Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Predicting future disease state with generative navigation
Osteoarthritis is the most common joint disorder, and it affects a substantial proportion of the population. Han et al. explore whether advanced machine learning techniques can predict future radiographs of knee joints. A deep learning model generated the most likely future radiograph and helped medical experts to predict the future course of osteoarthritis.
AI promises to bring many benefits to healthcare and research, but mistrust has built up owing to many instances of harm to under-represented communities. To amend this, participatory approaches can directly involve communities in AI research that will impact them. An important element of such approaches is ensuring that communities can take control over their own data and how they are shared.
Tool use is one of the defining traits of human cognition that sets our species apart from other animals. A novel computational framework may enable robots to use tools as intelligently as humans do.
Indigenous peoples are under-represented in genomic datasets, which can lead to limited accuracy and utility of machine learning models in precision health. While open data sharing undermines rights of Indigenous communities to govern data decisions, federated learning may facilitate secure and community-consented data sharing.
The use of decision-support systems based on artificial intelligence approaches in antimicrobial prescribing raises important moral questions. Adopting ethical frameworks alongside such systems can aid the consideration of infection-specific complexities and support moral decision-making to tackle antimicrobial resistance.
Finding good benchmarks is an important and pervasive problem in machine learning for healthcare. This Perspective highlights key aspects that require scrutiny in the whole process of benchmark generation and use, including problem formulation, creation of datasets, development of a suite of machine learning models and evaluation of these models.
The metaverse is gaining prominence in industry, academia and social media. Wang and colleagues envision a medical technology and AI ecosystem, and present this perspective on the future of healthcare in the metaverse.
Recognition of speech from lip movements is still a challenging problem and much effort is concentrated on the English language. Ma et al. have used auxiliary tasks to train a model such that it works for a range of different languages, including Mandarin, Spanish, Italian, French and Portuguese.
Single-cell multi-omics technologies have increased dramatically in biomedical research. Lakkis et al. develop a deep learning method to address computational challenges in CITE-seq and single-cell RNA-seq datasets.
Image noise is a common problem in light microscopy, and denoising is a key step in microscopic imaging pipelines. Lequyer et al. propose a self-supervised denoising method and apply it to diverse imaging and analysis pipelines.
The effects of novel antibodies are hard to predict owing to the complex interactions between antibodies and antigens. Zhang and colleagues use a graph-based method to learn a dynamic representation that allows for predictions of neutralization activity and demonstrate the method by recommending probable antibodies for human immunodeficiency virus, severe acute respiratory syndrome coronavirus 2, influenza and dengue.
To enable electrification of cities, thereby decarbonizing energy grids, it is essential to predict electricity consumption with high spatio-temporal accuracy. To reduce the need for large amounts of training data, an active deep learning approach is developed to make accurate forecasts of electric load profiles at the scale of single buildings.
Physical dynamical processes can be modelled with differential equations that may be solved with numerical approaches, but this is computationally costly as the processes grow in complexity. In a new approach, dynamical processes are modelled with closed-form continuous-depth artificial neural networks. Improved efficiency in training and inference is demonstrated on various sequence modelling tasks including human action recognition and steering in autonomous driving.
Predicting the properties of a molecule from its structure with high accuracy is a crucial problem in digital drug design. Instead of sequence features, Zeng and colleagues use an image representation of a large collection of bioactive molecules to pretrain a model that can be fine-tuned on specific property prediction tasks.
Computational methods are important for interpreting missense variants in genetic studies and clinical testing. Zhang and colleagues develop a method based on graph attention neural networks to predict pathogenic missense variants. The method pools information from functionally correlated positions and can improve the interpretation of missense variants.
Predicting disease progression is an important medical problem, but it can be challenging for end-to-end machine learning approaches. Han and colleagues demonstrate that generative models can work together with medical experts to jointly predict the progression of a disease, osteoarthritis.
To be useful in human life, robots need to learn the social rules of human society. Zhou et al. investigate the social rules that apply in spaces mutually occupied by humans and robots. The authors develop a social locomotion model for a mobile robot and implement it for socially aware navigation.