Many people in the world today may be wondering how to limit the impact of artificial intelligence (lack of privacy, copyright issues, unemployment, world domination, etc.). But that doesn’t mean AI doesn’t have great potential to improve the quality of life on Earth.
One such application is healthcare. The deployment of AI with the ability to process big data sets could lead to significant advances in predictive diagnostics, including early cancer detection. More research is needed, but one of the latest studies in this field shows promising results for AI-assisted diagnosis of lung cancer.
Physicians and researchers from the Royal Marsden NHS Foundation trust, Institute of Cancer Research, and Imperial College London have built an AI algorithm that can diagnose cancer growth more efficiently than current methods.
In a study named OCTAPUS-AI, researchers used images and clinical data from over 900 patients in the UK and the Netherlands after curative radiation therapy to develop and test an ML algorithm to determine how well the model would respond to recurrence. I checked if it can be predicted accurately.
Specifically, this study investigated whether AI could help identify the risk of cancer recurrence in patients with non-small cell lung cancer (NSCLC). Researchers used his CT scans to develop his AI algorithms using radiomics. This is a quantitative approach to extract novel data and predictive biomarkers from medical images.
A research algorithm that outperforms current technology
NSCLC patients account for 85% of lung cancer cases. Although the disease is often treatable if detected early, the cancer recurs in more than one-third of her patients. The study found that using an algorithm could ultimately help clinicians identify recurrences earlier in high-risk patients.
Scientists used a measure called the area under the curve (AUC) to check how efficient the model was at detecting cancer. A perfect 100% accuracy score would be 1, but a model that was purely guessing 50-50 would get 0.5. In this study, the AI algorithm built by the researchers scored 0.87. This can be compared to his 0.67 score for technology currently in use.
Dr Sumeet Hindocha, Clinical Oncology Specialist Registrar, The Royal Marsden NHS Foundation Trust and Clinical Research Fellow, Imperial College London, Said“Next, we would like to test this model in newly diagnosed NSCLC patients and follow up to see if the model can accurately predict recurrence risk.”
Practitioner and Patient Support
Rather than thinking that AI will replace doctors, most people now see AI in health tech as a tool to help healthcare professionals provide the best care possible. Improving bedside mannersDespite investors becoming increasingly risk averse over the past year, the healthcare AI sector remains expected to grow It will grow from nearly $14 billion in 2023 to $103 billion by 2028.
The UK is flooded with AI healthtech startups. Many are focused on drug development, genomics analysis, or more consumer-centric telemedicine symptom checks and wearables. These include his Mendelian, who received nearly £1.5m to deploy AI-based solutions for rare disease diagnosis as part of government investment in his AI technology within the NHS. includes things.
The rest of Europe also has a sizeable share of diagnostic AI startups. Among them is Liège-based Radiomics. The company focuses on solid tumor detection and phenotypic quantification 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 treatment choices to avoid over- and under-treatment.
On the other hand, a few percentage points of more accurate diagnoses, while important for affected individuals, may not be the only positive impact AI can have on our systems of care.
According to Eric Topol, author of Deep Medicine: How Artificial Intelligence Brings Healthcare Back to Humans“The greatest opportunity offered by AI is not to reduce errors and workload, nor to cure cancer. It’s an opportunity to recover.”
