Search

Key Clinical Message: Large language models have made artificial intelligence readily available to the general public and potentially have a role in healthcare; however, their use in difficult differential diagnosis is still limited, as demonstrated by a case of necrotizing otitis externa. This case report presents a peculiar case of necrotizing otitis externa (NOE) with skull base involvement which proved diagnostically challenging. The initial patient presentation and the imaging performed on the 78‐year‐old patient suggested a neoplastic rhinopharyngeal lesion and only after several unsuccessful biopsies the patient was transferred to our unit. Upon re‐evaluation of the clinical picture, a clinical hypothesis of NOE with skull base erosion was made and confirmed by identifying Pseudomonas aeruginosa in biopsy specimens of skull base bone and external auditory canal skin. Upon diagnosis confirmation, the patient was treated with culture‐oriented long‐term antibiotics with complete resolution of the disease. Given the complex clinical presentation, we chose to submit a posteriori this NOE case to two large language models (LLM) to test their ability to handle difficult differential diagnoses. LLMs are easily approachable artificial intelligence tools that enable human‐like interaction with the user relying upon large information databases for analyzing queries. The LLMs of choice were ChatGPT‐3 and ChatGPT‐4 and they were requested to analyze the case being provided with only objective clinical and imaging data. [ABSTRACT FROM AUTHOR]

A complex aeromagnetic anomaly in Southern Apennines (Italy) is analysed and interpreted by a multiscale method based on the scaling function. We use multiscale methods allowing analysis of a potential field along ridges, which are lines defined by the position of the extrema of the field at the considered scales. The method developed and applied in this paper is based on the study of the scaling function of the total magnetic field. It allows recovering of source parameters such as depth and structural index. The studied area includes a Pleistocene volcanic structure (Mt. Vulture) whose intense dipolar anomaly is superimposed on a longer wavelength regional anomaly. The interpretation of ridges of the modulus of the analytic signal at different altitude ranges allows recognition of at least three distinct sources between about 5 km and 20 km depth. Their interpretation is discussed in light of borehole data and other geophysical constraints. A reasonable geological model for these sources indicates the presence of intrusions, probably linked to the past activity of Mt. Vulture. [ABSTRACT FROM AUTHOR]

We show how a denoising technique based on the wavelet transform can be used to deal with localized noise related to DC electrified railway lines. This method, which performs localized and sharp filtering of cultural noise, was applied to high-resolution aeromagnetic data acquired in the Phlegrean volcanic area, southern Italy, in 1999 and 2001. The helicopter-borne survey was aimed at giving new detailed insights into the distribution of the magnetization of the area and, therefore, into the volcanological characteristics of the region. The surveyed area is characterized by the presence of towns, buildings and DC electrified railway lines whose magnetic effects influenced the measurements and were responsible for some of the measured anomalies. This cultural noise has, therefore, to be minimized as much as possible in order to allow the data to be interpreted accurately. Due to the excellent space-scale localization properties of the discrete wavelet transform, the cultural disturbance was removed very precisely, leaving the field in the adjacent areas unchanged. [ABSTRACT FROM AUTHOR]