Much of the world may be concerned right now about how to limit the impact (lack of privacy, copyright issues, job losses, world domination, etc.) of artificial intelligence. However, that doesn’t mean there isn’t tremendous potential for AI to improve the quality of life on Earth.
One such application is healthcare. With the ability to process large data sets, the use of AI could lead to significant advances in predictive diagnostics, including early detection of cancer. While more research is needed, one of the latest studies in this field shows promising results for AI-assisted diagnosis of lung cancer.
Doctors and researchers at the Royal Marsden NHS Foundation Trust, the Institute of Cancer Research and Imperial College London have developed an AI algorithm they say can diagnose cancerous ulcers more efficiently than current methods.
In the study, dubbed OCTAPUS-AI, researchers used imaging and clinical data from over 900 patients from the UK and the Netherlands after curative radiation therapy to develop and test ML algorithms to see how accurate the Models can predict recurrence.
Specifically, the study examined whether AI could help identify the risk of cancer coming back in patients with non-small cell lung cancer (NSCLC). Researchers used CT scans to develop an AI algorithm using radiomics. This is a quantitative approach that extracts novel data and predictive biomarkers from medical imaging.
Research algorithm superior to current technology
NSCLC patients account for 85% of lung cancer cases. While the disease is often treatable if caught early, the cancer returns in over a third of patients. The study found that with the algorithm, clinicians may be able to detect recurrence earlier in high-risk patients.
The scientists used a measure called area under the curve (AUC) to see how efficient the model was at detecting cancer. A perfect 100% accuracy score would be a 1, while a model that only guessed 50-50 would get a 0.5. In the study, the AI algorithm developed by the researchers scored 0.87. This can be compared to the 0.67 rating of the technology currently in use.
“Next, we want to explore more advanced machine learning techniques like deep learning to see if we can get even better results,” Dr. Sumeet Hindocha, Clinical Oncology Specialist Registrar at The Royal Marsden NHS Foundation Trust and Clinical Research Fellow at Imperial College London, called. “We then want to test this model on newly diagnosed NSCLC patients and follow them to see if the model can accurately predict their risk of recurrence.”
Support for practitioners – and patients
Rather than believing that it will replace doctors, most today see AI in health tech as a tool to help doctors provide the best possible care – including improved bed manners. Although investors have gradually become more risk-averse over the past year, the healthcare AI sector is still active expected to grow from nearly $14 billion in 2023 to $103 billion in 2028.
The UK is teeming with AI healthtech startups. Many are focused on drug development, genomic analysis, or more consumer-focused telemedicine symptom testing and wearables. However, some are striving to improve the detection and diagnosis of diseases. These include Mendelian, who has just been awarded nearly £1.5million to roll out his AI-based solution for rare disease diagnostics as part of the government’s investment in AI technology within the NHS.
The rest of Europe also has its fair share of diagnostic AI startups. Among them is Radiomics from Liège. The Company is focused on the detection and phenotypic quantification of solid tumors based on standard-of-care imaging. In Norway, DoMore Diagnostics uses AI and deep learning to increase the prognostic and predictive value of cancer tissue biopsies. The company’s founders also say it could help guide therapy choices to avoid over- and under-treatment.
In the meantime, a few percentage points of more accurate diagnoses, important as they are for the person affected, may not be the only positive impact AI could have on our care systems.
According to Eric Topol, the author of Deep Medicine: How artificial intelligence can make healthcare human again“The greatest opportunity AI offers is not the reduction of errors or workload, or even the cure of cancer: it is the opportunity to restore the precious and time-honoured connection and trust – the human touch – between patients and physicians.”
Comments are closed.