Dr. Mercaldo received a BA in Mathematics from Colorado College and a Ph.D. in Biostatistics from Vanderbilt University. She is a Statistician in the Department of Radiology at Massachusetts General Hospital, and an Instructor of Radiology and Statistics at Harvard Medical School. Her research interests include improving the accuracy prediction models when dealing with missing data, and improving the robustness and reproducibility of large-scale inferential procedures, especially those commonly encountered in genetic studies.
Selected Publications
Anderson, Mark A; Mercaldo, Sarah; Cao, Jinjin; Mroueh, Nayla; Furtado, Felipe S; Cochran, Rory L; Chung, Ryan; Goiffon, Reece J; Sertic, Madeleine; Pierce, Theodore T; Kilcoyne, Aoife; Mojtahed, Amirkasra; Shenoy-Bhangle, Anuradha S; Catalano, Onofrio A; Kambadakone, Avinash
In: AJR Am J Roentgenol, vol. 222, no. 5, pp. e2330720, 2024, ISSN: 1546-3141.
@article{pmid38353447b,
title = {Society of Radiologists in Ultrasound Consensus Conference Recommendations for Incidental Gallbladder Polyp Management: Interreader Agreement Among 10 Radiologists},
author = {Mark A Anderson and Sarah Mercaldo and Jinjin Cao and Nayla Mroueh and Felipe S Furtado and Rory L Cochran and Ryan Chung and Reece J Goiffon and Madeleine Sertic and Theodore T Pierce and Aoife Kilcoyne and Amirkasra Mojtahed and Anuradha S Shenoy-Bhangle and Onofrio A Catalano and Avinash Kambadakone},
doi = {10.2214/AJR.23.30720},
issn = {1546-3141},
year = {2024},
date = {2024-05-01},
journal = {AJR Am J Roentgenol},
volume = {222},
number = {5},
pages = {e2330720},
abstract = { The 2022 Society of Radiologists in Ultrasound (SRU) consensus conference recommendations for small gallbladder polyps support management that is less aggressive than earlier approaches and may help standardize evaluation of polyps by radiologists. The purpose of the present study was to assess the interreader agreement of radiologists in applying SRU recommendations for management of incidental gallbladder polyps on ultrasound. This retrospective study included 105 patients (75 women and 30 men; median age, 51 years) with a gallbladder polyp on ultrasound (without features highly suspicious for invasive or malignant tumor) who underwent cholecystectomy between January 1, 2003, and January 1, 2021. Ten abdominal radiologists independently reviewed ultrasound examinations and, using the SRU recommendations, assessed one polyp per patient to assign risk category (extremely low risk, low risk, or indeterminate risk) and make a possible recommendation for surgical consultation. Five radiologists were considered less experienced (< 5 years of experience), and five were considered more experienced (≥ 5 years of experience). Interreader agreement was evaluated. Polyps were classified pathologically as nonneoplastic or neoplastic. For risk category assignments, interreader agreement was substantial among all readers (k = 0.710), less-experienced readers (k = 0.705), and more-experienced readers (k = 0.692). For surgical consultation recommendations, inter-reader agreement was substantial among all readers (k = 0.795) and more-experienced readers (k = 0.740) and was almost perfect among less-experienced readers (k = 0.811). Of 10 readers, a median of 5.0 (IQR, 2.0-8.0), 4.0 (IQR, 2.0-7.0), and 0.0 (IQR, 0.0-0.0) readers classified polyps as extremely low risk, low risk, and indeterminate risk, respectively. Across readers, the percentage of polyps classified as extremely low risk ranged from 32% to 72%; as low risk, from 24% to 65%; and as indeterminate risk, from 0% to 8%. Of 10 readers, a median of zero change to 0 (IQR, 0.0-1.0) readers recommended surgical consultation; the percentage of polyps receiving a recommendation for surgical consultation ranged from 4% to 22%. Of a total of 105 polyps, 102 were nonneo-plastic and three were neoplastic (all benign). Based on readers' most common assessments for nonneoplastic polyps, the risk category was extremely low risk for 53 polyps, low risk for 48 polyps, and indeterminate risk for one polyp; surgical consultation was recommended for 16 polyps. Ten abdominal radiologists showed substantial agreement for polyp risk categorizations and surgical consultation recommendations, although areas of reader variability were identified. The findings support the overall reproducibility of the SRU recommendations, while indicating opportunity for improvement.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The 2022 Society of Radiologists in Ultrasound (SRU) consensus conference recommendations for small gallbladder polyps support management that is less aggressive than earlier approaches and may help standardize evaluation of polyps by radiologists. The purpose of the present study was to assess the interreader agreement of radiologists in applying SRU recommendations for management of incidental gallbladder polyps on ultrasound. This retrospective study included 105 patients (75 women and 30 men; median age, 51 years) with a gallbladder polyp on ultrasound (without features highly suspicious for invasive or malignant tumor) who underwent cholecystectomy between January 1, 2003, and January 1, 2021. Ten abdominal radiologists independently reviewed ultrasound examinations and, using the SRU recommendations, assessed one polyp per patient to assign risk category (extremely low risk, low risk, or indeterminate risk) and make a possible recommendation for surgical consultation. Five radiologists were considered less experienced (< 5 years of experience), and five were considered more experienced (≥ 5 years of experience). Interreader agreement was evaluated. Polyps were classified pathologically as nonneoplastic or neoplastic. For risk category assignments, interreader agreement was substantial among all readers (k = 0.710), less-experienced readers (k = 0.705), and more-experienced readers (k = 0.692). For surgical consultation recommendations, inter-reader agreement was substantial among all readers (k = 0.795) and more-experienced readers (k = 0.740) and was almost perfect among less-experienced readers (k = 0.811). Of 10 readers, a median of 5.0 (IQR, 2.0-8.0), 4.0 (IQR, 2.0-7.0), and 0.0 (IQR, 0.0-0.0) readers classified polyps as extremely low risk, low risk, and indeterminate risk, respectively. Across readers, the percentage of polyps classified as extremely low risk ranged from 32% to 72%; as low risk, from 24% to 65%; and as indeterminate risk, from 0% to 8%. Of 10 readers, a median of zero change to 0 (IQR, 0.0-1.0) readers recommended surgical consultation; the percentage of polyps receiving a recommendation for surgical consultation ranged from 4% to 22%. Of a total of 105 polyps, 102 were nonneo-plastic and three were neoplastic (all benign). Based on readers' most common assessments for nonneoplastic polyps, the risk category was extremely low risk for 53 polyps, low risk for 48 polyps, and indeterminate risk for one polyp; surgical consultation was recommended for 16 polyps. Ten abdominal radiologists showed substantial agreement for polyp risk categorizations and surgical consultation recommendations, although areas of reader variability were identified. The findings support the overall reproducibility of the SRU recommendations, while indicating opportunity for improvement.
