MILES AXLE Translation. Region: Russian Federation –
Source: State University Higher School of Economics – State University Higher School of Economics –
Artificial intelligence will not replace a doctor, but it can be a great assistant. At the same time, healthcare needs high-tech products that can quickly analyze and monitor the condition of patients. HSE scientists have used AI for preoperative planning and postoperative evaluation of results in spinal surgery and developed an automatic intelligent system for assessing the biomechanics of the arms and legs.
At the joint scientific seminar of the strategic project “AI technologies for humans” (as part of the Priority 2030 program), HSE scientists presented two developments related to the use of artificial intelligence in medical practice. This area is not new for the Higher School of Economics, noted HSE Vice-Rector Elena Odoevskaya in her opening remarks. Despite the fact that the university does not have educational programs in medicine, it still deals with medical products and plans to enter this market.
“In terms of goals and objectives, we must understand that this is a product, not just research. This means that we must have partners, including external ones, including industrial ones, and we must understand how this product will continue to live with us or without us. This is a question of how we implement it,” she emphasized.
Spine Marking App
The first report was devoted to the use of AI for preoperative planning and postoperative outcome assessment in spinal surgery. Chief Scientific Officer International Laboratory of Dynamic Systems and Applications (NRU HSE – Nizhny Novgorod) Vladimir Klinshov spoke about how computer vision technologies can improve the speed and quality of spinal X-ray analysis, helping to optimize the routine work of neurosurgeons. The working title of the product is VerteScan (from the word vertebra – vertebra). This is a service for viewing and analyzing X-ray images of the human spine, including an automatic marking system based on artificial intelligence. “We are making a specific and very utilitarian tool for automatic marking and analysis of spinal X-ray images. We want to relieve the doctor of a fairly routine part of his work, leaving him with the most important decisions. This product is made by surgeons for surgeons. This means that it will be intuitively understandable to doctors, it will be comfortable for them to use, and doctors will need it,” he said.
Spinal pathology accounts for 76% of patient visits to the neurological service, and 72% of visits result in temporary disability. Every year, more than a thousand surgical interventions on the spine are performed at the University Clinic of the Privolzhsky Research Medical University of the Ministry of Health of the Russian Federation (PIMU — project partner).
VerteScan will help to determine the patient’s anatomy, the course of his disease, select the minimum permissible volume of surgical intervention, carry out a personalized selection of implants and surgical techniques to achieve the optimal result, and also predict the behavior of intact sections of the spine taking into account the change in biomechanics as a result of the intervention.
“There are many options for performing surgical interventions for spinal diseases. And each of the possible approaches must be carefully planned. Adequate preparation will lead to an adequate result, when we can not only perform the tasks that we set before the operation, but also evaluate and prevent negative changes in adjacent segments of the spine. Using the basic tools of the service that are already working, we can evaluate the parameters unique to each person – for example, the sagittal balance of the spine. It will be possible to plan the installation of implants so as not to disturb these parameters if they are normal, or we will be able to predict how much we will correct these parameters, how much we will change the local anatomy in order to bring these values u200bu200bto normal and ensure a good quality of life for the patient,” explained the team’s neurosurgeon Anatoly Bulkin.
Key partners for the project may include medical institutions, manufacturers of medical implants, and professional associations of orthopedic and spinal surgeons. A free trial version of the software is planned to attract initial users and collect feedback, while premium features will be available by subscription or one-time payment.
If the surgical intervention on the spine is performed suboptimally, it will lead to rapid wear of the intact spinal motor segments, and the treatment result will be worse than the disease itself, said Andrey Bokov, head of the neurosurgery department at PMU.
“If you do not take into account all possible parameters, the patient feels well after the operation for the first few years at most, and then decompensation sets in. This person is on sick leave for a long time, he is excluded from social life. This burden is sometimes even heavier than a life-threatening disease. Relatives who care for a patient with limited mobility are also involved. If we manage to reduce the percentage of such cases, the social effect will be very high,” he emphasized.
Physiotherapy under AI control
The second report was devoted to an automatic intelligent system designed to assess the biomechanics of the arms and legs. This system uses machine learning algorithms to analyze biomechanical data, which can significantly improve the diagnosis and rehabilitation of patients. It was presented by the project leader, research fellow Laboratory of Theory and Practice of Decision Support Systems of the Faculty of Informatics, Mathematics and Computer Science of the National Research University Higher School of Economics in Nizhny Novgorod Andrey Kovalchuk. He emphasized that diseases of the musculoskeletal system are called the non-infectious epidemic of the 21st century. A promising direction for the rehabilitation of patients with such pathologies is remote rehabilitation using digital technologies. This requires the presence of hardware and software systems (HSS) for video motion capture.
The PACs developed to date for remote motor rehabilitation have common drawbacks: high cost, complexity of operation, and the need for a doctor to be present at all times. This makes them inaccessible for mass use.
Remote rehabilitation will increase the number of patients per doctor by reducing the time of face-to-face interaction, but at the same time will improve the quality of service by transferring some of the doctor’s functionality to AI.
The patient will no longer need to visit a hospital, while maintaining a personalized approach and a flexible rehabilitation plan based on objectively measurable parameters.
“Within the framework of this project, it is planned to create a prototype of an automated system (mobile application) based on computer vision technology and designed for remote controlled rehabilitation of patients with musculoskeletal pathology, including after endoprosthetic surgery. With the help of this application, the doctor will be able to create an individual training program for the patient, and will also be able to control the following indicators: the ratio of correctly/incorrectly performed repetitions per session, the maximum, minimum and median joint flexion angles,” said Andrey Kovalchuk.
He emphasized that currently there are no domestic analogues of the mobile solution, and Western ones cannot be used in rehabilitation on the territory of the Russian Federation. The competitiveness of the system will be determined by its autonomy, efficiency and accessibility for a wide range of users, regardless of their location and financial status.
The application will not only collect and analyze video data of movement scenarios and transmit them to the doctor for monitoring and correction, but also interact with the user in real time through voice commands, voicing the mistakes and events made by the user.
Most neurological and orthopedic diseases are accompanied by movement disorders, said Anna Belova, head of the department of medical rehabilitation at PIMU, chief neurologist of the Ministry of Health of the Nizhny Novgorod Region. A patient discharged from the hospital should be regularly monitored by a doctor at home, do gymnastics for many months. But in reality, this does not happen due to a shortage of personnel. Therefore, the emphasis is placed on remote rehabilitation all over the world.
“The basis of recovery is not medication, it is not even surgery, it is therapeutic exercise. Movement is the basis of recovery, and not only for patients, but also for healthy people as they age. But these movements must be performed regularly and correctly – this is very important. For example, those who have undergone endoprosthetics should not perform a number of movements – for example, they cannot cross their legs, bend their knee more than 90 degrees, otherwise this will lead to dislocation of the joint. Therefore, this feedback for independent exercises is extremely important,” she explained.
Please note: This information is raw content directly from the source of the information. It is exactly what the source states and does not reflect the position of MIL-OSI or its clients.
Please note; This information is raw content directly from the information source. It is accurate to what the source is stating and does not reflect the position of MIL-OSI or its clients.