Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review.

BACKGROUND: The widespread use of immune checkpoint inhibitors (ICIs) has revolutionised treatment of multiple cancer types. However, selecting patients who may benefit from ICI remains challenging. Artificial intelligence (AI) approaches allow exploitation of high-dimension oncological data in research and development of precision immuno-oncology. MATERIALS AND METHODS: We conducted a systematic literature review of peer-reviewed original articles studying the ICI efficacy prediction in cancer patients across five data modalities: genomics (including genomics, transcriptomics, and epigenomics), radiomics, digital pathology (pathomics), and real-world and multimodality data. RESULTS: A total of 90 studies were included in this systematic review, with 80% published in 2021-2022. Among them, 37 studies included genomic, 20 radiomic, 8 pathomic, 20 real-world, and 5 multimodal data. Standard machine learning (ML) methods were used in 72% of studies, deep learning (DL) methods in 22%, and both in 6%. The most frequently studied cancer type was non-small-cell lung cancer (36%), followed by melanoma (16%), while 25% included pan-cancer studies. No prospective study design incorporated AI-based methodologies from the outset; rather, all implemented AI as a post hoc analysis. Novel biomarkers for ICI in radiomics and pathomics were identified using AI approaches, and molecular biomarkers have expanded past genomics into transcriptomics and epigenomics. Finally, complex algorithms and new types of AI-based markers, such as meta-biomarkers, are emerging by integrating multimodal/multi-omics data. CONCLUSION: AI-based methods have expanded the horizon for biomarker discovery, demonstrating the power of integrating multimodal data from existing datasets to discover new meta-biomarkers. While most of the included studies showed promise for AI-based prediction of benefit from immunotherapy, none provided high-level evidence for immediate practice change. A priori planned prospective trial designs are needed to cover all lifecycle steps of these software biomarkers, from development and validation to integration into clinical practice.

Ink-based textile electrodes for wearable functional electrical stimulation: A proof-of-concept study to evaluate comfort and efficacy.

BACKGROUND: Functional Electrical Stimulation (FES) represents a promising technique for promoting functional recovery in individuals with neuromuscular diseases. Traditionally, current pulses are delivered through self-adhesive hydrogel Ag/AgCl electrodes, which allow a good contact with the skin, are easy-to-use and have a moderate cost. However, skin adherence decreases after a few uses and skin irritations can originate. Recently, textile electrodes have become an attractive alternative as they assure increased durability, easy integration into clothes and can be conveniently cleaned, improving the wearability of FES. However, as various manufacture processes were attempted, their clear validation is lacking. This proof-of-concept study proposes a novel set of ink-based printed textile electrodes and compares them to adhesive hydrogel electrodes in terms of impedance, stimulation performance and perceived comfort. METHODS: The skin-electrode impedance was evaluated for both types of electrodes under different conditions. These electrodes were then used to deliver FES to the Rectus Femoris of 14 healthy subjects to induce its contraction in both isometric and dynamic conditions. This allowed to compare the two types of electrodes in terms of sensory, motor, maximum and pain thresholds, FES-induced range of motion during dynamic tests, FES-induced torque during isometric tests and perceived stimulation comfort. RESULTS: No statistically significant differences were found both in terms of stimulation performance (Wilcoxon test) and comfort (Generalized Linear Mixed Model). CONCLUSION: The results showed that the proposed ink-based printed textile electrodes can be effectively used as alternative to hydrogel ones. Further experiments are needed to evaluate their durability and their response to sterilizability and stretching tests.

Hybrid Cooperative Control of Functional Electrical Stimulation and Robot Assistance for Upper Extremity Rehabilitation.

OBJECTIVE: Hybrid systems that integrate Functional Electrical Stimulation (FES) and robotic assistance have been proposed in neurorehabilitation to enhance therapeutic benefits. This study focuses on designing a cooperative controller capable of distributing the required torque for movement between robotic actuation and FES, thereby eliminating the need for time-consuming calibration procedures. METHODS: The control schema comprises three main blocks: a motion generation block that defines the desired trajectory, a motor control block including both a weight compensation feedforward and a feedback impedance controller, and an FES control block, based on trial-by-trial Iterative Learning Control (ILC), that adjusts the stimulation intensity according to a predefined stimulation waveform. The feedforward motor assistance can be dynamically regulated using an allocation factor. Experiments involving 12 healthy volunteers were conducted using a one-degree-of-freedom elbow testbed. RESULTS: The experimental results showcased the successful integration of Functional Electrical Stimulation (FES) with robotic actuation, ensuring precise trajectory tracking with a Root Mean Square Error (RMSE) below 7°. Notably, allocating more torque to FES led to a 51 % reduction in motor torque. In conditions where FES operated alone, there was poorer tracking performance with an RMSE of 24° and an early onset of muscle fatigue, as evidenced by a reduced number of achieved repetitions. Furthermore, the hybrid approach enabled 100 fatigue-free elbow flexion repetitions, underscoring the effectiveness of cooperative FES-motor control in extending the benefits of FES-induced exercises. SIGNIFICANCE: This study proposes a flexible approach which can be extended to a multi-degree-of-freedom hybrid system. Furthermore, it underscores the significance of employing a straightforward and adaptable methodology with a rapid calibration procedure, making it easily transferable to clinical applications.