Anderson, Mark A; Mercaldo, Sarah; Cao, Jinjin; Mroueh, Nayla; Furtado, Felipe S; Cochran, Rory L; Chung, Ryan; Goiffon, Reece J; Sertic, Madeleine; Pierce, Theodore T; Kilcoyne, Aoife; Mojtahed, Amirkasra; Shenoy-Bhangle, Anuradha S; Catalano, Onofrio A; Kambadakone, Avinash
In: AJR Am J Roentgenol, vol. 222, no. 5, pp. e2330720, 2024, ISSN: 1546-3141.
@article{pmid38353447c,
title = {Society of Radiologists in Ultrasound Consensus Conference Recommendations for Incidental Gallbladder Polyp Management: Interreader Agreement Among 10 Radiologists},
author = {Mark A Anderson and Sarah Mercaldo and Jinjin Cao and Nayla Mroueh and Felipe S Furtado and Rory L Cochran and Ryan Chung and Reece J Goiffon and Madeleine Sertic and Theodore T Pierce and Aoife Kilcoyne and Amirkasra Mojtahed and Anuradha S Shenoy-Bhangle and Onofrio A Catalano and Avinash Kambadakone},
doi = {10.2214/AJR.23.30720},
issn = {1546-3141},
year = {2024},
date = {2024-05-01},
journal = {AJR Am J Roentgenol},
volume = {222},
number = {5},
pages = {e2330720},
abstract = { The 2022 Society of Radiologists in Ultrasound (SRU) consensus conference recommendations for small gallbladder polyps support management that is less aggressive than earlier approaches and may help standardize evaluation of polyps by radiologists. The purpose of the present study was to assess the interreader agreement of radiologists in applying SRU recommendations for management of incidental gallbladder polyps on ultrasound. This retrospective study included 105 patients (75 women and 30 men; median age, 51 years) with a gallbladder polyp on ultrasound (without features highly suspicious for invasive or malignant tumor) who underwent cholecystectomy between January 1, 2003, and January 1, 2021. Ten abdominal radiologists independently reviewed ultrasound examinations and, using the SRU recommendations, assessed one polyp per patient to assign risk category (extremely low risk, low risk, or indeterminate risk) and make a possible recommendation for surgical consultation. Five radiologists were considered less experienced (< 5 years of experience), and five were considered more experienced (≥ 5 years of experience). Interreader agreement was evaluated. Polyps were classified pathologically as nonneoplastic or neoplastic. For risk category assignments, interreader agreement was substantial among all readers (k = 0.710), less-experienced readers (k = 0.705), and more-experienced readers (k = 0.692). For surgical consultation recommendations, inter-reader agreement was substantial among all readers (k = 0.795) and more-experienced readers (k = 0.740) and was almost perfect among less-experienced readers (k = 0.811). Of 10 readers, a median of 5.0 (IQR, 2.0-8.0), 4.0 (IQR, 2.0-7.0), and 0.0 (IQR, 0.0-0.0) readers classified polyps as extremely low risk, low risk, and indeterminate risk, respectively. Across readers, the percentage of polyps classified as extremely low risk ranged from 32% to 72%; as low risk, from 24% to 65%; and as indeterminate risk, from 0% to 8%. Of 10 readers, a median of zero change to 0 (IQR, 0.0-1.0) readers recommended surgical consultation; the percentage of polyps receiving a recommendation for surgical consultation ranged from 4% to 22%. Of a total of 105 polyps, 102 were nonneo-plastic and three were neoplastic (all benign). Based on readers' most common assessments for nonneoplastic polyps, the risk category was extremely low risk for 53 polyps, low risk for 48 polyps, and indeterminate risk for one polyp; surgical consultation was recommended for 16 polyps. Ten abdominal radiologists showed substantial agreement for polyp risk categorizations and surgical consultation recommendations, although areas of reader variability were identified. The findings support the overall reproducibility of the SRU recommendations, while indicating opportunity for improvement.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The 2022 Society of Radiologists in Ultrasound (SRU) consensus conference recommendations for small gallbladder polyps support management that is less aggressive than earlier approaches and may help standardize evaluation of polyps by radiologists. The purpose of the present study was to assess the interreader agreement of radiologists in applying SRU recommendations for management of incidental gallbladder polyps on ultrasound. This retrospective study included 105 patients (75 women and 30 men; median age, 51 years) with a gallbladder polyp on ultrasound (without features highly suspicious for invasive or malignant tumor) who underwent cholecystectomy between January 1, 2003, and January 1, 2021. Ten abdominal radiologists independently reviewed ultrasound examinations and, using the SRU recommendations, assessed one polyp per patient to assign risk category (extremely low risk, low risk, or indeterminate risk) and make a possible recommendation for surgical consultation. Five radiologists were considered less experienced (< 5 years of experience), and five were considered more experienced (≥ 5 years of experience). Interreader agreement was evaluated. Polyps were classified pathologically as nonneoplastic or neoplastic. For risk category assignments, interreader agreement was substantial among all readers (k = 0.710), less-experienced readers (k = 0.705), and more-experienced readers (k = 0.692). For surgical consultation recommendations, inter-reader agreement was substantial among all readers (k = 0.795) and more-experienced readers (k = 0.740) and was almost perfect among less-experienced readers (k = 0.811). Of 10 readers, a median of 5.0 (IQR, 2.0-8.0), 4.0 (IQR, 2.0-7.0), and 0.0 (IQR, 0.0-0.0) readers classified polyps as extremely low risk, low risk, and indeterminate risk, respectively. Across readers, the percentage of polyps classified as extremely low risk ranged from 32% to 72%; as low risk, from 24% to 65%; and as indeterminate risk, from 0% to 8%. Of 10 readers, a median of zero change to 0 (IQR, 0.0-1.0) readers recommended surgical consultation; the percentage of polyps receiving a recommendation for surgical consultation ranged from 4% to 22%. Of a total of 105 polyps, 102 were nonneo-plastic and three were neoplastic (all benign). Based on readers' most common assessments for nonneoplastic polyps, the risk category was extremely low risk for 53 polyps, low risk for 48 polyps, and indeterminate risk for one polyp; surgical consultation was recommended for 16 polyps. Ten abdominal radiologists showed substantial agreement for polyp risk categorizations and surgical consultation recommendations, although areas of reader variability were identified. The findings support the overall reproducibility of the SRU recommendations, while indicating opportunity for improvement.
