Posts

Artificial Intelligence: A Revolution in Rehabilitation?

/0 Comments/in /by

Artificial Intelligence (AI) is transforming the way medical professionals approach rehabilitation, offering innovative tools that enhance the quality of treatment. At ISICO, we are increasingly committed to exploring how AI can support daily clinical work and contribute to highly personalised therapeutic decisions.

We discussed this with Francesco Negrini, a specialist physiatrist at ISICO and the author of a groundbreaking 2023 study on AI and rehabilitation. This study, titled “Developing a new tool for scoliosis screening in a tertiary specialist setting using artificial intelligence: a retrospective study on 10,813 patients,” won the prestigious SOSORT Award in 2023.

Dr Negrini recently presented another paper exploring the use of AI in rehabilitation projects, particularly in stroke recovery.

What Are the Key Areas Where AI Can Be Used in Rehabilitation?
Artificial Intelligence (AI) is incredibly versatile and can be applied at various stages of the medical process, ranging from diagnosis, using automated analysis of X-ray or MRI images to identify pathologies with greater precision, to prognosis, with predictions on treatment outcomes, and on to the personalisation of treatments, determining the most effective therapeutic pathway based on patient data. AI also enables continuous monitoring, allowing real-time evaluation of a patient’s progress to adapt the treatment accordingly.
At ISICO, we are exploring, for example, how AI can support personalised treatment approaches. This technology could analyse a patient’s natural history and the likelihood of success when using one type of brace over another, providing physicians with more accurate decision-making tools.

Can you give a concrete example of how ISICO is using AI?
A significant example is the research that won the SOSORT Award 2023, recently published (link). The study demonstrated how analysing clinical data using advanced techniques can enhance our understanding of scoliosis and its treatments.

Another potential application involves the diagnosis of low back pain, where AI can analyse radiographic images to identify aetiologies that might otherwise be missed by the human eye. This approach takes advantage of today’s enhanced computational power, enabling the rapid and accurate processing of large volumes of data.

How Could AI Transform the Management of Spinal Disorders in the Future?
There are three key areas where we see tremendous potential. The first is screening and early diagnosis, which involves detecting scoliosis or other conditions at an early stage to improve treatment outcomes. The second area is the customisation of braces, using data collected from clinical centres to predict which type of brace will be most effective for a specific patient. Lastly, monitoring outcomes plays a crucial role, as it allows for tracking the progress of therapy and adapting it based on observed improvements, thereby enhancing the overall effectiveness of treatment.

What Makes AI Such a Valuable Ally for Clinicians?
AI amplifies a clinician’s capabilities, providing more detailed information and helping them make data-driven decisions. However, as we always emphasise at ISICO, the doctor-patient relationship remains central. AI does not replace the experience and empathy of a clinician; instead, it offers tools that enhance human expertise.

What is the Future of AI in Rehabilitation Medicine?
I believe we will see an increasingly close integration of AI in clinical practice. At ISICO, we are moving in this direction, exploring how AI can improve therapeutic outcomes and make rehabilitation more targeted. We are just at the beginning, but the possibilities are immense, especially if we can combine the best of technology with the invaluable expertise of healthcare professionals.

SOSORT Conference: Isico in the front row

/0 Comments/in /by

Once again, ISICO receives the acceptance, in the form of an oral presentation or a poster, of all nine abstracts submitted for the next annual international conference SOSORT that will be held from May 1 to May 4 in Boston, United States.

This is a reconfirmation with full marks for Isico, among the best researchers in the world in the rehabilitation treatment of spinal pathologies.
The following abstracts will be presented, where the first authors Dr. Fabio Zaina, Dr. Greta Jurenaite and Dr. Carlotte Kiekens, physiatrists, Michele Romano, director of physiotherapy, Giulia Fregna, physiotherapist, are from Isico further to Claudio Cordani, a physiotherapist.

– Normative data for radiographic sagittal parameters in asymptomatic population from childhood to adulthood: a systematic search and review (oral presentation)

– Lessons learned on trunk neurophysiology and motor control from adolescent idiopathic scoliosis. A scoping review (poster)

– Influence of specific interventions on bracing compliance in adolescents with idiopathic scoliosis. A systematic review of the literature including sensors’ monitoring (oral presentation)

– Can currently used questionnaires like ODI (and SRS-22) discriminate patients with scoliosis in a population with chronic back pain? (oral presentation)

– Personal and clinical determinants of brace wearing time in adolescents with idiopathic scoliosis (oral presentation)

– Convexity orientation of single scoliotic curves. Are they as we have always been taught? Verification of 4470 single curves (oral presentation)

– Suspected high prevalence and gender difference of scoliotic curves with the apex at T12 (poster)

– PREPARE: Personalized rehabilitation via novel AI patient stratification strategies – the case for idiopathic scoliosis during growth (poster)

– Case series report of atypical lumbar Scheuermann’s disease treated with braces and physiotherapeutic specific exercises (poster)

One of the 9 abstracts presented is linked to the European project PREPARE, in which ISICO takes part.

PREPARE Rehab aims to provide healthcare professionals with valuable insights and tools to predict better and stratify patients, ultimately leading to more personalized and effective rehabilitation interventions. Artificial Intelligence (AI) may help predict treatment outcomes and improve rehabilitation strategies for Idiopathic Scoliosis.