Motor and Cognitive Modulation of a Single Session of Transcutaneous Auricular Vagus Nerve Stimulation in Post Stroke Patients: A Pilot Study.

Objective: The aim of the present study is to explore whether a single session of transcutaneous Vagus Nerve Stimulation (tVNS) can enhance the ipsilesional, and contralesional upper limb motor functions as well as cognitive functions in stroke patients. The effects of the stimulation were evaluated through two different tasks: the box and blocks test (BB), indexing manual dexterity, and the Go/No-go task, a visuomotor paradigm used to assess both motor readiness and response inhibition. Tests were administered without tVNS, during tVNS and during sham tVNS. Results: The BB showed a statistical difference for both contralesional side (p = 0.05) between Basal-Real condition (p = 0.042) and ipsilesional side (p = 0.001) between Basal-Real (p = 0.008) and for Real-Sham (p = 0.005). Any statistical difference was found for the mean latencies in the three conditions of the Go/No-go test. Conclusion: A single session of tVNS seems to improve upper limb motor functions but not cognitive functions in post-stroke patients, despite a positive trend was detected.

A novel environmental chamber for neuronal network multisite recordings.

Environmental stability is a critical issue for neuronal networks in vitro. Hence, the ability to control the physical and chemical environment of cell cultures during electrophysiological measurements is an important requirement in the experimental design. In this work, we describe the development and the experimental verification of a closed chamber for multisite electrophysiology and optical monitoring. The chamber provides stable temperature, pH and humidity and guarantees cell viability comparable to standard incubators. Besides, it integrates the electronics for long-term neuronal activity recording. The system is portable and adaptable for multiple network housings, which allows performing parallel experiments in the same environment. Our results show that this device can be a solution for long-term electrophysiology, for dual network experiments and for coupled optical and electrical measurements.

A force-based human machine interface to drive a motorized upper limb exoskeleton. a pilot study.

Muscular dystrophy is a strongly invalidating disease that causes the progressive loss of motor skills. The use of assistive devices, especially those in support of the upper limb, can increase the ability to perform daily-life activities and foster a partial recovery of the lost motor functionalities. However, for the use of these devices to be truly effective and accepted by patients, their activation must coincide with the user's intention to move. This work describes a new human-machine interface based on the integration of a six-axis force sensor to drive an upper limb motorized exoskeleton. This novel system can detect the patient's intention to move and produce displacements of the robotic device that are of magnitude and direction consistent with the user's wishes. The integration of the force-sensor interface in the BRIDGE/EMPATIA exoskeletal system was successful, and tests performed on both healthy and dystrophic subjects showed promising results, especially for the execution of planar movements.

Upper limb exosuit cable routing optimization.

Exosuits are emerging as promising in assisting with activities of daily living. In the design phase of an exosuit, it is fundamental to maximize its portability. The goal of this work was to identify the best cable routing configuration for an upper limb cable-driven exosuit to assist elbow flexion. Simulations were run in OpenSim. Different cable configurations were evaluated. The goal was to minimize the overall tension of the cables to reduce the device's power consumption and torque requirements. The optimal configuration was evaluated in simulation for different percentages of assistance to study its effects in terms of muscle activation and joint reaction forces. We then tested three different configurations on a test bench to both evaluate the motor current and their effect on the pronation/supination of the elbow. Simulation results suggested that a double cable configuration might help to lower the motor torque and power consumption. This conclusion was supported by the experimental results, in which the motor current was reduced by 12.5% with respect to the single cable configuration. Simulation results also showed that the optimal configuration lowered muscle activation without greatly affecting joint reactions at the elbow, even though it might cause unwanted pronation/supination, as experimental results confirmed. However, since a double configuration results in greater complexity and reduced efficiency, single-cable solutions still represent a good option.

Hand grip support for rehabilitation and assistance: from patent to TRL5.

