Algorithm Change Protocols in the Regulation of Adaptive Machine Learning-Based Medical Devices.

One of the greatest strengths of artificial intelligence (AI) and machine learning (ML) approaches in health care is that their performance can be continually improved based on updates from automated learning from data. However, health care ML models are currently essentially regulated under provisions that were developed for an earlier age of slowly updated medical devices-requiring major documentation reshape and revalidation with every major update of the model generated by the ML algorithm. This creates minor problems for models that will be retrained and updated only occasionally, but major problems for models that will learn from data in real time or near real time. Regulators have announced action plans for fundamental changes in regulatory approaches. In this Viewpoint, we examine the current regulatory frameworks and developments in this domain. The status quo and recent developments are reviewed, and we argue that these innovative approaches to health care need matching innovative approaches to regulation and that these approaches will bring benefits for patients. International perspectives from the World Health Organization, and the Food and Drug Administration's proposed approach, based around oversight of tool developers' quality management systems and defined algorithm change protocols, offer a much-needed paradigm shift, and strive for a balanced approach to enabling rapid improvements in health care through AI innovation while simultaneously ensuring patient safety. The draft European Union (EU) regulatory framework indicates similar approaches, but no detail has yet been provided on how algorithm change protocols will be implemented in the EU. We argue that detail must be provided, and we describe how this could be done in a manner that would allow the full benefits of AI/ML-based innovation for EU patients and health care systems to be realized.

Electroencephalography.

Electroencephalography (EEG) is the non-invasive measurement of the brain's electric fields. Electrodes placed on the scalp record voltage potentials resulting from current flow in and around neurons. EEG is nearly a century old: this long history has afforded EEG a rich and diverse spectrum of applications. On the one hand, foundations of EEG in clinical diagnostics have dovetailed more recently into brain-triggered neurorehabilitation treatments. On the other hand, EEG has not only been a workhorse for providing brain correlates of constructs in the field of experimental psychology, but has also been used as a true neuroimaging method with more recent extensions in translational as well as computational neuroscience. The versatility and accessibility of the technique, in combination with advances in signal processing, allow for this 'old dog' to still deliver new tricks and innovations.

Electrically Assisted Movement Therapy in Chronic Stroke Patients With Severe Upper Limb Paresis: A Pilot, Single-Blind, Randomized Crossover Study.

OBJECTIVE: To evaluate the effects of electrically assisted movement therapy (EAMT) in which patients use functional electrical stimulation, modulated by a custom device controlled through the patient's unaffected hand, to produce or assist task-specific upper limb movements, which enables them to engage in intensive goal-oriented training. DESIGN: Randomized, crossover, assessor-blinded, 5-week trial with follow-up at 18 weeks. SETTING: Rehabilitation university hospital. PARTICIPANTS: Patients with chronic, severe stroke (N=11; mean age, 47.9y) more than 6 months poststroke (mean time since event, 46.3mo). INTERVENTIONS: Both EAMT and the control intervention (dose-matched, goal-oriented standard care) consisted of 10 sessions of 90 minutes per day, 5 sessions per week, for 2 weeks. After the first 10 sessions, group allocation was crossed over, and patients received a 1-week therapy break before receiving the new treatment. MAIN OUTCOME MEASURES: Fugl-Meyer Motor Assessment for the Upper Extremity, Wolf Motor Function Test, spasticity, and 28-item Motor Activity Log. RESULTS: Forty-four individuals were recruited, of whom 11 were eligible and participated. Five patients received the experimental treatment before standard care, and 6 received standard care before the experimental treatment. EAMT produced higher improvements in the Fugl-Meyer scale than standard care (P<.05). Median improvements were 6.5 Fugl-Meyer points and 1 Fugl-Meyer point after the experimental treatment and standard care, respectively. The improvement was also significant in subjective reports of quality of movement and amount of use of the affected limb during activities of daily living (P<.05). CONCLUSIONS: EAMT produces a clinically important impairment reduction in stroke patients with chronic, severe upper limb paresis.

Transferring brain-computer interfaces beyond the laboratory: successful application control for motor-disabled users.

OBJECTIVES: Brain-computer interfaces (BCIs) are no longer only used by healthy participants under controlled conditions in laboratory environments, but also by patients and end-users, controlling applications in their homes or clinics, without the BCI experts around. But are the technology and the field mature enough for this? Especially the successful operation of applications - like text entry systems or assistive mobility devices such as tele-presence robots - requires a good level of BCI control. How much training is needed to achieve such a level? Is it possible to train naïve end-users in 10 days to successfully control such applications? MATERIALS AND METHODS: In this work, we report our experiences of training 24 motor-disabled participants at rehabilitation clinics or at the end-users' homes, without BCI experts present. We also share the lessons that we have learned through transferring BCI technologies from the lab to the user's home or clinics. RESULTS: The most important outcome is that 50% of the participants achieved good BCI performance and could successfully control the applications (tele-presence robot and text-entry system). In the case of the tele-presence robot the participants achieved an average performance ratio of 0.87 (max. 0.97) and for the text entry application a mean of 0.93 (max. 1.0). The lessons learned and the gathered user feedback range from pure BCI problems (technical and handling), to common communication issues among the different people involved, and issues encountered while controlling the applications. CONCLUSION: The points raised in this paper are very widely applicable and we anticipate that they might be faced similarly by other groups, if they move on to bringing the BCI technology to the end-user, to home environments and towards application prototype control.

Adaptation of hybrid human-computer interaction systems using EEG error-related potentials.

Performance improvement in both humans and artificial systems strongly relies in the ability of recognizing erroneous behavior or decisions. This paper, that builds upon previous studies on EEG error-related signals, presents a hybrid approach for human computer interaction that uses human gestures to send commands to a computer and exploits brain activity to provide implicit feedback about the recognition of such commands. Using a simple computer game as a case study, we show that EEG activity evoked by erroneous gesture recognition can be classified in single trials above random levels. Automatic artifact rejection techniques are used, taking into account that subjects are allowed to move during the experiment. Moreover, we present a simple adaptation mechanism that uses the EEG signal to label newly acquired samples and can be used to re-calibrate the gesture recognition system in a supervised manner. Offline analysis show that, although the achieved EEG decoding accuracy is far from being perfect, these signals convey sufficient information to significantly improve the overall system performance.