Alcoholic liver disease: A registry view on comorbidities and disease prediction.

Alcoholic-related liver disease (ALD) is the cause of more than half of all liver-related deaths. Sustained excess drinking causes fatty liver and alcohol-related steatohepatitis, which may progress to alcoholic liver fibrosis (ALF) and eventually to alcohol-related liver cirrhosis (ALC). Unfortunately, it is difficult to identify patients with early-stage ALD, as these are largely asymptomatic. Consequently, the majority of ALD patients are only diagnosed by the time ALD has reached decompensated cirrhosis, a symptomatic phase marked by the development of complications as bleeding and ascites. The main goal of this study is to discover relevant upstream diagnoses helping to understand the development of ALD, and to highlight meaningful downstream diagnoses that represent its progression to liver failure. Here, we use data from the Danish health registries covering the entire population of Denmark during nineteen years (1996-2014), to examine if it is possible to identify patients likely to develop ALF or ALC based on their past medical history. To this end, we explore a knowledge discovery approach by using high-dimensional statistical and machine learning techniques to extract and analyze data from the Danish National Patient Registry. Consistent with the late diagnoses of ALD, we find that ALC is the most common form of ALD in the registry data and that ALC patients have a strong over-representation of diagnoses associated with liver dysfunction. By contrast, we identify a small number of patients diagnosed with ALF who appear to be much less sick than those with ALC. We perform a matched case-control study using the group of patients with ALC as cases and their matched patients with non-ALD as controls. Machine learning models (SVM, RF, LightGBM and NaiveBayes) trained and tested on the set of ALC patients achieve a high performance for data classification (AUC = 0.89). When testing the same trained models on the small set of ALF patients, their performance unsurprisingly drops a lot (AUC = 0.67 for NaiveBayes). The statistical and machine learning results underscore small groups of upstream and downstream comorbidities that accurately detect ALC patients and show promise in prediction of ALF. Some of these groups are conditions either caused by alcohol or caused by malnutrition associated with alcohol-overuse. Others are comorbidities either related to trauma and life-style or to complications to cirrhosis, such as oesophageal varices. Our findings highlight the potential of this approach to uncover knowledge in registry data related to ALD.

Polymorphisms in the NFkB, TNF-alpha, IL-1beta, and IL-18 pathways are associated with response to anti-TNF therapy in Danish patients with inflammatory bowel disease.

BACKGROUND: Anti-tumor necrosis factor-α (TNF-α) is used for the treatment of severe cases of IBD, including Crohn's disease (CD) and ulcerative colitis (UC). However, one-third of the patients do not respond to the treatment. We have previously investigated whether single nucleotide polymorphisms (SNPs) in genes involved in inflammation were associated with response to anti-TNF therapy among patients with CD or UC. AIM: A new cohort of patients was established for replication of the previous findings and to identify new SNPs associated with anti-TNF response. METHODS: Fifty-three SNPs assessed previously in cohort 1 (482 CD and 256 UC patients) were genotyped in cohort 2 (587 CD and 458 UC patients). The results were analysed using logistic regression (adjusted for age and gender). RESULTS: Ten SNPs were associated with anti-TNF response either among patients with CD (TNFRSF1A(rs4149570) (OR: 1.92, 95% CI: 1.02-3.60, P = 0.04), IL18(rs187238) (OR: 1.35, 95% CI: 1.00-1.82, P = 0.05), and JAK2(rs12343867) (OR: 1.35, 95% CI: 1.02-1.78, P = 0.03)), UC (TLR2(rs11938228) (OR: 0.55, 95% CI: 0.33-0.92, P = 0.02), TLR4(rs5030728) (OR: 2.23, 95% CI: 1.24-4.01, P = 0.01) and (rs1554973) (OR: 0.49, 95% CI: 0.27-0.90, P = 0.02), NFKBIA(rs696) (OR: 1.45, 95% CI: 1.06-2.00, P = 0.02), and NLRP3(rs4612666) (OR: 0.63, 95% CI: 0.44-0.91, P = 0.01)) or in the combined cohort of patient with CD and UC (IBD) (TLR4(rs5030728) (OR: 1.46, 95% CI: 1.01-2.11, P = 0.04) and (rs1554973)(OR: 0.80, 95% CI: 0.65-0.98, P = 0.03), NFKBIA(rs696) (OR: 1.25, 95% CI: 1.01-1.54, P = 0.04), NLRP3(rs4612666) (OR: 0.73, 95% CI: 0.57-0.95, P = 0.02), IL1RN(rs4251961) (OR: 0.81, 95% CI: 0.66-1.00, P = 0.05), IL18(rs1946518) (OR: 1.24, 95% CI: 1.01-1.53, P = 0.04), and JAK2(rs12343867) (OR: 1.24, 95% CI: 1.01-1.53, P = 0.04)). CONCLUSIONS: The results support that polymorphisms in genes involved in the regulation of the NFκB pathway (TLR2, TLR4, and NFKBIA), the TNF-α signalling pathway (TNFRSF1A), and other cytokine pathways (NLRP3, IL1RN, IL18, and JAK2) were associated with response to anti-TNF therapy. Our multi-SNP model predicted response rate of more than 82% (in 9% of the CD patients) and 75% (in 15% of the UC patients), compared to 71% and 64% in all CD and UC patients, respectively. More studies are warranted to predict response for use in the clinic.