In the last decades, the continuous increase in the number of the vast cohort of chronic patients that constantly need medical assistance and supervision, and the widespread lack of therapist has brought to an increased interest in the role of medical technologies in rehabilitative programs and assistive scenarios. Current clinical evidence in rehabilitation demonstrates that there is an important and increasing demand for innovative therapeutic solutions to recover the hand functions to prevent patients to need assistance in performing daily life activities. This works describes the pathway from patent to TRL5 of a device to support hand grip actions and interaction with daily life objects. E-KIRO is based on the use of electromagnets, which are able to attach/detach interactive objects equipped with a ferromagnetic plate. Five end-users used the device and scored it with excellent usability based on the System Usability Scale.

Upper-limb actuated exoskeleton for muscular dystrophy patients: preliminary results.

Being able to perform a lost movement is an important experience towards increased independence and self-esteem, particularly for neuromuscular patients, who see their muscles weaken day after day. In this pilot study, preliminary results on the testing of a motorized upper-limb exoskeleton for muscular dystrophy patients are presented. The mechatronic system is a five Degrees of Freedom exoskeleton, which acts at shoulder, elbow, and wrist levels. It is designed to help severely impaired people to regain independence during daily-life activities. While wearing the exoskeleton, the user has the direct control of the system by actively piloting the position of end-effector by means of joystick or vocal control. The usability of the system and a quantitative assessment of arm functionality with and without the exoskeleton are evaluated on five muscular dystrophy patients. According to the objective functional benefit evaluation performed through the PUL scale, all participants strongly increased their range of motion and they were able to perform activities that were not possible without the exoskeleton, such as such as feeding, playing activities at the table, combing hair or using a keyboard. As for the evaluation of self-perceived functional benefit, four patients reflected the effective measured functional improvement. System usability has been evaluated to be good.

The combined action of a passive exoskeleton and an EMG-controlled neuroprosthesis for upper limb stroke rehabilitation: First results of the RETRAINER project.

The combined use of Functional Electrical Stimulation (FES) and robotic technologies is advocated to improve rehabilitation outcomes after stroke. This work describes an arm rehabilitation system developed within the European project RETRAINER. The system consists of a passive 4-degrees-of-freedom exoskeleton equipped with springs to provide gravity compensation and electromagnetic brakes to hold target positions. FES is integrated in the system to provide additional support to the most impaired muscles. FES is triggered based on the volitional EMG signal of the same stimulated muscle; in order to encourage the active involvement of the patient the volitional EMG is also monitored throughout the task execution and based on it a happy or sad emoji is visualized at the end of each task. The control interface control of the system provides a GUI and multiple software tools to organize rehabilitation exercises and monitor rehabilitation progress. The functionality and the usability of the system was evaluated on four stroke patients. All patients were able to use the system and judged positively its wearability and the provided support. They were able to trigger the stimulation based on their residual muscle activity and provided different levels of active involvement in the exercise, in agreement with their level of impairment. A randomized controlled trial aimed at evaluating the effectiveness of the RETRAINER system to improve arm function after stroke is currently ongoing.

A patient-controlled functional electrical stimulation system for arm weight relief.

A patient-driven control strategy for Functional Electrical Stimulation (FES), which amplifies volitionally-initiated shoulder abductions, is proposed to improve stroke patients' rehabilitation. Based on the measured abduction angle, a FES-induced muscle recruitment is generated that yields a pre-specified percentage of this angle - yielding arm weight relief. To guarantee the correct recruitment also under fatigue and uncertain muscle activation we employ feedback control of the recruitment level determined by filtering the FES-evoked electromyogram. Filter parameters are user-optimized to obtain a linear relation between filter output and angle with a good signal-to-noise ratio. The auto-tuned recruitment controller (RC) was tested on five healthy subjects and compared to direct stimulation (DS) while muscle fatigue progressively occurred. Results showed a more linear relation between recruitment level and angle than between non-controlled stimulation intensity and angle (R2=0.93 vs. R2=0.79, angular range of 54°). After 6 min of stimulation, abduction decreased by 42% ± 14 for DS and by 0% ± 12 for RC, showing an effective compensation of fatigue. RC yielded significant smaller errors than DS in generating desired angles (0.23% ± 5.9 vs. 14.6% ± 9.7). When FES-induced arm weight support was provided, a mean reduction of the volitional effort (determined by Electromyography) of 78% was achieved compared to angular tracking without FES. First experiments with one acute stroke patient are also reported.

Quantitative Evaluation of Performance during Robot-assisted Treatment.

