CMR Predictors of Favorable Outcome in Myocarditis: A Single-Center Experience.

Background: Cardiovascular magnetic resonance (CMR) has emerged as the most accurate, non-invasive method to support the diagnosis of clinically suspected myocarditis and as a risk-stratification tool in patients with cardiomyopathies. We aim to assess the diagnostic and prognostic role of CMR at diagnosis in patients with myocarditis. Methods: We enrolled consecutive single-center patients with 2013 ESC consensus-based endomyocardial biopsy (EMB)-proven or clinically suspected myocarditis undergoing CMR at diagnosis. The pre-specified outcome was defined as NYHA class > I and echocardiographic left ventricular ejection fraction (LVEF) < 50% at follow-up. Results: We included 207 patients (74% male, median age 36 years; 25% EMB-proven). CMR showed the highest sensitivity in myocarditis with infarct-like presentation. Patients with EMB-proven myocarditis were more likely to have diffuse LGE and right ventricular LGE (p < 0.001), which was also more common among patients with arrhythmic presentation (p = 0.001). The outcome was met in 17 patients at any follow-up time point, more commonly in those with larger biventricular volumes (p < 0.001), CMR-based diagnosis of dilated cardiomyopathy (p < 0.001), and ischemic LGE (p = 0.005). Higher biventricular systolic function (p < 0.001) and greater LGE extent (p = 0.033) at diagnosis had a protective effect. Conclusions: In our single-center cohort of rigorously defined myocarditis patients, higher biventricular systolic function and greater LGE extent on CMR at diagnosis identified patients with better functional class and higher left ventricular ejection fraction at follow-up. Conversely, larger biventricular volumes, CMR-based DCM features, and the presence of an ischemic LGE pattern at diagnosis were predictors of worse functional class and LV systolic dysfunction at follow-up. Larger prospective studies are warranted to extend our findings to multi-center cohorts.

Physical activity assessment with wearable devices in rheumatic diseases: a systematic review and meta-analysis.

OBJECTIVES: In the management of rheumatic musculoskeletal disorders (RMDs), regular physical activity (PA) is an important recognized non-pharmacological intervention. This systematic review and meta-analysis aims to evaluate how the use of wearable devices (WDs) impacts physical activity in patients with noninflammatory and inflammatory rheumatic diseases. METHODS: A comprehensive search of articles was performed in PubMed, Embase, CINAHL and Scopus. A random-effect meta-analysis was carried out on the number of steps and moderate-vigorous physical activity (MVPA). Univariable meta-regression models were computed to assess the possibility that the study characteristics may act as modifiers on the final meta-analysis estimate. RESULTS: In the analysis, 51 articles were included, with a total of 7488 participants. Twenty-two studies considered MVPA outcome alone, 16 studies considered the number of steps alone, and 13 studies reported information on both outcomes. The recommended PA threshold was reached for MVPA (36.35, 95% CI 29.39, 43.31) but not for daily steps (-1092.60, -1640.42 to -544.77). Studies on patients with fibromyalgia report a higher number (6290, 5198.65-7381.62) of daily steps compared with other RMDs. Patients affected by chronic inflammatory arthropathies seemed to fare better in terms of daily steps than the other categories. Patients of younger age reported a higher overall level of PA than elderly individuals for both the number of steps and MVPA. CONCLUSION: Physical activity can be lower than the recommended threshold in patients with RMDs when objectively measured using WD. WDs could be a useful and affordable instrument for daily monitoring physical activity in RMDs and may support an increase in activity levels. PROSPERO TRIAL REGISTRATION: CRD42021227681, https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=227681.

A Machine-Learning Model for the Prognostic Role of C-Reactive Protein in Myocarditis.

Aims: The role of inflammation markers in myocarditis is unclear. We assessed the diagnostic and prognostic correlates of C-reactive protein (CRP) at diagnosis in patients with myocarditis. Methods and results: We retrospectively enrolled patients with clinically suspected (CS) or biopsy-proven (BP) myocarditis, with available CRP at diagnosis. Clinical, laboratory and imaging data were collected at diagnosis and at follow-up visits. To evaluate predictors of death/heart transplant (Htx), a machine-learning approach based on random forest for survival data was employed. We included 409 patients (74% males, aged 37 ± 15, median follow-up 2.9 years). Abnormal CRP was reported in 288 patients, mainly with CS myocarditis (p < 0.001), recent viral infection, shorter symptoms duration (p = 0.001), chest pain (p < 0.001), better functional class at diagnosis (p = 0.018) and higher troponin I values (p < 0.001). Death/Htx was reported in 13 patients, of whom 10 had BP myocarditis (overall 10-year survival 94%). Survival rates did not differ according to CRP levels (p = 0.23). The strongest survival predictor was LVEF, followed by anti-nuclear auto-antibodies (ANA) and BP status. Conclusions: Raised CRP at diagnosis identifies patients with CS myocarditis and less severe clinical features, but does not contribute to predicting survival. Main death/Htx predictors are reduced LVEF, BP diagnosis and positive ANA.

Identifying Predictors of Anal HPV Status in HPV-Vaccinated MSM: A Machine Learning Approach.

