Systemic sclerosis is associated with increased in-patient mortality in patients hospitalized for heart failure.

AIMS: We aimed to analyse the characteristics and in-hospital outcomes of patients hospitalized for heart failure (HF) with co-morbid systemic sclerosis (SSc) and compare them to those without SSc, using data from the National Inpatient Sample from years 2016 to 2019. METHODS AND RESULTS: International Classification of Diseases, Tenth Revision diagnosis codes were used to identify hospitalized patients with a primary diagnosis of HF and secondary diagnoses of SSc from the National Inpatient Sample database from 2016 to 2019. Patients were divided into two groups: those with and without a secondary diagnosis of SSc. Baseline characteristics including demographics and co-morbidities, outcomes of mortality, length of stay (LOS), and costs were compared between the two groups. Multivariable logistic regression analysis was performed to adjust for confounders and assess the impact of SSc on in-hospital mortality, cost, and LOS. A total of 4 709 724 hospitalizations for HF were identified, with 8150 (0.17%) having a secondary diagnosis of SSc. These patients were predominantly female (82.3% vs. 47.8%; P = 0.01), younger (mean age of 67.4 vs. 71.4; P < 0.01), and had significantly lower rates of traditional cardiovascular risk factors such as coronary artery disease (35.8% vs. 50.6%; P < 0.01), hyperlipidaemia (39.1% vs. 52.9%; P < 0.01), diabetes (22.5% vs. 49.1%; P < 0.01), obesity (13.2% vs. 25.0%; P < 0.01), and hypertension (20.2% vs. 23.8%; P < 0.01). Higher rates of co-morbid pulmonary disease in the form of interstitial lung disease (23.1% vs. 2.0%; P < 0.01) and pulmonary hypertension (36.6% vs. 12.7%; P < 0.01) were noted in the SSc cohort. Unadjusted in-hospital mortality was significantly higher in the HF with SSc group [5.1% vs. 2.6%; odds ratio: 1.99; 95% confidence interval (CI): 1.60-2.48; P < 0.001]. Unadjusted mortality was also higher among female (86.7% vs. 47.0%; P < 0.01), Black (15.7% vs. 13.0%; P < 0.01), and Hispanic (13.3% vs. 6.9%; P < 0.01) patients in the SSc cohort. After adjusting for potential confounders, SSc remained independently associated with higher in-hospital mortality (adjusted odds ratio: 1.81; 95% CI: 1.44-2.28; P < 0.001). Patients with HF and SSc also had longer LOS (6.4 vs. 5.4; adjusted mean difference [AMD]: 0.37, 95% CI: 0.05-0.68; P = 0.02) and higher hospitalization costs ($67 363 vs. $57 128; AMD: 198.9; 95% CI: -4780 to 5178; P = 0.93). CONCLUSIONS: In patients hospitalized for HF, those with SSc were noted to have higher odds of in-hospital mortality than those without SSc. Patients with HF and SSc were more likely to be younger, female, and have higher rates of co-morbid interstitial lung disease and pulmonary hypertension at baseline with fewer traditional cardiovascular risk factors.

Prediction of Liver Enzyme Elevation Using Supervised Machine Learning in Patients With Rheumatoid Arthritis on Treatment with Methotrexate.

Objective The aim of this study is to develop a machine learning (ML) model to accurately predict liver enzyme elevation in rheumatoid arthritis (RA) patients on treatment with methotrexate (MTX) using electronic health record (EHR) data from a real-world RA cohort. Methods Demographic, clinical, biochemical, and prescription information from 569 RA patients initiated on MTX were collected retrospectively. The primary outcome was the liver transaminase elevation above the upper limit of normal (40 IU/mL), following the initiation of MTX. The total dataset was randomly split into a training (80%) and test set (20%) and used to develop a random forest classifier model. The best model was selected after hyper-parameter tuning and fivefold cross-validation. Results A total of 104 (18.2%) patients developed elevated transaminase while on MTX therapy. The best-performing predictive model had an accuracy/F1 score of 0.87. The top 10 predictive features were then used to create a limited feature model that retained most of the predictive accuracy, with an accuracy/F1 score of 0.86. Baseline high-normal transaminase levels, and higher lymphocyte and neutrophil blood count proportions were the highest predictors of elevated transaminase levels after MTX therapy. Conclusion Our proof-of-concept study suggests the possibility of building a well-performing ML model to predict liver transaminase elevation in RA patients being treated with MTX. Similar ML models could be used to identify "high-risk" patients and target them for early stratification.

Artificial intelligence in rheumatoid arthritis: potential applications and future implications.

The widespread adoption of digital health records, coupled with the rise of advanced diagnostic testing, has resulted in an explosion of patient data, comparable in scope to genomic datasets. This vast information repository offers significant potential for improving patient outcomes and decision-making, provided one can extract meaningful insights from it. This is where artificial intelligence (AI) tools like machine learning (ML) and deep learning come into play, helping us leverage these enormous datasets to predict outcomes and make informed decisions. AI models can be trained to analyze and interpret patient data, including physician notes, laboratory testing, and imaging, to aid in the management of patients with rheumatic diseases. As one of the most common autoimmune diseases, rheumatoid arthritis (RA) has attracted considerable attention, particularly concerning the evolution of diagnostic techniques and therapeutic interventions. Our aim is to underscore those areas where AI, according to recent research, demonstrates promising potential to enhance the management of patients with RA.

Assessing Anticoagulation Management and Shared Decision-Making Documentation From Providers Participating in the SUPPORT-AF II Study.

BACKGROUND: A previously tested intervention featured educational outreach with modified academic detailing (AD) to increase anticoagulation use in patients with atrial fibrillation. Currently, this study compares providers receiving and not receiving AD in terms of inclusion of AD educational topics and shared decision-making elements in documentation. METHODS: Physicians reviewed themes discussed with providers during AD and evaluated charts for evidence of shared decision-making. Frequencies of documentation of individual items for providers receiving AD versus non-AD providers were compared. To understand baseline documentation practices of AD providers, encounters of AD providers before their AD participation were randomly selected. RESULTS: There were 113 eligible encounters in the four months after AD-36 from AD providers and 77 from non-AD providers. Thirty-five encounters were identified from AD providers before participating in the intervention. Providers infrequently documented many reviewed items (% documenting): anticoagulation mentioned (44%), multiple options for anticoagulation (5%), CHA2DS2-VASc score (11%), bleeding risk factors (2%). Compared with non-AD providers, AD providers had statistically significant higher percentages for the following items: mention of anticoagulation (64% versus 35%), stroke risk (11% versus 0%), anticoagulation benefits (8% versus 0%), and patient involvement (17% versus 0%). There was no improvement, however, for AD providers compared with baseline documentation percentages. DISCUSSION: Providers infrequently documented important items in anticoagulation management and shared decision-making. AD participation did not improve documentation. Improving adoption of AD educational items may require more prolonged interaction with providers. Improving shared decision-making may require an intervention more focused on it and its documentation.