Properties of ultrasound-rapid MRI clinical diagnostic pathway in suspected pediatric appendicitis
Suzanne SchuhCarina ManEman MarieGhufran H. AlhashmiDan HalevyPaul W. WalesDana Singer‐HarelAya FinkelsteinJudith SweeneyAndréa S. Doria
2
Citation
38
Reference
10
Related Paper
Citation Trend
To investigate diagnostic accuracy in patient histories involving nonspecific complaints and the extent to which characteristics of physicians and structural properties of patient histories are associated with accuracy.Six histories of patients presenting to the emergency department (ED) with nonspecific complaints were provided to 112 physicians: 36 ED physicians, 50 internists, and 26 family practitioners. Physicians listed the 3 most likely diagnoses for each history and indicated which cue(s) they considered crucial. Four weeks later, a subset of 20 physicians diagnosed the same 6 histories again. For each history, experts had previously determined the correct diagnoses and the diagnostic cues.Accuracy ranged from 14% to 64% correct diagnoses (correct diagnosis listed as the most likely) and from 29% to 87% correct differential diagnoses (correct diagnosis listed in the differential). Acute care physicians (ED physicians and internists) included the correct diagnosis in the differential in, on average, 3.4 histories, relative to 2.6 for the family practitioners (P = 0.001, d = .75). Diagnostic performance was fairly reliable (r = .61, P < 0.001). Clinical experience was negatively correlated with diagnostic accuracy (r = -.25, P = 0.008). Two structural properties of patient histories-cue consensus and cue substitutability-were significantly associated with diagnostic accuracy, whereas case difficulty was not. Finally, prevalence of diagnosis also proved significantly correlated with accuracy.Average diagnostic accuracy in cases with nonspecific complaints far exceeds chance performance, and accuracy varies with medical specialty. Analyzing cue properties in patient histories can help shed light on determinants of diagnostic performance and thus suggest ways to enhance physicians' ability to accurately diagnose cases with nonspecific complaints.
Specialty
Medical History
Cite
Citations (17)
Cite
Citations (5)
Cite
Citations (2)
Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagnoses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The diagnostic accuracy was 56.4% for the top 5 suggested diagnoses and 22.8% when only considering the most probable diagnosis. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development.
Cite
Citations (16)
Neuroradiology
Cite
Citations (120)
To assess the usefulness of HELISAL in the diagnosis of Helicobacter pylori infection by comparing it with ELISA, JATROX and histopathologic findings.Randomized prospective study.Sixty-one patients, thirty-three males and twenty-eight females, 18-73 years old, submitted to esophagogastroduodenoscopy.The sensitivity of HELISAL when compared to ELISA test was 60.8%, the specificity 73.3%, the positive predictive value 87.5%, the negative predictive value 37.9%, and the kappa index 0.26. When compared to histopathologic test: sensitivity 60.9%, specificity 65%, positive predictive value 78.1%, negative predictive value 44.7%, kappa 0.28. When compared to JATROX, sensitivity 57.7%, specificity 62.5%, positive predictive value 81.2%, negative predictive value 34.4%, kappa 0.21.The sensitivity of HELISAL test is lower than that of other compared tests, and the negative predictive value is very low. The specificity and the positive predictive value are higher than the sensitivity. The kappa index shows a very low concordance.
Kappa
Concordance
Esophagogastroduodenoscopy
Positive predicative value
Cite
Citations (9)
We conducted a pilot study to assess the feasibility of telecytology as a diagnostic tool in difficult cases originating from a hospital in East Africa. Forty cytology cases considered difficult by a referring pathologist were posted on a telepathology website. Six pathologists independently assessed the static images. Telecytology diagnoses were compared with the consensus diagnoses made on glass slides and also with the histogical diagnoses when available. The diagnostic agreement of the six pathologists was 71–93% and tended to be higher for pathologists with more experience. Reasons for discordance included poor image quality, presence of diagnostic cells in thick areas of smears, sampling bias and screening errors. The consensus diagnoses agreed with histological diagnoses in all 17 cases in which a biopsy was performed. Diagnostic accuracy rates (i.e. telecytology diagnosis vs. histological diagnosis) for individual pathologists were 65–88%. To ensure diagnostic accuracy both referring and consulting pathologists must have adequate training in cytology, image acquisition and image-based diagnosis and the diagnostic questions of importance must be clearly communicated by the referring pathologist when posting a case.
Telepathology
Cite
Citations (22)
To evaluate the diagnostic performance of ultrasound and to determine which ultrasound findings are useful to differentiate appendicitis from non-appendicitis in patients who underwent ultrasound re-evaluation owing to equivocal CT features of acute appendicitis.
Cite
Citations (13)
Patients with right lower quadrant (RLQ) pain referred for imaging studies with a clinical diagnosis of appendicitis may have other pathologic conditions mimicking appendicitis. Appropriate diagnostic imaging may establish other specific diagnoses and thereby play a significant role in determining proper medical or surgical treatment. In this pictorial essay, we present a spectrum of imaging findings in patients whose clinical features were suggestive of appendicitis, but the diagnoses of a broad spectrum of other diseases were established with the imaging studies. The differential diagnoses of diseases mimicking appendicitis are reviewed.
Quadrant (abdomen)
Broad spectrum
Clinical Diagnosis
Cite
Citations (23)
ABSTRACT Objective Adopting digital technologies as diagnostic support tools in medicine is unquestionable. However, the accuracy in suggesting diagnoses remains controversial and underexplored. We aimed to evaluate and compare the diagnostic accuracy of two primary and accessible internet search tools: Google and ChatGPT 3.5. Method We used 60 clinical cases related to urological pathologies to evaluate both platforms. These cases were divided into two groups: one with common conditions (constructed from the most frequent symptoms, following EAU and UpToDate guidelines) and another with rare disorders - based on case reports published between 2022 and 2023 in Urology Case Reports. Each case was inputted into Google Search and ChatGPT 3.5, and the results were categorized as "correct diagnosis," "likely differential diagnosis," or "incorrect diagnosis." A team of researchers evaluated the responses blindly and randomly. Results In typical cases, Google achieved 53.3% accuracy, offering a likely differential diagnosis in 23.3% and errors in the rest. ChatGPT 3.5 exhibited superior performance, with 86.6% accuracy, and suggested a reasonable differential diagnosis in 13.3%, without mistakes. In rare cases, Google did not provide correct diagnoses but offered a likely differential diagnosis in 20%. ChatGPT 3.5 achieved 16.6% accuracy, with 50% differential diagnoses. Conclusion ChatGPT 3.5 demonstrated higher diagnostic accuracy than Google in both contexts. The platform showed acceptable accuracy in common cases; however, limitations in rare cases remained evident.
Cite
Citations (0)