Faculty Bibliography

OBJECTIVES/OBJECTIVE:To evaluate the proficiency of a HIPAA-compliant version of GPT-4 in identifying actionable, incidental findings from unstructured radiology reports of Emergency Department patients. To assess appropriateness of artificial intelligence (AI)-generated, patient-facing summaries of these findings. MATERIALS AND METHODS/METHODS:Radiology reports extracted from the electronic health record of a large academic medical center were manually reviewed to identify non-emergent, incidental findings with high likelihood of requiring follow-up, further sub-stratified as "definitely actionable" (DA) or "possibly actionable-clinical correlation" (PA-CC). Instruction prompts to GPT-4 were developed and iteratively optimized using a validation set of 50 reports. The optimized prompt was then applied to a test set of 430 unseen reports. GPT-4 performance was primarily graded on accuracy identifying either DA or PA-CC findings, then secondarily for DA findings alone. Outputs were reviewed for hallucinations. AI-generated patient-facing summaries were assessed for appropriateness via Likert scale. RESULTS:For the primary outcome (DA or PA-CC), GPT-4 achieved 99.3% recall, 73.6% precision, and 84.5% F-1. For the secondary outcome (DA only), GPT-4 demonstrated 95.2% recall, 77.3% precision, and 85.3% F-1. No findings were "hallucinated" outright. However, 2.8% of cases included generated text about recommendations that were inferred without specific reference. The majority of True Positive AI-generated summaries required no or minor revision. CONCLUSION/CONCLUSIONS:GPT-4 demonstrates proficiency in detecting actionable, incidental findings after refined instruction prompting. AI-generated patient instructions were most often appropriate, but rarely included inferred recommendations. While this technology shows promise to augment diagnostics, active clinician oversight via "human-in-the-loop" workflows remains critical for clinical implementation.

OBJECTIVE:A small fraction of oral lichenoid conditions (OLC) have potential for malignant transformation. Distinguishing OLCs from other oral potentially malignant disorders (OPMDs) can help prevent unnecessary concern or testing, but accurate identification by nonexpert clinicians is challenging due to overlapping clinical features. In this study, the authors developed a 'cytomics-on-a-chip' tool and integrated predictive model for aiding the identification of OLCs. STUDY DESIGN/METHODS:All study subjects underwent both scalpel biopsy for histopathology and brush cytology. A predictive model and OLC Index comprising clinical, demographic, and cytologic features was generated to discriminate between subjects with lichenoid (OLC+) (N = 94) and nonlichenoid (OLC-) (N = 237) histologic features in a population with OPMDs. RESULTS:The OLC Index discriminated OLC+ and OLC- subjects with area under the curve (AUC) of 0.76. Diagnostic accuracy of the OLC Index was not significantly different from expert clinician impressions, with AUC of 0.81 (P = .0704). Percent agreement was comparable across all raters, with 83.4% between expert clinicians and histopathology, 78.3% between OLC Index and expert clinician, and 77.3% between OLC Index and histopathology. CONCLUSIONS:The cytomics-on-a-chip tool and integrated diagnostic model have the potential to facilitate both the triage and diagnosis of patients presenting with OPMDs and OLCs.