Anderson, Mark A; Mercaldo, Sarah; Cao, Jinjin; Mroueh, Nayla; Furtado, Felipe S; Cochran, Rory L; Chung, Ryan; Goiffon, Reece J; Sertic, Madeleine; Pierce, Theodore T; Kilcoyne, Aoife; Mojtahed, Amirkasra; Shenoy-Bhangle, Anuradha S; Catalano, Onofrio A; Kambadakone, Avinash
In: AJR Am J Roentgenol, 2024, ISSN: 1546-3141.
@article{pmid38353447,
title = {Society of Radiologists in Ultrasound Consensus Conference Recommendations for Incidental Gallbladder Polyp Management: Interreader Agreement Among Ten Radiologists},
author = {Mark A Anderson and Sarah Mercaldo and Jinjin Cao and Nayla Mroueh and Felipe S Furtado and Rory L Cochran and Ryan Chung and Reece J Goiffon and Madeleine Sertic and Theodore T Pierce and Aoife Kilcoyne and Amirkasra Mojtahed and Anuradha S Shenoy-Bhangle and Onofrio A Catalano and Avinash Kambadakone},
doi = {10.2214/AJR.23.30720},
issn = {1546-3141},
year = {2024},
date = {2024-02-01},
journal = {AJR Am J Roentgenol},
abstract = { The 2022 Society of Radiologists in Ultrasound (SRU) consensus conference recommendations support less-aggressive management of small gallbladder polyps on ultrasound versus earlier approaches and may help standardize polyp evaluation by radiologists. To assess radiologists' interreader agreement in applying the SRU recommendations for management of incidental gallbladder polyps on ultrasound. This retrospective study included 105 patients (median age, 52 years; 75 women, 27 men) with a gallbladder polyp on ultrasound (without features highly suspicious for invasive or malignant tumor) who underwent cholecystectomy between January 1, 2003 and January 1, 2021. Ten abdominal radiologists independently reviewed ultrasound examinations and, using SRU recommendations, assessed one polyp per patient for risk category (extremely low-risk, low-risk, or indeterminate risk) and possible recommendation for surgical consultation. Five radiologists were considered less-experienced (<5 years), and five more-experienced (≥5 years). Interreader agreement was evaluated. Polyps were classified pathologically as nonneoplastic or neoplastic. For risk category assignments, interreader agreement was substantial among all readers (k=0.710), less-experienced readers (k=0.705), and more-experienced readers (k=0.692). For surgical consultation recommendations, interreader agreement was substantial among all readers (k=0.795) and more-experienced readers (kappa=0.740), and almost perfect among less-experienced readers (k=0.811). Of ten readers, a median of 5 (IQR, 2-8), 4 (IQR, 2-7), and 0 (IQR, 0-0) classified polyps as extremely low risk, low risk, and indeterminate risk, respectively. Across readers, the fraction of polyps classified as extremely low risk ranged from 32-72%, as low risk from 24-65%, and as indeterminate risk from 0-8%. Of ten readers, a median of 0 (IQR, 0-1) recommended surgical consultation; the fraction of polyps receiving a surgical consultation recommendation ranged from 4-22%. A total of 102/105 polyps were nonneoplastic; 3/105 were neoplastic (all benign). Based on readers' most-common assessments for the nonneoplastic polyps, the risk category was extremely low risk in 53, low risk in 48, and indeterminate risk in 1; surgical consultation was recommended in 16. Ten abdominal radiologists showed substantial agreement for polyp risk categorizations and surgical consultation recommendations, although areas of reader variability were identified. The findings support overall reproducibility of the SRU recommendations, while indicating opportunity for improvement.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The 2022 Society of Radiologists in Ultrasound (SRU) consensus conference recommendations support less-aggressive management of small gallbladder polyps on ultrasound versus earlier approaches and may help standardize polyp evaluation by radiologists. To assess radiologists' interreader agreement in applying the SRU recommendations for management of incidental gallbladder polyps on ultrasound. This retrospective study included 105 patients (median age, 52 years; 75 women, 27 men) with a gallbladder polyp on ultrasound (without features highly suspicious for invasive or malignant tumor) who underwent cholecystectomy between January 1, 2003 and January 1, 2021. Ten abdominal radiologists independently reviewed ultrasound examinations and, using SRU recommendations, assessed one polyp per patient for risk category (extremely low-risk, low-risk, or indeterminate risk) and possible recommendation for surgical consultation. Five radiologists were considered less-experienced (<5 years), and five more-experienced (≥5 years). Interreader agreement was evaluated. Polyps were classified pathologically as nonneoplastic or neoplastic. For risk category assignments, interreader agreement was substantial among all readers (k=0.710), less-experienced readers (k=0.705), and more-experienced readers (k=0.692). For surgical consultation recommendations, interreader agreement was substantial among all readers (k=0.795) and more-experienced readers (kappa=0.740), and almost perfect among less-experienced readers (k=0.811). Of ten readers, a median of 5 (IQR, 2-8), 4 (IQR, 2-7), and 0 (IQR, 0-0) classified polyps as extremely low risk, low risk, and indeterminate risk, respectively. Across readers, the fraction of polyps classified as extremely low risk ranged from 32-72%, as low risk from 24-65%, and as indeterminate risk from 0-8%. Of ten readers, a median of 0 (IQR, 0-1) recommended surgical consultation; the fraction of polyps receiving a surgical consultation recommendation ranged from 4-22%. A total of 102/105 polyps were nonneoplastic; 3/105 were neoplastic (all benign). Based on readers' most-common assessments for the nonneoplastic polyps, the risk category was extremely low risk in 53, low risk in 48, and indeterminate risk in 1; surgical consultation was recommended in 16. Ten abdominal radiologists showed substantial agreement for polyp risk categorizations and surgical consultation recommendations, although areas of reader variability were identified. The findings support overall reproducibility of the SRU recommendations, while indicating opportunity for improvement.
