Can AI save lives? A recent cancer detection study suggests it can. Researchers from the Royal Marsden NHS foundation trust, Institute of Cancer Research, and Imperial College London conducted a study to analyze if artificial intelligence (AI) can detect recurrence in high-risk patients of non-small-cell lung cancer (NSCLC). Results from the OCTAPUS-AI study showed that AI has the capability to detect recurrence of the cancer more efficiently than current methods.
Using imaging and clinical data from over 900 patients from the UK and Netherlands following curative radiotherapy, doctors and researchers developed an AI algorithm. The model uses radiomics, a quantitative approach which extracts novel data and predictive biomarkers from medical imaging. The scientists used the measure of area under the curve (AUC) to measure the efficiency of this model. With an AUC score of 0.87, the algorithm showed better results than current technology which only scored 0.67.
The potential of AI to improve detection and diagnosis of diseases extends beyond just cancer. With the ability to process large sets of data, AI is being developed to detect and predict other diseases such as rare diseases. The UK has seen many startups developing AI-based solutions to healthtech, some of which have received government investments. For example, Mendelian, a rare-disease diagnostics startup, recently received close to £1.5 million from the government. In addition, the European Union is also teeming with AI healthtech companies such as Radiomics from Liége and DoMore Diagnostics from Norway.
AI does not plan to replace doctors, but instead assist them in providing better care for patients. AI could not only help with more accurate diagnostic and early detection, but also help to better guide selection of therapy to avoid over- and under-treatment. While some doubts have risen regarding the safety of AI, the potential of this technology to greatly improve lives cannot be overlooked.
