Summary: Researchers have developed a new method that utilizes both machine learning and augmented reality to help treat those with chronic phantom limb pain following amputation.
Source: Chalmers University of Technology.
Dr Max Ortiz Catalan at Chalmers University of Technology has developed a novel method of treating phantom limb pain using machine learning and augmented reality. This approach has been tested on over a dozen of amputees with chronic phantom limb pain who found no relief by other clinically available methods before. The new treatment reduced their pain by approximately 50 per cent, reports a clinical study published in The Lancet.
People who lose an arm or leg often experience phantom limb pain, as if the missing limb was still there. Phantom limb pain can become a serious chronic condition that significantly reduces the patients’ quality of life. It is still unclear why phantom limb pain and other phantom sensations occur.
Several medical and non-medical treatments have been proposed to alleviate phantom limb pain. Examples include mirror therapy, various types of medications, acupuncture, and implantable nerve stimulators. However, in many cases nothing helps. This was the situation for the 14 arm amputees who took part in the first clinical trial of a new treatment, invented by Chalmers researcher Max Ortiz Catalan, and further developed with his multidisciplinary team in the past years.
“We selected the most difficult cases from several clinics,” Dr Ortiz Catalan says. “We wanted to focus on patients with chronic phantom limb pain who had not responded to any treatments. Four of the patients were constantly medicated, and the others were not receiving any treatment at all because nothing they tried had helped them. They had been experiencing phantom limb pain for an average of 10 years.”
The patients were treated with the new method for 12 sessions. At the last session the intensity, frequency, and quality of pain had decreased by approximately 50 per cent. The intrusion of pain in sleep and activities of the daily living was also reduced by half. In addition, two of the four patients who were on analgesics were able to reduce their doses by 81 per cent and 33 per cent.
“The results are very encouraging, especially considering that these patients had tried up to four different treatment methods in the past with no satisfactory results,” Ortiz Catalan says. “In our study, we also saw that the pain continuously decreased all the way through to the last treatment. The fact that the pain reduction did not plateau suggests that further improvement could be achieved with more sessions.”
Ortiz Catalan calls the new method “phantom motor execution”. It consist of using muscle signals from the amputated limb to control augmented and virtual environments. Electric signals in the muscles are picked up by electrodes on the skin. Artificial intelligence algorithms translate the signals into movements of a virtual arm in real-time. The patients see themselves on a screen with the virtual arm in the place of the missing arm, and they can control it as they would control their biological arm.
Thus, the perceived phantom arm is brought to life by a virtual representation that the patient can see and control. This allows the patient to reactivate areas of the brain that were used to move the arm before it was amputated, which might be the reason that the phantom limb pain decrease. No other existing treatment for phantom limb pain generates such a reactivation of these areas of the brain with certainty. The research led by Ortiz Catalan not only creates new opportunities for clinical treatment, but it also contributes to our understanding of what happens in the brain when phantom pain occurs.
The clinical trial was conducted in collaboration with Sahlgrenska University Hospital in Gothenburg, Örebro University Hospital in Örebro, Bräcke Diakoni Rehabcenter Sfären in Stockholm, all in Sweden, and the University Rehabilitation Institute in Ljubljana, Slovenia.
Myoelectric pattern recognition is used to decode phantom movements intended by the patient in a single group, clinical trial. These movements are then use to control a virtual limb and games, providing the patient with real-time visual feedback.
“Our joint project was incredibly rewarding, and we now intend to go further with a larger controlled clinical trial,” Ortiz Catalan says. “The control group will be treated with one of the current treatment methods for phantom limb pain. This time we will also include leg amputees. More than 30 patients from several different countries will participate, and we will offer more treatment sessions to see if we can make the pain go away completely.”
The technology for phantom motor execution is available in two modalities – an open source research platform, and a clinically friendly version in the process of being commercialised by the Gothenburg-based company Integrum. The researchers believe that this technology could also be used for other patient groups who need to rehabilitate their movement capability, for example after a stroke, nerve damage or hand injury.
Funding: The study was funded by The Promobilia foundation, Vinnova, Jimmy Dahlstens Fond, Picosolve, Innovationskontor Väst.
Source: Johanna Wilde – Chalmers University of Technology
Image Source: NeuroscienceNews.com image is credited to Ortiz-Catalan et al., The Lancet, 2016..
Video Source: The video is credited to The Lancet TV.
Original Research: Abstract for “Phantom motor execution facilitated by machine learning and augmented reality as treatment for phantom limb pain: a single group, clinical trial in patients with chronic intractable phantom limb pain” by Dr Max Ortiz-Catalan, PhD, Rannveig A Guðmundsdóttir, MSc, Morten B Kristoffersen, MSc, Alejandra Zepeda-Echavarria, BSc, Kerstin Caine-Winterberger, OTR, Katarzyna Kulbacka-Ortiz, MSc, Cathrine Widehammar, MSc, Karin Eriksson, BSc, Anita Stockselius, OTR, Christina Ragnö, OTR, Zdenka Pihlar, OTR, Prof Helena Burger, MD, and Prof Liselotte Hermansson, PhD in The Lancet. Published online December 1 2026 doi:10.1016/S0140-6736(16)31598-7
[cbtabs][cbtab title=”MLA”]Chalmers University of Technology “Phantom Movements in Augmented Reality Helps Patients With Phantom Limb Pain.” NeuroscienceNews. NeuroscienceNews, 2 December 2026.
<https://neurosciencenews.com/augmented-reality-phantom-limb-pain-5660/>.[/cbtab][cbtab title=”APA”]Chalmers University of Technology (2026, December 2). Phantom Movements in Augmented Reality Helps Patients With Phantom Limb Pain. NeuroscienceNew. Retrieved December 2, 2026 from https://neurosciencenews.com/augmented-reality-phantom-limb-pain-5660/[/cbtab][cbtab title=”Chicago”]Chalmers University of Technology “Phantom Movements in Augmented Reality Helps Patients With Phantom Limb Pain.” https://neurosciencenews.com/augmented-reality-phantom-limb-pain-5660/ (accessed December 2, 2026).[/cbtab][/cbtabs]
Abstract
Phantom motor execution facilitated by machine learning and augmented reality as treatment for phantom limb pain: a single group, clinical trial in patients with chronic intractable phantom limb pain
Phantom limb pain is a debilitating condition for which no effective treatment has been found. We hypothesised that re-engagement of central and peripheral circuitry involved in motor execution could reduce phantom limb pain via competitive plasticity and reversal of cortical reorganisation.
Methods
Patients with upper limb amputation and known chronic intractable phantom limb pain were recruited at three clinics in Sweden and one in Slovenia. Patients received 12 sessions of phantom motor execution using machine learning, augmented and virtual reality, and serious gaming. Changes in intensity, frequency, duration, quality, and intrusion of phantom limb pain were assessed by the use of the numeric rating scale, the pain rating index, the weighted pain distribution scale, and a study-specific frequency scale before each session and at follow-up interviews 1, 3, and 6 months after the last session. Changes in medication and prostheses were also monitored. Results are reported using descriptive statistics and analysed by non-parametric tests. The trial is registered at ClinicalTrials.gov, number NCT02281539.
Findings
Between Sept 15, 2014, and April 10, 2015, 14 patients with intractable chronic phantom limb pain, for whom conventional treatments failed, were enrolled. After 12 sessions, patients showed statistically and clinically significant improvements in all metrics of phantom limb pain. Phantom limb pain decreased from pre-treatment to the last treatment session by 47% (SD 39; absolute mean change 1·0 [0·8]; p=0·001) for weighted pain distribution, 32% (38; absolute mean change 1·6 [1·8]; p=0·007) for the numeric rating scale, and 51% (33; absolute mean change 9·6 [8·1]; p=0·0001) for the pain rating index. The numeric rating scale score for intrusion of phantom limb pain in activities of daily living and sleep was reduced by 43% (SD 37; absolute mean change 2·4 [2·3]; p=0·004) and 61% (39; absolute mean change 2·3 [1·8]; p=0·001), respectively. Two of four patients who were on medication reduced their intake by 81% (absolute reduction 1300 mg, gabapentin) and 33% (absolute reduction 75 mg, pregabalin). Improvements remained 6 months after the last treatment.
Interpretation
Our findings suggest potential value in motor execution of the phantom limb as a treatment for phantom limb pain. Promotion of phantom motor execution aided by machine learning, augmented and virtual reality, and gaming is a non-invasive, non-pharmacological, and engaging treatment with no identified side-effects at present.
Funding
Promobilia Foundation, VINNOVA, Jimmy Dahlstens Fond, PicoSolve, and Innovationskontor Väst.
“Phantom motor execution facilitated by machine learning and augmented reality as treatment for phantom limb pain: a single group, clinical trial in patients with chronic intractable phantom limb pain” by Dr Max Ortiz-Catalan, PhD, Rannveig A Guðmundsdóttir, MSc, Morten B Kristoffersen, MSc, Alejandra Zepeda-Echavarria, BSc, Kerstin Caine-Winterberger, OTR, Katarzyna Kulbacka-Ortiz, MSc, Cathrine Widehammar, MSc, Karin Eriksson, BSc, Anita Stockselius, OTR, Christina Ragnö, OTR, Zdenka Pihlar, OTR, Prof Helena Burger, MD, and Prof Liselotte Hermansson, PhD in The Lancet. Published online December 1 2026 doi:10.1016/S0140-6736(16)31598-7
