Improving lung cancer diagnosis by combining exhaled-breath data and clinical parameters

Progress and challenges of developing volatile metabolites from exhaled breath as a biomarker platform

BACKGROUND

The multitude of metabolites generated by physiological processes in the body can serve as valuable biomarkers for many clinical purposes. They can provide a window into relevant metabolic pathways for health and disease, as well as be candidate therapeutic targets. A subset of these metabolites generated in the human body are volatile, known as volatile organic compounds (VOCs), which can be detected in exhaled breath. These can diffuse from their point of origin throughout the body into the bloodstream and exchange into the air in the lungs. For this reason, breath VOC analysis has become a focus of biomedical research hoping to translate new useful biomarkers by taking advantage of the non-invasive nature of breath sampling, as well as the rapid rate of collection over short periods of time that can occur. Despite the promise of breath analysis as an additional platform for metabolomic analysis, no VOC breath biomarkers have successfully been implemented into a clinical setting as of the time of this review.

AIM OF REVIEW

This review aims to summarize the progress made to address the major methodological challenges, including standardization, that have historically limited the translation of breath VOC biomarkers into the clinic. We highlight what steps can be taken to improve these issues within new and ongoing breath research to promote the successful development of the VOCs in breath as a robust source of candidate biomarkers. We also highlight key recent papers across select fields, critically reviewing the progress made in the past few years to advance breath research.

KEY SCIENTIFIC CONCEPTS OF REVIEW

VOCs are a set of metabolites that can be sampled in exhaled breath to act as advantageous biomarkers in a variety of clinical contexts.

Exhaled breath and urinary volatile organic compounds (VOCs) for cancer diagnoses, and microbial-related VOC metabolic pathway analysis: a systematic review and meta-analysis

BACKGROUND

The gradual evolution of the detection and quantification of volatile organic compounds (VOCs) has been instrumental in cancer diagnosis. The primary objective of this study was to assess the diagnostic potential of exhaled breath and urinary VOCs in cancer detection. As VOCs are indicative of tumor and human metabolism, our work also sought to investigate the metabolic pathways linked to the development of cancerous tumors.

MATERIALS AND METHODS

An electronic search was performed in the PubMed database. Original studies on VOCs within exhaled breath and urine for cancer detection with a control group were included. A meta-analysis was conducted using a bivariate model to assess the sensitivity and specificity of the VOCs for cancer detection. Fagan's nomogram was designed to leverage the findings from our diagnostic analysis for the purpose of estimating the likelihood of cancer in patients. Ultimately, MetOrigin was employed to conduct an analysis of the metabolic pathways associated with VOCs in relation to both human and/or microbiota.

RESULTS

The pooled sensitivity, specificity and the area under the curve for cancer screening utilizing exhaled breath and urinary VOCs were determined to be 0.89, 0.88, and 0.95, respectively. A pretest probability of 51% can be considered as the threshold for diagnosing cancers with VOCs. As the estimated pretest probability of cancer exceeds 51%, it becomes more appropriate to emphasize the 'ruling in' approach. Conversely, when the estimated pretest probability of cancer falls below 51%, it is more suitable to emphasize the 'ruling out' approach. A total of 14, 14, 6, and 7 microbiota-related VOCs were identified in relation to lung, colorectal, breast, and liver cancers, respectively. The enrichment analysis of volatile metabolites revealed a significant enrichment of butanoate metabolism in the aforementioned tumor types.

CONCLUSIONS

The analysis of exhaled breath and urinary VOCs showed promise for cancer screening. In addition, the enrichment analysis of volatile metabolites revealed a significant enrichment of butanoate metabolism in four tumor types, namely lung, colorectum, breast and liver. These findings hold significant implications for the prospective clinical application of multiomics correlation in disease management and the exploration of potential therapeutic targets.

