1
|
Aripoli A, Gurney M, Sourk RF, Ash R, Walker CM, Peterson J, Huppe A, Smith C, Walter C, Clark L, Winblad O. The Impact of Closed-Loop Imaging on Actionable CT-Detected Breast Findings. J Am Coll Radiol 2024; 21:1024-1032. [PMID: 38220037 DOI: 10.1016/j.jacr.2024.01.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Revised: 01/02/2024] [Accepted: 01/04/2024] [Indexed: 01/16/2024]
Abstract
PURPOSE Closed-loop imaging programs (CLIPs) are designed to ensure that patients receive appropriate follow-up, but a review of incidental CT-detected breast findings in the setting of CLIPs has not been performed. METHODS A retrospective review was conducted of CT reports at a single academic institution from July 1, 2020, to January 31, 2022, to identify reports with recommendations for breast imaging follow-up. Medical records were reviewed to evaluate patient adherence to follow-up, CLIP intervention, subsequent BI-RADS assessment, and diagnosis. Adherence was defined as diagnostic breast imaging performed within 6 months of the CT recommendation. RESULTS Follow-up recommendations for breast imaging were included in CT report impressions for 311 patients. Almost half of patients (47.3% [147 of 311]) underwent follow-up breast imaging within 6 months, yielding breast cancer diagnoses in 12.9% (19 of 147) and a biopsy-proven positive predictive value of 65.5% (19 of 29). Most patients who returned for follow-up within 6 months did so without CLIP intervention. The majority of CT report impressions in the follow-up group (85.0% [125 of 147]) contained specific recommendations for "diagnostic breast imaging." For patients who did not receive follow-up, the CLIP team tracked all cases and intervened in 19.1% (28 of 147). The most common intervention was a phone call and/or fax to the primary care provider. Outpatient CT examination setting and specific recommendation for diagnostic breast imaging were significantly associated with higher follow-up adherence (P < .0001). CONCLUSIONS Actionable CT-detected breast findings require follow-up diagnostic breast imaging because of a relevant cancer detection rate of 12.9%. Although many patients return for breast imaging without intervention, almost half of patients did not receive follow-up and may account for a significant number of missed cancer diagnoses. Specific CT recommendation verbiage is associated with higher follow-up adherence, which can be addressed across settings even without CLIPs.
Collapse
Affiliation(s)
- Allison Aripoli
- Department of Radiology, Breast Imaging Section, University of Kansas Medical Center, Kansas City, Kansas.
| | - Madeleine Gurney
- Department of Radiology, University of Kansas Medical Center, Kansas City, Kansas
| | - Rebecca Flynn Sourk
- Department of Radiology, University of Kansas Medical Center, Kansas City, Kansas
| | - Ryan Ash
- Vice Chair, Vice Chair of Quality and Safety, and Medical Director, Department of Radiology, Abdominal Imaging Section, University of Kansas Medical Center, Kansas City, Kansas
| | - Christopher M Walker
- Department of Radiology, Cardiothoracic Imaging Section, University of Kansas Medical Center, Kansas City, Kansas
| | - Jessica Peterson
- Department of Radiology, Breast Imaging Section, University of Kansas Medical Center, Kansas City, Kansas
| | - Ashley Huppe
- Department of Radiology, Breast Imaging Section, University of Kansas Medical Center, Kansas City, Kansas
| | - Camron Smith
- Department of Radiology, Breast Imaging Section, University of Kansas Medical Center, Kansas City, Kansas
| | - Carissa Walter
- Department of Radiology, University of Kansas Medical Center, Kansas City, Kansas
| | - Lauren Clark
- Department of Biostatistics and Data Science, University of Kansas Medical Center, Kansas City, Kansas
| | - Onalisa Winblad
- Division Director of Breast Imaging, Department of Radiology, University of Kansas Medical Center, Kansas City, Kansas
| |
Collapse
|
2
|
Nguyen DL, Ren Y, Jones TM, Thomas SM, Lo JY, Grimm LJ, Gamagami E. Patient Characteristics Impact Performance of AI Algorithm in Interpreting Negative Screening Digital Breast Tomosynthesis Studies. Radiology 2024; 311:e232286. [PMID: 38771177 PMCID: PMC11140531 DOI: 10.1148/radiol.232286] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Revised: 01/22/2024] [Accepted: 03/25/2024] [Indexed: 05/22/2024]