Anderson, Mark A; Mercaldo, Sarah; Chung, Ryan; Ulrich, Ethan; Jones, Randall W; Harisinghani, Mukesh
Improving Prostate Cancer Detection With MRI: A Multi-Reader, Multi-Case Study Using Computer-Aided Detection (CAD) Journal Article
In: Acad Radiol, vol. 30, iss. 7, pp. 1340-1349, 2023, ISSN: 1878-4046.
@article{pmid36216684,
title = {Improving Prostate Cancer Detection With MRI: A Multi-Reader, Multi-Case Study Using Computer-Aided Detection (CAD)},
author = {Mark A Anderson and Sarah Mercaldo and Ryan Chung and Ethan Ulrich and Randall W Jones and Mukesh Harisinghani},
doi = {10.1016/j.acra.2022.09.009},
issn = {1878-4046},
year = {2023},
date = {2023-07-01},
urldate = {2022-10-01},
journal = {Acad Radiol},
volume = {30},
issue = {7},
pages = {1340-1349},
abstract = {RATIONALE AND OBJECTIVES: To evaluate whether addition of a computer-aided diagnostic (CAD) generated MRI series improves detection of clinically significant prostate cancer.
MATERIALS AND METHODS: Nine radiologists retrospectively interpreted 150 prostate MRI examinations without and then with an additional random forest-based CAD model-generated MRI series. Characteristics of biopsy negative versus positive (Gleason ≥ 7 adenocarcinoma) groups were compared using the Wilcoxon test for continuous and Pearson's chi-squared test for categorical variables. The diagnostic performance of readers was compared without versus with CAD using MRMC methods to estimate the area under the receiver operator characteristic curve (AUC). Inter-reader agreement was assessed using weighted inter-rater agreement statistics. Analyses were repeated in peripheral and transition zone subgroups.
RESULTS: Among 150 men with median age 67 ± 7.4 years, those with clinically significant prostate cancer were older (68 ± 7.6 years vs. 66 ± 7.0 years; p \< .02), had smaller prostate volume (43.9 mL vs. 60.6 mL; p \< .001), and no difference in prostate specific antigen (PSA) levels (7.8 ng/mL vs. 6.9 ng/mL; p = .08), but higher PSA density (0.17 ng/mL/cc vs. 0.10 ng/mL/cc; p \< .001). Inter-rater agreement (IRA) for PI-RADS scores was moderate without CAD and significantly improved to substantial with CAD (IRA = 0.47 vs. 0.65; p \< .001). CAD also significantly improved average reader AUC (AUC = 0.72, vs. AUC = 0.67; p = .02).
CONCLUSION: Addition of a random forest method-based, CAD-generated MRI image series improved inter-reader agreement and diagnostic performance for detection of clinically significant prostate cancer, particularly in the transition zone.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
RATIONALE AND OBJECTIVES: To evaluate whether addition of a computer-aided diagnostic (CAD) generated MRI series improves detection of clinically significant prostate cancer.
MATERIALS AND METHODS: Nine radiologists retrospectively interpreted 150 prostate MRI examinations without and then with an additional random forest-based CAD model-generated MRI series. Characteristics of biopsy negative versus positive (Gleason ≥ 7 adenocarcinoma) groups were compared using the Wilcoxon test for continuous and Pearson's chi-squared test for categorical variables. The diagnostic performance of readers was compared without versus with CAD using MRMC methods to estimate the area under the receiver operator characteristic curve (AUC). Inter-reader agreement was assessed using weighted inter-rater agreement statistics. Analyses were repeated in peripheral and transition zone subgroups.
RESULTS: Among 150 men with median age 67 ± 7.4 years, those with clinically significant prostate cancer were older (68 ± 7.6 years vs. 66 ± 7.0 years; p < .02), had smaller prostate volume (43.9 mL vs. 60.6 mL; p < .001), and no difference in prostate specific antigen (PSA) levels (7.8 ng/mL vs. 6.9 ng/mL; p = .08), but higher PSA density (0.17 ng/mL/cc vs. 0.10 ng/mL/cc; p < .001). Inter-rater agreement (IRA) for PI-RADS scores was moderate without CAD and significantly improved to substantial with CAD (IRA = 0.47 vs. 0.65; p < .001). CAD also significantly improved average reader AUC (AUC = 0.72, vs. AUC = 0.67; p = .02).
CONCLUSION: Addition of a random forest method-based, CAD-generated MRI image series improved inter-reader agreement and diagnostic performance for detection of clinically significant prostate cancer, particularly in the transition zone.
MATERIALS AND METHODS: Nine radiologists retrospectively interpreted 150 prostate MRI examinations without and then with an additional random forest-based CAD model-generated MRI series. Characteristics of biopsy negative versus positive (Gleason ≥ 7 adenocarcinoma) groups were compared using the Wilcoxon test for continuous and Pearson's chi-squared test for categorical variables. The diagnostic performance of readers was compared without versus with CAD using MRMC methods to estimate the area under the receiver operator characteristic curve (AUC). Inter-reader agreement was assessed using weighted inter-rater agreement statistics. Analyses were repeated in peripheral and transition zone subgroups.
RESULTS: Among 150 men with median age 67 ± 7.4 years, those with clinically significant prostate cancer were older (68 ± 7.6 years vs. 66 ± 7.0 years; p < .02), had smaller prostate volume (43.9 mL vs. 60.6 mL; p < .001), and no difference in prostate specific antigen (PSA) levels (7.8 ng/mL vs. 6.9 ng/mL; p = .08), but higher PSA density (0.17 ng/mL/cc vs. 0.10 ng/mL/cc; p < .001). Inter-rater agreement (IRA) for PI-RADS scores was moderate without CAD and significantly improved to substantial with CAD (IRA = 0.47 vs. 0.65; p < .001). CAD also significantly improved average reader AUC (AUC = 0.72, vs. AUC = 0.67; p = .02).
CONCLUSION: Addition of a random forest method-based, CAD-generated MRI image series improved inter-reader agreement and diagnostic performance for detection of clinically significant prostate cancer, particularly in the transition zone.
