Should the Use of Adaptive Machine Learning Systems in Medicine be Classified as Research?

A novel advantage of the use of machine learning (ML) systems in medicine is their potential to continue learning from new data after implementation in clinical practice. To date, considerations of the ethical questions raised by the design and use of adaptive machine learning systems in medicine have, for the most part, been confined to discussion of the so-called "update problem," which concerns how regulators should approach systems whose performance and parameters continue to change even after they have received regulatory approval. In this paper, we draw attention to a prior ethical question: whether the continuous learning that will occur in such systems after their initial deployment should be classified, and regulated, as medical research? We argue that there is a strong prima facie case that the use of continuous learning in medical ML systems should be categorized, and regulated, as research and that individuals whose treatment involves such systems should be treated as research subjects.

A continuous learning approach to brain tumor segmentation: integrating multi-scale spatial distillation and pseudo-labeling strategies

Introduction

This study presents a novel continuous learning framework tailored for brain tumour segmentation, addressing a critical step in both diagnosis and treatment planning. This framework addresses common challenges in brain tumour segmentation, such as computational complexity, limited generalisability, and the extensive need for manual annotation.

Methods

Our approach uniquely combines multi-scale spatial distillation with pseudo-labelling strategies, exploiting the coordinated capabilities of the ResNet18 and DeepLabV3+ network architectures. This integration enhances feature extraction and efficiently manages model size, promoting accurate and fast segmentation. To mitigate the problem of catastrophic forgetting during model training, our methodology incorporates a multi-scale spatial distillation scheme. This scheme is essential for maintaining model diversity and preserving knowledge from previous training phases. In addition, a confidence-based pseudo-labelling technique is employed, allowing the model to self-improve based on its predictions and ensuring a balanced treatment of data categories.

Results

The effectiveness of our framework has been evaluated on three publicly available datasets (BraTS2019, BraTS2020, BraTS2021) and one proprietary dataset (BraTS_FAHZU) using performance metrics such as Dice coefficient, sensitivity, specificity and Hausdorff95 distance. The results consistently show competitive performance against other state-of-the-art segmentation techniques, demonstrating improved accuracy and efficiency.

Discussion

This advance has significant implications for the field of medical image segmentation. Our code is freely available at https://github.com/smallboy-code/A-brain-tumor-segmentation-frameworkusing-continual-learning.

A spiking neural network with continuous local learning for robust online brain machine interface

Objective.Spiking neural networks (SNNs) are powerful tools that are well suited for brain machine interfaces (BMI) due to their similarity to biological neural systems and computational efficiency. They have shown comparable accuracy to state-of-the-art methods, but current training methods require large amounts of memory, and they cannot be trained on a continuous input stream without pausing periodically to perform backpropagation. An ideal BMI should be capable training continuously without interruption to minimize disruption to the user and adapt to changing neural environments.Approach.We propose a continuous SNN weight update algorithm that can be trained to perform regression learning with no need for storing past spiking events in memory. As a result, the amount of memory needed for training is constant regardless of the input duration. We evaluate the accuracy of the network on recordings of neural data taken from the premotor cortex of a primate performing reaching tasks. Additionally, we evaluate the SNN in a simulated closed loop environment and observe its ability to adapt to sudden changes in the input neural structure.Main results.The continuous learning SNN achieves the same peak correlation (ρ=0.7) as existing SNN training methods when trained offline on real neural data while reducing the total memory usage by 92%. Additionally, it matches state-of-the-art accuracy in a closed loop environment, demonstrates adaptability when subjected to multiple types of neural input disruptions, and is capable of being trained online without any prior offline training.Significance.This work presents a neural decoding algorithm that can be trained rapidly in a closed loop setting. The algorithm increases the speed of acclimating a new user to the system and also can adapt to sudden changes in neural behavior with minimal disruption to the user.

Corrigendum: Studying Brains. What could neurometaphysics be to NeurotechEU?

[This corrects the article DOI: 10.3389/fnins.2023.1155547.].