INTRODUCTION: This article is part of the Focus Theme of Methods of Information in Medicine on "Methodologies, Models and Algorithms for Patients Rehabilitation". OBJECTIVES: The great potential of robots in extracting quantitative and meaningful data is not always exploited in clinical practice. The aim of the present work is to describe a simple parameter to assess the performance of subjects during upper limb robotic training exploiting data automatically recorded by the robot, with no additional effort for patients and clinicians. METHODS: Fourteen children affected by cerebral palsy (CP) performed a training with Armeo®Spring. Each session was evaluated with P, a simple parameter that depends on the overall performance recorded, and median and interquartile values were computed to perform a group analysis. RESULTS: Median (interquartile) values of P significantly increased from 0.27 (0.21) at T0 to 0.55 (0.27) at T1 . This improvement was functionally validated by a significant increase of the Melbourne Assessment of Unilateral Upper Limb Function. CONCLUSIONS: The parameter described here was able to show variations in performance over time and enabled a quantitative evaluation of motion abilities in a way that is reliable with respect to a well-known clinical scale.

Evaluation of theories of complex movement planning in different levels of gravity.

Due to high redundancy of degrees of freedom in the human body, we can perform any movement, from the simplest to the most complex, in many different ways. Several studies are still trying to identify the motor strategies that master this redundancy and generate the movements whose characteristics are highly stereotyped. The aim of this work is to build a simulator that is able to evaluate different motor planning hypotheses. The most interesting applications of this tool occur in studies of the motor strategy in microgravity conditions. The comparison between simulated movements and kinematics data recorded both on Earth, and during a 5-month mission on board the Mir station shows that for a complex whole-body movement (such as trunk bending) a single planning criterion cannot explain all movement aspects. However, the simulator allows an understanding of the motor planning adaptation of astronauts. In space, the lack of equilibrium constraint (which on Earth brings about the center of mass control) leads to a new motor strategy that minimizes dynamic interactions with the floor.

Neuro-mechanics of muscle coordination during recumbent pedaling in post-acute stroke patients.

Motor impairment after stroke has been hypothesized to be related, among others, to impairments in the modular control of movement. In this study we analyzed muscle coordination and pedal forces during a recumbent pedaling exercise from a sample of post-acute stroke patients (n=5) and a population of age-matched healthy individuals (n=4). Healthy subjects and the less impaired patients showed a shared modular organization of pedaling based on 4 similar muscle synergies. The most impaired patient, characterized by a Motricity Index of 52/100, showed a reduced complexity (only 2 muscle synergies for the affected side). Differences between healthy subjects and post-stroke patients in the execution of the task were identified in terms of unbalance in mechanical work production, which well corresponded to the level of impairment. This pedaling unbalance could be traced back to different activation strategies of the 4 identified modules. Investigation on a more representative sample will provide a full characterization of the neuro-mechanics of pedaling after stroke, helping our understandings of the disruption of motor coordination at central level after stroke and of the most effective solutions for functional recovery.

An ecological evaluation of the metabolic benefits due to robot-assisted gait training.

Cerebral palsy (CP), one of the most common neurological disorders in childhood, features affected individual's motor skills and muscle actions. This results in elevated heart rate and rate of oxygen uptake during sub-maximal exercise, thus indicating a mean energy expenditure higher than healthy subjects. Rehabilitation, currently involving also robot-based devices, may have an impact also on these aspects. In this study, an ecological setting has been proposed to evaluate the energy expenditure of 4 children with CP before and after a robot-assisted gait training. Even if the small sample size makes it difficult to give general indications, results presented here are promising. Indeed, children showed an increasing trend of the energy expenditure per minute and a decreasing trend of the energy expenditure per step, in accordance to the control group. These data suggest a metabolic benefit of the treatment that may increase the locomotion efficiency of disabled children.

Static and dynamic postural control in long-term microgravity: evidence of a dual adaptation.

The adaptation of dynamic movement-posture coordination during forward trunk bending was investigated in long-term weightlessness. Three-dimensional movement analysis was carried out in two astronauts during a 4-mo microgravity exposure. The principal component analysis was applied to joint-angle kinematics for the assessment of angular synergies. The anteroposterior center of mass (CM) displacement accompanying trunk flexion was also quantified. The results reveal that subjects kept typically terrestrial strategies of movement-posture coordination. The temporary disruption of joint-angular synergies observed at subjects' first in-flight session was promptly recovered when repetitive sessions in flight were analyzed. The CM anteroposterior shift was consistently <3-4 cm, suggesting that subjects could dynamically control the CM position throughout the whole flight. This is in contrast to the observed profound microgravity-induced disruption of the quasi-static body orientation and initial CM positioning. Although this study was based on only two subjects, evidence is provided that static and dynamic postural control might be under two separate mechanisms, adapting with their specific time course to the constraints of microgravity.

