Volume 4 Issue 10, October 2022

There is a tendency among AI researchers to use the concepts of democracy and democratization in ways that are only loosely connected to their political and historical meanings. We argue that it is important to take the concept more seriously in AI research by engaging with political philosophy.

To deliver value in healthcare, artificial intelligence and machine learning models must be integrated not only into technology platforms but also into local human and organizational ecosystems and workflows. To realize the promised benefits of applying these models at scale, a roadmap of the challenges and potential solutions to sociotechnical transferability is needed.

Identifying epidemic hotspots in a timely way with syndromic surveillance can provide highly valuable information for public health policy. A machine learning early indicator model that uses highly granular data from digitalized healthcare-seeking behaviour, including from Google Trends and National Health Service Pathways calls, can identify SARS-CoV-2 risk at small geographic scales. The model can retrospectively identify hotspots in the United Kingdom for various variants in 2020 and 2021 before the wider spread and growth of these variants being confirmed by clinical data.

Earth system models (ESMs) are powerful tools for simulating climate fields, but weather forecasting and in particular precipitation prediction with ESMs are challenging. A generative adversarial network, constrained by the sum of global precipitation, is developed that substantially improves ESM predictions of spatial patterns and intermittency of daily precipitation.

The space of possible proteins is vast, and optimizing proteins for specific target properties computationally is an ongoing challenge, even with large amounts of data. Castro and colleagues combine a transformer-based model with regularized prediction heads to form a smooth and pseudoconvex latent space that allows for easier navigation and more efficient optimization of proteins.

Cell type annotation is a core task for single cell RNA-sequencing, but current bioinformatic tools struggle with some of the underlying challenges, including high dimensionality, data sparsity, batch effects and a lack of labels. In a self-supervised approach, a transformer model called scBERT is pretrained on millions of unlabelled public single cell RNA-seq data and then fine-tuned with a small number of labelled samples for cell annotation tasks.

Saliency methods are used to localize areas of medical images that influence machine learning model predictions, but their accuracy and reliability require investigation. Saporta and colleagues evaluate seven saliency methods using different model architectures, and find that saliency maps perform worse than a human radiologist benchmark.

Predicting patient-specific clinical drug responses from cell-line screens using machine learning is challenging. He and colleagues develop a deep learning method to predict patient-specific clinical responses from cell-line and other disease models for drug discovery and personalized medicine.

The haptic interface is an essential part of human–machine interfaces where tactile information is delivered between human and machine. Yao et al. develop a soft, ultrathin, miniaturized and wireless electrotactile system that allows virtual tactile information to be reproduced over the hand.