ABSTRACT
BACKGROUND: Artificial intelligence (AI)-assisted image interpretation is a fast-developing area of clinical innovation. Most research to date has focused on the performance of AI-assisted algorithms in comparison with that of radiologists rather than evaluating the algorithms' impact on the clinicians who often undertake initial image interpretation in routine clinical practice. This study assessed the impact of AI-assisted image interpretation on the diagnostic performance of frontline acute care clinicians for the detection of pneumothoraces (PTX). METHODS: A multicentre blinded multi-case multi-reader study was conducted between October 2021 and January 2022. The online study recruited 18 clinician readers from six different clinical specialties, with differing levels of seniority, across four English hospitals. The study included 395 plain CXR images, 189 positive for PTX and 206 negative. The reference standard was the consensus opinion of two thoracic radiologists with a third acting as arbitrator. General Electric Healthcare Critical Care Suite (GEHC CCS) PTX algorithm was applied to the final dataset. Readers individually interpreted the dataset without AI assistance, recording the presence or absence of a PTX and a confidence rating. Following a 'washout' period, this process was repeated including the AI output. RESULTS: Analysis of the performance of the algorithm for detecting or ruling out a PTX revealed an overall AUROC of 0.939. Overall reader sensitivity increased by 11.4% (95% CI 4.8, 18.0, p=0.002) from 66.8% (95% CI 57.3, 76.2) unaided to 78.1% aided (95% CI 72.2, 84.0, p=0.002), specificity 93.9% (95% CI 90.9, 97.0) without AI to 95.8% (95% CI 93.7, 97.9, p=0.247). The junior reader subgroup showed the largest improvement at 21.7% (95% CI 10.9, 32.6), increasing from 56.0% (95% CI 37.7, 74.3) to 77.7% (95% CI 65.8, 89.7, p<0.01). CONCLUSION: The study indicates that AI-assisted image interpretation significantly enhances the diagnostic accuracy of clinicians in detecting PTX, particularly benefiting less experienced practitioners. While overall interpretation time remained unchanged, the use of AI improved diagnostic confidence and sensitivity, especially among junior clinicians. These findings underscore the potential of AI to support less skilled clinicians in acute care settings.
ABSTRACT
A previously healthy 51-year-old woman presented to the ED with a one-week history of malaise, myalgia, unsteadiness, and an intermittent mild headache. Physical examination revealed neurological signs including a broad-based gait and bilateral low amplitude tremor. Laboratory testing of electrolytes revealed acute severe hyponatremia (115 mmol/L). Further, history-taking revealed increased urinary frequency following regular consumption of an over-the-counter detoxification tea product. The patient made a good recovery following admission to the intensive care unit. We identify similar cases in the literature and explore potential causal mechanisms. This case highlights the importance of enquiring about the use of supplementary health products when taking a history, and specifically identifies a growing number of reports of acute severe hyponatremia following the use of "detox teas".
ABSTRACT
We present a case of azathioprine hypersensitivity presenting as septic shock with associated encephalopathy. The patient was presented with rapid onset of fever, hypotension, confusion and a rapidly declining conscious level. He was admitted to the intensive care unit where he received numerous invasive investigations and treatments with broad-spectrum antibiotics, antivirals and antifungals. All microbial cultures were negative. The patient-consistent with azathioprine hypersensitivity-made a spontaneous recovery after 7 days. The case shows that a time line of drug initiation is a key part of the medical history and consideration of azathioprine hypersensitivity could avoid unnecessary interventions and excessive antimicrobial use.
Subject(s)
Azathioprine/adverse effects , Brain Diseases/chemically induced , Drug Hypersensitivity/etiology , Immunosuppressive Agents/adverse effects , Shock, Septic/chemically induced , Aged , Drug Hypersensitivity/diagnosis , Humans , MaleABSTRACT
BACKGROUND: The inability to smile stands out as a notable difficulty for individuals with facial nerve palsies; a problem that facial reanimation surgery aims to rectify. However, smile reconstruction currently lacks quantitative data by which to objectively measure outcomes. This study aims to identify the relative importance of different oral muscles in terms of smiling, and explore the percentage function that needs to be restored for a smile to be perceived by an observer. METHODS: A computer animation tool was developed to model the oral facial muscles and demonstrate the facial expressions produced by contraction of different muscle groups. By programming a variable unilateral paralysis of the zygomaticus major, the effects of 0-100% function of this muscle can also be seen in a further set of animations using the basic muscular structure of a smile to produce a computerized proxy smile. These animations were shown to 75 adults from the general population who reported those expressions they perceived as a smile. RESULTS: The only facial expression consistently associated with a perceived smile was caused by the combined contraction of the zygomaticus major and the levator anguli oris (P < 0.001). This concurs with previously reported observations of the human smile. Over 70% of the subjects were able to perceive a smile with just 40% function of the unilateral paralyzed zygomaticus major. CONCLUSIONS: These results present an objective target for facial reanimation surgery by which outcomes may be measured. This computerized model also provides a valuable tool for patient education during pre-operative consent.
