Enhancing the identification of rheumatoid arthritis-associated interstitial lung disease through text mining of chest computerized tomography reports.

OBJECTIVES: Algorithms have been developed to identify rheumatoid arthritis-interstitial lung disease (RA-ILD) in administrative data with positive predictive values (PPVs) between 70 and 80%. We hypothesized that including ILD-related terms identified within chest computed tomography (CT) reports through text mining would improve the PPV of these algorithms in this cross-sectional study. METHODS: We identified a derivation cohort of possible RA-ILD cases (n = 114) using electronic health record data from a large academic medical center and performed medical record review to validate diagnoses (reference standard). ILD-related terms (e.g., ground glass, honeycomb) were identified in chest CT reports by natural language processing. Administrative algorithms including diagnostic and procedural codes as well as specialty were applied to the cohort both with and without the requirement for ILD-related terms from CT reports. We subsequently analyzed similar algorithms in an external validation cohort of 536 participants with RA. RESULTS: The addition of ILD-related terms to RA-ILD administrative algorithms increased the PPV in both the derivation (improvement ranging from 3.6 to 11.7%) and validation cohorts (improvement 6.0 to 21.1%). This increase was greatest for less stringent algorithms. Administrative algorithms including ILD-related terms from CT reports exceeded a PPV of 90% (maximum 94.6% derivation cohort). Increases in PPV were accompanied by a decline in sensitivity (validation cohort -3.9 to -19.5%). CONCLUSIONS: The addition of ILD-related terms identified by text mining from chest CT reports led to improvements in the PPV of RA-ILD algorithms. With high PPVs, use of these algorithms in large data sets could facilitate epidemiologic and comparative effectiveness research in RA-ILD.

Risk of malignancy in patients with chronic kidney disease.

BACKGROUND: Fifteen percent of US adults have chronic kidney disease (CKD). The effect of CKD on the development of different malignancies is unknown. Understanding the effect of CKD on the risk of development of cancer could have important implications for screening and early detection of cancer in these patients. METHODS: Adult CKD patients [estimated GFR (eGFR) <60ml/min/1.73m2] between January 2001 and December 2020 were identified in this single institution study. Patients were divided into four stages of CKD by eGFR. The incidence of cancer and time to development of the first cancer were identified. Multivariable models were used to compare the overall cancer incidence while considering death as a competing risk event and adjusting for relevant covariates (sex, race, diabetes, hypertension, CAD, smoking or not, BMI, and CKD stages). Separate multivariable models of the incidence of cancers were conducted in each age group. Multivariable Cox models were used to fit the overall death adjusting for relevant covariates. Patients were censored at the conclusion of the study period (December 31, 2020). Statistical analysis was performed with SAS software (version 9.4). RESULTS: Of the 13,750 patients with a diagnosis of CKD in this cohort, 2,758 (20.1%) developed a malignancy. The median time to development of cancer following a diagnosis of CKD was 8.5 years. Factors associated with the risk of developing cancer in CKD patients included increasing age, male sex and worsening chronic kidney disease, while diabetes was associated with a lower risk of malignancy. On multivariate analysis, the factors associated with increased mortality in patients who developed cancer included increasing age, diabetes and lower eGFR. CONCLUSION: CKD is an increased risk factor for the development of various malignancies. Age appropriate cancer screening should be aggressively pursued in those with progressive CKD.

Comparison of Rates of Lower Extremity Amputation in Patients With and Without Gout in the US Department of Veterans Affairs Health System.

Importance: Cardiometabolic and other risk factors could render patients with gout more likely to undergo lower extremity amputation (LEA). Objective: To examine the rate of and factors associated with LEA in patients with gout. Design, Setting, and Participants: In this matched cohort study using national administrative data, multivariable Cox proportional hazards regression models were used to examine the associations of gout with LEA. In analyses limited to patients with gout, attributes of serum urate control and treatment with urate-lowering therapy were examined as factors associated with LEA. This study included patients who used US Department of Veterans Affairs services from January 1, 2000, to July 31, 2015. Patients with gout were identified using diagnostic codes and matched with up to 10 controls by age, sex, and year of benefit enrollment. Data analysis was performed from January 26, 2021, to September 3, 2021. Exposures: Gout classification served as the primary independent variable of interest. In analyses limited to patients with gout, factors associated with serum urate control and urate-lowering therapy were examined. Main Outcomes and Measures: Overall LEA, as well as toe, transmetatarsal, below-the-knee, and above-the-knee amputation. Results: This cohort study included 5 924 918 patients, 556 521 with gout (mean [SD] age, 67 [12] years; 550 963 (99.0%) male; 88 853 [16.0%] Black non-Hispanic; 16 981 [4.3%] Hispanic/Latinx; 345 818 [62.1%] White non-Hispanic; 80 929 [14.5%] with race and ethnicity data missing; and 23 940 [4.3%] classified as other) and 5 368 397 without gout (mean [SD] age, 67 [12] years; 5 314 344 [99.0%] male; 558 464 [10.4%] Black non-Hispanic; 204 291 [3.0%] Hispanic/Latinx; 3 188 504 [59.4%] White non-Hispanic; 1 257 739 [23.4%)] with race and ethnicity data missing; and 159 399 [3.0%] classified as other). Compared with patients without gout, patients with gout were more likely to undergo amputation, an increased rate that remained after adjustment (adjusted hazard ratio, 1.20; 95% CI, 1.16-1.24) and was highest for below-the-knee amputation (adjusted hazard ratio, 1.59; 95% CI, 1.39-1.81). In those with gout, poor serum urate control (mean >7 mg/dL during the preceding year) was associated with a 25% to 37% increase in the rate of amputation. In contrast, treatment with urate-lowering therapy was not associated with the LEA rate. Conclusions and Relevance: In this matched cohort study, patients with gout were more likely to undergo LEA. This increase was independent of other comorbidities that have been associated with amputation, including diabetes and peripheral vascular disease. Serum urate control was independently associated with the LEA rate, suggesting the possibility that lower extremity amputation may be preventable in some patients.