Staging of colorectal cancer using lipid biomarkers and machine learning.

INTRODUCTION: Colorectal cancer (CRC) is the third most commonly diagnosed cancer worldwide. Alteration in lipid metabolism and chemokine expression are considered hallmark characteristics of malignant progression and metastasis of CRC. Validated diagnostic and prognostic biomarkers are urgently needed to define molecular heterogeneous CRC clinical stages and subtypes, as liver dominant metastasis has poor survival outcomes. OBJECTIVES: The aim of this study was to integrate lipid changes, concentrations of chemokines, such as platelet factor 4 and interleukin 8, and gene marker status measured in plasma samples, with clinical features from patients at different CRC stages or who had progressed to stage-IV colorectal liver metastasis (CLM). METHODS: High-resolution liquid chromatography-mass spectrometry (HR-LC-MS) was used to determine the levels of candidate lipid biomarkers in each CRC patient's preoperative plasma samples and combined with chemokine, gene and clinical data. Machine learning models were then trained using known clinical outcomes to select biomarker combinations that best classify CRC stage and group. RESULTS: Bayesian neural net and multilinear regression-machine learning identified candidate biomarkers that classify CRC (stages I-III), CLM patients and control subjects (cancer-free or patients with polyps/diverticulitis), showing that integrating specific lipid signatures and chemokines (platelet factor-4 and interluken-8; IL-8) can improve prognostic accuracy. Gene marker status could contribute to disease prediction, but requires ubiquitous testing in clinical cohorts. CONCLUSION: Our findings demonstrate that correlating multiple disease related features with lipid changes could improve CRC prognosis. The identified signatures could be used as reference biomarkers to predict CRC prognosis and classify stages, and monitor therapeutic intervention.

Development of simple and sensitive hydrogel based colorimetric sensor array for the real-time quantification of gaseous ammonia.

A real-time colorimetric sensor array (CSA) offers the advantages of diversity and accuracy for the quantification of multiple analytes; however, traditional sensors require a complex fabrication process. Therefore, to take full advantage of this sensing platform, we have developed a simple CSA system composed of a polymer, a reducing agent, and different pH indicators. Distinctive color response patterns were classified by extracting the hidden information, (i.e., red, green, and blue (RGB) values) from the indicators. This triple-channel sensing platform is further applied for statistical analysis, to quantify different concentrations of ammonia and other analytes. The sensor array showed a limit of detection of 0.3ppm, which is well below the diagnostic criteria for ammonia concentration in the breath of healthy individuals and of patients with end-stage renal disease. As this sensor would be able to quantify gaseous ammonia in the breath, it is relevant to the point-of-care diagnosis of patients with renal diseases.

Recent analytical approaches to detect exhaled breath ammonia with special reference to renal patients.

The ammonia odor from the exhaled breath of renal patients is associated with high levels of blood urea nitrogen. Typically, in the liver, ammonia and ammonium ions are converted into urea through the urea cycle. In the case of renal dysfunction, urea is unable to be removed and that causes a buildup of excessive ammonia. As small molecules, ammonia and ammonium ions can be forced into the blood-lung barrier and occur in exhaled breath. Therefore, people with renal failure have an ammonia (fishy) odor in their exhaled breath. Thus, exhaled breath ammonia can be a potential biomarker for monitoring renal diseases during hemodialyis. In this review, we have summarized the source of ammonia in the breath of end-stage renal disease patient, cause of renal disorders, exhaled breath condensate, and breath sampling. Further, various biosensor approaches to detect exhaled ammonia from renal patients and other ammonia systems are also discussed. We conclude with future perspectives, namely colorimetric-based real-time breathing diagnosis of renal failure, which might be useful for prospective studies.