BACKGROUND:Mild traumatic brain injury is theorized to cause widespread functional changes to the brain. Resting-state fMRI may be able to measure functional connectivity changes after traumatic brain injury, but resting-state fMRI studies are heterogeneous, using numerous techniques to study ROIs across various resting-state networks. PURPOSE/OBJECTIVE:We systematically reviewed the literature to ascertain whether adult patients who have experienced mild traumatic brain injury show consistent functional connectivity changes on resting-state -fMRI, compared with healthy patients. DATA SOURCES/METHODS:We used 5 databases (PubMed, EMBASE, Cochrane Central, Scopus, Web of Science). STUDY SELECTION/METHODS:Five databases (PubMed, EMBASE, Cochrane Central, Scopus, and Web of Science) were searched for research published since 2010. Search strategies used keywords of "functional MR imaging" and "mild traumatic brain injury" as well as related terms. All results were screened at the abstract and title levels by 4 reviewers according to predefined inclusion and exclusion criteria. For full-text inclusion, each study was evaluated independently by 2 reviewers, with discordant screening settled by consensus. DATA ANALYSIS/METHODS:Data regarding article characteristics, cohort demographics, fMRI scan parameters, data analysis processing software, atlas used, data characteristics, and statistical analysis information were extracted. DATA SYNTHESIS/RESULTS:Across 66 studies, 80 areas were analyzed 239 times for at least 1 time point, most commonly using independent component analysis. The most analyzed areas and networks were the whole brain, the default mode network, and the salience network. Reported functional connectivity changes varied, though there may be a slight trend toward decreased whole-brain functional connectivity within 1 month of traumatic brain injury and there may be differences based on the time since injury. LIMITATIONS/CONCLUSIONS:Studies of military, sports-related traumatic brain injury, and pediatric patients were excluded. Due to the high number of relevant studies and data heterogeneity, we could not be as granular in the analysis as we would have liked. CONCLUSIONS:Reported functional connectivity changes varied, even within the same region and network, at least partially reflecting differences in technical parameters, preprocessing software, and analysis methods as well as probable differences in individual injury. There is a need for novel rs-fMRI techniques that better capture subject-specific functional connectivity changes.

Cervical cancer is a common gynecological malignancy worldwide. Cervical cancer is staged based on the International Federation of Gynecology and Obstetrics (FIGO) classification system, which was revised in 2018 to incorporate radiologic and pathologic data. Imaging plays an important role in pretreatment assessment including initial staging and treatment response assessment of cervical cancer. Accurate determination of tumor size, local extension, and nodal and distant metastases is important for treatment selection and for prognostication. Although local recurrence can be diagnosed by physical examination, imaging plays a critical role in detection and follow-up of local and distant recurrence and subsequent treatment selection. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

This review focuses on the initial imaging in the reproductive age adult population with acute pelvic pain, including patients with positive and negative beta-human chorionic gonadotropin (β-hCG) levels with suspected gynecological and nongynecological etiology. For all patients, a combination of transabdominal and transvaginal pelvic ultrasound with Doppler is usually appropriate as an initial imaging study. If nongynecological etiology in patients with negative β-hCG is suspected, then CT of the abdomen and pelvis with or without contrast is also usually appropriate. In patients with positive β-hCG and suspected nongynecological etiology, CT of the abdomen and pelvis with contrast and MRI of the abdomen and pelvis without contrast may be appropriate. In patients with negative β-hCG and suspected gynecological etiology, CT of the abdomen and pelvis with contrast, MRI of pelvis without contrast, or MRI of pelvis with and without contrast may be appropriate. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Asymptomatic adnexal masses are commonly encountered in daily radiology practice. Although the vast majority of these masses are benign, a small subset have a risk of malignancy, which require gynecologic oncology referral for best treatment outcomes. Ultrasound, using a combination of both transabdominal, transvaginal, and duplex Doppler technique can accurately characterize the majority of these lesions. MRI with and without contrast is a useful complementary modality that can help characterize indeterminate lesions and assess the risk of malignancy is those that are suspicious. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

