Current and future diagnostic approaches: from serologies to imaging

Utility of four machine learning approaches for identifying ulcerative colitis and Crohn's disease

Objective

Peripheral blood routine parameters (PBRPs) are simple and easily acquired markers to identify ulcerative colitis (UC) and Crohn's disease (CD) and reveal the severity, whereas the diagnostic performance of individual PBRP is limited. We, therefore used four machine learning (ML) models to evaluate the diagnostic and predictive values of PBRPs for UC and CD.

Methods

A retrospective study was conducted by collecting the PBRPs of 414 inflammatory bowel disease (IBD) patients, 423 healthy controls (HCs), and 344 non-IBD intestinal diseases (non-IBD) patients. We used approximately 70 % of the PBRPs data from both patients and HCs for training, 30 % for testing, and another group for external verification. The area under the receiver operating characteristic curve (AUC) was used to evaluate the diagnosis and prediction performance of these four ML models.

Results

Multi-layer perceptron artificial neural network model (MLP-ANN) yielded the highest diagnostic performance than the other three models in six subgroups in the training set, which is helpful for discriminating IBD and HCs, UC and CD, active CD and remissive CD, active UC and remissive UC, non-IBD and HCs, and IBD and non-IBD with the AUC of 1.00, 0.988, 0.942, 1.00, 0.986, and 0.97 in the testing set, as well as the AUC of 1.00, 1.00, 0.773, 0.904, 1.00 and 0.992 in the external validation set.

Conclusion

PBRPs-based MLP-ANN model exhibited good performance in discriminating between UC and CD and revealing the disease activity; however, a larger sample size and more models need to be considered for further research.

Predictive Significance of the Preoperative Neutrophil-lymphocyte Ratio for Recurrence in Idiopathic Granulomatous Mastitis Patients

BACKGROUND

To investigate and assess the correlation between inflammatory markers, such as the preoperative neutrophil-lymphocyte ratio (NLR), and the recurrence of idiopathic granulomatous mastitis (IGM).

METHODS

All patients with IGM who were free of malignancy or inflammatory diseases were included in this retrospective analysis between January 2013 and December 2019. On the basis of the presence or absence of recurrence, the patients were split into two groups. After collecting retrospective data, the relationship between patient characteristics, hematological markers such as C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), NLR, platelet-lymphocyte ratio (PLR), and white blood cell count (WBC), and their connection with postoperative recurrence were assessed utilizing univariate and multivariate analyses, receiver operating characteristic curves (ROC curves), and logistic regression.

RESULTS

Recurrences occurred in 40.0% (32/80) of the 80 patients over a median follow-up duration of 35.5 months (22.0-47.8 months). The recurrent group showed higher NLR and CRP than the non-recurrent group (PNLR = .003, PCRP = .02). Neutrophil-lymphocyte ratio and postoperative recurrence were associated (correlation coefficient r = .436, P = .01). The ROC curve's ideal threshold, which had predictive value for IGM recurrence, was 2.18 (sensitivity: 46.9%; specificity: 14.6%).

CONCLUSION

The preoperative NLR is a simple and affordable way to predict IGM relapse, which is important for directing clinical work.

Does neutrophil-to-lymphocyte ratio predict active ulcerative colitis?

BACKGROUND

Inflammatory markers have been studied in ulcerative colitis (UC) for diagnosis, disease activity, and prediction of relapse. Blood neutrophil-to-lymphocyte (N/L) ratio has been used to determine outcomes of some malignancies and coronary artery disease. Blood N/L ratio is a simple sign of clinical inflammation. In this study, we examined N/L ratio in recurrent patients suffering from UC.

METHODS

The aim of the present study was to analyze N/L ratios in serum samples of UC patients in remission and active phases. Patients' age, extend of the disease, disease duration, disease activity, drug, and other medical history were all noted for patients. C-reactive protein, erythrocyte sedimentation rate, and complete blood count were determined for patients.