Chou, Shinn-Huey S; Baikpour, Masoud; Zhang, Wei; Mercaldo, Sarah Fletcher; Lehman, Constance D; Samir, Anthony E
Shear-Wave Elastography of the Breast: Impact of Technical Image Quality Parameters on Diagnostic Accuracy. Journal Article
In: AJR. American journal of roentgenology, vol. 216, pp. 1205–1215, 2021, ISSN: 1546-3141, ().
@article{Chou2021,
title = {Shear-Wave Elastography of the Breast: Impact of Technical Image Quality Parameters on Diagnostic Accuracy.},
author = {Shinn-Huey S Chou and Masoud Baikpour and Wei Zhang and Sarah Fletcher Mercaldo and Constance D Lehman and Anthony E Samir},
url = {https://pubmed.ncbi.nlm.nih.gov/33729888/},
doi = {10.2214/AJR.19.22728},
issn = {1546-3141},
year = {2021},
date = {2021-05-01},
journal = {AJR. American journal of roentgenology},
volume = {216},
pages = {1205--1215},
abstract = {The purpose of this study is to determine the impact of shear-wave elastography (SWE) image quality parameters on the diagnostic performance of elasticity measurements in classifying breast lesions. This retrospective study included 281 breast lesions that underwent SWE and ultrasound-guided biopsy performed between October 1, 2017, and August 31, 2018. Three readers who were blinded to pathologic outcomes independently scored the image quality of each SWE image (with low quality denoted by a score of 0 and high quality indicated by a score of 1) on the basis of five parameters: B-mode visualization of the lesion on a dual-panel display, SWE red pattern (denoting high stiffness) in the near field of the FOV, appearance of the surrounding tissue, FOV placement, and ROI placement for the maximum (E ), minimum (E ), mean (E ), and SD (E ) of Young modulus elasticity measurements. Using ROC analysis, we compared the performance of E , E , and E in diagnosing malignancy on low- and high-quality images on the basis of consensus (i.e., majority) scores for each individual quality parameter as well as two models combining a few of the quality parameters. Three quality parameters (B-mode visualization of the lesion, presence of a near-field red pattern, and the appearance of the surrounding tissue) showed moderate-to-substantial interobserver agreement. SWE images were considered high quality ( = 167) if both B-mode visualization and near-field red pattern received a consensus score of 1, and they were considered low quality ( = 114) if either parameter received a consensus score of 0. High-quality images had a statistically higher AUC value than low-quality images when E ( \< .001), E ( = .002), and E ( \< .001) were used as classifiers of malignancy. Quality parameters can support radiologists who are performing and interpreting breast SWE images. These quality parameters have the potential to improve the accuracy of SWE in differentiating malignant from benign breast lesions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The purpose of this study is to determine the impact of shear-wave elastography (SWE) image quality parameters on the diagnostic performance of elasticity measurements in classifying breast lesions. This retrospective study included 281 breast lesions that underwent SWE and ultrasound-guided biopsy performed between October 1, 2017, and August 31, 2018. Three readers who were blinded to pathologic outcomes independently scored the image quality of each SWE image (with low quality denoted by a score of 0 and high quality indicated by a score of 1) on the basis of five parameters: B-mode visualization of the lesion on a dual-panel display, SWE red pattern (denoting high stiffness) in the near field of the FOV, appearance of the surrounding tissue, FOV placement, and ROI placement for the maximum (E ), minimum (E ), mean (E ), and SD (E ) of Young modulus elasticity measurements. Using ROC analysis, we compared the performance of E , E , and E in diagnosing malignancy on low- and high-quality images on the basis of consensus (i.e., majority) scores for each individual quality parameter as well as two models combining a few of the quality parameters. Three quality parameters (B-mode visualization of the lesion, presence of a near-field red pattern, and the appearance of the surrounding tissue) showed moderate-to-substantial interobserver agreement. SWE images were considered high quality ( = 167) if both B-mode visualization and near-field red pattern received a consensus score of 1, and they were considered low quality ( = 114) if either parameter received a consensus score of 0. High-quality images had a statistically higher AUC value than low-quality images when E ( < .001), E ( = .002), and E ( < .001) were used as classifiers of malignancy. Quality parameters can support radiologists who are performing and interpreting breast SWE images. These quality parameters have the potential to improve the accuracy of SWE in differentiating malignant from benign breast lesions.
Bahl, Manisha; Mercaldo, Sarah Fletcher; Dang, Pragya A.; McCarthy, Anne Marie; Lowry, Kathryn; Lehman, Constance D.
Breast Cancer Screening with Digital Breast Tomosynthesis: Are Initial Benefits Sustained? Journal Article
In: Radiology, pp. 191030, 2020, ISSN: 1527-1315, ().
