With lung cancer being the leading cause of cancer-related deaths worldwide, advancements in AI-powered healthcare technology are offering newfound hope. Over the span of the next few decades, AI is poised to revolutionize lung cancer outcomes by detecting cancer at its earliest stages. By improving upon and providing proactive detection by accelerating the identification of high-risk patients, this technology has the capability to dramatically lower mortality rates.
A major milestone occurred to the progress of AI’s integration in lung-cancer screenings due to the National Lung Screening Trial (NLST), published in 2011, which showed that a 20% reduction in Lung Cancer Deaths was possible when high-risk populations were screened using CT. This discovery is what pushed the National Preventive Services Task Force to recommend Lung Cancer screening for high-risk patients, which in turn triggered a breakthrough in reimbursement compliance for CT-based Lung Cancer screening by Medicare. It was also at this same time that the first AI system for the detection of lung nodules in CT scans was approved by the FDA, marking the transformative beginning of the connection between AI and lung cancer diagnosis.
Today, over a dozen nodule detectors are being sold in the US and Europe. CT resolution has improved, radiation dose has decreased, and the early detection of lung cancer through CT screening has been shown to save lives. A 20-year follow-up study published by I-ELCAP demonstrated that Lung Cancer detected early through CT screening can essentially be cured. The reported 20-year survival was just over 80% which is a huge leap from the traditional methods that are often impacted by late-stage diagnosis in many cases, where lung nodules have been inaccurately assigned in their health status and potentially benign composition.
Through the power of AI integration, we now have a highly sensitive, non-invasive test in CT screening, which is available nearly everywhere in developed nations. This software has improved sensitivity with enhanced data refinement, providing radiologists the ability to conduct examinations faster and more accurately.
A few key challenges remain despite industry momentum. One of them is that though sensitivity is high for the detection of Lung Cancer, rates of specificity are quite low. Another is the challenging process of identifying high-risk patients for screening. Fortunately, new data shows that consistent AI integration and refinement in this area can help address and improve both of these more sensitive elements.
The abundance of false positives creates a huge problem for health systems. Ruling out cancer by dramatically increasing lung biopsies is not the answer, as these are quite physically invasive and expensive, along with often time-consuming and potentially counterproductive, so when nodules are found (in about 40% of Chest CT Scans), each nodule is tracked, whether or not a health necessity.
To track a patient’s nodule, follow-up scans are performed months later (frequently multiple times) in an attempt to detect cancer-like growth. This process is expensive and administratively difficult, which is said to complicate things, causing patient compliance to consequently display lower rates with these time-demanding appointments. The choice to integrate AI in radiology and lung-cancer screenings is to increase proactivity and early-stage screenings, so ensuring accurate data from the first appointment can foster higher patient engagement with fewer unnecessary subsequent medical visits.
This is why, to help resolve these ongoing issues, we are looking to AI. A study published in 2023 showed that an AI tool can identify high-risk and low-risk nodules. Smaller nodules, for example, have a less than 1% chance of being malignant, but when flagged by the AI as high risk, the likelihood of malignancy increases to close to 20%. This significant jump in proactive malignancy assignment showcases the immense potential and medical benefit in its use.
While identifying patients at high risk using smoking history makes sense, data continue to emerge that it is not sufficient. Approximately 20% of lung cancers that are diagnosed this year will be in never-smokers. Additionally, a 2022 study showed that when incidentally found nodules are tracked, about half of the Lung Cancers found were in patients who did not qualify for Lung Cancer Screenings, as they were non-smokers or had not smoked long enough to satisfy the screening guidelines. These findings are notable as Lung Cancer in never smokers has been rising significantly; as a result, we need to expand our scope of who is considered high-risk to increase early detection. Incorporating multiple risk factors into the decision to screen for lung cancer is something AI can do well by analyzing the vast amounts of data available efficiently. This personalized approach can help us in turning data into a diagnosis faster than ever, allowing for expansion of who is able to be identified as a high-risk patient.
Lung cancer remains the biggest cancer killer and the prognosis remains quite poor when caught in later stages, when patients are symptomatic. Despite these obstacles, there exists great hope on the horizon for the future of lung cancer screenings.
When it comes to screening for lung cancer, recommending an ‘earlier the better’ approach is a grave understatement from the major difference proactive detection can make prior to malignancy. As humans, we do all that we physically can to catch abnormalities and pre-cancerous growth with the trained eye and careful examination, but with entering this new age, harnessing the power of AI’s knowledgeable database able to assign high-accuracy lung nodule scores, we need not only to default to our own capabilities. What is essentially a second eye trained on millions of datapoints from previous scans and precise diagnoses, is set to transform lung-cancer radiology–detecting earlier, mitigating unnecessary biopsies, and saving lives.
About Chris Wood
Chris Wood is the CEO of Reveal Dx, a Seattle-based software company whose vision is to dramatically improve lung cancer outcomes. Chris Wood is fighting cancer by building companies that enable early diagnosis through AI applied to medical imaging. A medical physicist and seasoned CEO/CTO, he brings exceptional radiology industry expertise. Over the course of his career, Chris has founded three medical imaging software startups, each achieving groundbreaking milestones and successful exits.
His first startup became the first to receive FDA 510(k) clearance for computer-aided detection of breast cancer. His second now powers the workflow for 25% of all radiology exams in the United States. His third was the first medical imaging AI company to achieve reimbursement in the European Union.