Alteration of the Exhaled Volatile Organic Compound Pattern in Colorectal Cancer Patients after Intentional Curative Surgery-A Prospective Pilot Study

As current follow-up modalities for colorectal carcinoma (CRC) have restricted sensitivity, novel diagnostic tools are needed. The presence of CRC changes the endogenous metabolism, resulting in the release of a specific volatile organic compounds (VOC) pattern that can be detected with an electronic nose or AeonoseTM. To evaluate the use of an electronic nose in the follow-up of CRC, we studied the effect of curative surgery on the VOC pattern recognition using AeonoseTM. A prospective cohort study was performed, in which 47 patients diagnosed with CRC were included, all of whom underwent curative surgical resection. Breath testing was performed before and after surgery using the AeonoseTM. A machine learning model was developed by discerning between the 94 pre-and postoperative breath samples. The training model differentiated between the pre-and postoperative CRC breath samples with a sensitivity and specificity of 0.78 (95%CI 0.61-0.90) and 0.73 (95%CI 0.56-0.86), respectively, with an accuracy of 0.76 (95%CI 0.66-0.85), and an area under the curve of 0.79 (95%CI 0.68-0.89). The internal validation of the test set resulted in an accuracy of 0.75 (95%CI 0.51-0.91) and AUC of 0.82 (95%CI 0.61-1). In conclusion, our results suggest that the VOC pattern of CRC patients is altered by curative surgery in a short period, indicating that the exhaled VOCs might be closely related to the presence of CRC. However, to use AeonoseTM as a potential diagnostic tool in the clinical follow-up of CRC patients, the performance of the models needs to be improved through further large-scale prospective research.

Diagnosing Non-Small Cell Lung Cancer by Exhaled Breath Profiling Using an Electronic Nose: A Multicenter Validation Study

BACKGROUND

Despite the potential of exhaled breath analysis of volatile organic compounds to diagnose lung cancer, clinical implementation has not been realized, partly due to the lack of validation studies.

RESEARCH QUESTION

This study addressed two questions. First, can we simultaneously train and validate a prediction model to distinguish patients with non-small cell lung cancer from non-lung cancer subjects based on exhaled breath patterns? Second, does addition of clinical variables to exhaled breath data improve the diagnosis of lung cancer?

STUDY DESIGN AND METHODS

In this multicenter study, subjects with non-small cell lung cancer and control subjects performed 5 min of tidal breathing through the aeoNose, a handheld electronic nose device. A training cohort was used for developing a prediction model based on breath data, and a blinded cohort was used for validation. Multivariable logistic regression analysis was performed, including breath data and clinical variables, in which the formula and cutoff value for the probability of lung cancer were applied to the validation data.

RESULTS

A total of 376 subjects formed the training set, and 199 subjects formed the validation set. The full training model (including exhaled breath data and clinical parameters from the training set) were combined in a multivariable logistic regression analysis, maintaining a cut off of 16% probability of lung cancer, resulting in a sensitivity of 95%, a specificity of 51%, and a negative predictive value of 94%; the area under the receiver-operating characteristic curve was 0.87. Performance of the prediction model on the validation cohort showed corresponding results with a sensitivity of 95%, a specificity of 49%, a negative predictive value of 94%, and an area under the receiver-operating characteristic curve of 0.86.

INTERPRETATION

Combining exhaled breath data and clinical variables in a multicenter, multi-device validation study can adequately distinguish patients with lung cancer from subjects without lung cancer in a noninvasive manner. This study paves the way to implement exhaled breath analysis in the daily practice of diagnosing lung cancer.

CLINICAL TRIAL REGISTRATION

The Netherlands Trial Register; No.: NL7025; URL: https://trialregister.nl/trial/7025.

Clinical Scores, Biomarkers and IT Tools in Lung Cancer Screening-Can an Integrated Approach Overcome Current Challenges?

As most lung cancer (LC) cases are still detected at advanced and incurable stages, there are increasing efforts to foster detection at earlier stages by low dose computed tomography (LDCT) based LC screening. In this scoping review, we describe current advances in candidate selection for screening (selection phase), technical aspects (screening), and probability evaluation of malignancy of CT-detected pulmonary nodules (PN management). Literature was non-systematically assessed and reviewed for suitability by the authors. For the selection phase, we describe current eligibility criteria for screening, along with their limitations and potential refinements through advanced clinical scores and biomarker assessments. For LC screening, we discuss how the accuracy of computerized tomography (CT) scan reading might be augmented by IT tools, helping radiologists to cope with increasing workloads. For PN management, we evaluate the precision of follow-up scans by semi-automatic volume measurements of CT-detected PN. Moreover, we present an integrative approach to evaluate the probability of PN malignancy to enable safe decisions on further management. As a clear limitation, additional validation studies are required for most innovative diagnostic approaches presented in this article, but the integration of clinical risk models, current imaging techniques, and advancing biomarker research has the potential to improve the LC screening performance generally.