Abstract
Background Artificial intelligence (AI) is increasingly used to manage radiologists' workloads. The impact of patient characteristics on AI performance has not been well studied. Purpose To understand the impact of patient characteristics (race and ethnicity, age, and breast density) on the performance of an AI algorithm interpreting negative screening digital breast tomosynthesis (DBT) examinations. Materials and Methods This retrospective cohort study identified negative screening DBT examinations from an academic institution from January 1, 2016, to December 31, 2019. All examinations had 2 years of follow-up without a diagnosis of atypia or breast malignancy and were therefore considered true negatives. A subset of unique patients was randomly selected to provide a broad distribution of race and ethnicity. DBT studies in this final cohort were interpreted by a U.S. Food and Drug Administration-approved AI algorithm, which generated case scores (malignancy certainty) and risk scores (1-year subsequent malignancy risk) for each mammogram. Positive examinations were classified based on vendor-provided thresholds for both scores. Multivariable logistic regression was used to understand relationships between the scores and patient characteristics. Results A total of 4855 patients (median age, 54 years [IQR, 46-63 years]) were included: 27% (1316 of 4855) White, 26% (1261 of 4855) Black, 28% (1351 of 4855) Asian, and 19% (927 of 4855) Hispanic patients. False-positive case scores were significantly more likely in Black patients (odds ratio [OR] = 1.5 [95% CI: 1.2, 1.8]) and less likely in Asian patients (OR = 0.7 [95% CI: 0.5, 0.9]) compared with White patients, and more likely in older patients (71-80 years; OR = 1.9 [95% CI: 1.5, 2.5]) and less likely in younger patients (41-50 years; OR = 0.6 [95% CI: 0.5, 0.7]) compared with patients aged 51-60 years. False-positive risk scores were more likely in Black patients (OR = 1.5 [95% CI: 1.0, 2.0]), patients aged 61-70 years (OR = 3.5 [95% CI: 2.4, 5.1]), and patients with extremely dense breasts (OR = 2.8 [95% CI: 1.3, 5.8]) compared with White patients, patients aged 51-60 years, and patients with fatty density breasts, respectively. Conclusion Patient characteristics influenced the case and risk scores of a Food and Drug Administration-approved AI algorithm analyzing negative screening DBT examinations. © RSNA, 2024.
Collapse
Affiliation(s)
| | | | - Tyler M. Jones
- From the Department of Radiology, Duke University School of Medicine,
10 Duke Medicine Cir, Durham, NC 27710 (D.L.N., J.Y.L., L.J.G.); Pratt School of
Engineering (Y.R.) and Department of Biostatistics and Bioinformatics (T.M.J.,
S.M.T.), Duke University, Durham, NC; and iCAD, Nashua, NC (Y.R.)
| | - Samantha M. Thomas
- From the Department of Radiology, Duke University School of Medicine,
10 Duke Medicine Cir, Durham, NC 27710 (D.L.N., J.Y.L., L.J.G.); Pratt School of
Engineering (Y.R.) and Department of Biostatistics and Bioinformatics (T.M.J.,
S.M.T.), Duke University, Durham, NC; and iCAD, Nashua, NC (Y.R.)
| | - Joseph Y. Lo
- From the Department of Radiology, Duke University School of Medicine,
10 Duke Medicine Cir, Durham, NC 27710 (D.L.N., J.Y.L., L.J.G.); Pratt School of
Engineering (Y.R.) and Department of Biostatistics and Bioinformatics (T.M.J.,
S.M.T.), Duke University, Durham, NC; and iCAD, Nashua, NC (Y.R.)
| | - Lars J. Grimm
- From the Department of Radiology, Duke University School of Medicine,
10 Duke Medicine Cir, Durham, NC 27710 (D.L.N., J.Y.L., L.J.G.); Pratt School of
Engineering (Y.R.) and Department of Biostatistics and Bioinformatics (T.M.J.,
S.M.T.), Duke University, Durham, NC; and iCAD, Nashua, NC (Y.R.)
| | - Eileen Gamagami
- From the Department of Radiology, Duke University School of Medicine,
10 Duke Medicine Cir, Durham, NC 27710 (D.L.N., J.Y.L., L.J.G.); Pratt School of
Engineering (Y.R.) and Department of Biostatistics and Bioinformatics (T.M.J.,
S.M.T.), Duke University, Durham, NC; and iCAD, Nashua, NC (Y.R.)
