Prospective Evaluation of Artificial Intelligence Triage of Intracranial Hemorrhage on Noncontrast Head CT Examinations.

Background: Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation. Objective: To evaluate the impact on radiologists' real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department's implementation of an AI triage and notification system for ICH detection on head NCCT examinations. Methods: This prospective single-center study included adult patients who underwent head NCCT examinations from May 12, 2021 to June 30, 2021 (phase 1) or September 30, 2021 to December 4, 2021 (phase 2). Before phase 1, the radiology department implemented a commercial AI triage system for ICH detection that processed head NCCT examinations and notified radiologists of positive results through a widget with a floating pop-up display. Examinations were interpreted by neuroradiologists or emergency radiologists, who evaluated examinations without and with AI assistance in phase 1 and phase 2, respectively. A panel of radiologists conducted a review process for all examinations with discordance between the radiology report and AI and a subset of remaining examinations, to establish the reference standard. Diagnostic performance and report turnaround times were compared using Pearson chi-square test and Wilcoxon rank-sum test, respectively. Bonferroni correction was used to account for five diagnostic performance metrics (adjusted significance threshold, .01 [α=.05/5]). Results: A total of 9954 examinations from 7371 patients (mean age, 54.8±19.8 years; 3773 female, 3598 male) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (P=.01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 99.7%), or NPV (99.7% vs 99.7%) (all P>.01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, P=.004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (P=.11). Conclusion: An AI triage system for ICH detection did not improve radiologists' diagnostic performance or report turnaround times. Clinical Impact: This large prospective real-world study does not support use of AI assistance for ICH detection.

The Impact of Surgical Training on Residents' Relationships and Life Choices.

OBJECTIVE: Our study investigated the effects of surgical training on residents' personal relationships. It aimed to address the gaps in understanding of how the surgical training commitment can influence relationship stability, decision-making, and life planning within this unique professional group. DESIGN: We used cross-sectional survey methodology to gather data on the intricacies of relationship dynamics amid the rigors of surgical training. The survey focused on marital status, relationship dynamics, personal life choices, the challenges and rewards of dual-healthcare relationships, and the support networks that individuals and couples rely on. SETTING: All surgical departments at The Johns Hopkins Hospital. PARTICIPANTS: The study comprised 111 participants, including residents, fellows, and attending surgeons. Of those reporting sex, 56/105 (53%) were female, and the predominant age category was 25 to 34 years, making up 61/104 (59%) of respondents. RESULTS: The majority (73/105, 70%) of respondents were or had been married, and 50/96 (52%) had partners in the medical field. Among those in a dual-healthcare relationship, 38/46 (83%) reported that their relationship was strengthened through understanding and empathy, yet 37/46 (80%) acknowledged complications in work-life balance. However, women were significantly more likely than men to report at least one negative effect of a dual-healthcare relationship (84% [16/19] versus 22% [6/27], p = .003). Among those with partners outside medicine, 39/46 (85%) acknowledged that their partner had to adjust their lifestyle significantly. A considerable number (73/92, 79%) postponed life events such as starting a family, and 57/85 (67%) experienced relationship strain due to long working hours. CONCLUSIONS: Residents in dual-healthcare couples derived support from their relationships, but surgical training placed a significant strain on residents' personal relationships and often prompted residents to postpone major life events such as starting a family. Enhanced support systems and targeted interventions are needed to assist surgical professionals in navigating the complexities of balancing a demanding career with personal life.

Prospective Evaluation of Artificial Intelligence Triage of Incidental Pulmonary Emboli on Contrast-Enhanced CT Examinations of the Chest or Abdomen.

BACKGROUND. Artificial intelligence (AI) algorithms improved detection of incidental pulmonary embolism (IPE) on contrast-enhanced CT (CECT) examinations in retrospective studies; however, prospective validation studies are lacking. OBJECTIVE. The purpose of this study was to assess the effect on radiologists' real-world diagnostic performance and report turnaround times of a radiology department's clinical implementation of an AI triage system for detecting IPE on CECT examinations of the chest or abdomen. METHODS. This prospective single-center study included consecutive adult patients who underwent CECT of the chest or abdomen for reasons other than pulmonary embolism (PE) detection from May 12, 2021, to June 30, 2021 (phase 1), or from September 30, 2021, to December 4, 2021 (phase 2). Before phase 1, the radiology department installed a commercially available AI triage algorithm for IPE detection that automatically processed CT examinations and notified radiologists of positive results through an interactive floating widget. In phase 1, the widget was inactive, and radiologists interpreted examinations without AI assistance. In phase 2, the widget was activated, and radiologists interpreted examinations with AI assistance. A review process involving a panel of radiologists was implemented to establish the reference standard for the presence of IPE. Diagnostic performance and report turnaround times were compared using the Pearson chi-square test and Wilcoxon rank sum test, respectively. RESULTS. Phase 1 included 1467 examinations in 1434 patients (mean age, 53.8 ± 18.5 [SD] years; 753 men, 681 women); phase 2 included 3182 examinations in 2886 patients (mean age, 55.4 ± 18.2 years; 1520 men, 1366 women). The frequency of IPE was 1.4% (20/1467) in phase 1 and 1.6% (52/3182) in phase 2. Radiologists without AI, in comparison to radiologists with AI, showed significantly lower sensitivity (80.0% vs 96.2%, respectively; p = .03), without a significant difference in specificity (99.9% vs 99.9%, p = .58), for the detection of IPE. The mean report turnaround time for IPE-positive examinations was not significantly different between radiologists without AI and radiologists with AI (78.3 vs 74.6 minutes, p = .26). CONCLUSION. An AI triage system improved radiologists' sensitivity for IPE detection on CECT examinations of the chest or abdomen without significant change in report turnaround times. CLINICAL IMPACT. This prospective real-world study supports the use of AI assistance for maximizing IPE detection.

