Artificial intelligence for automated detection and measurements of carpal instability signs on conventional radiographs.

OBJECTIVES: To develop and validate an artificial intelligence (AI) system for measuring and detecting signs of carpal instability on conventional radiographs. MATERIALS AND METHODS: Two case-control datasets of hand and wrist radiographs were retrospectively acquired at three hospitals (hospitals A, B, and C). Dataset 1 (2178 radiographs from 1993 patients, hospitals A and B, 2018-2019) was used for developing an AI system for measuring scapholunate (SL) joint distances, SL and capitolunate (CL) angles, and carpal arc interruptions. Dataset 2 (481 radiographs from 217 patients, hospital C, 2017-2021) was used for testing, and with a subsample (174 radiographs from 87 patients), an observer study was conducted to compare its performance to five clinicians. Evaluation metrics included mean absolute error (MAE), sensitivity, and specificity. RESULTS: Dataset 2 included 258 SL distances, 189 SL angles, 191 CL angles, and 217 carpal arc labels obtained from 217 patients (mean age, 51 years ± 23 [standard deviation]; 133 women). The MAE in measuring SL distances, SL angles, and CL angles was respectively 0.65 mm (95%CI: 0.59, 0.72), 7.9 degrees (95%CI: 7.0, 8.9), and 5.9 degrees (95%CI: 5.2, 6.6). The sensitivity and specificity for detecting arc interruptions were 83% (95%CI: 74, 91) and 64% (95%CI: 56, 71). The measurements were largely comparable to those of the clinicians, while arc interruption detections were more accurate than those of most clinicians. CONCLUSION: This study demonstrates that a newly developed automated AI system accurately measures and detects signs of carpal instability on conventional radiographs. CLINICAL RELEVANCE STATEMENT: This system has the potential to improve detections of carpal arc interruptions and could be a promising tool for supporting clinicians in detecting carpal instability.

Are there gender disparities in symptom presentation or triage of patients with chest discomfort at primary care out-of-hours services? An observational study.

OBJECTIVES: Previous hospital-based studies have suggested delayed recognition of acute coronary syndrome (ACS) in women. We wanted to assess differences in symptom presentation or triage among women and men who contacted primary care out-of-hours services (OHS) for chest discomfort. DESIGN: Retrospective observational study. SETTING: Primary care OHS. PARTICIPANTS: 276 women and 242 men with chest discomfort who contacted a primary care OHS in the Netherlands in 2013 and 2014. MAIN OUTCOME MEASURES: Differences between women and men regarding symptom presentation and urgency allocation. RESULTS: 8.4% women and 14.0% men had ACS. Differences in symptoms between patients with and without ACS were in general small, for both women and men. In women with ACS compared with women without ACS, mean duration of telephone calls was discriminative; 5.22 (SD 2.53) vs 7.26 (SD 3.11) min, p value=0.003. In men, radiation of pain (89.3% vs 54.9%, p value=0.011) was discriminative for ACS, and stabbing chest pain (3.7% vs 24.0%, p value=0.014) for absence of ACS . Women and men with chest discomfort received similar high urgency allocation (crude and adjusted OR after correction for ACS and age; 1.03 (95% CI 0.72 to 1.48) and 1.04 (95% CI 0.72 to 1.52), respectively). Women with ACS received a high urgency allocation in 22/23 (95.7%) and men with ACS in 30/34 (88.2%), p value=0.331. CONCLUSIONS: Discriminating ACS in patients with chest discomfort who contacted primary care OHS is difficult in both women and men. Women and men with chest discomfort received similar high urgency allocation.

Haematological response and overall survival in two consecutive Dutch patient cohorts with AL amyloidosis diagnosed between 2008 and 2016.

BACKGROUND: Although survival has improved in recent decades, the short-term prognosis of patients with immunoglobulin light chain (AL) amyloidosis remains grim. We aimed to assess overall survival (OS) of AL amyloidosis patients by comparing cohorts in two consecutive time periods. METHODS: Data were collected and compared on 126 patients from two tertiary referral centres in The Netherlands during the time periods 2008-2012 and 2013-2016. RESULTS: There was a non-significant trend to improved 6-month OS in the last cohort (78% vs. 67%, p = .216, crude odds ratio 1.66, 95%CI 0.74-3.70, adjusted odds ratio 2.22, 95%CI 0.88-5.56). Patients in this cohort had higher Mayo risk scores (stage III 40% vs. 24%, p < .001 and revised stage IV 14% vs. 11%, p < .001), higher use of bortezomib (50% vs. 30%), and better haematological response (complete response/very good partial response in 39% vs. 27%, p < .001). Diagnostic delay was similar in both time periods. CONCLUSIONS: In the 2013-2016 cohort there was a trend toward improved 6-month OS, and an improved haematological response. Patients in this cohort had more advanced cardiac disease and received bortezomib more frequently, but diagnostic delay was similar to the 2008-2012 cohort. For further prognostic improvement, practitioners should be more alert, especially for cardiac amyloidosis.