The Unknown Abnormal Condition Monitoring Method for Pumped-Storage Hydroelectricity

Pumped-storage hydroelectricity (PSH) is a facility that stores energy in the form of the gravitational potential energy of water by pumping water from a lower to a higher elevation reservoir in a hydroelectric power plant. The operation of PSH can be divided into two states: the turbine state, during which electric energy is generated, and the pump state, during which this generated electric energy is stored as potential energy. Additionally, the condition monitoring of PSH is generally challenging because the hydropower turbine, which is one of the primary components of PSH, is immersed in water and continuously rotates. This study presents a method that automatically detects new abnormal conditions in target structures without the intervention of experts. The proposed method automatically updates and optimizes existing abnormal condition classification models to accommodate new abnormal conditions. The performance of the proposed method was evaluated with sensor data obtained from on-site PSH. The test results show that the proposed method detects new abnormal PSH conditions with an 85.89% accuracy using fewer than three datapoints and classifies each condition with a 99.73% accuracy on average.

Studying brains what could neurometaphysics be to NeurotechEU?

NeurotechEU has introduced a new conceptual hierarchy for neuroscientific research and its applications along 8 different core research areas, including the so-called 'neurometaphysics'. This paper explores this concept of neurometaphysics, its topics and its potential approach. It warns against an endemic Cartesianism in (neuro)science that somehow seems to survive explicit refutations by implicitly persisting in our conceptual scheme. Two consequences of this persisting Cartesian legacy are discussed; the isolated brain assumption and the idea that activity requires identifiable neural 'decisions'. Neuropragmatism is introduced as offering the promise of progress in neurometaphysics, by emphasizing that (1) studying brains interact organically with their environment and (2) studying brains requires an attitude of continuous learning.

#MedEd: Mapping the Current Landscape of Medical Education Discourse and Stakeholder Participation Across Social Media Platforms

Background Medical education is a constantly evolving and multifaceted field that requires ongoing discussion and innovation. Social media platforms have emerged as a popular medium for disseminating information and engaging in professional discourse among medical educators. In particular, the hashtag #MedEd has gained widespread recognition amongst individuals and organizations within the medical education community. Our objective is to gain insights into the types of information and discussions surrounding medical education, as well as the individuals or organizations involved in these conversations. Methods Searches were conducted across major social media platforms, including Twitter, Instagram, and Facebook, using the hashtag #MedEd. The top 20 posts posted on these platforms were analyzed through a reflexive thematic analysis approach utilizing the Braun and Clarke method. Furthermore, an examination was conducted on the profiles of those responsible for posting the aforementioned top posts, to ascertain the degree of participation from individuals versus organizations within the broader discourse pertaining to the topic. Results Our analysis revealed three thematic categories associated with the usage of the #MedEd hashtag, including discussions on "continuous learning and medical case presentations," "medical specialties and topics," and "medical education pedagogy." The analysis revealed that social media can serve as a valuable platform for medical education by providing access to a diverse range of learning resources, fostering collaboration and professional networking, and providing innovative teaching methods. Furthermore, profile analysis showed that individuals were more actively involved in the discussion of medical education topics on social media compared to organizations across all three platforms. Conclusion Our study highlights the significant role that social media platforms play in facilitating the exchange of information and ideas within the medical education community. The hashtag #MedEd serves as a means of connecting individuals and organizations across the globe, enabling them to engage in professional discourse and stay informed on the latest developments in the field. Our findings suggest that a better understanding of the thematic categories and stakeholders involved in medical education discussions on social media can aid educators, learners, and organizations in enhancing their engagement with this dynamic field.

Educational Needs in Oncology Nursing: A Scoping Review

Care in oncology requires both technical and psychosocial skills by nursing staff, so continuous learning is necessary. Evidence suggests there are some educational gaps in oncology nursing staff, and continuing educational interventions have been effective in overcoming these deficiencies. Aim: to determine the basic educational lines that a continuous training program should have for oncology nurses. A bibliographic review study was carried out in two phases from October 2020 to January 2021. In a first phase, the main databases were analyzed: PubMed, Web of Science, Dialnet and Medline, following the PRISMA methodology; and subsequently, an analysis of the most important thematic nuclei that a training program in cancer nursing should contain. The DAFO matrix and the Hanlon prioritization method were used. Four competencies that every oncology nurse should have were described: communication, coping, self-direction of learning and technical health. The thematic contents that a training program should contain were then determined, and aspects such as stress prevention and burnout, adequate communication with patient and family, and continuous educational and technical skills were considered. The results found suggest that there are deficiencies in the education of nursing staff. Continuing education programs are effective in supplementing them. They should develop the four skills described in the results section.