RESULTS

Forty-nine UC patients were admitted into the present study. The blood N/L ratios were significantly increased in active phase compared with inactive UC patients (p < 0.05). The cut-off value for N/L ratio for the detection of active UC patients was calculated as ≥ 2.3 using receiver operating characteristic analysis [sensitivity: 61.2 %, specificity: 66.7 %, AUC: 0.650 (0.540-0.760), p = 0.01].

CONCLUSIONS

Present study shows that in patients with UC, the blood N/L ratio is associated with active disease. N/L ratio may be used as an activity parameter in UC.

Neutrophil-lymphocyte ratio as a predictor of disease severity in ulcerative colitis

BACKGROUND

Blood neutrophil-to-lymphocyte (N/L) ratio is an indicator of the overall inflammatory status of the body, and an alteration in N/L ratio may be found in ulcerative colitis (UC) patients. The aims of this study were to investigate the utility of N/L ratio as a simple and readily available predictor for clinical disease activity in UC.

METHODS

Twenty-six patients and 28 healthy controls were enrolled in the study. The neutrophil and lymphocyte counts were recorded, and the N/L ratio was calculated from these parameters. The extent of disease classified according to the Montreal classification, clinical disease activity was evaluated using a modified Truelove-Witts severity index, and endoscopic disease activities were classified according to Schroder et al.

RESULTS

The serum N/L ratios of active patients were significantly higher than those of inactive UC and controls (P < 0.001). The optimum N/L ratio cut-off point for active UC was 2.47. There was no significant difference between inflammation parameters, disease extension, and disease activity.

CONCLUSION

Our results demonstrate that N/L ratio is higher in patients with active UC compared with controls and UC patients in remission and a cut-off value of 2.47 can be used to identify patients with active ulcerative colitis.

Mean platelet volume: a controversial marker of disease activity in Crohn's disease

Background

We investigated and compared the capacity of mean platelet volume (MPV) and other inflammatory markers in detecting Crohn’s disease (CD) activity and differentiating CD patients from healthy controls.

Methods

MPV, C-reactive protein (CRP), erythrocyte sedimentation rate (ESR) and white blood cells were measured in 61 CD patients and 50 healthy subjects. Disease activity was assessed by the Crohn’s Disease Activity Index.

Results

A significant decrease in MPV was noted in patients with CD compared with healthy controls (P <0.0001), but statistical difference was not found between active and inactive CD groups. In CD, no significant correlation was found between MPV and other inflammatory markers. The overall accuracy of MPV (cutoff: 10.35 fl), CRP (cutoff: 4.85 mg/dl) and ESR (cutoff: 8.5 mm/hour) in differentiating CD patients from healthy controls was 76.6%, 65.8% and 72.1% respectively. The overall accuracy of CRP (cutoff: 4.95 mg/dl) and ESR (cutoff: 16.5 mm/hour) in determination of active CD was 80.3% and 73.8%.

Conclusions

MPV declined in CD patients compared with healthy subjects. MPV had the best accuracy in determination of CD patients and healthy controls. MPV did not show a discriminative value in disease activity.

Assessment of neutrophil-lymphocyte ratio in ulcerative colitis: a promising marker in predicting disease severity

BACKGROUND AND AIM

In order to diagnosis and monitor the disease activity of ulcerative colitis (UC), serum biomarkers are generally used, but none of them are specific for intestinal inflammation. It is therefore desirable in clinical practice to be able to assess disease activity with simple, inexpensive and objective tools. The objective of the present study was to assess whether the neutrophil-lymphocyte ratio (NLR) would be useful in predicting disease severity in UC patients who had not received corticosteroid or immunosuppressive drugs within a defined period of time. Additionally, a possible relationship of NLR with other inflammatory markers in UC patients was also investigated.