Perspectives on MEMS in bioengineering: a novel capacitive position microsensor.

We describe a novel capacitive position sensor using micromachining to achieve high sensitivity and large range of motion. These sensors require a new theoretical framework to describe and optimize their performance. Employing a complete description of the electrical fields, the sensor should deviate from the standard geometries used for capacitive sensors. By this optimization, the sensor gains a twofold increase in sensitivity. Results on a PC board 10x model imply that the micromachined sensor should achieve a sensitivity of less than 10 nm over 500-micron range of travel. Some bioengineering applications are addressed, including positioning of micromirrors for laser surgery and dose control for implantable drug delivery systems.

Optimisation of shape kernel and threshold in image-processing motion analysers.

The aim of the work is to optimise the image processing of a motion analyser. This is to improve accuracy, which is crucial for neurophysiological and rehabilitation applications. A new motion analyser, ELITE-S2, for installation on the International Space Station is described, with the focus on image processing. Important improvements are expected in the hardware of ELITE-S2 compared with ELITE and previous versions (ELITE-S and Kinelite). The core algorithm for marker recognition was based on the current ELITE version, using the cross-correlation technique. This technique was based on the matching of the expected marker shape, the so-called kernel, with image features. Optimisation of the kernel parameters was achieved using a genetic algorithm, taking into account noise rejection and accuracy. Optimisation was achieved by performing tests on six highly precise grids (with marker diameters ranging from 1.5 to 4 mm), representing all allowed marker image sizes, and on a noise image. The results of comparing the optimised kernels and the current ELITE version showed a great improvement in marker recognition accuracy, while noise rejection characteristics were preserved. An average increase in marker co-ordinate accuracy of +22% was achieved, corresponding to a mean accuracy of 0.11 pixel in comparison with 0.14 pixel, measured over all grids. An improvement of +37%, corresponding to an improvement from 0.22 pixel to 0.14 pixel, was observed over the grid with the biggest markers.

Motor coordination in weightless conditions revealed by long-term microgravity adaptation.

The functional approach to studying human motor systems attempts to give a better understanding of the processes behind planning movements and their coordinated performance by relying on weightlessness as a particularly enlightening experimental condition. Indeed, quantitative monitoring of sensorimotor adaptation of subjects exposed to weightlessness outlines the functional role of gravity in motor and postural organization. The recent accessibility of the MIR Space Station has allowed for the first time experimental quantitative kinematic analysis of long-term sensorimotor and postural adaptation to the weightless environment though opto-electronic techniques. In the frame of the EUROMIR'95 Mission, two protocols of voluntary posture perturbation (erect posture, EP; forward trunk bending, FTB) were carried out during four months of microgravity exposure. Results show that postural strategies for quasistatic body orientation in weightlessness are based on the alignment of geometrical body axes (head and trunk) along external references. A proper whole body positioning appears to be recovered only after months of microgravity exposure. By contrast, typically, terrestrial strategies of co-ordination between movement and posture are promptly restored and used when performing motor activities in the weightless environment. This result is explained under the assumption that there may be different sensorimotor integration processes for static and dynamic postural function and that the organisation of coordinated movement might rely stably on egocentric references and kinematics synergies for motor control.

ELITE-S2: the multifactorial movement analysis facility for the International Space Station.

Experimental observations of adaptation processes of the motor control system to altered gravity conditions can provide useful elements to the investigations on the mechanisms underlying motor control of human subject. The microgravity environment obtained on orbital flights represents a unique experimental condition for the monitoring of motor adaptation. The research in motor control exploits the changes caused by microgravity on the overall sensorimotor process, due to the impairment of the sensory systems whose function depends upon the presence of the gravity vector. Motor control in microgravity has been investigated during parabolic flights and short-term space missions, in particular for analysis of movement-posture co-ordination when equilibrium is no longer a constraint. Analysis of long-term adaptation would also be very interesting, calling for long-term body motion observations during the process of complete motor adaptation to the weightlessness environment. ELITE-S2 is an innovative facility for quantitative human movement analysis in weightless conditions onboard the International Space Station (ISS). ELITE-S2 is being developed by the Italian Space Agency, ASI is to be delivering the flight models to NASA to be included in an expressed rack in US Lab Module in February 2004. First mission is currently planned for summer 2004 (increment 10 ULF 2 ISS).