Non-invasive Exhaled Breath and Skin Analysis to Diagnose Lung Cancer: Study of Age Effect on Diagnostic Accuracy

Development of simple, fast, and non-invasive tests for lung cancer diagnostics is essential for clinical practice. In this paper, exhaled breath and skin were studied as potential objects to diagnose lung cancer. The influence of age on the performance of diagnostic models was studied. Gas chromatography in combination with mass spectrometry (MS) was used to analyze the exhaled breath of 110 lung cancer patients and 212 healthy individuals of various ages. Peak area ratios of volatile organic compounds (VOCs) were used for data analysis instead of VOC peak areas. Various machine learning algorithms were applied to create diagnostic models, and their performance was compared. The best results on the test data set were achieved using artificial neural networks (ANNs): classification of patients with lung cancer and young healthy volunteers: 88 ± 4% sensitivity and 83 ± 3% specificity; classification of patients with lung cancer and old healthy individuals: 81 ± 3% sensitivity and 85 ± 1% specificity. The difference between performance of models based on young and old healthy groups was minor. The results obtained have shown that metabolic dysregulation driven by the disease biology is too high, which significantly overlaps the age effect. The influence of tumor localization and histological type on exhaled breath samples of lung cancer patients was studied. Statistically significant differences between some parameters in these samples were observed. A possibility of assessing the disease status by skin analysis in the Zakharyin-Ged zones using an electronic nose based on the quartz crystal microbalance sensor system was evaluated. Diagnostic models created using ANNs allow us to classify the skin composition of patients with lung cancer and healthy subjects of different ages with a sensitivity of 69 ± 2% and a specificity of 68 ± 8% for the young healthy group and a sensitivity of 74 ± 7% and a specificity of 66 ± 6% for the old healthy group. Primary results of skin analysis in the Zakharyin-Ged zones for the lung cancer diagnosis have shown its utility, but further investigation is required to confirm the results obtained.

Diagnostic Performance of Electronic Noses in Cancer Diagnoses Using Exhaled Breath: A Systematic Review and Meta-analysis

IMPORTANCE

There has been a growing interest in the use of electronic noses (e-noses) in detecting volatile organic compounds in exhaled breath for the diagnosis of cancer. However, no systematic evaluation has been performed of the overall diagnostic accuracy and methodologic challenges of using e-noses for cancer detection in exhaled breath.

OBJECTIVE

To provide an overview of the diagnostic accuracy and methodologic challenges of using e-noses for the detection of cancer.

DATA SOURCES

An electronic search was performed in the PubMed and Embase databases (January 1, 2000, to July 1, 2021).

STUDY SELECTION

Inclusion criteria were the following: (1) use of e-nose technology, (2) detection of cancer, and (3) analysis of exhaled breath. Exclusion criteria were (1) studies published before 2000; (2) studies not performed in humans; (3) studies not performed in adults; (4) studies that only analyzed biofluids; and (5) studies that exclusively used gas chromatography-mass spectrometry to analyze exhaled breath samples.

DATA EXTRACTION AND SYNTHESIS

PRISMA guidelines were used for the identification, screening, eligibility, and selection process. Quality assessment was performed using Quality Assessment of Diagnostic Accuracy Studies 2. Generalized mixed-effects bivariate meta-analysis was performed.

MAIN OUTCOMES AND MEASURES

Main outcomes were sensitivity, specificity, and mean area under the receiver operating characteristic curve.

RESULTS

This review identified 52 articles with a total of 3677 patients with cancer. All studies were feasibility studies. The sensitivity of e-noses ranged from 48.3% to 95.8% and the specificity from 10.0% to 100.0%. Pooled analysis resulted in a mean (SE) area under the receiver operating characteristic curve of 94% (95% CI, 92%-96%), a sensitivity of 90% (95% CI, 88%-92%), and a specificity of 87% (95% CI, 81%-92%). Considerable heterogeneity existed among the studies because of differences in the selection of patients, endogenous and exogenous factors, and collection of exhaled breath.

CONCLUSIONS AND RELEVANCE

Results of this review indicate that e-noses have a high diagnostic accuracy for the detection of cancer in exhaled breath. However, most studies were feasibility studies with small sample sizes, a lack of standardization, and a high risk of bias. The lack of standardization and reproducibility of e-nose research should be addressed in future research.

