1
|
Abbasi N, Lacson R, Kapoor N, Licaros A, Guenette JP, Burk KS, Hammer M, Desai S, Eappen S, Saini S, Khorasani R. Development and External Validation of an Artificial Intelligence Model for Identifying Radiology Reports Containing Recommendations for Additional Imaging. AJR Am J Roentgenol 2023; 221:377-385. [PMID: 37073901 DOI: 10.2214/ajr.23.29120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/20/2023]
Abstract
BACKGROUND. Reported rates of recommendations for additional imaging (RAIs) in radiology reports are low. Bidirectional encoder representations from transformers (BERT), a deep learning model pretrained to understand language context and ambiguity, has potential for identifying RAIs and thereby assisting large-scale quality improvement efforts. OBJECTIVE. The purpose of this study was to develop and externally validate an artificial intelligence (AI)-based model for identifying radiology reports containing RAIs. METHODS. This retrospective study was performed at a multisite health center. A total of 6300 radiology reports generated at one site from January 1, 2015, to June 30, 2021, were randomly selected and split by 4:1 ratio to create training (n = 5040) and test (n = 1260) sets. A total of 1260 reports generated at the center's other sites (including academic and community hospitals) from April 1 to April 30, 2022, were randomly selected as an external validation group. Referring practitioners and radiologists of varying sub-specialties manually reviewed report impressions for presence of RAIs. A BERT-based technique for identifying RAIs was developed by use of the training set. Performance of the BERT-based model and a previously developed traditional machine learning (TML) model was assessed in the test set. Finally, performance was assessed in the external validation set. The code for the BERT-based RAI model is publicly available. RESULTS. Among a total of 7419 unique patients (4133 women, 3286 men; mean age, 58.8 years), 10.0% of 7560 reports contained RAI. In the test set, the BERT-based model had 94.4% precision, 98.5% recall, and an F1 score of 96.4%. In the test set, the TML model had 69.0% precision, 65.4% recall, and an F1 score of 67.2%. In the test set, accuracy was greater for the BERT-based than for the TML model (99.2% vs 93.1%, p < .001). In the external validation set, the BERT-based model had 99.2% precision, 91.6% recall, an F1 score of 95.2%, and 99.0% accuracy. CONCLUSION. The BERT-based AI model accurately identified reports with RAIs, outperforming the TML model. High performance in the external validation set suggests the potential for other health systems to adapt the model without requiring institution-specific training. CLINICAL IMPACT. The model could potentially be used for real-time EHR monitoring for RAIs and other improvement initiatives to help ensure timely performance of clinically necessary recommended follow-up.
Collapse
Affiliation(s)
- Nooshin Abbasi
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | - Ronilda Lacson
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115
| | - Neena Kapoor
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115
| | - Andro Licaros
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | - Jeffrey P Guenette
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115
| | - Kristine Specht Burk
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115
| | - Mark Hammer
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115
| | - Sonali Desai
- Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | - Sunil Eappen
- Department of Anesthesiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | - Sanjay Saini
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA
| | - Ramin Khorasani
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115
| |
Collapse
|
2
|
DiPiro PJ, Licaros A, Zhao AH, Glazer DI, Healey MJ, Curley PJ, Giess CS, Khorasani R. Frequency and Clinical Utility of Alerts for Intra-Institutional Radiologist Discrepant Opinions. J Am Coll Radiol 2023; 20:431-437. [PMID: 36841320 DOI: 10.1016/j.jacr.2022.12.021] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2022] [Revised: 12/15/2022] [Accepted: 12/17/2022] [Indexed: 02/26/2023]
Abstract
OBJECTIVE Determine the rate of documented notification, via an alert, for intra-institutional discrepant radiologist opinions and addended reports and resulting clinical management changes. METHODS This institutional review board-exempt, retrospective study was performed at a large academic medical center. We defined an intra-institutional discrepant opinion as when a consultant radiologist provides a different interpretation from that formally rendered by a colleague at our institution. We implemented a discrepant opinion policy requiring closed-loop notification of the consulting radiologist's second opinion to the original radiologist, who must acknowledge this alert within 30 days. This study included all discrepant opinion alerts created December 1, 2019, to December 31, 2021, of which two radiologists and an internal medicine physician performed consensus review. Primary outcomes were degree of discrepancy and percent of discrepant opinions leading to change in clinical management. Secondary outcome was report addendum rate compared with an existing peer learning program using Fisher's exact test. RESULTS Of 114 discrepant opinion alerts among 1,888,147 reports generated during the study period (0.006%), 58 alerts were categorized as major (50.9%), 41 as moderate (36.0%), and 15 as minor discrepancies (13.1%). Clinical management change occurred in 64 of 114 cases (56.1%). Report addendum rate for discrepant opinion alerts was 4-fold higher than for peer learning alerts at our institution (66 of 315 = 21% versus 432 of 8,273 =5.2%; P < .0001). DISCUSSION Although discrepant intra-institutional radiologist second opinions were rare, they frequently led to changes in clinical management. Capturing these discrepancies by encouraging alert use may help optimize patient care and document what was communicated to the referring or consulting care team by consulting radiologists.
