Exploring Volatile Organic Compounds in Breath for High-Accuracy Prediction of Lung Cancer

Tsou, Ping-Hsien; Lin, Zong-Lin; Pan, Yu-Chiang; Yang, Hsuan-Chia; Chang, Chiung‐Fang; Liang, Sheng-Kai; Wen, Yueh-Feng; Chang, Chia Hao; Chang, Li-Chien; Yu, Kai-Lun; Liu, Chia-Jung; Keng, Li‐Ta; Lee, Meng-Rui; Ko, Jen-Chung; Huang, Guan‐Hua; Li, Yaw-Kuen

doi:10.3390/cancers13061431

Cited by 49 publications

(37 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method is repeated until the gap between successive models is negligible, indicating that we have found the best possible model. XGBoost has been successfully applied to medicine tasks, such as prediction of diabetes risk [ 10 ], hypertension [ 11 ], drug response [ 12 ], smoking-induced diseases [ 13 ], lung cancer [ 14 ], mortality in elderly patients [ 15 ] or bone mass loss [ 16 ].…”

Section: Methodsmentioning

confidence: 99%

Age-Stratified Analysis of COVID-19 Outcome Using Machine Learning Predictive Models

et al. 2022

View full text Add to dashboard Cite

Since the emergence of COVID-19, most health systems around the world have experienced a series of spikes in the number of infected patients, leading to collapse of the health systems in many countries. The use of clinical laboratory tests can serve as a discriminatory method for disease severity, defining the profile of patients with a higher risk of mortality. In this paper, we study the results of applying predictive models to data regarding COVID-19 outcome, using three datasets after age stratification of patients. The extreme gradient boosting (XGBoost) algorithm was employed as the predictive method, yielding excellent results. The area under the receiving operator characteristic curve (AUROC) value was 0.97 for the subgroup of patients up to 65 years of age. In addition, SHAP (Shapley additive explanations) was used to analyze the feature importance in the resulting models.

show abstract

Section: Methodsmentioning

confidence: 99%

Age-Stratified Analysis of COVID-19 Outcome Using Machine Learning Predictive Models

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In the case of mass spectrometry-based analyses, several analytical platforms have been used for VOC identification, including selective-ion flow-tube mass spectrometry (SIFT-MS) 32 and proton-transfer reaction mass spectrometry (PTR-MS), 33 while GC-MS 20 has been deemed the gold standard. In addition to increased sensitivity of volatile analyte detection, mass spectrometry-based analyses offer a unique advantage in the ability to detect and identify new analytes that may not have been previously reported 34 as they are able to detect a wider array of VOCs reported by untargeted analyses to unravel prominent VOCs as biomarkers.…”

Section: Analytical Requirements and Emerging Technologies For Human ...mentioning

confidence: 99%

Analyses of lung cancer-derived volatiles in exhaled breath and in vitro models

Choueiry

Barham

Zhu

2022

Exp Biol Med (Maywood)

View full text Add to dashboard Cite

Lung cancer is one of the leading causes of cancer incidence and cancer-related deaths in the world. Early diagnosis of pulmonary tumors results in improved survival compared to diagnosis with more advanced disease, yet early disease is not reliably indicated by symptoms. Despite of the improved testing and monitoring techniques for lung cancer in the past decades, most diagnostic tests, such as sputum cytology or tissue biopsies, are invasive and risky, rendering them unfeasible for large population screening. The non-invasive analysis of exhaled breath has gained attentions as an innovative screening method to measure chemical alterations within the human volatilome profile as a result of oncogenesis. More importantly, volatile organic compounds (VOCs) have been correlated to the pathophysiology of disease since the source of volatile compounds relies mostly on endogenous metabolic processes that are altered as a result of disease onset. Therefore, studying VOCs emitted from human breath may assist lung cancer diagnosis, treatment monitoring, and other surveillance of this devastating disease. In this mini review, we evaluated recent human studies that have attempted to identify lung cancer-derived volatiles in exhaled breath of patients. We also examined reported volatiles in cell cultures of lung cancer to better understand the origins of cancer-associated VOCs. We highlight the metabolic processes of lung cancer that could be responsible for the endogenous synthesis of these VOCs and pinpoint the protein-encoding genes involved in these pathways. Finally, we highlight the potential value of a breath test in lung cancer and propose prominent areas for future research required for the incorporation of VOCs-based testing into clinical settings.

show abstract

“…Artificial intelligence (AI) has been increasingly developed and utilized in healthcare to assist medical personnel, such as computational pathology and chest x-ray screening [22]. Regarding VOC analysis, AI was applied to select the ideal combination of VOCs for diagnosing cancerous and non-cancerous diseases, e.g., tuberculosis, lung cancer, and HCC [19,[23][24][25]. Given the complexity and heterogeneity of tumor biology, the prediction model constructed using AI rather than conventional analyses is more capable of identifying the VOC pattern that differentiates cancer patients from individuals without cancer [26].…”

Section: Introductionmentioning

confidence: 99%

VOCs from Exhaled Breath for the Diagnosis of Hepatocellular Carcinoma

et al. 2023

View full text Add to dashboard Cite

Background: Volatile organic compound (VOC) profiles as biomarkers for hepatocellular carcinoma (HCC) are understudied. We aimed to identify VOCs from the exhaled breath for HCC diagnosis and compare the performance of VOCs to alpha-fetoprotein (AFP). The performance of VOCs for predicting treatment response and the association between VOCs level and survival of HCC patients were also determined. Methods: VOCs from 124 HCC patients and 219 controls were identified using the XGBoost algorithm. ROC analysis was used to determine VOCs performance in differentiating HCC patients from controls and in discriminating treatment responders from non-responders. The association between VOCs and the survival of HCC patients was analyzed using Cox proportional hazard analysis. Results: The combination of 9 VOCs yielded 70.0% sensitivity, 88.6% specificity, and 75.0% accuracy for HCC diagnosis. When differentiating early HCC from cirrhotic patients, acetone dimer had a significantly higher AUC than AFP, i.e., 0.775 vs. 0.714, respectively, p = 0.001. Acetone dimer classified HCC patients into treatment responders and non-responders, with 95.7% sensitivity, 73.3% specificity, and 86.8% accuracy. Isopropyl alcohol was independently associated with the survival of HCC patients, with an adjusted hazard ratio of 7.23 (95%CI: 1.36–38.54), p = 0.020. Conclusions: Analysis of VOCs is a feasible noninvasive test for diagnosing and monitoring HCC treatment response.

show abstract

Exploring Volatile Organic Compounds in Breath for High-Accuracy Prediction of Lung Cancer

Cited by 49 publications

References 54 publications

Age-Stratified Analysis of COVID-19 Outcome Using Machine Learning Predictive Models

Age-Stratified Analysis of COVID-19 Outcome Using Machine Learning Predictive Models

Analyses of lung cancer-derived volatiles in exhaled breath and in vitro models

VOCs from Exhaled Breath for the Diagnosis of Hepatocellular Carcinoma

Contact Info

Product

Resources

About