Artificial intelligence could be used in the future to help guide when to use mechanical ventilation and the likelihood of complications in the ventilation of patients. This is according to the first systematic review of studies in this area, led by clinicians at Guy’s and St Thomas’ NHS Foundation Trust.

The review found 1,342 papers on AI and mechanical ventilation and looked in detail at 95 of these. They found that many were looking at the early testing of AI technology and models. One was already at the next stage of clinical trials in patients, with many technologies on the cusp of this step.

The team of academics at Guy’s and St Thomas’ and King’s College London made recommendations for further transparency, to help avoid bias and to facilitate rapid developments in this field. {module title="INSIDE STORY"} 

Artificial intelligence shows great promise in guiding treatment in many diseases. Its ability to analyze large amounts of data could help clinicians in their decision-making by calculating complex probabilities which might take clinicians a lot of time and experience.

Mechanical ventilation in particular is considered an area where AI could help, as patients put on mechanical ventilation can vary hugely, and AI may help to personalize approaches to an individual’s characteristics. They may also be used to flag to a clinician exactly when a person should be taken off or put on to ventilation.

Of the 1,342 papers found in this area, the team looked in detail at 95 particularly relevant studies, where information specifically on AI applied to mechanical ventilation in humans was presented. They made recommendations for researchers to improve work in this field. These included improving the availability of data. They also recommended better reporting of characteristics like ethnicity and gender, to help scientists assess how well findings can be generalized across wider populations.

Dr. Luigi Camporota, consultant in intensive care medicine at Guy’s and St Thomas’ said: “Our systematic review of the literature revealed an exponential increase in the rate of publications on artificial intelligence as applied to mechanical ventilation in the past few years. Despite this increased scientific and clinical interest, artificial intelligence is still very little used in mechanical ventilators.”

Dr. Jack Gallifant, from the Centre for Human and Applied Physiological Sciences at King’s College London, said: “Artificial intelligence has the potential to improve the management of mechanical ventilation therapy. Our review highlights a need for greater code and data availability, and thorough validation that, combined with smaller bias, will facilitate translation of data science into improved patient care.”

Researchers have developed an AI model to help computers work more efficiently with a wider variety of languages. 

African languages have received little attention from computer scientists, so few natural language processing capabilities have been available to large swaths of the continent. The new language model, developed by researchers at the University of Waterloo’s David R. Cheriton School of Computer Science, begins to fill that gap by enabling computers to analyze text in African languages for many useful tasks.

The new neural network model, which the researchers have dubbed AfriBERTa, uses deep-learning techniques to achieve state-of-the-art results for low-resource languages. 

The neural language model works specifically with 11 African languages, such as Amharic, Hausa, and Swahili, spoken collectively by more than 400 million people. It achieves output quality comparable to the best existing models despite learning from just one gigabyte of text, while other models require thousands of times more data.

“Pretrained language models have transformed the way computers process and analyze textual data for tasks ranging from machine translation to question answering,” said Kelechi Ogueji, a master’s student in computer science at Waterloo. “Sadly, African languages have received little attention from the research community.”

“One of the challenges is that neural networks are bewilderingly text- and computer-intensive to build. And unlike English, which has enormous quantities of available text, most of the 7,000 or so languages spoken worldwide can be characterized as low-resource, in that there is a lack of data available to feed data-hungry neural networks.”

Most of these models work using a technique known as pretraining. To accomplish this, the researcher presented the model with text where some of the words had been covered up or masked. The model then had to guess the masked words. By repeating this process, many billions of times, the model learns the statistical associations between words, which mimics human knowledge of the language.

“Being able to pretrain models that are just as accurate for certain downstream tasks, but using vastly smaller amounts of data has many advantages,” said Jimmy Lin, the Cheriton Chair in Computer Science and Ogueji’s advisor. “Needing less data to train the language model means that less computation is required and consequently lower carbon emissions associated with operating massive data centers. Smaller datasets also make data curation more practical, which is one approach to reduce the biases present in the models.”

“This work takes a small but important step to bringing natural language processing capabilities to more than 1.3 billion people on the African continent.”

Assisting Ogueji and Lin in this research is Yuxin Zhu, who recently completed an undergraduate degree in computer science at Waterloo. Together, they present their research paper, Small data? No problem! Exploring the viability of pretrained multilingual language models for low-resource languages, at the Multilingual Representation Learning Workshop at the 2021 Conference on Empirical Methods in Natural Language Processing.