Background The field of radiology relies on accurate interpretation of medical images for effective diagnosis and patient care. Recent advancements in artificial intelligence (AI) and natural language processing have sparked interest in exploring the potential of AI models in assisting radiologists. However, limited research has been conducted to assess the performance of AI models in radiology case interpretation, particularly in comparison to human experts. Objective This study aimed to evaluate the performance of ChatGPT, Google Bard, and Bing in solving radiology case vignettes (Fellowship of the Royal College of Radiologists 2A [FRCR2A] examination style questions) by comparing their responses to those provided by two radiology residents. Methods A total of 120 multiple-choice questions based on radiology case vignettes were formulated according to the pattern of FRCR2A examination. The questions were presented to ChatGPT, Google Bard, and Bing. Two residents wrote the examination with the same questions in 3 hours. The responses generated by the AI models were collected and compared to the answer keys and explanation of the answers was rated by the two radiologists. A cutoff of 60% was set as the passing score. Results The two residents (63.33 and 57.5%) outperformed the three AI models: Bard (44.17%), Bing (53.33%), and ChatGPT (45%), but only one resident passed the examination. The response patterns among the five respondents were significantly different (p = 0.0117). In addition, the agreement among the generative AI models was significant (intraclass correlation coefficient [ICC] = 0.628), but there was no agreement between the residents (Kappa = –0.376). The explanation of generative AI models in support of answer was 44.72% accurate. Conclusion Humans exhibited superior accuracy compared to the AI models, showcasing a stronger comprehension of the subject matter. All three AI models included in the study could not achieve the minimum percentage needed to pass an FRCR2A examination. However, generative AI models showed significant agreement in their answers where the residents exhibited low agreement, highlighting a lack of consistency in their responses.
A 23-year-old man presented to the emergency department with a history of recurrent episodes of subacute intestinal obstruction. Palpation revealed a firm, non-tender, mobile, non-pulsatile mass of size 8–10 cm with indistinct margins and smooth surface in the hypogastrium. Contrast-enhanced CT scan of the abdomen showed clumping of the small bowel loops within a well-defined membrane-like structure without dilatation or thickening of bowel loops. The patient underwent a laparotomy with incision of the membrane and separation of all the small bowel loops inside the cocoon. Abdominal cocoon is the idiopathic variety of sclerosing encapsulating peritonitis and is an unusual cause of acute or subacute intestinal obstruction. Clinical diagnosis is difficult because of non-specific symptoms. CT has facilitated accurate preoperative diagnosis, long before the patient presents with full-fledged symptoms of acute intestinal obstruction. CT scan plays a significant role in excluding the secondary causes and helps in patient management.
10 September 2022 in Indian Journal of Orthopaedics
Iatrogenic femoral artery pseudoaneurysms (IFAPs) are not uncommon due to the increase in various minimally-invasive endovascular procedures. Percutaneous thrombin injection is an established technique for large pseudoaneurysms. When ultrasound-guided compression of an aneurysmal neck is not feasible, percutaneous thrombin injection can be combined with endovascular balloon occlusion to prevent leakage of thrombin into the parent artery. We describe a large IFAP following the removal of the femoral dialysis catheter after an inadvertent arterial puncture, which was managed with percutaneous ultrasound-guided (USG) thrombin injection with simultaneous balloon occlusion at the level of the aneurysmal neck without any complications. Follow-up imaging showed thrombosed IFAP without any recurrence.
1 January 2021 in Journal of Postgraduate Medicine
J Postgrad Med, Online version this peer-reviewed periodical, a publication of the Staff Society of Seth G. S. Medical College and K. E. M. Hospital, India, provides free full-text access to articles.