| |
Collapse
|
3
|
Oluyemi ET, Grimm LJ, Goldman L, Burleson J, Simanowith M, Yao K, Rosenberg RD. Rate and Timeliness of Diagnostic Evaluation and Biopsy After Recall From Screening Mammography in the National Mammography Database. J Am Coll Radiol 2024; 21:427-438. [PMID: 37722468 DOI: 10.1016/j.jacr.2023.09.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Revised: 08/28/2023] [Accepted: 09/01/2023] [Indexed: 09/20/2023]
Abstract
OBJECTIVE To describe the rate and timeliness of diagnostic resolution after an abnormal screening mammogram in the ACR's National Mammography Database. METHODS Abnormal screening mammograms (BI-RADS 0 assessment) in the National Mammography Database from January 1, 2008, to December 31, 2021, were retrospectively identified. The rates and timeliness of follow-up with diagnostic evaluation and biopsy were assessed and compared across patient and facility demographics. RESULTS Among the 2,874,310 screening mammograms reported as abnormal, follow-up was documented in 66.4% (n = 1,909,326). Lower follow-up rates were observed in younger women (59.4% in women < 30 years, 63.2% in women 30-39 years), Black (57.4%) and American Indian (59.5%) women, and women with no breast cancer family history (63.0%). The overall median time to diagnostic evaluation was 9 days. Longer median diagnostic evaluation time was noted in Black (14 days), other or mixed race (14 days), and Hispanic women (13 days). Of the 318,977 recalled screening mammograms recommended for biopsy, 238,556 (74.8%) biopsies were documented. Lower biopsy rates were noted in older women (71.5% in women aged ≥80) and Black (71.5%) and American Indian (52.2%) women. The overall median time from diagnostic evaluation to biopsy was 21 days. Longer median biopsy time was noted in older (23 days aged ≥80), Black (25 days), mixed or other race (26 days), and Hispanic women (23 days), and rural (24 days) or community hospital affiliated facilities (22 days). DISCUSSION There is variability in the rates and timeliness of diagnostic evaluation and biopsy in women with abnormal screening mammogram. Subsets of women and facilities could benefit from targeted interventions to promote timely diagnostic resolution and biopsy after an abnormal screening mammogram.
Collapse
Affiliation(s)
- Eniola T Oluyemi
- Department of Radiology, Johns Hopkins University, Baltimore, Maryland.
| | - Lars J Grimm
- Department of Radiology, Duke University, Durham, North Carolina; Chair, National Mammography Database
| | | | - Judy Burleson
- Vice President, Quality Programs, ACR, Reston, Virginia
| | | | - Katharine Yao
- Vice Chair of Research and Development and Director of Breast Cancer Research, Department of Surgery, NorthShore University Health System, Evanston Hospital, Evanston, Illinois
| | | |
Collapse
|
4
|
Giess CS, Lynch E, Lacson R, Kapoor N, Desai S, Khorasani R. Patient and System Factors Associated With Completed Follow-Up of Probably Benign (BI-RADS 3) Breast Imaging Findings. J Am Coll Radiol 2023; 20:889-901. [PMID: 37023884 DOI: 10.1016/j.jacr.2023.02.028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Revised: 02/09/2023] [Accepted: 02/17/2023] [Indexed: 04/08/2023]
Abstract
OBJECTIVE Evaluate patient factors and health system test ordering and scheduling processes associated with completed BI-RADS 3 breast imaging follow-up. METHODS Retrospective review of reports from January 1, 2021, to July 31, 2021, identified BI-RADS 3 findings corresponding to unique patient encounters (index examinations). The electronic health record was queried for patient, examination, and health system ordering or scheduling data including follow-up order status (order placed, performed; order placed, scheduled, but not performed; order placed, unscheduled; no order placed); ordering provider specialty and health system affiliation (primary care versus other, internal versus external to health system); and ordering department (radiology staff versus referring physician staff). Patient home addresses were categorized by area deprivation index (University of Wisconsin's Neighborhood Atlas). Univariable and multivariable analysis identified patient, examination, and ordering or scheduling factors associated with completed follow-up imaging within 15 months of BI-RADS 3 assessment. RESULTS There were 3,104 unique BI-RADS 3 assessments, 2,561 (82.5%) with completed BI-RADS 3 follow-up within 15 months of study examination. In multivariable analysis, factors associated with incomplete follow-up included ultrasound (odds ratio [OR] 0.48; 95% confidence interval [95% CI] 0.38-0.60; P < .001) and MRI (OR 0.71; 95% CI 0.50-1.00; P = .049) versus mammogram; patients living in the highest disadvantaged neighborhoods (OR 0.70; 95% CI 0.50-0.98; P = .04); patients <40 years (OR 0.14; 95% CI 0.11-0.19; P < .001); Asian race (OR 0.55; 95% CI 0.37-0.81; P = .003); order placement >3 months (OR, 0.05; 95% CI 0.02-0.16; P < .001) after index examination or scheduling >6 months after order placement (OR, 0.35; 95% CI 0.14-0.87; P = .02); order placement by breast oncology or breast surgery departments (OR 0.35; 95% CI 0.17-0.73; P = .01) versus radiology department. DISCUSSION Incomplete BI-RADS 3 follow-up is associated with ultrasound or MRI, most socioeconomically disadvantaged patients, younger patients, Asian race, delayed order entry, and follow-up examination ordering and scheduling by non-radiology departments.