Collapse
Affiliation(s)
- Pamela J DiPiro
- Radiology Quality and Safety Officer, Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts; and Department of Imaging, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts.
| | - Andro Licaros
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; and Oncologic Imaging Fellow, Department of Imaging, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| | - Anna H Zhao
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; and Radiology Resident, Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts
| | - Daniel I Glazer
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; Medical Director of CT and Director, Cross-Sectional Interventional Radiology (CSIR), Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts; and Department of Imaging, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| | - Michael J Healey
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; and Associate Chief Medical Officer, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts
| | - Patrick J Curley
- Executive Director, Quality, Safety, Equity & Experience, Enterprise Radiology, Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts
| | - Catherine S Giess
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; Deputy Chair, Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts; and Department of Imaging, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| | - Ramin Khorasani
- Vice Chair, Radiology Quality and Safety, Mass General Brigham; Vice Chair, Department of Radiology; Distinguished Chair, Medical Informatics; Director, Center for Evidence Based Imaging; Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women's Hospital, Boston, Massachusetts; Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts; and Department of Imaging, Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
3
|
Lacson R, Hooton S, Licaros A, Lynch E, Healey M, Eappen S, Khorasani R. A Comparison of Two Scheduling Models for Prompt Resolution of Diagnostic Imaging Orders. J Am Coll Radiol 2023; 20:218-221. [PMID: 36509219 DOI: 10.1016/j.jacr.2022.09.035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2022] [Revised: 08/29/2022] [Accepted: 09/08/2022] [Indexed: 12/13/2022]
Affiliation(s)
- Ronilda Lacson
- Associate Director of Center for Evidence Based Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts; Associate Professor of Radiology, Harvard Medical School, Boston, Massachusetts.
| | - Stuart Hooton
- Director of Radiology Care Coordination Services, Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts
| | - Andro Licaros
- Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts
| | - Elyse Lynch
- Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts
| | - Michael Healey
- Assistant Professor of Radiology, Harvard Medical School, Boston, Massachusetts; Associate Chief Medical Officer, Brigham and Women's Physicians Organization, Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts
| | - Sunil Eappen
- Harvard Medical School, Boston, Massachusetts; Senior Vice President, Medical Affairs; Chief Medical Officer; Interim President, Department of Anesthesiology, Brigham and Women's Hospital, Boston, Massachusetts
| | - Ramin Khorasani
- Vice Chair of Radiology, Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts; Distinguished Chair, Medical Informatics, Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts; Director of Center for Evidence Based Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts; Professor of Radiology, Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
4
|
Lacson R, Eskian M, Cochon L, Gujrathi I, Licaros A, Zhao A, Vetrano N, Schneider L, Raja A, Khorasani R. Representing narrative evidence as clinical evidence logic statements. JAMIA Open 2022; 5:ooac024. [PMID: 35474718 PMCID: PMC9030217 DOI: 10.1093/jamiaopen/ooac024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2021] [Revised: 03/05/2022] [Accepted: 03/25/2022] [Indexed: 11/12/2022] Open
Abstract
Abstract
Objective
Clinical evidence logic statements (CELS) are shareable knowledge artifacts in a semistructured “If-Then” format that can be used for clinical decision support systems. This project aimed to assess factors facilitating CELS representation.
Materials and Methods
We described CELS representation of clinical evidence. We assessed factors that facilitate representation, including authoring instruction, evidence structure, and educational level of CELS authors. Five researchers were tasked with representing CELS from published evidence. Represented CELS were compared with the formal representation. After an authoring instruction intervention, the same researchers were asked to represent the same CELS and accuracy was compared with that preintervention using McNemar’s test. Moreover, CELS representation accuracy was compared between evidence that is structured versus semistructured, and between CELS authored by specialty-trained versus nonspecialty-trained researchers, using χ2 analysis.
Results
261 CELS were represented from 10 different pieces of published evidence by the researchers pre- and postintervention. CELS representation accuracy significantly increased post-intervention, from 20/261 (8%) to 63/261 (24%, P value < .00001). More CELS were assigned for representation with 379 total CELS subsequently included in the analysis (278 structured and 101 semistructured) postintervention. Representing CELS from structured evidence was associated with significantly higher CELS representation accuracy (P = .002), as well as CELS representation by specialty-trained authors (P = .0004).
Discussion
CELS represented from structured evidence had a higher representation accuracy compared with semistructured evidence. Similarly, specialty-trained authors had higher accuracy when representing structured evidence.
Conclusion
Authoring instructions significantly improved CELS representation with a 3-fold increase in accuracy. However, CELS representation remains a challenging task.
Collapse
Affiliation(s)
- Ronilda Lacson
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| | - Mahsa Eskian
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
| | - Laila Cochon
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
| | - Isha Gujrathi
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
| | - Andro Licaros
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
| | - Anna Zhao
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| | - Nicole Vetrano
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
| | - Louise Schneider
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| | - Ali Raja
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
- Department of Emergency Medicine, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Ramin Khorasani
- Department of Radiology, Center for Evidence-Based Imaging, Brigham and Women’s Hospital, Boston, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
5
|
Lacson R, Licaros A, Cochon L, Hammer M, Gagne S, Kapoor N, Khorasani R. Factors Associated With Follow-up Testing Completion in Patients With Incidental Pulmonary Nodules Assessed to Require Follow-up. J Am Coll Radiol 2022; 19:433-436. [PMID: 35123957 DOI: 10.1016/j.jacr.2021.11.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2021] [Revised: 11/22/2021] [Accepted: 11/23/2021] [Indexed: 10/19/2022]
|