Machine learning: Predicting hospital length of stay in patients admitted for lupus flares.

BACKGROUND: Although rare, severe systemic lupus erythematosus (SLE) flares requiring hospitalization account for most of the direct costs of SLE care. New machine learning (ML) methods may optimize lupus care by predicting which patients will have a prolonged hospital length of stay (LOS). Our study uses a machine learning approach to predict the LOS in patients admitted for lupus flares and assesses which features prolong LOS. METHODS: Our study sampled 5831 patients admitted for lupus flares from the National Inpatient Sample Database 2016-2018 and collected 90 demographics and comorbidity features. Four machine learning (ML) models were built (XGBoost, Linear Support Vector Machines, K Nearest Neighbors, and Logistic Regression) to predict LOS, and their performance was evaluated using multiple metrics, including accuracy, receiver operator area under the curve (ROC-AUC), precision-recall area under the curve (PR- AUC), and F1-score. Using the highest-performing model (XGBoost), we assessed the feature importance of our input features using Shapley value explanations (SHAP) to rank their impact on LOS. RESULTS: Our XGB model performed the best with a ROC-AUC of 0.87, PR-AUC of 0.61, an F1 score of 0.56, and an accuracy of 95%. The features with the most significant impact on the model were "the need for a central line," "acute dialysis," and "acute renal failure." Other top features include those related to renal and infectious comorbidities. CONCLUSION: Our results were consistent with the established literature and showed promise in ML over traditional methods of predictive analyses, even with rare rheumatic events such as lupus flare hospitalizations.

Colorectal Cancer Among Gout Patients Undergoing Colonoscopy.

BACKGROUND/OBJECTIVE: The connection between gout and various cancers remains unclear. We assessed the relationship between gout and colorectal cancer in a population of veterans. METHODS: We reviewed the Computerized Patient Record System of the VA New York Harbor Health Care System to assess the 10-year occurrence of colorectal cancer in patients with gout undergoing colonoscopy, versus patients with osteoarthritis but no gout. RESULTS: Gout and osteoarthritis subjects were similar in age, ethnicity, body mass index, and smoking history. Among 581 gout and 598 osteoarthritis subjects with documented colonoscopies, the 10-year prevalence of colorectal cancer was significantly lower in gout (0.8%) versus osteoarthritis (3.7%) (p = 0.0008) patients. Differences in colorectal cancer rates remained significant after stratifying for nonsteroidal anti-inflammatory drug use. Among gout subjects, use of colchicine and/or allopurinol, as well as the presence/absence of concomitant osteoarthritis, did not influence colorectal cancer occurrence. On subanalysis, differences in colorectal cancer occurrence between gout and osteoarthritis subjects persisted among those who underwent diagnostic (0.5% in gout vs 4.6% in osteoarthritis subjects, p < 0.001) but not screening (0.9% in gout subjects vs 1% in osteoarthritis subjects, p = 1.0) colonoscopy. There was no significant difference in nonmalignant colorectal polyp occurrence between gout and osteoarthritis subjects. CONCLUSIONS: Subjects with gout had decreased colonoscopy-documented occurrence of colorectal cancer compared with osteoarthritis subjects, suggesting a possible protective effect.

Update on colchicine, 2017.

Colchicine is an ancient medication that is currently approved for the treatment of gout and FMF. However, colchicine has a wide range of anti-inflammatory activities, and studies indicate that it may be beneficial in a variety of other conditions. This paper reviews the evidence for the well-established use of colchicine in gout, as well as several other rheumatic diseases. In addition, we highlight the potential benefit of colchicine in cardiac disease, including coronary artery disease in patients both with and without gout.

Allopurinol use and type 2 diabetes incidence among patients with gout: A VA retrospective cohort study.