“By combining different factors that influence treatment success, AI-based models can provide a better understanding of the natural progression of the disease and the factors that determine the effectiveness of treatments. This allows us to personalize therapies better and avoid both over-treatment and under-treatment  – explains Dr. Carlotte Kiekens, one of the researchers of this project. With its ability to analyze large amounts of data and utilize deep learning techniques, AI offers a comprehensive approach to predicting functional prognosis and setting goals in Individual Rehabilitation Projects (IRPs)”.
In this study, data from over 21 thousand patients were taken into consideration. What do we expect to achieve?
“Three results: a clinical decision support system to be used by clinicians to make shared decisions with their patients and families, integrating big data and thus providing real-time insights; the development of innovative methods and models for categorizing patients into different groups based on specific criteria – ends Dr. Kiekens – and a roadmap that outlines the steps and requirements for ensuring compliance with medical device regulations.  These expected results indicate a comprehensive approach to improving healthcare through the integration of advanced technology, data analytics, and regulatory compliance measures”.

SOSORT Award: Isico is back on the podium!

/0 Comments/in /by

And once again, the winner is… Isico! For the fifth consecutive year, our institute has been awarded the prestigious SOSORT Award, recognising our innovative and cutting-edge research focused on Artificial Intelligence in the rehabilitation treatment of the spine. The winning research, titled “Developing a new tool for scoliosis screening in a tertiary specialist setting using artificial intelligence: a retrospective study on 10,813 patients,” was one of the eight Isico studies presented at the Sosort conference held in Melbourne, Australia, a few weeks ago.

This prize shows the quality of research conducted at Isico, combining scientific evidence with daily clinical practise to enhance rehabilitation treatment for patients worldwide. Dr. Francesco Negrini, a physiatrist and author of the study, explains the motivation behind the research: “We sought to explore ways to reduce the need for radiographs while ensuring accurate and timely scoliosis screening. Through collaboration with engineers in Zurich, we employed advanced analysis methods using artificial intelligence to develop a model that accurately identifies cases warranting X-rays.”

This international collaboration enabled Isico to harness innovative technologies and present research able to achieve this prestigious recognition. Dr. Negrini further emphasises the significance of the prize, stating, “I am immensely satisfied with this achievement. It reaffirms the validity and excellence of Isico’s scientific dedication, paving the way for a reduction in the number of X-rays prescribed to patients while maintaining optimal care.”

https://en.isico.it/isico/ricerca/pdf/ID00665.pdf

Scoliosis screening: the ISICO study on artificial intelligence in the running for the SOSORT Award

/0 Comments/in /by

Developing a new tool for scoliosis screening in a tertiary specialist setting using artificial intelligence: a retrospective study on 10,813 patients is one of the ISICO studies due to be presented at the next SOSORT conference, which will take place in Melbourne, Australia. The fact that the study is also a candidate for the SOSORT Award consolidates the standing of ISICO, which in recent years has not only participated with its research but also been awarded this prestigious prize on several occasions. 

In recent years, we have seen an increasing body of evidence supporting the efficacy of conservative treatment (e.g., exercises, soft and rigid braces) for adolescent idiopathic scoliosis (AIS), because treating a skeletally immature spine conservatively is certainly more effective and gives better results. The use of the conservative approach, however, has to be based on accurate and sensitive early screening for the condition, which often involves the use of X-rays.

What can be done to continue screening patients while at the same time making less use of X-rays? “Although technological improvements have, in recent years, made it possible to reduce the radiation dose in radiographic examinations, it is not possible to completely eliminate the long-term risk of cancer due to the stochastic effect of even low doses of radiation,” explains Dr Francesco Negrini, ISICO physiatrist and author of the research. “This is why we set out to analyse whether adding other rapid and reliable clinical parameters to the angle of trunk rotation (ATR°) might improve scoliosis screening in terms of sensitivity and specificity, making it possible to limit the use of X-rays to cases in which it is indispensable.”

How was the research conducted? The researchers looked at 10,813 patients between the ages of 4 and 18 who underwent clinical and radiological evaluation for scoliosis at a tertiary clinic specialising in spinal deformities. After excluding patients who wore a brace, had secondary scoliosis, or had no hump, 7,378 cases remained and were included in the analysis. In these cases, the following information was collected: ATR°, hump (mm), visible asymmetry of the waist, scapulae and shoulders, family history, sex, BMI, age, menarche (yes/no), and location of the curve. “At this point, we applied advanced analysis methods involving the use of artificial intelligence to try and create a model that would allow us to accurately select the cases needing to be X-rayed,” Dr Negrini goes on, “and we identified ATR°, hump (mm) and visible waist asymmetry as the clinical parameters best able to accurately classify Cobb angle measurements.”

On the basis of this conclusion, the researchers were able to affirm that classification models obtained through artificial intelligence may effectively improve non-invasive screening for AIS, thereby making it possible to reduce the X-ray exposure of healthy young individuals. “On the basis of the positive results obtained in the study, we may, in the near future, be able to develop a very flexible and user-friendly tool” says Dr Negrini. “This would allow doctors working in this specialised field to decide to prescribe radiographic imaging only when it is strictly necessary.”

https://en.isico.it/isico/ricerca/pdf/ID00665.pdf