Lung cancer is the second most common cancer in incidence and the leading cause of cancer deaths worldwide. Finding ways to reduce cases and to deal with those affected earlier is a medical imperative.
A new medical tool uses takes health records and uses these to predict people’s risk of developing lung cancer within the next 10 years. The assessment of the tool shows a very good predictive power. An important component of lung cancer screening is with catching the condition early since the earlier the cancer is detected, the better the survival rates.
A tool has been jointly developed between researchers from the University of Oxford and the University of Nottingham. The system is called ‘CanPredict’, and it is able to identify those most at risk of developing lung cancer across a decade. For those indicated to be at a greater risk, the software can alter medics so that individuals can be brought forward for screening tests earlier.
This proactive initiative not only save lives; it also saves time and money for the health system.
The artificial intelligence was developed and tested using the anonymised health records of over 19 million adults from across the U.K. The system was able to identify common factors which might be used to statistically predict their risk of developing the cancer. Factors such as smoking, age, ethnicity, body mass index, medical conditions and social deprivation (and others). Each of these factors was considered as part of the analysis.
The CanPredict tool correctly identified more people who went on to develop lung cancer and was more sensitive than current recommended methods of predicting risk, across 5-, 6-, and 10-year forecasts.
One of the developers, Professor Fergus Gleeson (University of Oxford) explains the importance of early lung cancer detection: “Around 48,500 people are diagnosed with lung cancer each year in the U.K. In its early stages, there are usually no obvious signs or symptoms, and it can go undetected for some time. Using a technique called low-dose computerised tomography (CT) for lung cancer screening we can catch this disease and treat it earlier, and that improves people’s outcomes.”
With this lies a problem since this type of screening is not something the health system can achieve for a large population. Therefore, the health system needs a mechanism to target those at the greatest risk and put them forward for screening.
The answer is with CanPredict, which examines existing patient health records and objectively prioritises patients and alerting their medical doctors that they might benefit from further screening
The new tool has been reported to the journal Lancet Respiratory Medicine. The article is titled: “Predicting the future risk of lung cancer: development, and internal and external validation of the CanPredict (lung) model in 19·67 million people and evaluation of model performance against seven other risk prediction models.”
The research was part of the DART (The Integration and Analysis of Data using Artificial Intelligence to Improve Patient Outcomes with Thoracic Diseases) project, funded by Innovate UK (UK Research and Innovation).
