Dataset Information

Computer-Aided Prediction of Long-Term Prognosis of Patients with Ulcerative Colitis after Cytoapheresis Therapy.

ABSTRACT: Cytoapheresis (CAP) therapy is widely used in ulcerative colitis (UC) patients with moderate to severe activity in Japan. The aim of this study is to predict the need of operation after CAP therapy of UC patients on an individual level using an artificial neural network system (ANN). Ninety UC patients with moderate to severe activity were treated with CAP. Data on the patients' demographics, medication, clinical activity index (CAI) and efficacy of CAP were collected. Clinical data were divided into training data group and validation data group and analyzed using ANN to predict individual outcomes. The sensitivity and specificity of predictive expression by ANN were 0.96 and 0.97, respectively. Events of admission, operation, and use of immunomodulator, and efficacy of CAP were significantly correlated to the outcome. Requirement of operation after CAP therapy was successfully predicted by using ANN. This newly established ANN strategy would be used as powerful support of physicians in the clinical practice.

SUBMITTER: Takayama T

PROVIDER: S-EPMC4481415 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Computer-Aided Prediction of Long-Term Prognosis of Patients with Ulcerative Colitis after Cytoapheresis Therapy.

Takayama Tetsuro T Okamoto Susumu S Hisamatsu Tadakazu T Naganuma Makoto M Matsuoka Katsuyoshi K Mizuno Shinta S Bessho Rieko R Hibi Toshifumi T Kanai Takanori T

PloS one 20150625 6

Cytoapheresis (CAP) therapy is widely used in ulcerative colitis (UC) patients with moderate to severe activity in Japan. The aim of this study is to predict the need of operation after CAP therapy of UC patients on an individual level using an artificial neural network system (ANN). Ninety UC patients with moderate to severe activity were treated with CAP. Data on the patients' demographics, medication, clinical activity index (CAI) and efficacy of CAP were collected. Clinical data were divided ...[more]

PMID: 26111148

Similar Datasets

Project description:AimsThe endoscopic evaluation is crucial for the management and treatment of ulcerative colitis (UC). Currently, the Mayo Endoscopic Score (MES) and the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) are two major endoscopic score systems to evaluate the status of mucosal inflammation and disease activity. However, in both MES and UCEIS systems, the disease extent is not included. The Degree of Ulcerative Colitis Burden of Luminal Inflammation (DUBLIN) score is a simple clinical score which is calculated as a product of the MES (0-3) and the extent of disease (E1-E3). The objective of this study was to compare the correlation among DUBLIN, UCEIS and MES, and also investigate the clinical characteristics for predicting treatment failure in patients with active UC.MethodsBetween March 2015 and April 2019, 172 patients who were previously diagnosed with UC and had undergone colonoscopy were recruited in this study. We retrospectively reviewed the endoscopic scores and clinical characteristics at the time of the colonoscopy and assessed the prognosis of the patients. Endoscopic response was defined as the decrease in MES ⩾1 grade.ResultsDUBLIN showed significant correlation with MES (r = 0.748) and partial Mayo score (pMayo) (r = 0.707), and moderately correlated with CRP (r = 0.590). UCEIS also showed strong correlation with MES (r = 0.712) but moderate correlation with pMayo (r = 0.609) and CRP (r = 0.588). Compared with the UCEIS (cut-off value: 4; sensitivity: 75.73%), DUBLIN score (cut-off value: 4; sensitivity: 86.41%) showed higher diagnostic sensitivity than UCEIS score (McNemar test, p < 0.05). Furthermore, a multivariate analysis also revealed that DUBLIN ⩾4 was the independent factor for predicting treatment failure for UC (p < 0.001, odds ratio: 1.547; 95% confidence interval: 1.32-1.88).ConclusionThe DUBLIN score shows superior diagnostic performances in terms of sensitivity value compared with the UCEIS. Moreover, multivariate analysis indicates that DUBLIN ⩾4 is an independent factor for predicting medium- to long-term treatment failure in active UC patients.

Project description:BackgroundThe long-term outcomes of Ulcerative colitis (UC) after discontinuation of biological therapy are largely unknown. There is also a lack of accurate and validated markers that can predict outcome after withdrawal accurately. The aims of this study were to describe the long-term outcomes in UC patients following cessation of anti-TNF therapy and explore potential biomarkers as an approach towards precision medicine.MethodsSeventy-five patients with moderate to severe UC treated to remission with anti-tumor necrosis factor (TNF) were included in the study. This is a follow-up of previously reported UC outcomes. The patients were categorized as either "Remission" or "Relapse". The "Relapse" group was divided into subgroups determined by the highest treatment level needed to obtain remission the last 3 years of observation: non-biological therapy, biological therapy or colectomy. Remission were divided in long term remission (LTR), those using immunomodulating drugs (LTR + imids) and those using only 5-amino-salicylate (5-ASA) treatment (LTR) for the past 3 years. Analyses of mucosal gene expression by real-time PCR were performed.ResultsThe median (IQR) observation time of all patients included was 121 (111-137) months. Of the 75 patients, 46 (61%) did not receive biological therapy, including 23 (31%) in LTR ± imids. Of these 23 patients, 16 (21%) were defined as LTR with a median observation time of (IQR) 95 (77-113) months. In total 14 patients (19%) underwent colectomy during the 10 years after first remission. Mucosal TNF copies/µg mRNA < 10 000 at anti-TNF discontinuation predicted long-term remission, biological free remission and lower risk of colectomy with a HR 0.36 (0.14-0.92) for long-term remission, HR 0.17 (0.04-0.78) for biological free remission and HR 0.12 (0.01-0.91) for colectomy. IL1RL1 was normalized in LTR phenotype and higher in relapsing UC.ConclusionIn this 10-year follow-up of UC of patients with moderate to severe disease, 61% of patients experience an altered phenotype to a milder disease course without need of biological therapy. Twenty-one percent of the patients were LTR without any medication except of 5-ASA. Mucosal TNF gene expression and IL1RL1- transcripts may be of clinical utility for long term prognosis in development of precision medicine in UC.

Dataset Information

Computer-Aided Prediction of Long-Term Prognosis of Patients with Ulcerative Colitis after Cytoapheresis Therapy.

Publications

Computer-Aided Prediction of Long-Term Prognosis of Patients with Ulcerative Colitis after Cytoapheresis Therapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets