Noemi Gozzi

Last Name

Gozzi

First Name

Noemi

ORCID

0000-0003-0126-7893

Show all metadata

Search Results

Publications 1 - 10 of 12

Multiparametric non-linear TENS modulation to integrate intuitive sensory feedback
Bucciarelli, Vittoria; Gozzi, Noemi; Katic, Natalija; et al. (2023)
Journal of Neural Engineering
Objective. Transcutaneous electrical nerve stimulation (TENS) has been recently introduced in neurorehabilitation and neuroprosthetics as a promising, non-invasive sensory feedback restoration alternative to implantable neurostimulation. Yet, the adopted stimulation paradigms are typically based on single-parameter modulations (e.g. pulse amplitude (PA), pulse-width (PW) or pulse frequency (PF)). They elicit artificial sensations characterized by a low intensity resolution (e.g. few perceived levels), low naturalness and intuitiveness, hindering the acceptance of this technology. To address these issues, we designed novel multiparametric stimulation paradigms, featuring the simultaneous modulation of multiple parameters, and implemented them in real-time tests of performance when exploited as artificial sensory inputs.Approach. We initially investigated the contribution of PW and PF variations to the perceived sensation magnitude through discrimination tests. Then, we designed three multiparametric stimulation paradigms comparing them with a standard PW linear modulation in terms of evoked sensation naturalness and intensity. The most performant paradigms were then implemented in real-time in a Virtual Reality-TENS platform to assess their ability to provide intuitive somatosensory feedback in a functional task.Main results. Our study highlighted a strong negative correlation between perceived naturalness and intensity: less intense sensations are usually deemed as more similar to natural touch. In addition, we observed that PF and PW changes have a different weight on the perceived sensation intensity. As a result, we adapted the activation charge rate (ACR) equation, proposed for implantable neurostimulation to predict the perceived intensity while co-modulating the PF and charge per pulse, to TENS (ACRT). ACRTallowed to design different multiparametric TENS paradigms with the same absolute perceived intensity. Although not reported as more natural, the multiparametric paradigm, based on sinusoidal PF modulation, resulted being more intuitive and subconsciously integrated than the standard linear one. This allowed subjects to achieve a faster and more accurate functional performance.Significance. Our findings suggest that TENS-based, multiparametric neurostimulation, despite not consciously perceived naturally, can provide integrated and more intuitive somatosensory information, as functionally proved. This could be exploited to design novel encoding strategies able to improve the performance of non-invasive sensory feedback technologies.
From a deep understanding of neurophysiological mechanisms to AI-based neurostimulation treatments
Gozzi, Noemi (2025)
Neural interfaces are devices designed to interact with the brain, spinal cord, and peripheral nerves. Using electrical stimulation emulating the natural neural language, these devices hold great promise for treating and restoring functions lost due to injury or disease. Yet, their clinical translation remains hindered by our limited understanding of the underlying biophysical and neurophysiological mechanisms and by technological limitations in current neuromodulation methods. This thesis aims to address these challenges by developing an intelligent, scalable, and adaptive neuromodulation framework that integrates biophysical and neurophysiological knowledge, neuromodulation principles, and AI-driven models. Given the shared anatomical and biophysical mechanisms of peripheral nerve stimulation, this work explores three key applications: the exploration and restoration of sensory information through non-invasive neurostimulation, the monitoring and treatment of pain, and the investigation and stimulation of the vagus nerve (VNS) for autonomic regulation. First, we demonstrate that lost sensations can be restored using a wearable, non-invasive neural interface in neuropathic patients with progressively damaged nerves. These sensations are somatotopic, processed in the brain in the natural location, and seamlessly integrated into the sensorimotor scheme. The integration of lost sensory information through neuromodulation, calibrated via AI-driven automatic algorithms, leads to significant functional gait improvements and pain decrease in neuropathic patients. Second, we leverage AI to disentangle the multidimensional nature of pain, distinguishing between its physiological and emotional components. We successfully identify new pain-related biomarkers in clinically controlled environments, potentially serving as clinical endpoints. However, bridging the gap between experimental validation and real-life applications remains challenging. To this end, we develop a home telemonitoring tool capable of tracking both physiological and psychological aspects of pain. Building on this deeper understanding of pain, as well as our preliminary findings demonstrating pain reduction through targeted sensory restoration, we show that a multimodal therapy, combining somatotopic neurostimulation with immersive virtual reality, effectively clinically decreases neuropathic pain. Therapy efficacy is confirmed by both subjective reports and objective neural and sensory biomarkers. Finally, we investigate the physiological and biophysical mechanisms of VNS through a combination of in vivo and in silico studies. We develop anatomically realistic computational models that accurately replicate experimental data and physiological responses. These models enable the design of selective neural interfaces and AI-driven closed-loop optimization frameworks using Bayesian optimization to refine neurostimulation parameters for efficacy and minimal side effects. The interface and AI frameworks are first designed and validated in silico, addressing safety concerns and minimizing reliance on extensive in vivo testing, before being tested in proof-of- concept animal experiments. By bridging fundamental neurophysiological understanding with engineering and AI-driven optimization, this thesis lays the foundation for next-generation neuromodulation therapies that are adaptive, personalized, and clinically translatable.
Towards enhanced functionality of vagus neuroprostheses through in silico optimized stimulation
Ciotti, Federico; John, Robert; Katic Secerovic, Natalija; et al. (2024)
Nature Communications
Bioelectronic therapies modulating the vagus nerve are promising for cardiovascular, inflammatory, and mental disorders. Clinical applications are however limited by side-effects such as breathing obstruction and headache caused by non-specific stimulation. To design selective and functional stimulation, we engineered VaStim, a realistic and efficient in-silico model. We developed a protocol to personalize VaStim in-vivo using simple muscle responses, successfully reproducing experimental observations, by combining models with trials conducted on five pigs. Through optimized algorithms, VaStim simulated the complete fiber population in minutes, including often omitted unmyelinated fibers which constitute 80% of the nerve. The model suggested that all Aα-fibers across the nerve affect laryngeal muscle, while heart rate changes were caused by B-efferents in specific fascicles. It predicted that tripolar paradigms could reduce laryngeal activity by 70% compared to typically used protocols. VaStim may serve as a model for developing neuromodulation therapies by maximizing efficacy and specificity, reducing animal experimentation.
Wearable non-invasive neuroprosthesis for targeted sensory restoration in neuropathy
Gozzi, Noemi; Chee, Lauren; Odermatt, Ingrid; et al. (2024)
Nature Communications
Peripheral neuropathy (PN), the most common complication of diabetes, leads to sensory loss and associated health issues as pain and increased fall risk. However, present treatments do not counteract sensory loss, but only partially manage its consequences. Electrical neural stimulation holds promise to restore sensations, but its efficacy and benefits in PN damaged nerves are yet unknown. We designed a wearable sensory neuroprosthesis (NeuroStep) providing targeted neurostimulation of the undamaged nerve portion and assessed its functionality in 14 PN participants. Our system partially restored lost sensations in all participants through a purposely calibrated neurostimulation, despite PN nerves being less sensitive than healthy nerves (N = 22). Participants improved cadence and functional gait and reported a decrease of neuropathic pain after one day. Restored sensations activated cortical patterns resembling naturally located foot sensations. NeuroStep restores real-time intuitive sensations in PN participants, holding potential to enhance functional and health outcomes while advancing effective non-invasive neuromodulation.
The Development of an Intelligent Agent to Detect and Non-Invasively Characterize Lung Lesions on CT Scans: Ready for the “Real World”?
Sollini, Martina; Kirienko, Margarita; Gozzi, Noemi; et al. (2023)
Cancers
(1) Background: Once lung lesions are identified on CT scans, they must be characterized by assessing the risk of malignancy. Despite the promising performance of computer-aided systems, some limitations related to the study design and technical issues undermine these tools’ efficiency; an “intelligent agent” to detect and non-invasively characterize lung lesions on CT scans is proposed. (2) Methods: Two main modules tackled the detection of lung nodules on CT scans and the diagnosis of each nodule into benign and malignant categories. Computer-aided detection (CADe) and computer aided-diagnosis (CADx) modules relied on deep learning techniques such as Retina U-Net and the convolutional neural network; (3) Results: Tests were conducted on one publicly available dataset and two local datasets featuring CT scans acquired with different devices to reveal deep learning performances in “real-world” clinical scenarios. The CADe module reached an accuracy rate of 78%, while the CADx’s accuracy, specificity, and sensitivity stand at 80%, 73%, and 85.7%, respectively; (4) Conclusions: Two different deep learning techniques have been adapted for CADe and CADx purposes in both publicly available and private CT scan datasets. Experiments have shown adequate performance in both detection and diagnosis tasks. Nevertheless, some drawbacks still characterize the supervised learning paradigm employed in networks such as CNN and Retina U-Net in real-world clinical scenarios, with CT scans from different devices with different sensors’ fingerprints and spatial resolution. Continuous reassessment of CADe and CADx’s performance is needed during their implementation in clinical practice.
Explainable domain transfer of distant supervised cancer subtyping model via imaging-based rules extraction
Cavinato, Lara; Gozzi, Noemi; Sollini, Martina; et al. (2023)
Artificial intelligence in medicine
Image texture analysis has for decades represented a promising opportunity for cancer assessment and disease progression evaluation, evolving in a discipline, i.e., radiomics. However, the road to a complete translation into clinical practice is still hampered by intrinsic limitations. As purely supervised classification models fail in devising robust imaging-based biomarkers for prognosis, cancer subtyping approaches would benefit from the employment of distant supervision, for instance exploiting survival/recurrence information. In this work, we assessed, tested, and validated the domain-generality of our previously proposed Distant Supervised Cancer Subtyping model on Hodgkin Lymphoma. We evaluate the model performance on two independent datasets coming from two hospitals, comparing and analyzing the results. Although successful and consistent, the com-parison confirmed the instability of radiomics due to an across-center lack of reproducibility, leading to explainable results in one center and poor interpretability in the other. We thus propose a Random Forest-based Explainable Transfer Model for testing the domain-invariance of imaging biomarkers extracted from retrospec-tive cancer subtyping. In doing so, we tested the predictive ability of cancer subtyping in a validation and perspective setting, which led to successful results and supported the domain-generality of the proposed approach. On the other hand, the extraction of decision rules enables to draw of risk factors and robust bio-markers to inform clinical decisions. This work shows the potentialities of the Distant Supervised Cancer Sub-typing model to be further evaluated in larger multi-center datasets, to reliably translate radiomics into medical practice. The code is available at this GitHub repository.
Neural encoding of artificial sensations evoked by peripheral nerve stimulation for neuroprosthetic applications
Gozzi, Noemi; Valle, Giacomo (2023)
Artificial Intelligence in Tissue and Organ Regeneration
Restoring sensory feedback in prostheses is critical in the pursuit of high functional performance, heightened embodiment, and improved limb acceptance. While early efforts have focused on the functional effect of adding sensory feedback, recent studies have shown the benefits and feasibility of using different encoding strategies to provide artificial somatosensory information to the users. More specifically, sensory encoding based on nerve stimulation has been used by multiple research groups to provide tactile feedback to limb amputees. In this chapter, we report the possibility of providing sensory feedback using electrical peripheral nerve stimulation, and we highlight the differences among the sensory encoding schemes. We present methods that are exploiting implantable neuro-stimulating devices physically connected with the nerves (neural interfaces) and noninvasive stimulating devices targeting the peripheral nerves through the skin. Moreover, we report novel adaptive methods based on artificial intelligence for optimizing the neurostimulation parameters for application in somatosensory neuroprosthetics. These insights may help guide the development of future multimodal neuroprosthetic limbs.
Unraveling the physiological and psychosocial signatures of pain by machine learning
Gozzi, Noemi; Preatoni, Greta; Ciotti, Federico; et al. (2024)
Med
Background Pain is a complex subjective experience, strongly impacting health and quality of life. Despite many attempts to find effective solutions, present treatments are generic, often unsuccessful, and present significant side effects. Designing individualized therapies requires understanding of multidimensional pain experience, considering physical and emotional aspects. Current clinical pain assessments, relying on subjective one-dimensional numeric self-reports, fail to capture this complexity. Methods To this aim, we exploited machine learning to disentangle physiological and psychosocial components shaping the pain experience. Clinical, psychosocial, and physiological data were collected from 118 chronic pain and healthy participants undergoing 40 pain trials (4,697 trials). Findings To understand the objective response to nociception, we classified pain from the physiological signals (accuracy >0.87), extracting the most important biomarkers. Then, using multilevel mixed-effects models, we predicted the reported pain, quantifying the mismatch between subjective level and measured physiological response. From these models, we introduced two metrics: TIP (subjective index of pain) and Φ (physiological index). These represent possible added value in the clinical process, capturing psychosocial and physiological pain dimensions, respectively. Patients with high TIP are characterized by frequent sick leave from work and increased clinical depression and anxiety, factors associated with long-term disability and poor recovery, and are indicated for alternative treatments, such as psychological ones. By contrast, patients with high Φ show strong nociceptive pain components and could benefit more from pharmacotherapy. Conclusions TIP and Φ, explaining the multidimensionality of pain, might provide a new tool potentially leading to targeted treatments, thereby reducing the costs of inefficient generic therapies.
XAI for myo-controlled prosthesis: Explaining EMG data for hand gesture classification
Gozzi, Noemi; Malandri, Lorenzo; Mercorio, Fabio; et al. (2022)
Knowledge-Based Systems
Machine Learning has recently found a fertile ground in EMG signal decoding for prosthesis control. However, its understanding and acceptance are strongly limited by the notion of AI models as black-boxes. In critical fields, such as medicine and neuroscience, understanding the neurophysiological phenomena underlying models’ outcomes is as relevant as the classification performances. In this work, we adapt state-of-the-art XAI algorithms to EMG hand gesture classification to understand the outcome of machine learning models with respect to physiological processes, evaluating the contribution of each input feature to the prediction and showing that AI models recognize the hand gestures by mapping and fusing efficiently high amplitude activity of synergic muscles. This allows us to (i) drastically reduce the number of required electrodes without a significant loss in classification performances, ensuring the suitability of the system for a larger population of amputees and simplifying the realization of near real-time applications and (ii) perform an efficient selection of features based on their classification relevance, apprehended by the XAI algorithms. This feature selection leads to classification improvements in term of robustness and computational time, outperforming correlation based methods. Finally, (iii) comparing the physiological explanations produced by the XAI algorithms with the experimental setting highlights inconsistencies in the electrodes positioning over different rounds or users, then improving the overall quality of the process.
Automated calibration of somatosensory stimulation using reinforcement learning
Borda, Luigi; Gozzi, Noemi; Preatoni, Greta; et al. (2023)
Journal of NeuroEngineering and Rehabilitation
Background: The identification of the electrical stimulation parameters for neuromodulation is a subject-specific and time-consuming procedure that presently mostly relies on the expertise of the user (e.g., clinician, experimenter, bioengineer). Since the parameters of stimulation change over time (due to displacement of electrodes, skin status, etc.), patients undergo recurrent, long calibration sessions, along with visits to the clinics, which are inefficient and expensive. To address this issue, we developed an automatized calibration system based on reinforcement learning (RL) allowing for accurate and efficient identification of the peripheral nerve stimulation parameters for somatosensory neuroprostheses. Methods: We developed an RL algorithm to automatically select neurostimulation parameters for restoring sensory feedback with transcutaneous electrical nerve stimulation (TENS). First, the algorithm was trained offline on a dataset comprising 49 subjects. Then, the neurostimulation was then integrated with a graphical user interface (GUI) to create an intuitive AI-based mapping platform enabling the user to autonomously perform the sensation characterization procedure. We assessed the algorithm against the performance of both experienced and naïve and of a brute force algorithm (BFA), on 15 nerves from five subjects. Then, we validated the AI-based platform on six neuropathic nerves affected by distal sensory loss. Results: Our automatized approach demonstrated the ability to find the optimal values of neurostimulation achieving reliable and comfortable elicited sensations. When compared to alternatives, RL outperformed the naïve and BFA, significantly decreasing the time for mapping and the number of delivered stimulation trains, while improving the overall quality. Furthermore, the RL algorithm showed performance comparable to trained experimenters. Finally, we exploited it successfully for eliciting sensory feedback in neuropathic patients. Conclusions: Our findings demonstrated that the AI-based platform based on a RL algorithm can automatically and efficiently calibrate parameters for somatosensory nerve stimulation. This holds promise to avoid experts’ employment in similar scenarios, thanks to the merging between AI and neurotech. Our RL algorithm has the potential to be used in other neuromodulation fields requiring a mapping process of the stimulation parameters. Trial registration: ClinicalTrial.gov (Identifier: NCT04217005)

Publications 1 - 10 of 12

Noemi Gozzi

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results