To assess the impact of allopurinol on diabetes in a retrospective cohort of Veterans' Affairs patients with gout.The New York Harbor VA computerized patient record system was searched to identify patients with an ICD-9 code for gout meeting at least 4 modified 1977 American Rheumatology Association gout diagnostic criteria. Patients were divided into subgroups based on >30 continuous days of allopurinol, versus no allopurinol. New diagnoses of diabetes, defined according to American Diabetes Association diagnostic criteria or clinical documentation explicitly stating a new diagnosis of diabetes, were identified during an observation period from January 1, 2000 through December 31, 2015.Six hundred six gout patients used allopurinol >30 continuous days, and 478 patients never used allopurinol. Over an average 7.9 ±â€Š4.8 years of follow-up, there was no significant difference in diabetes incidence between the allopurinol and non-allopurinol groups (11.7/1000 person-years vs 10.0/1000 person-years, P = .27). A lower diabetes incidence in the longest versus shortest quartiles of allopurinol use (6.3 per 1000 person-years vs 19.4 per 1000 person-years, P<.0001) was attributable to longer duration of medical follow-up.In this study, allopurinol use was not associated with decreased diabetes incidence. Prospective studies may further elucidate the relationship between hyperuricemia, gout, xanthine oxidase activity, and diabetes, and the potential impact of gout treatments on diabetes incidence.

Colchicine Use and Incident Coronary Artery Disease in Male Patients With Gout.

BACKGROUND: Inflammation is associated with coronary artery disease (CAD) and myocardial infarction (MI). Patients with gout are at increased risk of MI, and colchicine is associated with a reduced risk of MI. The objective of this study was to determine whether colchicine prevents incident development of CAD in patients with gout. METHODS: This retrospective study followed a cohort of male patients with gout without known CAD at the time of diagnosis of gout in the VA New York Harbor Healthcare System. The association between colchicine use and development of incident CAD, defined as evidence of ischemia or obstructive CAD on stress test or angiography, was determined using an inverse probability weighted (IPW) Cox proportional hazard model. RESULTS: Among 178,877 patients, 1638 met criteria of gout, of whom 722 without known CAD at baseline (446 colchicine users and 276 nonusers) were followed for a median of 96 months (57 to 117). A trend toward association between use of colchicine and reduced incident CAD was observed but not statistically significant (IPW hazard ratio [HR], 0.49; 0.23-1.05). In patients without chronic kidney disease, use of colchicine was associated with a lower rate of incident CAD (interaction P = 0.005, IPW HR, 0.31; 0.14-0.70). Colchicine was also associated with a lower rate of the composite of incident CAD and MI (IPW HR, 0.37; 0.16-0.83). CONCLUSIONS: In male patients with gout and no known CAD, a trend of reduced incident CAD was observed with use of colchicine that was not statistically significant. Larger, prospective studies will be required to assess the primary prevention benefit of colchicine definitively.

Colchicine: old and new.

Although colchicine has been a focus of research, debate, and controversy for thousands of years, the US Food and Drug Administration just approved it in 2009. Over the past decade, advances in the knowledge of colchicine pharmacology, drug safety, and mechanisms of action have led to changes in colchicine dosing and to potential new uses for this very old drug. In this review, we discuss the pharmacologic properties of colchicine and summarize what is currently known about its mechanisms of action. We then discuss and update the use of colchicine in a variety of illnesses, including rheumatic and, most recently, cardiovascular diseases.

Early glaucoma involves both deep local, and shallow widespread, retinal nerve fiber damage of the macular region.

PURPOSE: To better understand the nature of early glaucomatous damage of the macula by comparing the results from 10-2 visual fields, optical coherence tomography (OCT) macular cube scans, and OCT circumpapillary circle scans. METHODS: One eye of each of 66 glaucoma patients or suspects, with a mean deviation (MD) on the 24-2 visual field (VF) test of better than -6 decibels (dB), was prospectively tested with 10-2 VFs and OCT macular cube and circumpapillary circle scans. Thickness and probability maps of the retinal ganglion cell plus inner plexiform (RGC+) layers were generated. A hemifield was considered abnormal if both the macular RGC+ and the 10-2 probability plots were abnormal (cluster criteria). The thickness plots of the circumpapillary retinal nerve fiber layer (RNFL) were analyzed in the context of a model that predicted the region of the disc associated with macular damage. RESULTS: Twenty-seven hemifields (20 eyes) had abnormal 10-2 and RGC+ probability plots: 7 in upper VF/inferior retina, 6 in lower VF/superior retina, and 7 in both hemifields. Both shallow widespread and deep local thinning of the circumpapillary RNFL were observed. The local defects were more common and closer to fixation in the upper VF/inferior retina as predicted. CONCLUSIONS: A model of glaucomatous damage of the macula predicted the location of both the widespread and local defects in the temporal and inferior disc quadrants. Optical coherence tomography scans of the circumpapillary RNFL and the macular RGC+ layer can aid in the identification of these defects and help in the interpretation of 24-2 and 10-2 VF tests.