General-Purpose Large Language Models Versus a Domain-Specific Natural Language Processing Tool for Label Extraction From Chest Radiograph Reports.

GPT-4 outperformed a radiology domain-specific natural language processing model in classifying imaging findings from chest radiograph reports, both with and without predefined labels. Prompt engineering for context further improved performance. The findings indicate a role for large language models to accelerate artificial intelligence model development in radiology by automating data annotation.

Prospective Evaluation of AI Triage of Pulmonary Emboli on CT Pulmonary Angiograms.

Background Artificial intelligence (AI) algorithms have shown high accuracy for detection of pulmonary embolism (PE) on CT pulmonary angiography (CTPA) studies in academic studies. Purpose To determine whether use of an AI triage system to detect PE on CTPA studies improves radiologist performance or examination and report turnaround times in a clinical setting. Materials and Methods This prospective single-center study included adult participants who underwent CTPA for suspected PE in a clinical practice setting. Consecutive CTPA studies were evaluated in two phases, first by radiologists alone (n = 31) (May 2021 to June 2021) and then by radiologists aided by a commercially available AI triage system (n = 37) (September 2021 to December 2021). Sixty-two percent of radiologists (26 of 42 radiologists) interpreted studies in both phases. The reference standard was determined by an independent re-review of studies by thoracic radiologists and was used to calculate performance metrics. Diagnostic accuracy and turnaround times were compared using Pearson χ2 and Wilcoxon rank sum tests. Results Phases 1 and 2 included 503 studies (participant mean age, 54.0 years ± 17.8 [SD]; 275 female, 228 male) and 1023 studies (participant mean age, 55.1 years ± 17.5; 583 female, 440 male), respectively. In phases 1 and 2, 14.5% (73 of 503) and 15.9% (163 of 1023) of CTPA studies were positive for PE (P = .47). Mean wait time for positive PE studies decreased from 21.5 minutes without AI to 11.3 minutes with AI (P < .001). The accuracy and miss rate, respectively, for radiologist detection of any PE on CTPA studies was 97.6% and 12.3% without AI and 98.6% and 6.1% with AI, which was not significantly different (P = .15 and P = .11, respectively). Conclusion The use of an AI triage system to detect any PE on CTPA studies improved wait times but did not improve radiologist accuracy, miss rate, or examination and report turnaround times. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Murphy and Tee in this issue.

Limited ability of the renal ablation-specific (MC)2 risk scoring system to predict major adverse events from percutaneous renal microwave ablation.

PURPOSE: To access if the (MC)2 scoring system can identify patients at risk for major adverse events following percutaneous microwave ablation of renal tumors. METHODS: Retrospective review of all adult patients who underwent percutaneous renal microwave ablation at two centers. Patient demographics, medical histories, laboratory work, technical details of the procedure, tumor characteristics, and clinical outcomes were collected. The (MC)2 score was calculated for each patient. Patients were assigned to low-risk (<5), moderate-risk (5-8) and high-risk (>8) groups. Adverse events were graded according to the criteria from the Society of Interventional Radiology guidelines. RESULTS: A total of 116 patients (mean age = 67.8 [95%CI 65.5-69.9], 66 men) were included. 10 (8.6%) and 22 (19.0%) experienced major or minor adverse events, respectively. The mean (MC)2 score for patients with major adverse events (4.6 [95%CI 3.3-5.8]) was not higher than those with either minor adverse events (4.1 [95%CI 3.4-4.8], p = 0.49) or no adverse events (3.7 [95%CI 3.4-4.1], p = 0.25). However, mean tumor size was greater in those with major adverse events (3.1 cm [95%CI 2.0-4.1]) than minor adverse events (2.0 cm [95%CI 1.8-2.3], p = 0.01). Patients with central tumors were also more likely to experience major adverse events compared to those without central tumors (p = 0.02). The area under the receiver operator curve to predict major adverse events was 0.61 (p = 0.15), indicating a poor ability of the (MC)2 score to predict major adverse events. CONCLUSION: The (MC)2 risk scoring system does not accurately identify patients at risk for major adverse events from percutaneous microwave ablation of renal tumors. The mean tumor size and central tumor location may serve as a better indicator for risk assessment of major adverse events.