METHODS

We designed a retrospective study examining the utility of NLR in estimating disease severity in UC patients admitted to our hospital between 2008 and 2011. In total, 119 patients with active UC and 77 patients with inactive UC were enrolled in the study group, and 59 age and gender matched healthy subjects were included as the control group. Disease activity was assessed using Truelove and Witts criteria.

RESULTS

In the active UC group, NLR values were found to be elevated compared to inactive UC patients and controls (3.22 ± 1.29, 1.84 ± 0.69 and 2.01 ± 0.64, respectively). Using ROC statistics, a cut-off value of 2.16 indicated the presence of active disease with a sensitivity of 81.8% and a specificity of 80.5% (positive predictive value [PPV] 86.8%, negative predictive value [NPV] 73.8%). NLR values were found to be correlated with WBC and ESR levels.

CONCLUSIONS

The present study revealed that NLR is increased in active UC. Peripheral blood NLR can reflect disease activity and can be used as an additional marker for estimating intestinal inflammation.

Serum adenosine deaminase activity as a predictor of disease severity in ulcerative colitis

BACKGROUND AND AIM

Ulcerative colitis (UC) is a chronic inflammatory disease characterized by recurrent inflammation and ulcerations of colonic mucosa and an inappropriate and delayed healing. Adenosine deaminase (ADA) is a cytoplasmic enzyme involved in the catabolism of purine bases, capable of catalyzing the deamination of adenosine, forming inosine in the result process. Although ADA has been shown to increase in several inflammatory conditions, there are no literature data indicating an alteration in UC.

METHODS

This study evaluated the activity of total ADA in serum of 43 patients with UC and 18 healthy controls. Patients' age, disease duration, drug intake, and other medical history were all noted for each subject. Complete blood count, erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) were determined for both patients and controls. Correlation analysis was also performed between ADA and other inflammation markers of UC.

RESULTS

Serum mean ADA levels were 11.12 ± 2.03 and 7.99 ± 2.04 U/l for patients with UC in active state and in remission and 8.55 ± 2.26 U/l in the healthy control group. Mean serum ADA levels were significantly elevated in active UC patients compared with patients with UC in remission and control groups. Overall accuracy of ADA in determination of active UC was 83.7 with sensitivity 83.3%, specificity 84.2%.

CONCLUSIONS

Serum ADA levels were found to be elevated in UC patients in active state suggesting a partial role of activated T-cell response in the disease pathophysiology. Further randomized controlled studies are warranted to demonstrate the role of ADA in UC patients, with a special interest in specifically targeted therapies against ADA for achieving disease remission.

Ulcerative colitis practice guidelines in adults: American College Of Gastroenterology, Practice Parameters Committee

Guidelines for clinical practice are aimed to indicate preferred approaches to medical problems as established by scientifically valid research. Double-blind placebo controlled studies are preferable, but compassionate-use reports and expert review articles are used in a thorough review of the literature conducted through Medline with the National Library of Medicine. When only data that will not withstand objective scrutiny are available, a recommendation is identified as a consensus of experts. Guidelines are applicable to all physicians who address the subject regardless of specialty training or interests and are aimed to indicate the preferable but not necessarily the only acceptable approach to a specific problem. Guidelines are intended to be flexible and must be distinguished from standards of care, which are inflexible and rarely violated. Given the wide range of specifics in any health-care problem, the physician must always choose the course best suited to the individual patient and the variables in existence at the moment of decision. Guidelines are developed under the auspices of the American College of Gastroenterology and its Practice Parameters Committee and approved by the board of trustees. Each has been intensely reviewed and revised by the Committee, other experts in the field, physicians who will use them, and specialists in the science of decision analysis. The recommendations of each guideline are therefore considered valid at the time of composition based on the data available. New developments in medical research and practice pertinent to each guideline will be reviewed at a time established and indicated at publication to assure continued validity. The recommendations made are based on the level of evidence found. Grade A recommendations imply that there is consistent level 1 evidence (randomized controlled trials), grade B indicates that the evidence would be level 2 or 3, which are cohort studies or case-control studies. Grade C recommendations are based on level 4 studies, meaning case series or poor-quality cohort studies, and grade D recommendations are based on level 5 evidence, meaning expert opinion.

