A group of researchers, scientists and doctors has created a Artificial Intelligence model to identify lung cancer accurately, and say it could speed up disease diagnoses. Along with this, fast track treatment can also be given to the patients.
As lung cancer is the most deadly disease then other cancers worldwide. Royal Marsden NHS foundation trust, the Institute of Cancer Research, London, and Imperial College London experts designed AI tool that identify the abnormal growth found in CT scans are cancerous or not.
According to the study, the algorithm performs more efficiently and effectively than current methods. Lancet’s eBioMedicine journal published this study.
As Dr Benjamin Hunter, a clinical oncology registrar at the Royal Marsden and a clinical research fellow at Imperial said “In the future, we hope it will improve early detection and potentially make cancer treatment more successful by highlighting high-risk patients and fast-tracking them to earlier intervention.”
For this research, the team of researchers, scientists and doctors use the CT scan of 500 patients with large lung nodules to develop an AI algorithm using radiomics. This technology can extract important information from medical images that are not easily visible to the human eye.
Area under the curve (AUC) measure is used in this study to see how effective the model was at predicting cancer. If the model get AUC of 1 it shows that the model is perfect and AUC of 0.5 tells that the model was randomly guessing.
With AUC of 0.87 the AI model could identify each nodule’s risk of cancer. In Brock score performance improved with score 0.67. In another comparable test Herder score had AUC of 0.83.
Hunter said “According to these initial results, our model appears to identify cancerous large lung nodules accurately. Next, we plan to test the technology on patients with large lung nodules in clinic to see if it can accurately predict their risk of lung cancer.”
The AI model could help doctors make quicker decisions about patients with abnormal growths who are currently considered moderate-risk.
Dr Richard Lee. the Libra study’s chief investigator said “Through this work, we hope to push boundaries to speed up the detection of the disease using innovative technologies such as AI.”
The information shared in this blog is for educational purposes only and is certainly not a substitute for medical advice. Please consult your healthcare practitioner for any medical needs.