Applications of Machine Learning in Cardiology.

In this digital era, artificial intelligence (AI) is establishing a strong foothold in commercial industry and the field of technology. These effects are trickling into the healthcare industry, especially in the clinical arena of cardiology. Machine learning (ML) algorithms are making substantial progress in various subspecialties of cardiology. This will have a positive impact on patient care and move the field towards precision medicine. In this review article, we explore the progress of ML in cardiovascular imaging, electrophysiology, heart failure, and interventional cardiology.

Artificial intelligence and machine learning in cardiovascular computed tomography.

Computed tomography (CT) is emerging as a prominent diagnostic modality in the field of cardiovascular imaging. Artificial intelligence (AI) is making significant strides in the field of information technology, the commercial industry, and health care. Machine learning (ML), a branch of AI, can optimize the performance of CT and augment the assessment of coronary artery disease. These ML platforms can automate multiple tasks, perform calculations, and integrate information from a variety of data sources. In this review article, we explore the ML in CT imaging.

Outpatient Antibiotic Prescribing Patterns for Adult End-Stage Renal Disease Patients in New York State.

BACKGROUND: Infections are important complications of end-stage renal disease (ESRD) with few studies having investigated oral antibiotic use. Inappropriate antibiotic prescribing can contribute to multidrug-resistant organisms and Clostridioides difficile infections seen in ESRD. This study investigates antibiotic prescribing practices in ESRD across New York State (NYS). METHODS: Retrospective case-control study from 2016 to 2017 of NYS ESRD and non-ESRD patients analyzing Medicare part B billing codes, 7 days before and 3 days after part D claims. Frequencies of each infection, each antibiotic, dosages, and the antibiotics associated with infections were assessed using χ 2 analysis. A NYS small dialysis organization comprising approximately 2200 patients was also analyzed. Outcomes measured were the frequencies of infections and of each antibiotic prescribed. Incidence measures included antibiotics per 1000 and individuals receiving antibiotics per 1000. RESULTS: A total of 48 100 infections were treated in 35 369 ESRD patients and 2 544 443 infections treated in 3 777 314 non-ESRD patients. ESRD patients were younger, male, and African American. ESRD and non-ESRD patients receiving antibiotics was 520.29/1000 and 296.48/1000, respectively (P < .05). The prescription incidence was 1359.95/1000 ESRD vs 673.61/1000 non-ESRD patients. In 36%, trimethoprim-sulfamethoxazole dosage was elevated by current ESRD guidelines. Top infectious categories included nonspecific symptoms, skin, and respiratory for ESRD; and respiratory, nonspecific symptoms, and genitourinary in non-ESRD. CONCLUSIONS: This study identifies issues with appropriate antibiotic usage stressing the importance of antibiotic education to nephrologist and nonnephrologist providers. It provides support for outpatient antibiotic stewardship programs.

TSAT is a better predictor than ferritin of hemoglobin response to Epoetin alfa in US dialysis patients.

Clinical guidelines recommend concurrent treatment of anemia in end-stage renal disease with erythropoiesis-stimulating agents (ESAs) and iron. However, there are mixed data about optimal iron supplementation. To help address this gap, the relationship between iron markers and hemoglobin (Hb) response to ESA (Epoetin alfa) dose was examined. Electronic medical records of 1902 US chronic hemodialysis patients were analyzed over a 12-month period between June 2009 and June 2010. The analysis included patients who had at least one Hb value during each 4-week interval for four consecutive intervals (k - 2, k - 1, k, and k + 1; k is the index interval), received at least one ESA dose during intervals k - 1 or k, had at least one transferrin saturation (TSAT) value at interval k, and at least one ferritin value during intervals k - 2, k - 1, or k. Effect modification by TSAT and ferritin on Hb response was evaluated using the generalized estimating equations approach. Patients had a mean (standard deviation) age of 62 (15) years; 41% were Caucasian, 34% African American, 65% had hypertension, and 39% diabetes. Transferrin saturation, but not ferritin, had a statistically significant (P < 0.05) modifying effect on Hb response. Maximum Hb response was achieved when TSAT was 34%, with minimal incremental effect beyond these levels. Of the two standard clinical iron markers, TSAT should be used as the primary marker of the modifying effect of iron on Hb response to ESA. Long-term safety of iron use to improve Hb response to ESA warrants further study.