Advances in lung cancer screening and early detection

Lung cancer is associated with a heavy cancer-related burden in terms of patients' physical and mental health worldwide. Two randomized controlled trials, the US-National Lung Screening Trial (NLST) and Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON), indicated that low-dose CT (LDCT) screening results in a statistically significant decrease in mortality in patients with lung cancer, LDCT has become the standard approach for lung cancer screening. However, many issues in lung cancer screening remain unresolved, such as the screening criteria, high false-positive rate, and radiation exposure. This review first summarizes recent studies on lung cancer screening from the US, Europe, and Asia, and discusses risk-based selection for screening and the related issues. Second, an overview of novel techniques for the differential diagnosis of pulmonary nodules, including artificial intelligence and molecular biomarker-based screening, is presented. Third, current explorations of strategies for suspected malignancy are summarized. Overall, this review aims to help clinicians understand recent progress in lung cancer screening and alleviate the burden of lung cancer.

Application of Artificial Intelligence in Lung Cancer

Simple Summary

Lung cancer is the leading cause of malignancy-related mortality worldwide. AI has the potential to help to treat lung cancer from detection, diagnosis and decision making to prognosis prediction. AI could reduce the labor work of LDCT, CXR, and pathology slides reading. AI as a second reader in LDCT and CXR reading reduces the effort of radiologists and increases the accuracy of nodule detection. Introducing AI to WSI in digital pathology increases the Kappa value of the pathologist and help to predict molecular phenotypes with radiomics and H&E staining. By extracting radiomics from image data and WSI from the histopathology field, clinicians could use AI to predict tumor properties such as gene mutation and PD-L1 expression. Furthermore, AI could help clinicians in decision-making by predicting treatment response, side effects, and prognosis prediction in medical treatment, surgery, and radiotherapy. Integrating AI in the future clinical workflow would be promising.

Abstract

Lung cancer is the leading cause of malignancy-related mortality worldwide due to its heterogeneous features and diagnosis at a late stage. Artificial intelligence (AI) is good at handling a large volume of computational and repeated labor work and is suitable for assisting doctors in analyzing image-dominant diseases like lung cancer. Scientists have shown long-standing efforts to apply AI in lung cancer screening via CXR and chest CT since the 1960s. Several grand challenges were held to find the best AI model. Currently, the FDA have approved several AI programs in CXR and chest CT reading, which enables AI systems to take part in lung cancer detection. Following the success of AI application in the radiology field, AI was applied to digitalized whole slide imaging (WSI) annotation. Integrating with more information, like demographics and clinical data, the AI systems could play a role in decision-making by classifying EGFR mutations and PD-L1 expression. AI systems also help clinicians to estimate the patient’s prognosis by predicting drug response, the tumor recurrence rate after surgery, radiotherapy response, and side effects. Though there are still some obstacles, deploying AI systems in the clinical workflow is vital for the foreseeable future.

The smell of lung disease: a review of the current status of electronic nose technology

There is a need for timely, accurate diagnosis, and personalised management in lung diseases. Exhaled breath reflects inflammatory and metabolic processes in the human body, especially in the lungs. The analysis of exhaled breath using electronic nose (eNose) technology has gained increasing attention in the past years. This technique has great potential to be used in clinical practice as a real-time non-invasive diagnostic tool, and for monitoring disease course and therapeutic effects. To date, multiple eNoses have been developed and evaluated in clinical studies across a wide spectrum of lung diseases, mainly for diagnostic purposes. Heterogeneity in study design, analysis techniques, and differences between eNose devices currently hamper generalization and comparison of study results. Moreover, many pilot studies have been performed, while validation and implementation studies are scarce. These studies are needed before implementation in clinical practice can be realised. This review summarises the technical aspects of available eNose devices and the available evidence for clinical application of eNose technology in different lung diseases. Furthermore, recommendations for future research to pave the way for clinical implementation of eNose technology are provided.

An Update on the Use of Exhaled Breath Analysis for the Early Detection of Lung Cancer

Lung cancer has historically been the main responsible for cancer associated deaths. Owing to this is our current inability to screen for and diagnose early pathological findings, preventing us from a timely intervention when cure is still achievable. Over the last decade, together with the extraordinary progress in therapeutical alternatives in the field, there has been an ongoing search for a biomarker that would allow for this. Numerous technologies have been developed but their clinical application is yet to come. In this review, we provide an update on volatile organic compounds, a non-invasive method that can hold the key for detecting early metabolic pathway changes in carcinogenesis. For its compilation, web-based search engines of scientific literature such as PubMed were explored and reviewed, using articles, research, and papers deemed meaningful by authors discretion. After a brief description, we depict how this technique can complement current methods and present the value of electronic noses in the identification of the “breathprint”. Lastly, we bring some of the latest updates in the field together with the current limitations and final remarks.

