Artificial Intelligence Lands in Hospitals: Helps in Emergency Rooms and Reduces Waiting Lists

Artificial intelligence is landing in the emergency room - where seconds can make the difference - to help doctors decide quickly and well what to do when there is a suspicion of a fracture or worse, a stroke, but AI can also help hospitals better manage visits and tests by preventing patients from "slacking" and not showing up for appointments and in the future by suggesting to doctors whether or not to prescribe a CT scan or an MRI. In this way, lightening the waiting lists and freeing up places for those who really need that service. Here are some of the most innovative experiences among the first forty included in the Observatory on Artificial Intelligence in Healthcare, presented at the Logos & Téchne' Forum, organized in Syracuse in recent days by Fiaso, the federation that brings together managers of ASL and hospitals.

At ASL 2 Sgavonese, for example, artificial intelligence has entered emergency radiology and has become an additional “second reading” tool for triaging patients, with acceptance by radiologists that has grown over time: here in particular, since 2021, an AI solution has been used that helps detect fractures on all X-rays. In another Ligurian hospital - ASL 4 Chiavarese - “Boneview” has been tested in the emergency room, another AI system for reading X-rays that helps intercept bone fractures. This latter technology has also entered the emergency department of the Asst Santi Paolo e Carlo in Milan. In the emergency room of the university hospital company of Perugia, a virtual assistant has entered for the early recognition of strokes thanks to vocal, facial and biometric analysis: this assistant has been well received by doctors for its usability and efficiency during triage, improving diagnosis, intervention and survival times. Artificial intelligence is also used at the Asst Santi Paolo e Carlo in Milan for the automatic analysis of CT images, again in cases of ischemic stroke.

So far the experiences in the emergency room. But artificial intelligence could also help better manage the number one problem in healthcare: waiting lists. According to a study that used an AI algorithm, in the Puglia region at least 4 out of 10 prescriptions for CT scans and MRIs are not necessary. Created by Aress Puglia, the project is based on an analysis of over 17 thousand prescriptions: the heart is a generative artificial intelligence system based on the LLaMA 3.1 model, capable of evaluating the clinical appropriateness of a diagnostic prescription. The algorithm was trained to associate each requested test with the patient's condition, comparing it with the official guidelines. The results revealed that only 39% of the requests fully respected the appropriateness criteria, 43% were inappropriate (therefore in fact unnecessary), while the remainder were only partially useful. At ASL Napoli 3, Robo-Cup, an automated system that uses an algorithm applied to the data of the Single Booking Center, has instead allowed to halve the empty slots between one appointment and the next, with benefits also on waiting lists. The system has allowed to reduce the percentage of the phenomenon of the so-called "no-show" from 40% to 20%, optimizing the gaps of the appointments left free. Using the booking data, Robo-Cup sends reminders via SMS, allowing patients to confirm or cancel the appointment. Then, always using Artificial Intelligence, it reassigns the available ones, also through recall services, controlled overbooking and pre-lists to optimize the use of free slots. In case of no response, the intervention is managed by the operator.

"Citizens are ready: they have understood the potential of artificial intelligence in healthcare and are asking for concrete solutions - explains Giovanni Migliore, president of Fiaso -. Now it is up to us, as a public healthcare system, to respond with vision and competence. Innovation is no longer a promise: it is already a reality, and it is transforming the way we take care of people and organize services". With the birth of the Faso AI Observatory "a concrete path of innovation began in Syracuse - adds Migliore - that will take us to Rome, next January 29, for a major event in which we will present the results and reward the best experiences gained thanks to the collaboration between healthcare companies, research and technology companies".