Assessment of appropriateness of indications for CT enterography in younger patients

BACKGROUND

The small potential risk of radiation-induced cancer is increased in younger patients undergoing serial imaging with computed tomography enterography (CTE). We sought to determine the appropriateness of CTEs based on clinical indication in patients < or =35 years old, and the potential impact of evolution of practice to alternative magnetic resonance enterography (MRE).

METHODS

Over a 7-year period, the medical records of all patients < or =35 years old undergoing CTE were reviewed to determine the clinical indications for each CTE exam. An interdisciplinary consensus panel evaluated the appropriateness of all CTE exams based on American College of Radiology appropriateness criteria and peer-reviewed literature, classifying indications into "appropriate" or "inappropriate." For repeat CTEs, an "alternative MRE suggested" pathway was created. Criteria for evolution of practice to "alternative MRE" were suspicion of obstruction and evaluation of disease activity/therapeutic response in the absence of new symptoms.

RESULTS

In all, 2022 patients < or =35 years old underwent 2295 CTEs. Ninety-nine percent (2008/2022) of first-time CTE exams were "appropriate" by the defined criteria. A total of 197 patients (9.7%) underwent multiple exams, with 73% of these patients having Crohn's disease. Repeat exams occurred in 9% (18/197) with obstructive symptoms and evaluation of disease activity/therapeutic response in the absence of new symptoms in 41% (80/197).

CONCLUSIONS

A multidisciplinary expert panel concluded that the vast majority of young patients underwent clinically appropriate first-time CTE exams. However, a shift in clinical practice to MRE appears warranted for approximately half of young patients undergoing repeat CTE examinations.

Noninvasive methods in evaluation of inflammatory bowel disease: where do we stand now? An update

The inflammatory bowel diseases, consisting of Crohn's disease, ulcerative colitis and indeterminate colitis, are distinguished by idiopathic and chronic inflammation of the digestive tract. The distinction between inflammatory bowel diseases and functional bowel disorders, such as irritable bowel syndrome, can be complex because they often present with similar symptoms. Rapid and inexpensive noninvasive tests that are sensitive, specific and simple are needed to prevent patient discomfort, delay in diagnosis, and unnecessary costs. None of the current commercially available serological biomarker tests can be used as a stand-alone diagnostic in clinics. Instead, these are used as an adjunct to endoscopy in diagnosis and prognosis of the disease. Along these lines,, fecal lactoferrin and calprotectin tests seem to be one step further from other tests with larger number of studies, higher sensitivity and specificity and wider availability.

An overlooked indicator of disease activity in ulcerative colitis: mean platelet volume

Many non-invasive tests have been studied for diagnosis and determining the activation degree of inflammatory bowel disease (IBD). Nevertheless, an ideal test has not been found yet. Mean platelet volume (MPV) is influenced by the inflammation. In a few study, decreased platelet volume have been reported in IBD. The aim of this study is to determine whether platelet volume would be useful in ulcerative colitis (UC) activity. Additionally we have analyzed overall accuracy of MPV in disease activity and compared with other inflammatory markers. A total of 61 UC patients (male/female : 41/20), and 27 healthy subjects (male/female : 18/9) were enrolled into the study. For all subjects following tests were performed; ESR, CRP, white blood cell count and mean platelet volume. A statistically significant decrease in MPV was noted in patients with UC (8.29 +/- 1.02 fL) compared with healthy controls (8.65 +/- 0.79 fL). MPV of active UC (8.06 +/- 1.19 fL) patients were significantly lower than that of inactive UC (8.45 +/- 0.87 fL). Overall accuracy of MPV in determination of active UC was 71% (with sensitivity 67%, specificity 73%). A negative correlation was found between MPV and endoscopic activity index (r : -0.358 p : 0.005). In UC, MPV did not correlate with ESR, CRP and white blood cell. Our study showed that MPV reduced in UC, particularly in patients with active UC. Decreased MPV may be an indicator for increased disease activity in patients with UC.

