Volatile organic compounds (VOCs) are an increasingly meaningful method for the early detection of various types of cancers, including lung cancer, through non-invasive methods. Traditional cancer detection techniques such as biopsies, imaging, and blood tests, though effective, often involve invasive procedures or are costly, time consuming, and painful. Recent advancements in technology have led to the exploration of VOC detection as a promising non-invasive and comfortable alternative. VOCs are organic chemicals that have a high vapor pressure at room temperature, making them readily detectable in breath, urine, and skin. The present study leverages artificial intelligence (AI) and machine learning algorithms to enhance classification accuracy and efficiency in detecting lung cancer through VOC analysis collected from exhaled breath air. Unlike other studies that primarily focus on identifying specific compounds, this study takes an agnostic approach, maximizing detection efficiency over the identification of specific compounds focusing on the overall compositional profiles and their differences across groups of patients. The results reported hereby uphold the potential of AI-driven techniques in revolutionizing early cancer detection methodologies towards their implementation in a clinical setting.
Background: Lung cancer (LC) is the leading cause of cancer-related deaths worldwide. Effective screening strategies for early diagnosis that could improve disease prognosis are lacking. Non-invasive breath analysis of volatile organic compounds (VOC) is a potential method for earlier LC detection. This study explores the association of VOC profiles with artificial intelligence (AI) to achieve a sensitive, specific, and fast method for LC detection. Patients and methods: Exhaled breath air samples were collected from 123 healthy individuals and 73 LC patients at two clinical sites. The enrolled patients had LC diagnosed with different stages. Breath samples were collected before undergoing any treatment, including surgery, and analyzed using gas chromatography coupled to ion-mobility spectrometry (GC-IMS). AI methods classified the overall chromatographic profiles. Results: GC-IMS is highly sensitive, yielding detailed chromatographic profiles. AI methods ranked the sets of exhaled breath profiles across both groups through training and validation steps, while qualitative information was deliberately not taking part nor influencing the results. The K-nearest neighbor (KNN) algorithm classified the groups with an accuracy of 90% (sensitivity = 87%, specificity = 92%). Narrowing the LC group to those only in early-stage IA, the accuracy was 90% (sensitivity = 90%, specificity = 93%). Conclusions: Evaluation of the global exhaled breath profiles using AI algorithms enabled LC detection and demonstrated that qualitative information may not be required, thus easing the frustration that many studies have experienced so far. The results show that this approach coupled with screening protocols may improve earlier detection of LC and hence its prognosis.
Background Anatomical surgical resection is the treatment of choice for early-stage non–small cell lung cancer (NSCLC) and is a part of the multimodality treatment for resectable, locally advanced NSCLC. Local, regional and distant recurrence is the most common cause of treatment failure after resection. Multiple studies have recommended chest computed tomography (CT) for lung cancer (LC) patient’s follow-up. Even though adopting this strategy, the recurrence will only be detected months after the onset of the disease once imaging changes will only occur with a high tumor burden. Methods Breath analysis is a promising technology and useful addition to the currently available modalities to achieve lung cancer diagnosis and management. The volatile organic compounds (VOCs) produced as end-products of metabolism by the LC cells (and present on the exhaled breath of the patients) seem to have a unique pattern that can be used as a tool to detect lung cancer (VOC profile). Discussion The BREATH-PATH study aims to establish a VOC profile for all LC patients at diagnosis and understand its variations with the different implemented treatments in order to find response patterns. By understanding these patterns and identifying their deviations thereof with disease relapse supported by imaging methods we will be able to validate the breath analysis as a useful tool for LC recurrence detection. This study intents not only to reiterate the methods’ efficacy but also to understand how high its sensitivity is in detecting a tumor recurrence, allowing breath analysis to be integrated into clinical decision algorithms.