A Machine-Learned Predictor of Colonic Polyps Based on Urinary Metabolomics

Eisner, Roman; Greiner, Russell; Tso, Victor; Wang, Haili; Fedorak, Richard N.

doi:10.1155/2013/303982

Cited by 35 publications

(34 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eisner et al (22) performed urinary metabolomics in search of such a predictor and reported that nicotinate and nicotinamide metabolites and the degradation of ketone bodies are associated with the presence of CP. They proposed a tool involving the use of urinary metabolomics to select patients at risk of CP, who would undergo further investigation with colonoscopy.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Higher serum uric acid levels and advanced age are associated with an increased prevalence of colorectal polyps

et al. 2015

View full text Add to dashboard Cite

Abstract. The present study retrospectively analyzed the laboratory data of patients who had undergone a colonoscopy between April 2011 and March 2014, with the aim of assessing whether these variables could be used to predict the presence of colorectal polyps (CP). A total of 1,471 patients were enrolled (731 men, 68.5±10.8 years; 740 women, 66.7±10.8 years). One-way analysis of variance was performed to analyze the association between the presence of CP and a range of laboratory variables. Logistic regression analysis was performed to establish a regression equation to predict the presence of CP. Receiver-operator characteristics analysis was applied to investigate the performance of the regression equation. Patients with CP were older than those without CP (P<0.0001). Serum uric acid (UA) levels were higher in patients with CP, compared to those without CP (P=0.0007). To investigate the possibility that older age and higher UA levels could predict the presence of CP, logistic regression analysis was performed (P=0.0008). The regression equation was as follows: ln(p/1 -p) = 2.79015 -0.01836 x age -0.28542 x UA (mg/dl), where p indicates the presence of CP. Receiver-operator characteristic analysis showed the area under the curve to be 0.62092 and the threshold value of P was 0.4370. Sensitivity and specificity of the threshold value were 77.6 and 44.2%, respectively. Advanced age and higher serum UA levels were associated with the presence of CP. In conclusion, logistic regression analysis obtained a regression equation that predicted the presence of CP with a higher sensitivity, but poorer specificity, compared to fecal occult blood testing.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Fecal occult blood testing is intended to select patients with colorectal cancer, rather than pre-cancerous CP (24). Eisner et al (22) analyzed fecal occult blood testing as a tool for the detection of CP. Fecal occult blood testing has been shown to have a sensitivity of 2.6-15.1% and a specificity of 94.5-99.4%.…”

Section: Discussionmentioning

confidence: 99%

Higher serum uric acid levels and advanced age are associated with an increased prevalence of colorectal polyps

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Patients with adenomatous polyps, a precursor of CRC, can be identified with a sensitivity of 64% and specificity of 65% using a machine learning algorithm to analyse 1 H-NMR spectroscopic profiles. 97 Studies associating the faecal metabolome with CRC have also been performed, but owing to the temporal and local variability in faecal composition, the number of participants required to generate meaningful conclusions is large. 98 Faecal samples from patients with CRC (n = 11) differed from healthy individuals (n = 10) in relative concentrations of fructose, linoleic acid, nicotinic acid.…”

Section: Colorectal Cancermentioning

confidence: 99%

The promise of metabolic phenotyping in gastroenterology and hepatology

Holmes

Wijeyesekera

Taylor-Robinson

et al. 2015

Nat Rev Gastroenterol Hepatol

View full text Add to dashboard Cite

Disease risk and treatment response are determined, at the individual level, by a complex history of genetic and environmental interactions, including those with our endogenous microbiomes. Personalized health care requires a deep understanding of patient biology that can now be measured using a range of '-omics' technologies. Patient stratification involves the identification of genetic and/or phenotypic disease subclasses that require different therapeutic strategies. Stratified medicine approaches to disease diagnosis, prognosis and therapeutic response monitoring herald a new dimension in patient care. Here, we explore the potential value of metabolic profiling as applied to unmet clinical needs in gastroenterology and hepatology. We describe potential applications in a number of diseases, with emphasis on large-scale population studies as well as metabolic profiling on the individual level, using spectrometric and imaging technologies that will leverage the discovery of mechanistic information and deliver novel health care solutions to improve clinical pathway management.

show abstract

“…This study used NMR spectra acquired from 988 urine samples previously obtained as part of a regional colon cancer screening program in Edmonton, Canada (SCOPE ® , Stop Colorectal Cancer through Prevention and Education) [17][18][19]. Study participants of average or increased colorectal carcinoma risk were recruited.…”

Section: Study Participants and Urine Collectionmentioning

confidence: 99%

Consistency of Metabolite Determination from NMR Spectra over Time and Between Operators

R¹

2015

Metabolomics

View full text Add to dashboard Cite

In analysis of NMR spectra, well trained people are not highly variable (within themselves), but there is a potential for variability when different operators are used for analysis. One study has shown similar analytical results between three analysts examining four samples for nine metabolites [14]. Another study used five people with multiple rounds of analysis of 18 spectra, to demonstrate good agreement between people for the most common metabolites [16]. Furthermore, the experimental group (sampling method) was generally more important than variation between people [16]. Despite the consistencies seen between people, it is still recommended that analysis be performed by the same person or group over a single study [16]. However, for studies with a large number of samples, or long-term experiments, single operator analysis may not be feasible. In this study, metabolite spectra of urine samples acquired using NMR were assessed for consistency of metabolite quantification either over time (3 years) or between two groups of operators. The aim was to identify the metabolites that are reliably quantified to improve our standard operating protocols and experimental procedures. We first performed a subjective analysis of 70 metabolites, categorizing them based on their apparent consistency in metabolite concentration over time. We also looked at the difference between the

show abstract

A Machine-Learned Predictor of Colonic Polyps Based on Urinary Metabolomics

Cited by 35 publications

References 41 publications

Higher serum uric acid levels and advanced age are associated with an increased prevalence of colorectal polyps

Higher serum uric acid levels and advanced age are associated with an increased prevalence of colorectal polyps

The promise of metabolic phenotyping in gastroenterology and hepatology

Consistency of Metabolite Determination from NMR Spectra over Time and Between Operators

Contact Info

Product

Resources

About