Collapse
Affiliation(s)
- Catherine S Giess
- Deputy Chair of Radiology, Center for Evidence Based Imaging, and Department of Radiology, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts.
| | - Elyse Lynch
- Department of Radiology, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts
| | - Ronilda Lacson
- Center for Evidence Based Imaging and Department of Radiology, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts
| | - Neena Kapoor
- Center for Evidence Based Imaging and Department of Radiology, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts; Associate Chair of Patient Experience, Department of Radiology, Mass General Brigham Health System, and Quality/Safety Officer for Brigham Radiology
| | - Sonali Desai
- Chief Quality Officer, Department of Medicine, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts
| | - Ramin Khorasani
- Vice Chair of Quality/Safety/Patient Experience for Mass General Brigham Health System, Center for Evidence Based Imaging and Department of Radiology, Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts
| |
Collapse
|
5
|
Lee WJ, Shah Y, Patel N, Ku A, Rodriguez A, Salvador M. The Consequences of COVID-19 on Breast Cancer Screenings in an Underserved Urban Population and the Screening Access of Value for Essex Program's Efforts to Control the Damage. Cureus 2023; 15:e42338. [PMID: 37614270 PMCID: PMC10444536 DOI: 10.7759/cureus.42338] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/23/2023] [Indexed: 08/25/2023] Open
Abstract
OBJECTIVE This study aims to examine the impact of the COVID-19 pandemic on breast cancer screening in an underserved population, identify patient barriers, and discuss strategies to promote the importance of screening. Methods/operations: The Rutgers New Jersey Medical School Screening Access of Value for Essex (SAVE) program delivers cancer prevention services to the most vulnerable population in Essex County, New Jersey. The SAVE program was shut down from March 2020 to June 2020 due to COVID-19. The number of mammograms performed 18 months before the pandemic (September 2018 to March 2020) and 18 months after the shutdown of the program (July 2020 to December 2021) were recorded. A calling project was created in response to the pandemic to educate patients about COVID-19 precautions and provide healthcare and social services resources. RESULTS There was a 15.4% reduction in screening mammograms during the post-shutdown period (1,459 pre-COVID-19 versus 1,234 post-shutdown). The number of diagnostic mammograms increased from 264 to 272. The calling project spoke with 1,548 patients and identified the following concerns: exposure to COVID-19, language barriers, and lack of health insurance. CONCLUSION Although COVID-19 had a profound impact on most patients, especially in the realm of breast cancer screening, the implementation of the SAVE program's strategies such as transitioning to an appointment-only system has helped minimize the negative impacts. Reaching out to the patients, partnering with community organizations, and promoting SAVE services have played a vital role in encouraging more patients to have screening done.
Collapse
Affiliation(s)
- William J Lee
- Radiology, Rutgers University New Jersey Medical School, Newark, USA
| | - Yash Shah
- Radiology, Rutgers University New Jersey Medical School, Newark, USA
| | - Nidhi Patel
- Radiology, Rutgers University New Jersey Medical School, Newark, USA
| | - Albert Ku
- Radiology, Drexel University College of Medicine, Philadelphia, USA
| | - Anibian Rodriguez
- Radiology, Rutgers University New Jersey Medical School, Newark, USA
| | | |
Collapse
|
6
|
Lopez EJ, Lee CI. Improving Health Equity in Adherence to Diagnostic Breast Imaging Workup Recommendations. J Am Coll Radiol 2022; 19:1310-1311. [PMID: 36208840 PMCID: PMC10150785 DOI: 10.1016/j.jacr.2022.07.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2022] [Accepted: 07/30/2022] [Indexed: 11/06/2022]
Affiliation(s)
- Eric J Lopez
- Department of Radiology, University of California, San Francisco, San Francisco, California.
| | - Christoph I Lee
- Department of Radiology, University of Washington School of Medicine, Seattle, Washington, and the Department of Health Systems and Population Health, University of Washington School of Public Health, Seattle, Washington, and Director of the Northwest Screening and Cancer Outcomes Research Enterprise at the University of Washington. https://twitter.com/christophleemd
| |
Collapse
|