@article{Bahl2020,
title = {Breast Cancer Screening with Digital Breast Tomosynthesis: Are Initial Benefits Sustained?},
author = {Manisha Bahl and Sarah Fletcher Mercaldo and Pragya A. Dang and Anne Marie McCarthy and Kathryn Lowry and Constance D. Lehman},
url = {https://www.ncbi.nlm.nih.gov/pubmed/32255414},
doi = {10.1148/radiol.2020191030},
issn = {1527-1315},
year = {2020},
date = {2020-04-01},
journal = {Radiology},
pages = {191030},
abstract = {Background Performance metrics with digital breast tomosynthesis (DBT) are based on early experiences. There is limited research on whether the benefits of DBT are sustained. Purpose To determine whether improved screening performance metrics with DBT are sustained over time at the population level and after the first screening round at the individual level. Materials and Methods A retrospective review was conducted of screening mammograms that had been obtained before DBT implementation (March 2008 to February 2011, two-dimensional digital mammography [DM] group) and for 5 years after implementation (January 2013 to December 2017, DBT1-DBT5 groups, respectively). Patients who underwent DBT were also categorized according to the number of previous DBT examinations they had undergone. Performance metrics were compared between DM and DBT groups and between patients with no previous DBT examinations and those with at least one prior DBT examination by using multivariable logistic regression models. Results The DM group consisted of 99 582 DM examinations in 55 086 women (mean age, 57.3 years ± 11.6 [standard deviation]). The DBT group consisted of 205 048 examinations in 76 276 women (mean age, 58.2 years ± 11.2). There were no differences in the cancer detection rate (CDR) between DM and DBT groups (4.6-5.8 per 1000 examinations, = .08 to = .95). The highest CDR was observed with a woman's first DBT examination (6.1 per 1000 examinations vs 4.4-5.7 per 1000 examinations with at least one prior DBT examination, = .001 to = .054). Compared with the DM group, the DBT1 group had a lower abnormal interpretation rate (AIR) (adjusted odds ratio [AOR], 0.85; \< .001), which remained reduced in the DBT2, DBT3, and DBT5 groups ( \< .001 to = .02). The reduction in AIR was also sustained after the first examination ( \< .001 to = .002). Compared with the DM group, the DBT1 group had a higher specificity (AOR, 1.20; \< .001), which remained increased in DBT2, DBT3, and DBT5 groups ( \< .001 to = .004). The increase in specificity was also sustained after the first examination ( \< .001 to = .01). Conclusion The benefits of reduced false-positive examinations and higher specificity with screening tomosynthesis were sustained after the first screening round at the individual level. © RSNA, 2020 See also the editorial by Taourel in this issue.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background Performance metrics with digital breast tomosynthesis (DBT) are based on early experiences. There is limited research on whether the benefits of DBT are sustained. Purpose To determine whether improved screening performance metrics with DBT are sustained over time at the population level and after the first screening round at the individual level. Materials and Methods A retrospective review was conducted of screening mammograms that had been obtained before DBT implementation (March 2008 to February 2011, two-dimensional digital mammography [DM] group) and for 5 years after implementation (January 2013 to December 2017, DBT1-DBT5 groups, respectively). Patients who underwent DBT were also categorized according to the number of previous DBT examinations they had undergone. Performance metrics were compared between DM and DBT groups and between patients with no previous DBT examinations and those with at least one prior DBT examination by using multivariable logistic regression models. Results The DM group consisted of 99 582 DM examinations in 55 086 women (mean age, 57.3 years ± 11.6 [standard deviation]). The DBT group consisted of 205 048 examinations in 76 276 women (mean age, 58.2 years ± 11.2). There were no differences in the cancer detection rate (CDR) between DM and DBT groups (4.6-5.8 per 1000 examinations, = .08 to = .95). The highest CDR was observed with a woman's first DBT examination (6.1 per 1000 examinations vs 4.4-5.7 per 1000 examinations with at least one prior DBT examination, = .001 to = .054). Compared with the DM group, the DBT1 group had a lower abnormal interpretation rate (AIR) (adjusted odds ratio [AOR], 0.85; < .001), which remained reduced in the DBT2, DBT3, and DBT5 groups ( < .001 to = .02). The reduction in AIR was also sustained after the first examination ( < .001 to = .002). Compared with the DM group, the DBT1 group had a higher specificity (AOR, 1.20; < .001), which remained increased in DBT2, DBT3, and DBT5 groups ( < .001 to = .004). The increase in specificity was also sustained after the first examination ( < .001 to = .01). Conclusion The benefits of reduced false-positive examinations and higher specificity with screening tomosynthesis were sustained after the first screening round at the individual level. © RSNA, 2020 See also the editorial by Taourel in this issue.
Mercaldo, Sarah Fletcher; Blume, Jeffrey D
Missing data and prediction: the pattern submodel. Journal Article
In: Biostatistics (Oxford, England), vol. 21, no. 2, pp. 236-252, 2020, ISSN: 1468-4357, ().
@article{FletcherMercaldo2018,
title = {Missing data and prediction: the pattern submodel.},
author = {Sarah Fletcher Mercaldo and Jeffrey D Blume},
url = {https://www.ncbi.nlm.nih.gov/pubmed/30203058},
doi = {10.1093/biostatistics/kxy040},
issn = {1468-4357},
year = {2020},
date = {2020-04-01},
journal = {Biostatistics (Oxford, England)},
volume = {21},
number = {2},
pages = {236-252},
abstract = {Missing data are a common problem for both the construction and implementation of a prediction algorithm. Pattern submodels (PS)-a set of submodels for every missing data pattern that are fit using only data from that pattern-are a computationally efficient remedy for handling missing data at both stages. Here, we show that PS (i) retain their predictive accuracy even when the missing data mechanism is not missing at random (MAR) and (ii) yield an algorithm that is the most predictive among all standard missing data strategies. Specifically, we show that the expected loss of a forecasting algorithm is minimized when each pattern-specific loss is minimized. Simulations and a re-analysis of the SUPPORT study confirms that PS generally outperforms zero-imputation, mean-imputation, complete-case analysis, complete-case submodels, and even multiple imputation (MI). The degree of improvement is highly dependent on the missingness mechanism and the effect size of missing predictors. When the data are MAR, MI can yield comparable forecasting performance but generally requires a larger computational cost. We also show that predictions from the PS approach are equivalent to the limiting predictions for a MI procedure that is dependent on missingness indicators (the MIMI model). The focus of this article is on out-of-sample prediction; implications for model inference are only briefly explored.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Missing data are a common problem for both the construction and implementation of a prediction algorithm. Pattern submodels (PS)-a set of submodels for every missing data pattern that are fit using only data from that pattern-are a computationally efficient remedy for handling missing data at both stages. Here, we show that PS (i) retain their predictive accuracy even when the missing data mechanism is not missing at random (MAR) and (ii) yield an algorithm that is the most predictive among all standard missing data strategies. Specifically, we show that the expected loss of a forecasting algorithm is minimized when each pattern-specific loss is minimized. Simulations and a re-analysis of the SUPPORT study confirms that PS generally outperforms zero-imputation, mean-imputation, complete-case analysis, complete-case submodels, and even multiple imputation (MI). The degree of improvement is highly dependent on the missingness mechanism and the effect size of missing predictors. When the data are MAR, MI can yield comparable forecasting performance but generally requires a larger computational cost. We also show that predictions from the PS approach are equivalent to the limiting predictions for a MI procedure that is dependent on missingness indicators (the MIMI model). The focus of this article is on out-of-sample prediction; implications for model inference are only briefly explored.
Bahl, Manisha; Pinnamaneni, Niveditha; Mercaldo, Sarah Fletcher; McCarthy, Anne Marie; Lehman, Constance D
Digital 2D versus Tomosynthesis Screening Mammography among Women Aged 65 and Older in the United States. Journal Article
In: Radiology, vol. 291, pp. 582–590, 2019, ISSN: 1527-1315, ().
