The rapid advancement of large language models like ChatGPT has significantly impacted natural language processing, expanding its applications across various fields, including healthcare. However, there remains a significant gap in understanding the consistency and reliability of ChatGPT’s performance across different medical domains. We conducted this systematic review according to an LLM-assisted PRISMA setup. The high-recall search term “ChatGPT” yielded 1101 articles from 2023 onwards. Through a dual-phase screening process, initially automated via ChatGPT and subsequently manually by human reviewers, 128 studies were included. The studies covered a range of medical specialties, focusing on diagnosis, disease management, and patient education. The assessment metrics varied, but most studies compared ChatGPT’s accuracy against evaluations by clinicians or reliable references. In several areas, ChatGPT demonstrated high accuracy, underscoring its effectiveness. However, performance varied, and some contexts revealed lower accuracy. The mixed outcomes across different medical domains emphasize the challenges and opportunities of integrating AI like ChatGPT into healthcare. The high accuracy in certain areas suggests that ChatGPT has substantial utility, yet the inconsistent performance across all applications indicates a need for ongoing evaluation and refinement. This review highlights ChatGPT’s potential to improve healthcare delivery alongside the necessity for continued research to ensure its reliability.
23 December 2024 in Microsystems & Nanoengineering
A new high-sensitivity, low-cost, Surface Enhanced Raman Spectroscopy (SERS) sensor allows for the rapid multiplex detection of foodborne pathogens in raw poultry. Self-assembled microspheres are used to pattern a hexagonal close-packed array of nanoantennas onto a side-polished multimode fiber core. Each microsphere focuses UV radiation to a photonic nanojet within a layer of photoresist on the fiber which allows the nanoantenna geometry to be controlled. Optimizing the geometry for the excitation layer generates electric field concentrations− referred to as a hotspot− within the analyte, thereby maximizing the Raman signal and improving the signal-to-noise ratio. The side polished configuration with a larger surface area has significantly better performance than the SERS sensor on the fiber tip. The use of additive manufacturing for the fiber polishing jigs as well as the sample testing compartment simplifies the sensor development and testing. Experimental results demonstrate a sensitivity range of 0.4–0.5 cells/ml achieved using raw chicken rinsates spiked with Salmonella typhimurium. Additionally, the sensor demonstrated its capability for multiplex and specific detection of Salmonella and E. coli O157:H7 with an optimal detection time of 10 min. The new sensor addresses a major global foodborne pathogen that poses significant public health concerns and can be readily adapted for the detection of other bacterial and viral pathogens such as E. coli O157:H7, Campylobacter, Listeria, and avian influenza and in other food products, e.g., dairy, beef, and produce, as well as clinical applications.