BackgroundWhereas heart failure (HF) is a complex clinical syndrome, conventional approaches to its management have treated it as a singular disease, leading to inadequate patient care and inefficient clinical trials. We hypothesized that applying advanced analytics to a large cohort of HF patients would improve prognostication of outcomes, identify distinct patient phenotypes, and detect heterogeneity in treatment response.Methods and ResultsThe Swedish Heart Failure Registry is a nationwide registry collecting detailed demographic, clinical, laboratory, and medication data and linked to databases with outcome information. We applied random forest modeling to identify predictors of 1‐year survival. Cluster analysis was performed and validated using serial bootstrapping. Association between clusters and survival was assessed with Cox proportional hazards modeling and interaction testing was performed to assess for heterogeneity in response to HF pharmacotherapy across propensity‐matched clusters. Our study included 44 886 HF patients enrolled in the Swedish Heart Failure Registry between 2000 and 2012. Random forest modeling demonstrated excellent calibration and discrimination for survival (C‐statistic=0.83) whereas left ventricular ejection fraction did not (C‐statistic=0.52): there were no meaningful differences per strata of left ventricular ejection fraction (1‐year survival: 80%, 81%, 83%, and 84%). Cluster analysis using the 8 highest predictive variables identified 4 clinically relevant subgroups of HF with marked differences in 1‐year survival. There were significant interactions between propensity‐matched clusters (across age, sex, and left ventricular ejection fraction and the following medications: diuretics, angiotensin‐converting enzyme inhibitors, β‐blockers, and nitrates, P<0.001, all).ConclusionsMachine learning algorithms accurately predicted outcomes in a large data set of HF patients. Cluster analysis identified 4 distinct phenotypes that differed significantly in outcomes and in response to therapeutics. Use of these novel analytic approaches has the potential to enhance effectiveness of current therapies and transform future HF clinical trials.

Background Radiofrequency ablation (RFA) is an effective means of eradicating Barrett's esophagus (BE), both with and without associated dysplasia. Several studies have documented high initial success rates with RFA. However, there is limited data on IM detection rates after eradication. Aims To determine the rate of detection of intestinal metaplasia (IM) after successful eradication of Barrett's esophagus. Methods BE patients with and without dysplasia who had undergone RFA were retrospectively identified. Only those who had complete eradication as documented on the initial post-ablation endoscopy, and had minimum two surveillance endoscopies, were included in the analyses. Clinical, demographic, and endoscopic data were collected. Cumulative incidence of IM detection was calculated by the Kaplan–Meier method. Results Forty-seven patients underwent RFA and had complete eradication of Barrett's epithelium. The majority of patients were male (76.6%), and the mean age was 64.2 years. The cumulative incidence of newly detected IM at 1 year was 25.9% (95% CI 15.1–42.1%). Dysplasia was detected at the time of recurrence in four patients, and all cases were detected at the GE junction in the absence of visible BE. Patients with recurrent IM had longer baseline segments of BE (median, 4 cm vs. 2 cm, p = 0.03). Conclusions The rate of detection of new IM is high in patients who have undergone successful eradication of BE by RFA. Additionally, dysplasia can recur at the GE junction in the absence of visible BE. Future studies are warranted to identify those patients at increased risk for the development of recurrent intestinal metaplasia.

No abstract

Background A proportion of Barrett’s esophagus (BE) and esophageal adenocarcinoma (EAC) displays familial aggregation, known as familial Barrett’s esophagus (FBE). Pedigrees and characteristics of EAC in these families have been previously described. Aims We aimed to evaluate endoscopic and clinical characteristics of Barrett’s esophagus in FBE. Methods A cohort of 979 BE patients were retrospectively evaluated for FBE, defined as having a first-degree relative with BE or esophageal cancer, confirmed when possible by interview. FBE and sporadic BE were compared regarding demographic, clinical, and endoscopic characteristics. Potential FBE probands were contacted and interviewed to obtain full family pedigrees. Results Of 603 BE probands (61.6% of total cohort) with a documented family history, 35 (5.8%) had FBE. There was no difference between FBE and non-FBE probands with regard to BE length (median: 3 cm, IQR 2-5 vs. 3 cm, IQR 1-6 cm, respectively; p = 0.78) or hiatal hernia size (p = 0.90). FBE probands were younger (mean, 58.4 vs. 63.8; p = 0.02) and had a significant association with less-advanced neoplasia (adjusted OR 0.41, 95% CI 0.19–0.90). There was no obvious association between FBE and other malignancies. Conclusions There were no differences in endoscopic characteristics between FBE and non-FBE probands. While FBE patients were younger and had less-advanced neoplasia, we speculate that these findings may have been the result of more aggressive screening due to the family history. Further studies are warranted to determine whether familial clustering is due to genetic predisposition to development of BE or to risk of neoplastic progression.

No abstract