A new microscope, using artificial intelligence (AI), can detect malaria parasites in blood just as accurately as human experts using standard diagnostic processes. The microscope can reduce the pressure on microscopists.
Malaria is an infectious disease caused by single-celled parasites. The parasite spreads among humans via mosquitoes. Figures from the World Health Organization (WHO) show that in 2021 about 247 million infections with malaria will have been discovered worldwide. The number of deaths per year cannot be determined with certainty, but the WHO estimates at 577,000 to 754,000 per year.
Reduce pressure on microscopists
Due to the large number of infections, detecting malaria puts considerable pressure on microscopists. For example, identifying malaria parasites requires expertise, while the workload is large. An international team of researchers wants to reduce this pressure. They rely on AI for this.
The researchers combine AI software with an automated microscope. This combination enables them to detect malaria in an automated manner, with an accuracy comparable to that of human experts.
Accuracy of 88%
The research was carried out at University College London Hospitals, part of the British National Health Services (NHS). The researchers collected 1,200 blood samples from travelers who returned to the United Kingdom (UK) from malaria areas. These blood samples were assessed both manually and with the AI system. In the manual analysis, a total of 133 samples were assessed as positive for malaria. The AI system assessed 99 samples as positive. This translates to an accuracy of 88%.
“With an 88% accuracy rate in diagnoses compared to microscopists, the IA system identifies malaria parasites almost – but not quite – as well as experts,” said Dr Roxanne Rees-Channer, researchers at The Hospital for Tropical Diseases at UCLH.
‘Big win for AI algorithms’
“This level of performance in a clinical setting is a major win for AI algorithms targeting malaria. It indicates that in the right circumstances the system can indeed be a clinically useful tool for malaria diagnoses.”
The system consists of both hardware and software. For example, an automated microscope scans the blood samples. Algorithms specifically trained to recognize malaria parasites then check the images. In this way, they not only determine whether malaria parasites are present, but also in what quantities.
Lower workload and less chance of human error
The benefits are broad, say the researchers. They not only point to the heavy workload on microscopists, but also to fatigue and the risk of human error. “Even specialized microscopists can get tired and make mistakes, especially when under a lot of pressure,” explains Rees-Channer. “Automated diagnosis of malaria using AI can reduce this pressure for microscopists and create a viable patient burden.”
The researchers emphasize that the accuracy of their AI system is not yet up to par. For example, the system incorrectly identified 122 samples as positive. In practice, this can lead to patients receiving unnecessary medication. The AI system must therefore be further developed.
More information is here available.
Author: Wouter Hoeffnagel
Photo: Mohamed Nuzrath via Pixabay
2023-08-30 02:01:06
#microscope #detects #malaria #Manufacturing #Industry #News