Volume 5 Issue 2, February 2023

Despite the promise of medical artificial intelligence applications, their acceptance in real-world clinical settings is low, with lack of transparency and trust being barriers that need to be overcome. We discuss the importance of the collaborative process in medical artificial intelligence, whereby experts from various fields work together and tackle transparency issues and build trust over time.

Predicting RNA degradation is a fundamental task in designing RNA-based therapeutic agents. Dual crowdsourcing efforts for dataset creation and machine learning were organized to learn biological rules and strategies for predicting RNA stability.

Co-designing hardware platforms and neural network software can help improve the computational efficiency and training affordability of deep learning implementations. A new approach designed for graph learning with echo state neural networks makes use of in-memory computing with resistive memory and shows up to a 35 times improvement in the energy efficiency and 99% reduction in training cost for graph classification on large datasets.

Disease phenotypes can be predicted from genetic profiles, but diseases with complex, non-additive interactions between genes are hard to disentangle. An approach called DiseaseCapsule makes use of capsule networks to identify the hierarchical structure in genomic data and can predict complex diseases such as amyotrophic lateral sclerosis with high accuracy.

Predicting drug–target interaction with computational models has attracted a lot of attention, but it is a difficult problem to generalize across domains to out-of-distribution data. Bai et al. present here a method that aims to model local interactions of proteins and drug molecules while being interpretable and provide cross-domain generalization.

In situations where some risk of injury is unavoidable for self-driving vehicles, how risk is distributed becomes an ethical question. Geisslinger and colleagues have developed a planning algorithm that takes five ethical principles into account and aims to comply with the emerging EU regulatory recommendations.

Reinforcement learning is a powerful technique to learn complex behaviours, but in the context of self-driving vehicles it might result in unsafe behaviour in previously unseen situations. Cao et al. create a confidence-aware method that improves through reinforcement learning but reverts to safe behaviour when a situation is new.

When learning a causal model from data, deriving counterfactual examples from the model can help to evaluate how plausible the mechanisms are and create hypotheses that can be tested with new data. Vlontzos and colleagues develop a deep learning-based method for answering counterfactual queries that can deal with categorical variables, rather than only binary ones, using the notion of ‘counterfactual ordering’.

The mechanical signals of the laryngeal vocal organ have not been well utilized by human speech processing technology. The authors develop a prototype of a wearable artificial throat that can sense speech- and vocalization-related actions. The results suggest a new technological pathway for speech recognition and interaction systems.

The organizers of the EvalRS recommender systems competition argue that accuracy should not be the only goal and explain how they took robustness and fairness into account.