BACKGROUND:Chronic kidney disease (CKD) is highly prevalent, affecting approximately 11% of U.S. adults. Multiple studies have evaluated a potential association between CKD and urinary tract malignancies. Summary estimates of urinary tract malignancy risk in CKD patients with and without common co-existing conditions may guide clinical practice recommendations. METHODS:Four electronic databases were searched for original cohort studies evaluating the association between CKD and urinary tract cancers (kidney cancer and urothelial carcinoma) through May 25, 2023, in persons with at least moderate CKD and no dialysis or kidney transplantation. Quality assessment was performed for studies meeting inclusion criteria using the Newcastle-Ottawa Scale. Meta-analysis with a random-effects model was performed for unadjusted incidence rate ratios (IRR) as well as adjusted hazard ratios (aHR) for confounding conditions (diabetes, hypertension, and/or tobacco use), shown to have association with kidney cancer and urothelial carcinoma. Sub-analysis was conducted for estimates associated with CKD stages separately. RESULTS:Six cohort studies with 8 617 563 persons were included. Overall, methodological quality of the studies was good. CKD was associated with both higher unadjusted incidence and adjusted hazard of kidney cancer (IRR, 3.36; 95% confidence interval [CI], 2.32-4.88; aHR, 2.04; 95% CI, 1.77-2.36) and urothelial cancer (IRR, 3.96; 95% CI, 2.44-6.40; aHR, 1.40; 95% CI, 1.22-1.68) compared with persons without CKD. Examining incident urinary tract cancers by CKD severity, risks were elevated in stage 3 CKD (kidney aHR, 1.89; 95% CI, 1.56-2.30; urothelial carcinoma aHR, 1.40; 95% CI, 1.18-1.65) as well as in stages 4/5 CKD (kidney cancer aHR, 2.30; 95% CI, 2.00-2.66, UC aHR, 1.24; 95% CI, 1.04-1.49). CONCLUSIONS:Even moderate CKD is associated with elevated risk of kidney cancer and UC. Providers should consider these elevated risks when managing individuals with CKD, particularly when considering evaluation for the presence and etiology of hematuria.

OBJECTIVE:To evaluate the association between census-tract level measures of social vulnerability and residential segregation and IPN follow up. METHODS:This retrospective cohort study included patients with IPN ≥6 mm in size or multiple subsolid/ground-glass IPNs <6 mm (with non-optional follow-up recommendations) diagnosed between January 1, 2018 and December 30, 2019 at a large urban tertiary center and followed ≥two years. Geographic sociodemographic context was characterized by 2018 U.S. Centers for Disease Control and Prevention Social Vulnerability Index (SVI) and the Index of Concentration at the Extreme (ICE), categorized in quartiles. Multivariable binomial regression models were utilized with a primary outcome of inappropriate IPN follow up (late or no follow up). Models were also stratified by nodule risk. RESULTS:The study consisted of 2,492 patients (mean age 65.6 years +/- 12.6 years; 1,361 women). Top-quartile SVI patients were more likely to have inappropriate follow up (Risk Ratio [RR]: 1.24, 95% Confidence Interval [95% CI], 1.12-1.36]), compared with the bottom quartile; risk was also elevated in top-quartile SVI subcategories of Socioeconomic Status (RR: 1.23, 95% CI, 1.13-1.34), Minority Status and Language (RR: 1.24, 95% CI, 1.03-1.48), Housing and Transportation (RR: 1.13, 95% CI, 1.02-1.26), and ICE (RR: 1.20, 95% CI, 1.11-1.30). Further, top-quartile ICE was associated with greater risk of inappropriate follow up among high-risk vs. lower-risk IPN (1.33 [1.18-1.50] vs. 1.13 [1.02-1.25]), respectively, P for interaction= 0.017). DISCUSSION/CONCLUSIONS:Local social vulnerability and residential segregation are associated with inappropriate IPN follow up and may inform policy or interventions tailored for neighborhoods.

Systematic reviews of diagnostic accuracy studies can provide the best available evidence to inform decisions regarding the use of a diagnostic test. In this guide, the authors provide a practical approach for clinicians to appraise diagnostic accuracy systematic reviews and apply their results to patient care. The first step is to identify an appropriate systematic review with a research question matching the clinical scenario. The user should evaluate the rigor of the review methods to evaluate its credibility (Did the review use clearly defined eligibility criteria, a comprehensive search strategy, structured data collection, risk of bias and applicability appraisal, and appropriate meta-analysis methods?). If the review is credible, the next step is to decide whether the diagnostic performance is adequate for clinical use (Do sensitivity and specificity estimates exceed the threshold that makes them useful in clinical practice? Are these estimates sufficiently precise? Is variability in the estimates of diagnostic accuracy across studies explained?). Diagnostic accuracy systematic reviews that are judged to be credible and provide diagnostic accuracy estimates with sufficient certainty and relevance are the most useful to inform patient care. This review discusses comparative, noncomparative, and emerging approaches to systematic reviews of diagnostic accuracy using a clinical scenario and examples based on recent publications.