Artificial Intelligence and fast-track journey in hip and knee replacement surgery
A project which, thanks to Artificial Intelligence, aims to identify patients who can be fast-tracked after primary hip and knee arthroplasty surgery.
Dr. Mattia Loppini, of the Hip Orthopaedics and Prosthetic Surgery Unit at Humanitas, introduces us to the project. New technologies can be of great help in the field of Research; the road to definitive treatments is still long and we need the contribution of everyone: that’s why it is important to support Research by donating your own 5×1000.
Joint replacement is widespread throughout the world and is considered a particularly effective treatment for various hip and knee pathologies in patients of all ages. This is also why an increase of total hip replacement (THA) and total knee replacement (PTG) has been observed over time, which is expected to increase significantly in the next decades. In the last decade, there has also been a growing interest in rapid hospitalizations characterized by a shorter stay and a faster functional recovery for the patient undergoing total hip and knee replacement surgery.
The fast-track journey is characterized by an optimized or accelerated perioperative progression compared to a standard surgical procedure. A fast-track journey aims at reducing perioperative morbidity, physiologically optimize anesthesiological procedures, optimize pain management and aggressive mobilization. Artificial intelligence can allow an accurate selection of patients eligible for a fast-track journey in prosthetic surgery. In this way it would be possible to reduce the duration of post-surgical hospital stay, guaranteeing the patient an appropriate functional recovery without increasing the risk of complications.
In recent years, the postoperative management of patients undergoing total hip and knee replacements has been focused on the length of recovery after surgery, encouraging the early discharge from hospitals and a replacement with at-home alternatives.
The identification of objective pre-operative criteria predicting the patient’s outcome is crucial in order to enable more efficient postoperative care management and would allow the development of a clinical prediction tool that uses artificial intelligence to identify patients at risk of delayed postoperative recovery and longer hospital stay.
The first phase of the project involves the development of the analysis tool through machine learning and the enlistment of patients with THA and PTG, operated in Humanitas, whose preoperative clinical, laboratory and instrumental data will be analyzed.
The second phase of the project provides for the enlistment of 150 patients with THA and 150 patients with PTG, who will be followed for one year after the intervention to validate the predictive ability of the software.
Ultimately, the aim of the project is to develop a machine learning algorithm that allows to identify, before the total hip and knee replacement surgery, the patients who may be candidates to a short hospitalization journey with an appropriate functional recovery.