet Quality Photo Navigation—a patented visual pattern recognition algorithm. Participants compare food photos representing different dietary patterns and select the one that best reflects their typical diet over the past month. The tool generates comprehensive nutritional profiles, and a Healthy Eating Index (HEI) score. This study aims to evaluate the feasibility of using the Diet ID™ platform to assess diet quality in breast cancer patients within a large integrated healthcare system. Methods: Eligible participants were women diagnosed with any stage of breast cancer within the past 24 months and receiving care at Kaiser Permanente San Francisco or Oakland. Recruitment is being conducted via email across three planned waves spaced three months apart, with the first wave launched in April 2025. Participants complete the Diet ID™ assessment online, with responses linked to electronic health records to capture additional demographic and clinical data. Feasibility metrics include recruitment yield, completion rates, and time to completion. Descriptive analyses summarize participant characteristics and HEI score distributions. Results: In the first wave, 1,349 potentially eligible patients were identified. After excluding 324 (24%) for reasons such as language preference, cognitive impairment, and lack of email, 1,021 were invited via email. Of those invited, 328 (32%) enrolled, with 93% completing the assessment in full. While enrollees were similar in age to invitees (mean = 58.9 vs. 60.7 years), White participants were overrepresented (62.8% enrolled vs. 47.0% invited) and Black/African American (5.8% vs. 13.7%), Asian/PI (18.6% vs. 23.4%), and Hispanic (6.4% vs. 8.0%) participants were underrepresented. Stage III/IV patients were also less likely to enroll (5.4% vs. 8.0%). Among 304 participants with complete dietary data, HEI scores ranged from 17 to 98 (mean ≈ 83, standard deviation ≈ 18) and were strongly right-skewed. Participants under age 50 were more common in the lowest HEI tertile (38%) than in the highest (27%). White participants were more likely to be in the top tertile (67% vs. 59% in the lowest), while Black/African American (5% vs. 9%) and Asian/PI (13% vs. 20%) participants were less represented. Higher HEI scores were linked to lower BMI: normal weight was more common in the top tertile (54% vs. 36%), while obesity was less prevalent (12% vs. 26%). Overall, about 15% of participants felt the tool did not accurately capture their diet, but dissatisfaction was more common in the lowest tertile (30%) compared to the highest (7%). Most participants found the tool quick (<5 minutes) and easy to use, with high acceptability (∼85%). Results from the July and October waves will be included in the final analysis and presented at the conference. Conclusions: Preliminary findings suggest that Diet ID™ is a feasible and acceptable tool for assessing diet quality among breast cancer patients in clinical care. Early results show meaningful variation in diet quality and expected associations with BMI. However, the strong right skew in HEI scores highlights the need to assess the tool’s sensitivity to lower-quality diets. Ongoing data collection and follow-up will inform its broader use in dietary surveillance and survivorship care. Citation Format: I. J. Ergas, C. Mindemann, J. Roh, D. Lia, L. Raymond, V. Shim, S. Siegel, M. Kwan, L. Kushi, R. Zwerling Baltrushes. Feasibility of Implementing a Novel Dietary Assessment Platform for Breast Cancer Patients: A Kaiser Permanente Pilot Study [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PS1-02-20.

Clinical Cancer ResearchVol. 32(4_Supplement)
Kaiser Permanente (US), Kaiser Permanente Oakland Medical Center (US), Kaiser Permanente San Francisco Medical Center (US)
Zero hunger
Openalex Percentile: Top 51%
Nutritional Studies and Diet
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.