Anal human papillomavirus (HPV) infection has a high prevalence in men who have sex with men (MSM), resulting in an increased risk for anal cancer. The present work aimed to identify factors associated with HPV in a prospective cohort of HPV-vaccinated MSM using a random forest (RF) approach. This observational study enrolled MSM patients admitted to an Italian (sexually transmitted infection) STI-AIDS Unit. For each patient, rectal swabs for 28 different HPV genotype detection were collected. Two RF algorithms were applied to evaluate predictors that were most associated with HPV. The cohort included 135 MSM, 49% of whom were HIV-positive with a median age of 39 years. In model 1 (baseline information), age, age sexual debut, HIV, number of lifetime sex partners, STIs, were most associated with the HPV. In model 2 (follow-up information), age, age sexual debut, HIV, STI class, and follow-up. The RF algorithm exhibited good performances with 61% and 83% accuracy for models 1 and 2, respectively. Traditional risk factors for anal HPV infection, such as drug use, receptive anal intercourse, and multiple sexual partner, were found to have low importance in predicting HPV status. The present results suggest the need to focus on HPV prevention campaigns.

The SYSTEMIC Project: A Pilot Study to Develop a Registry of Patients With an Ostomy for Predictive Modeling of Outcomes.

BACKGROUND: Stomal and peristomal skin complications represent a significant burden on the physical and psychological well-being of patients. PURPOSE: To develop a predictive tool for identifying the risk of complications in patients following ostomy surgery. METHODS: The oStomY regiSTry prEdictive ModelIng outCome (SYSTEMIC) project was developed to improve patient-oriented outcomes. Demographic, medical history, and stoma-related variables were obtained from patients at the wound ostomy clinic of the University Hospital of Padova, Italy. A follow-up assessment was completed 30 days after stoma surgery. Two (2) Bayesian machine learning approaches (naïve Bayes) were carried out to define an automatic peristomal complication predictive tool. A sensitivity analysis was performed to evaluate the possible effects of the prior choices on naïve Bayes performance. RESULTS: The algorithms were based on preliminary data from 52 patients (28 [53.3%] had a colostomy and 24 [46.7%] had an ileostomy). In terms of postoperative complications, no significant differences were observed between patients with different body mass indices (P = .16), those who underwent elective surgery compared with those who underwent emergency surgery (P = .66), and those who had or had not been preoperatively sited (P = .44). The algorithms showed an overall moderate ability to correctly classify patients according to the presence of peristomal complications (accuracy of nearly 70% in both models). In the the data-driven prior model, the probability of developing complications was greater for  participants with malignancies or other diseases (0.3314 for both levels) than for patients with diverticula and bowel perforation (0.1453) or inflammatory bowel disease (0.1918). CONCLUSION: The development of an easy-to-use algorithm may help nonspecialized nurses evaluate the likelihood of future peristomal complications in patients with an ostomy and implement preemptive measures.

A Machine Learning Approach for Investigating Delirium as a Multifactorial Syndrome.

Delirium is a psycho-organic syndrome common in hospitalized patients, especially the elderly, and is associated with poor clinical outcomes. This study aims to identify the predictors that are mostly associated with the risk of delirium episodes using a machine learning technique (MLT). A random forest (RF) algorithm was used to evaluate the association between the subject's characteristics and the 4AT (the 4 A's test) score screening tool for delirium. RF algorithm was implemented using information based on demographic characteristics, comorbidities, drugs and procedures. Of the 78 patients enrolled in the study, 49 (63%) were at risk for delirium, 32 (41%) had at least one episode of delirium during the hospitalization (38% in orthopedics and 31% both in internal medicine and in the geriatric ward). The model explained 75.8% of the variability of the 4AT score with a root mean squared error of 3.29. Higher age, the presence of dementia, physical restraint, diabetes and a lower degree are the variables associated with an increase of the 4AT score. Random forest is a valid method for investigating the patients' characteristics associated with delirium onset also in small case-series. The use of this model may allow for early detection of delirium onset to plan the proper adjustment in healthcare assistance.

Communicating Risk Regarding Food Consumption: The Case of Processed Meat.

The present research combines real data and parameters found in recent literature that were used to design realistic scenarios demonstrating the potential effects (benefits and costs) of the World Health Organization (WHO)'s risk communication regarding the consumption of processed meat, which was proven to be associated with an increased risk of colorectal cancer (CRC) in an International Agency for Research on Cancer (IARC)/WHO report. The impact of the risk communication of processed meat consumption was simulated using Monte Carlo microsimulation models. The results showed that a 1% reduction in the number of high-level processed meat consumers may lead to a yearly decrease in CRC cases of 406.43 (IC 95%: -243.94, 1056.81), while the more extreme scenario of a 15% reduction may lead to 2086.62 fewer cases (IC 95%: 1426.66, 2746.57). On the other hand, if demand contraction in the processed meat sector resulted in a 0.1% loss in employment, one could expect 27.23 all-cause mortalities attributable to job loss (IC 95%: 16.55, 37.80). This simulation study demonstrates that caution should be taken when implementing public awareness campaigns, particularly when the prevention message is not straightforward.