@article{Bahl2019,
title = {Digital 2D versus Tomosynthesis Screening Mammography among Women Aged 65 and Older in the United States.},
author = {Manisha Bahl and Niveditha Pinnamaneni and Sarah Fletcher Mercaldo and Anne Marie McCarthy and Constance D Lehman},
url = {https://www.ncbi.nlm.nih.gov/pubmed/30938625},
doi = {10.1148/radiol.2019181637},
issn = {1527-1315},
year = {2019},
date = {2019-06-01},
journal = {Radiology},
volume = {291},
pages = {582--590},
abstract = {Background Although breast cancer incidence and mortality rates increase with advancing age, there are limited data on the benefits and risks of screening mammography in older women and on the performance of two-dimensional digital mammography (DM) and digital breast tomosynthesis (DBT) in older women. Purpose To compare performance metrics of DM and DBT among women aged 65 years and older. Materials and Methods For this retrospective study, consecutive screening mammograms in patients aged 65 years and older from March 2008 to February 2011 (DM group) and from January 2013 to December 2015 (DBT group) were reviewed. Cancer detection rate, abnormal interpretation rate, positive predictive values, sensitivity, and specificity were calculated. Multivariable logistic regression models were fit to compare performance metrics in the DM versus DBT groups. Results The DM group had 15 019 women (mean age ± standard deviation, 72.7 years ± 6.3), and the DBT group had 20 646 women (mean age, 72.1 years ± 5.9). After adjusting for multiple variables, there was no difference in cancer detection rate between the DM and DBT groups (6.9 vs 8.2 per 1000 examinations; adjusted odds ratio [AOR], 1.13; = .23). Compared with the DM group, the DBT group had a lower abnormal interpretation rate (5.7% vs 5.8%; AOR, 0.88; \< .001), higher positive predictive value 1 (14.5% vs 11.9%; AOR, 1.26; = .03), and higher specificity (95.1% vs 94.8%; AOR, 1.18; \< .001). The DBT group had a higher proportion of invasive cancers relative to in situ cancers (81.1% vs 74.4%; = .06) and fewer node-positive cancers (10.2% vs 16.6%; = .054) than did the DM group. Conclusion In women aged 65 years and older, integration of digital breast tomosynthesis led to improved performance metrics, with a lower abnormal interpretation rate, higher positive predictive value 1, and higher specificity. © RSNA, 2019 See also the editorial by Philpotts and Durand in this issue.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background Although breast cancer incidence and mortality rates increase with advancing age, there are limited data on the benefits and risks of screening mammography in older women and on the performance of two-dimensional digital mammography (DM) and digital breast tomosynthesis (DBT) in older women. Purpose To compare performance metrics of DM and DBT among women aged 65 years and older. Materials and Methods For this retrospective study, consecutive screening mammograms in patients aged 65 years and older from March 2008 to February 2011 (DM group) and from January 2013 to December 2015 (DBT group) were reviewed. Cancer detection rate, abnormal interpretation rate, positive predictive values, sensitivity, and specificity were calculated. Multivariable logistic regression models were fit to compare performance metrics in the DM versus DBT groups. Results The DM group had 15 019 women (mean age ± standard deviation, 72.7 years ± 6.3), and the DBT group had 20 646 women (mean age, 72.1 years ± 5.9). After adjusting for multiple variables, there was no difference in cancer detection rate between the DM and DBT groups (6.9 vs 8.2 per 1000 examinations; adjusted odds ratio [AOR], 1.13; = .23). Compared with the DM group, the DBT group had a lower abnormal interpretation rate (5.7% vs 5.8%; AOR, 0.88; < .001), higher positive predictive value 1 (14.5% vs 11.9%; AOR, 1.26; = .03), and higher specificity (95.1% vs 94.8%; AOR, 1.18; < .001). The DBT group had a higher proportion of invasive cancers relative to in situ cancers (81.1% vs 74.4%; = .06) and fewer node-positive cancers (10.2% vs 16.6%; = .054) than did the DM group. Conclusion In women aged 65 years and older, integration of digital breast tomosynthesis led to improved performance metrics, with a lower abnormal interpretation rate, higher positive predictive value 1, and higher specificity. © RSNA, 2019 See also the editorial by Philpotts and Durand in this issue.
Ackman, Jeanne B; Nitiwarangkul, Chayanin; Mercaldo, Sarah Fletcher
In: Journal of thoracic imaging, vol. 34, no. 6, pp. 356-361, 2019, ISSN: 1536-0237, ().
@article{Ackman2019,
title = {Extent of Intraprotocol and Intersite Variability of Thoracic Magnetic Resonance Acquisition Times at a Large Quaternary Institution: MR Technologist Insights as to Its Causes.},
author = {Jeanne B Ackman and Chayanin Nitiwarangkul and Sarah Fletcher Mercaldo},
url = {https://www.ncbi.nlm.nih.gov/pubmed/30913138},
doi = {10.1097/RTI.0000000000000411},
issn = {1536-0237},
year = {2019},
date = {2019-03-01},
urldate = {2019-03-01},
journal = {Journal of thoracic imaging},
volume = {34},
number = {6},
pages = {356-361},
abstract = {The purpose of this study was to describe Thoracic magnetic resonance (MR) acquisition time (AT) variability, associations, and technologist insights as to its causes at a large quaternary institution, by MR protocol and imaging site. A retrospective review of our 2017 QI database of 1.5 T MR imaging ATs for adults 19 years and above at the main hospital and outpatient (OPT) satellites was performed for all 5 Thoracic MR protocols. Summary statistics were calculated for ATs. Multivariable linear regression was adjusted for age, sex, body mass index, time of examination relative to shift change, technologist experience, and language interpreter. An anonymous REDCap survey of our MR technologists sought their assessment of reasons for AT variability and techniques that help reduce it. A total of 174 adult OPT 1.5 T mediastinal, pleural, and lung MR examinations were analyzed, revealing high variability of median AT by protocol and site (P0.001)-for example, mean, median, slowest, and fastest ATs for Thymus I- protocol (n=38) were 34, 32, 66, and 8 minutes, respectively. OPT site with fewest MR technologists and a single MR scanner had shortest mean AT across all protocols (35±15 min). Full Chest I- protocol had shortest AT across all sites (mean AT=33±13 min), compared with focused imaging protocols. All I-/I+ protocols had greater than expected AT, compared with the same protocol performed (I-). Surveyed MR technologists noted limited Thoracic MR training/experience, discomfort with thoracic anatomy and Thoracic MR performance, and AT-related benefit of effective communication with the radiologist with regard to lesion location. There was tremendous intraprotocol and intersite variability of Thoracic MR ATs. Increased technologist training, amplified experience, and a solid understanding of lesion location for focused examinations may all help reduce Thoracic MR AT.