Comparison of the Diagnostic Accuracy of Mammogram-based Deep Learning and Traditional Breast Cancer Risk Models in Patients Who Underwent Supplemental Screening with MRI.

Background Access to supplemental screening breast MRI is determined using traditional risk models, which are limited by modest predictive accuracy. Purpose To compare the diagnostic accuracy of a mammogram-based deep learning (DL) risk assessment model to that of traditional breast cancer risk models in patients who underwent supplemental screening with MRI. Materials and Methods This retrospective study included consecutive patients undergoing breast cancer screening MRI from September 2017 to September 2020 at four facilities. Risk was assessed using the Tyrer-Cuzick (TC) and National Cancer Institute Breast Cancer Risk Assessment Tool (BCRAT) 5-year and lifetime models as well as a DL 5-year model that generated a risk score based on the most recent screening mammogram. A risk score of 1.67% or higher defined increased risk for traditional 5-year models, a risk score of 20% or higher defined high risk for traditional lifetime models, and absolute scores of 2.3 or higher and 6.6 or higher defined increased and high risk, respectively, for the DL model. Model accuracy metrics including cancer detection rate (CDR) and positive predictive values (PPVs) (PPV of abnormal findings at screening [PPV1], PPV of biopsies recommended [PPV2], and PPV of biopsies performed [PPV3]) were compared using logistic regression models. Results This study included 2168 women who underwent 4247 high-risk screening MRI examinations (median age, 54 years [IQR, 48-60 years]). CDR (per 1000 examinations) was higher in patients at high risk according to the DL model (20.6 [95% CI: 11.8, 35.6]) than according to the TC (6.0 [95% CI: 2.9, 12.3]; P < .01) and BCRAT (6.8 [95% CI: 2.9, 15.8]; P = .04) lifetime models. PPV1, PPV2, and PPV3 were higher in patients identified as high risk by the DL model (PPV1, 14.6%; PPV2, 32.4%; PPV3, 36.4%) than those identified as high risk with the TC (PPV1, 5.0%; PPV2, 12.7%; PPV3, 13.5%; P value range, .02-.03) and BCRAT (PPV1, 5.5%; PPV2, 11.1%; PPV3, 12.5%; P value range, .02-.05) lifetime models. Conclusion Patients identified as high risk by a mammogram-based DL risk assessment model showed higher CDR at breast screening MRI than patients identified as high risk with traditional risk models. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bae in this issue.

Contrast-enhanced Mammography: Current Applications and Future Directions.

Contrast-enhanced mammography (CEM) is a developing modality used for the workup and management of breast cancer. Although diagnostic imaging modalities such as mammography and US have historically been the mainstays of initial breast cancer workup, recent advances in breast MRI have allowed better disease evaluation. However, MRI is not always readily available, can be time consuming, and is contraindicated in certain patients. CEM is an alternative to US and MRI, and it can be used to obtain contrast material-enhanced information and standard mammograms simultaneously. A CEM examination is shorter than that of MRI, and the modalities have similar rates of sensitivity to detect lesions. CEM also costs less than MRI. The authors evaluate clinical uses of CEM and discuss the literature supporting these indications.©RSNA, 2019.

Coding and Billing in Surgical Education: A Systems-Based Practice Education Program.

OBJECTIVE: Despite increased emphasis on systems-based practice through the Accreditation Council for Graduate Medical Education core competencies, few studies have examined what surgical residents know about coding and billing. We sought to create and measure the effectiveness of a multifaceted approach to improving resident knowledge and performance of documenting and coding outpatient encounters. DESIGN: We identified knowledge gaps and barriers to documentation and coding in the outpatient setting. We implemented a series of educational and workflow interventions with a group of 12 residents in a surgical clinic at a tertiary care center. To measure the effect of this program, we compared billing codes for 1 year before intervention (FY2012) to prospectively collected data from the postintervention period (FY2013). All related documentation and coding were verified by study-blinded auditors. SETTING: Interventions took place at the outpatient surgical clinic at Rhode Island Hospital, a tertiary-care center. PARTICIPANTS: A cohort of 12 plastic surgery residents ranging from postgraduate year 2 through postgraduate year 6 participated in the interventional sequence. RESULTS: A total of 1285 patient encounters in the preintervention group were compared with 1170 encounters in the postintervention group. Using evaluation and management codes (E&M) as a measure of documentation and coding, we demonstrated a significant and durable increase in billing with supporting clinical documentation after the intervention. For established patient visits, the monthly average E&M code level increased from 2.14 to 3.05 (p < 0.01); for new patients the monthly average E&M level increased from 2.61 to 3.19 (p < 0.01). CONCLUSIONS: This study describes a series of educational and workflow interventions, which improved resident coding and billing of outpatient clinic encounters. Using externally audited coding data, we demonstrate significantly increased rates of higher complexity E&M coding in a stable patient population based on improved documentation and billing awareness by the residents.

PET/CT Helps Downgrade an Aggressive-Appearing Rib Mass to a Probable Benign Lesion in a 9-Year-Old Girl.

We present a case of a 9-year-old girl with no significant medical history who developed acute onset of shortness of breath and upper chest pain during cheerleading practice. Laboratory results and physical examination were unremarkable. Chest radiograph and chest CT showed an expansile lytic aggressive-appearing mass within the left sixth rib. Subsequent F-FDG PET/CT showed a left sixth rib lesion that was not hypermetabolic and appeared benign. Biopsy yielded a diagnosis of enchondroma, a benign intramedullary tumor that accounts for 24% of all bone tumors in children as well as adolescents.

Hospitalized Patients' Perceptions of Resident Fatigue, Duty Hours, and Continuity of Care.

BACKGROUND: Physicians' perceptions of duty hour regulations have been closely examined, yet patient opinions have been largely unstudied to date. OBJECTIVE: We studied patient perceptions of residency duty hours, fatigue, and continuity of care following implementation of the Accreditation Council for Graduate Medical Education 2011 Common Program Requirements. METHODS: A cross-sectional survey was administered between June and August 2013 to inpatients at a large academic medical center and an affiliated community hospital. Adult inpatients on teaching medical and surgical services were eligible for inclusion in the study. RESULTS: Survey response rate was 71.3% (513 of 720). Most respondents (57.1%, 293 of 513) believed residents should not be assigned to shifts longer than 12 hours, and nearly half (49.7%, 255 of 513) wanted to be notified if a resident caring for them had worked longer than 12 hours. Most patients (63.2%, 324 of 513) believed medical errors commonly occurred because of fatigue, and fewer (37.4%, 192 of 513; odds ratio, 0.56; P < .01) believed medical errors commonly occurred as a result of transfers of care. Given the choice between a familiar physician who "may be tired from a long shift" or a "fresh" physician who had received sign-out, more patients chose the fresh but unfamiliar physician (57.1% [293 of 513] versus 42.7% [219 of 513], P < .01). CONCLUSIONS: In a survey about physician attributes relevant to medical errors and patient safety, adult inpatients in a large and diverse sample reported greater concern about fatigue and working hours than about continuity of care.