Using a stepwise approach to simultaneously develop and validate machine learning based prediction models

Accurate diagnosis of a disease is essential in healthcare. Prediction models, based on classical regression techniques, are widely used in clinical practice. Machine Learning (ML) techniques might be preferred in case of a large amount of data per patient and relatively limited numbers of subjects. However, this increases the risk of overfitting, and external validation is imperative. However, in the field of ML, new and more efficient techniques are developed rapidly, and if recruiting patients for a validation study is time consuming, the ML technique used to develop the first model might have been surpassed by more efficient ML techniques, rendering this original model no longer relevant. We demonstrate a stepwise design for simultaneous development and validation of prediction models based on ML techniques. The design enables - in one study - evaluation of the stability and robustness of a prediction model over increasing sample size as well as assessment of the stability of sensitivity/specificity at a chosen cut-off. This will shorten the time to introduction of a new test in health care. We finally describe how to use regular clinical parameters in conjunction with ML based predictions, to further enhance differentiation between subjects with and without a disease.

Calculated indices of volatile organic compounds (VOCs) in exhalation for lung cancer screening and early detection

BACKGROUND

Breath analysis is a promising noninvasive technique that offers a wide range of opportunities to facilitate early diagnosis of lung cancer (LC).

METHOD

Exhaled breath samples of 352 subjects including 160 with lung cancer (LC), 70 with benign pulmonary nodule (BPN) and 122 healthy controls (HC) were analyzed through thermal desorption coupled with gas chromatography-mass spectrometry (TD-GC-MS) to obtain the metabolic information from volatile organic compounds (VOCs). Statistical classification models were used to find diagnostic clusters of VOCs for the discrimination of HC, BPN and LC patients' early and advanced stages, as well as subtypes of LC. Receiver operator characteristics (ROC) curves with 5-fold validations were used to evaluate the accuracy of these models.

RESULTS

The analysis revealed that 20, 19, 19, and 20 VOCs discriminated LC from HC, LC from BPN, histology and LC stages respectively. The calculated diagnostic indices showed a large area under the curve (AUC) to distinguish HC from LC (AUC: 0.987, 95 % confidence interval (CI): 0.976-0.997), BPN from LC (AUC: 0.809, 95 % CI: 0.758-0.860), NSCLC from SCLC (AUC: 0.939, 95 % CI: 0.875-0.995) and Stage III from stage III-IV (AUC: 0.827, 95 % CI: 0.768-0.886). The comparison between the high-risk groups (BPN and HC smokers) and early stages LC resulted in the AUC of 0.756 (95 %CI: 0.681-0.817) for BPN vs. early stage LC and AUC of 0.986 (95 % CI: 0.972-0.994) for HC smoker vs. early stage LC.

CONCLUSION

Volatome of breath of the LC patients was significantly different from that of both BPN patients and HC and showed an ability of distinguishing early from advance stage LC and NSCLC from SCLC. We conclude that the volatome has a potential to help improve early diagnosis of LC.

The promises and challenges of early non-small cell lung cancer detection: patient perceptions, low-dose CT screening, bronchoscopy and biomarkers

Lung cancer survival statistics are sobering with survival ranking among the poorest of all cancers despite the addition of targeted therapies and immunotherapies. However, improvements in tools for early detection hold promise. The Nederlands–Leuvens Longkanker Screenings Onderzoek (NELSON) trial recently corroborated the findings from the previous National Lung Screening Trial low‐dose Computerised Tomography (NLST) screening trial in reducing lung cancer mortality. Biomarker research and development is increasing at pace as the molecular life histories of lung cancers become further unravelled. Low‐dose CT screening (LDCT) is effective but targets only those at the highest risk and is burdensome on healthcare. An optimally designed CT screening programme at best will only detect a low proportion of overall lung cancers as only those at very high‐risk meet screening criteria. Biomarkers that help risk stratify suitable patients for LDCT screening, and those that assist in determining which LDCT detected nodules are likely to represent malignant disease are needed. Some biomarkers have been proposed as standalone lung cancer diagnosis tools. Bronchoscopy technology is improving, with better capacity to identify and obtain samples from early lung cancers. Clinicians need to be aware of each early lung cancer detection method’s inherent limitations. We anticipate that the future of early lung cancer diagnosis will involve a synergistic, multimodal approach, combining several early detection methods.