Most of the published papers on AI based diagnosis have focused on the algorithm's diagnostic performance in a ‘binary’ setting (i.e. disease vs no disease). However, no study evaluated the actual value for the clinicians of an AI based approach in diagnostic. Detection of Traumatic thoracolumbar (TL) fractures is challenging on planar radiographs, resulting in significant rates of missed diagnoses (30-60%), thus constituting a field in which a performance improvement is needed. Aim of this study is therefore to evaluate the value provided by AI generated saliency maps (SM), i.e. the maps that highlight the AI identified region of interests. An AI model aimed at identifying TL fractures on plain radiographs was trained and tested on 567 single vertebrae images. Three expert spine surgeons established the Introduction:
Methods:
The current pandemic caused by COVID-19 is the biggest challenge for national health systems for a century. While most medical resources are allocated to treat COVID-19 patients, several non-COVID-19 medical emergencies still need to be treated, including vertebral fractures and spinal cord compression. The aim of this paper is to report the early experience and an organizational protocol for emergency spinal surgery currently being used in a large metropolitan area by an integrated team of orthopaedic surgeons and neurosurgeons. An organizational model is presented based on case centralization in hub hospitals and early management of surgical cases to reduce hospital stay. Data from all the patients admitted for emergency spinal surgery from the beginning of the outbreak were prospectively collected and compared to data from patients admitted for the same reason in the same time span in the previous year, and treated by the same integrated team.Aims
Methods
The COVID-19 virus is a tremendous burden for the Italian health system. The regionally-based Italian National Health System has been reorganized. Hospitals' biggest challenge was to create new intensive care unit (ICU) beds, as the existing system was insufficient to meet new demand, especially in the most affected areas. Our institution in the Milan metropolitan area of Lombardy, the epicentre of the infection, was selected as one of the three regional hub for major trauma, serving a population of more than three million people. The aims were the increase the ICU beds and the rationalization of human and structural resources available for treating COVID-19 patients. In our hub hospital, the reorganization aimed to reduce the risk of infection and to obtained resources, in terms of beds and healthcare personnel to be use in the COVID-19 emergency. Non-urgent outpatient orthopaedic activity and elective surgery was also suspended. A training programme for healthcare personnel started immediately. Orthopaedic and radiological pathways dedicated to COVID-19 patients, or with possible infection, have been established. In our orthopaedic department, we passed from 70 to 26 beds. Our goal is to treat trauma surgery's patient in the “golden 72 hours” in order to reduce the overall hospital length of stay. We applied an objective priority system to manage the flow of surgical procedures in the emergency room based on clinical outcomes and guidelines. Organizing the present to face the emergency is a challenge, but in the global plan of changes in hospital management one must also think about the near future. We reported the Milan metropolitan area orthopaedic surgery management during the COVID-19 pandemic. Our decisions are not based on scientific evidence; therefore, the decision on how reorganize hospitals will likely remain in the hands of individual countries.