Evaluating and Improving Neonatal Gentamicin Pharmacokinetic Models Using Aggregated Routine Clinical Care Data

Model-informed precision dosing (MIPD) can aid dose decision-making for drugs such as gentamicin that have high inter-individual variability, a narrow therapeutic window, and a high risk of exposure-related adverse events. However, MIPD in neonates is challenging due to their dynamic development and maturation and by the need to minimize blood sampling due to low blood volume. Here, we investigate the ability of six published neonatal gentamicin population pharmacokinetic models to predict gentamicin concentrations in routine therapeutic drug monitoring from nine sites in the United State (n = 475 patients). We find that four out of six models predicted with acceptable levels of error and bias for clinical use. These models included known important covariates for gentamicin PK, showed little bias in prediction residuals over covariate ranges, and were developed on patient populations with similar covariate distributions as the one assessed here. These four models were refit using the published parameters as informative Bayesian priors or without priors in a continuous learning process. We find that refit models generally reduce error and bias on a held-out validation data set, but that informative prior use is not uniformly advantageous. Our work informs clinicians implementing MIPD of gentamicin in neonates, as well as pharmacometricians developing or improving PK models for use in MIPD.

A Continuous Learning Approach for Real-Time Network Intrusion Detection

Network intrusion detection is becoming a challenging task with cyberattacks that are becoming more and more sophisticated. Failing the prevention or detection of such intrusions might have serious consequences. Machine learning approaches try to recognize network connection patterns to classify unseen and known intrusions but also require periodic re-training to keep the performances at a high level. In this paper, a novel continuous learning intrusion detection system, called Soft-Forgetting Self-Organizing Incremental Neural Network (SF-SOINN), is introduced. SF-SOINN, besides providing continuous learning capabilities, is able to perform fast classification, is robust to noise, and it obtains good performances with respect to the existing approaches. The main characteristic of SF-SOINN is the ability to remove nodes from the neural network based on their utility estimate. SF-SOINN has been validated on the well-known NSL-KDD and CIC-IDS-2017 intrusion detection datasets as well as on some artificial data to show the classification capability on more general tasks.

Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions

A fundamental aspect of learning in biological neural networks is the plasticity property which allows them to modify their configurations during their lifetime. Hebbian learning is a biologically plausible mechanism for modeling the plasticity property in artificial neural networks (ANNs), based on the local interactions of neurons. However, the emergence of a coherent global learning behavior from local Hebbian plasticity rules is not very well understood. The goal of this work is to discover interpretable local Hebbian learning rules that can provide autonomous global learning. To achieve this, we use a discrete representation to encode the learning rules in a finite search space. These rules are then used to perform synaptic changes, based on the local interactions of the neurons. We employ genetic algorithms to optimize these rules to allow learning on two separate tasks (a foraging and a prey-predator scenario) in online lifetime learning settings. The resulting evolved rules converged into a set of well-defined interpretable types, that are thoroughly discussed. Notably, the performance of these rules, while adapting the ANNs during the learning tasks, is comparable to that of offline learning methods such as hill climbing.

Building a learning health community: By the people, for the people

The journey of illness as lived by patients and caregivers is not routinely captured for systematic sharing or continuous learning. Consequently, far too many people face the uncertainty of what to expect when confronted with the challenges of illness and caregiving. Patients and caregivers muddle through unfamiliar territory without the benefit of the accumulated knowledge of others who have been on the journey before them. Why do patients and caregivers continually need to search out or reinvent solutions to manage their daily lives with life-changing illness when others have surely faced similar challenges? Are not the lived experiences and contextual perspectives of patients and caregivers valuable for a learning health system? At PatientsLikeMe, an online patient research network, we believe it is not possible to realize the full potential of a continuously learning health system without the expertise and knowledge of patients and caregivers. This paper describes the development of the Patient and Caregiver Journey Framework and related patient-informed principles for design and measurement created by PatientsLikeMe in partnership with patients and caregivers using qualitative research methods, immersive observation and directed one-on-one conversations. These tools provide a person-centric foundation upon which the knowledge and experience of patients and caregivers are collected, curated, aggregated and shared to support a data-driven learning health community continuously powered by the people and for the people.