Cancer antigen 125 levels in inflammatory bowel diseases

BACKGROUND

Cancer antigen 125 (CA-125) is a tumor marker used for the diagnosis and monitoring of ovarian carcinoma. It can also be elevated in endometriosis, inflammations, and in nongynecological malignancies. Up to date, serum CA-125 levels in inflammatory bowel diseases (IBD) have not been studied before.

AIM

To assess the levels of CA-125 in patients with ulcerative colitis (UC) and Crohn's disease (CD).

METHODS

Serum levels of CA-125 were investigated in 68 cases with UC (male/female: 47/21), 32 CD (male/female: 21/11), and 31 healthy controls (male/female: 16/15). Levels of CA-125 were also compared among UC patients according to lesion location, severity, and activity of CD.

RESULTS

Serum CA-125 levels were 17.29+/-24.50 U/ml, 15.56+/-20.74 U/ml, and 8.85+/-2.62 U/ml in patients with UC, CD, and healthy controls, respectively. Serum CA-125 levels were significantly higher in UC compared to control group (P=0.001). Serum CA-125 levels were higher in CD patients compared to control group but there was no significance (P=0.087). Serum CA-125 levels were higher in pancolitis compared to distal type and left-sided UC.

CONCLUSIONS

Our data suggest that serum CA-125 levels may be increased in patients with IBDs.

New serological biomarkers of inflammatory bowel disease

Serological biomarkers in inflammatory bowel disease (IBD) are a rapidly expanding list of non-invasive tests for objective assessments of disease activity, early diagnosis, prognosis evaluation and surveillance. This review summarizes both old and new biomarkers in IBD, but focuses on the development and characterization of new serological biomarkers (identified since 2007). These include five new anti-glycan antibodies, anti-chitobioside IgA (ACCA), anti-laminaribioside IgG (ALCA), anti-manobioside IgG (AMCA), and antibodies against chemically synthesized (Σ) two major oligomannose epitopes, Man α-1,3 Man α-1,2 Man (ΣMan3) and Man α-1,3 Man α-1,2 Man α-1,2 Man (ΣMan4). These new biomarkers serve as valuable complementary tools to existing biomarkers not only in differentiating Crohn’s disease (CD), ulcerative colitis (UC), normal and other non-IBD gut diseases, but also in predicting disease involvement (ileum vs colon), IBD risk (as subclinical biomarkers), and disease course (risk of complication and surgery). Interestingly, the prevalence of the antiglycan antibodies, including anti-Saccharomyces cerevisiae antibodies (ASCA), ALCA and AMCA, was found to be associated with single nucleotide polymorphisms (SNPs) of IBD susceptible genes such as NOD2/CARD15, NOD1/CARD4, toll-like receptors (TLR) 2 and 4, and β-defensin-1. Furthermore, a gene dosage effect was observed: anti-glycan positivity became more frequent as the number of NOD2/CARD15 SNPS increased. Other new serum/plasma IBD biomarkers reviewed include ubiquitination factor E4A (UBE4A), CXCL16 (a chemokine), resistin, and apolipoprotein A-IV. This review also discusses the most recent studies in IBD biomarker discovery by the application of new technologies such as proteomics, fourier transform near-infrared spectroscopy, and multiplex enzyme-linked immunosorbent assay (ELISA)’s (with an emphasis on cytokine/chemokine profiling). Finally, the prospects of developing more clinically useful novel diagnostic algorithms by incorporating new technologies in serological biomarker profiling and integrating multiple biomarkers with bioinformatics analysis/modeling are also discussed.