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The purpose of this study was to describe Thoracic magnetic resonance (MR) acquisition time (AT) variability, associations, and technologist insights as to its causes at a large quaternary institution, by MR protocol and imaging site. A retrospective review of our 2017 QI database of 1.5 T MR imaging ATs for adults 19 years and above at the main hospital and outpatient (OPT) satellites was performed for all 5 Thoracic MR protocols. Summary statistics were calculated for ATs. Multivariable linear regression was adjusted for age, sex, body mass index, time of examination relative to shift change, technologist experience, and language interpreter. An anonymous REDCap survey of our MR technologists sought their assessment of reasons for AT variability and techniques that help reduce it. A total of 174 adult OPT 1.5 T mediastinal, pleural, and lung MR examinations were analyzed, revealing high variability of median AT by protocol and site (P0.001)-for example, mean, median, slowest, and fastest ATs for Thymus I- protocol (n=38) were 34, 32, 66, and 8 minutes, respectively. OPT site with fewest MR technologists and a single MR scanner had shortest mean AT across all protocols (35±15 min). Full Chest I- protocol had shortest AT across all sites (mean AT=33±13 min), compared with focused imaging protocols. All I-/I+ protocols had greater than expected AT, compared with the same protocol performed (I-). Surveyed MR technologists noted limited Thoracic MR training/experience, discomfort with thoracic anatomy and Thoracic MR performance, and AT-related benefit of effective communication with the radiologist with regard to lesion location. There was tremendous intraprotocol and intersite variability of Thoracic MR ATs. Increased technologist training, amplified experience, and a solid understanding of lesion location for focused examinations may all help reduce Thoracic MR AT.
Weaver, Davis; Lietz, Anna; Mercaldo, Sarah Fletcher; Peters, Mary Linton B.; Hur, Chin; Kong, Chung Yin; Wolpin, Brian M; Megibow, Alec J; Berland, Lincoln L; Knudsen, Amy; Pandharipande, Pari
In: AJR. American journal of roentgenology, vol. 212, no. 3, pp. 596-601, 2019, ISSN: 1546-3141.
@article{Weaver2019,
title = {Testing for Verification Bias in Reported Malignancy Risks for Side-Branch Intraductal Papillary Mucinous Neoplasms: A Simulation Modeling Approach.},
author = {Davis Weaver and Anna Lietz and Sarah Fletcher Mercaldo and Mary Linton B. Peters and Chin Hur and Chung Yin Kong and Brian M Wolpin and Alec J Megibow and Lincoln L Berland and Amy Knudsen and Pari Pandharipande},
url = {https://www.ncbi.nlm.nih.gov/pubmed/30620679},
doi = {10.2214/AJR.18.20180},
issn = {1546-3141},
year = {2019},
date = {2019-03-01},
urldate = {2019-03-01},
journal = {AJR. American journal of roentgenology},
volume = {212},
number = {3},
pages = {596-601},
abstract = {The objective of our study was to test for the possibility that published malignancy risks for side-branch intraductal papillary mucinous neoplasms (IPMNs) are overestimates, likely due to verification bias. We tested for possible verification bias using simulation modeling techniques. First, in age-defined hypothetical cohorts of 10 million persons, we projected the frequency of pancreatic ductal adenocarcinoma (PDAC) arising from side-branch IPMNs over 5 years using published estimates of their prevalence (4.4%) and rate of malignant transformation (1.9%). Second, we projected the total number of PDAC cases in corresponding cohorts over the same time horizon using national cancer registry data. For each cohort, we determined whether the percentage of all PDAC cases that arose from side-branch IPMNs (i.e., side-branch IPMN-associated PDAC cases) was clinically plausible using an upper limit of 10% to define plausibility, as estimated from the literature. Model assumptions and parameter uncertainty were evaluated in sensitivity analysis. Across all cohorts, percentages of side-branch IPMN-associated PDACs greatly exceeded 10%. In the base case (mean age = 55.7 years), 80% of PDAC cases arose from side-branch IPMNs (7877/9786). In the oldest cohort evaluated (mean age = 75 years), this estimate was 76% (14,227/18,714). In a secondary analysis, we found that if an upper limit threshold of 10% for side-branch IPMN-associated PDAC was imposed, the model-predicted rate of malignancy for side-branch IPMNs would be less than 0.24% over a 5-year time horizon, substantially lower than most literature-based estimates. Our results suggest that reported malignancy risks associated with side-branch IPMNs are likely to be overestimates and imply the presence of verification bias.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The objective of our study was to test for the possibility that published malignancy risks for side-branch intraductal papillary mucinous neoplasms (IPMNs) are overestimates, likely due to verification bias. We tested for possible verification bias using simulation modeling techniques. First, in age-defined hypothetical cohorts of 10 million persons, we projected the frequency of pancreatic ductal adenocarcinoma (PDAC) arising from side-branch IPMNs over 5 years using published estimates of their prevalence (4.4%) and rate of malignant transformation (1.9%). Second, we projected the total number of PDAC cases in corresponding cohorts over the same time horizon using national cancer registry data. For each cohort, we determined whether the percentage of all PDAC cases that arose from side-branch IPMNs (i.e., side-branch IPMN-associated PDAC cases) was clinically plausible using an upper limit of 10% to define plausibility, as estimated from the literature. Model assumptions and parameter uncertainty were evaluated in sensitivity analysis. Across all cohorts, percentages of side-branch IPMN-associated PDACs greatly exceeded 10%. In the base case (mean age = 55.7 years), 80% of PDAC cases arose from side-branch IPMNs (7877/9786). In the oldest cohort evaluated (mean age = 75 years), this estimate was 76% (14,227/18,714). In a secondary analysis, we found that if an upper limit threshold of 10% for side-branch IPMN-associated PDAC was imposed, the model-predicted rate of malignancy for side-branch IPMNs would be less than 0.24% over a 5-year time horizon, substantially lower than most literature-based estimates. Our results suggest that reported malignancy risks associated with side-branch IPMNs are likely to be overestimates and imply the presence of verification bias.