Safety and effectiveness of ferumoxytol in hemodialysis patients at 3 dialysis chains in the United States over a 12-month period.

BACKGROUND: Intravenous (IV) iron is the treatment of choice for iron-deficiency anemia (IDA) in patients with dialysis-dependent chronic kidney disease (DD-CKD). However, IV iron products have been associated with serious adverse events (SAEs), including anaphylactoid reactions. Ferumoxytol is an IV iron preparation that can be injected over a short period of time. Although randomized clinical trials support ferumoxytol's efficacy and safety, additional insights may be drawn from the acquisition of long-term, repeat dosing efficacy and safety data in a real-world setting. OBJECTIVE: The goal of this study was to characterize the effectiveness and safety profile of ferumoxytol as administered to adult DD-CKD patients with IDA in a real-world setting. The ability of ferumoxytol to maintain hemoglobin (Hb), transferrin saturation (TSAT), and ferritin treatment targets established by the 2006 Kidney Disease Outcomes Quality Initiative guidelines was determined in 3 medium-sized US-based dialysis chains. METHODS: This retrospective, observational study was conducted to examine laboratory and dosing data for all patients who received any dose of ferumoxytol at 3 US-based dialysis chains over a 12-month period. Investigators and/or physicians from each of the chains also made independent determinations regarding the seriousness of any adverse event (AE). Special attention was paid to the incidence and types of AEs and SAEs that were potentially associated with ferumoxytol. RESULTS: Over the 12-month observation period, 8666 patients (mean [SD] age in chains A, B and C, 63.9 [14.8], 63.9 [14.9] and 63.6 [15.1], respectively), were treated with 33,358 doses of ferumoxytol across the 3 chains. Treatment with ferumoxytol corresponded to an increased mean monthly Hb level relative to baseline (0.13-0.69 g/dL) and led to an increase in the proportion of patients maintained within the target Hb range of 10 to 12 g/dL (61%-72%). Ferumoxytol was also associated with increases in TSAT and ferritin that stabilized throughout the observation period. Incidence of AEs was similar across the 3 chains; between 0.07% and 1.77% of all patients treated at each chain experienced an AE associated with ferumoxytol administration. SAEs were reported in 0.2% of patients. The most common AEs reported (≥6 patients) were nausea (0.37% of patients), pruritus (0.29%), vomiting (0.25%), hypotension (0.21%), and dyspnea (0.20%). Two patients (0.02%) experienced anaphylactoid reactions. The AE profile of ferumoxytol remained consistent with that reported from controlled clinical trials. CONCLUSIONS: These long-term data, which include repeat dosing in a large number of DD-CKD patients with IDA in a real-world setting, confirm the effectiveness of ferumoxytol in increasing and maintaining Hb levels within the target range and with favorable assessments of long-term safety.

Projected impact of the proposed "bundled" ESRD payment system on a small dialysis organization.

Payment for outpatient hemodialysis services is currently made by the Centers for Medicare & Medicaid Services on a per-treatment basis using a partially "bundled" composite rate adjusted for geographic and patient characteristics, plus a separately billable portion for medications and services not included in the bundle. In response to concerns over rising costs of the End-Stage Renal Disease Program, and specifically the increasing use of erythropoiesis-stimulating agents, Congress has mandated a new, more inclusive prospective payment system, in which current composite rate services, separately billable medications, and dialysis-related laboratory services will be included in a single payment. It is expected that the so-called bundle will apply a geographic wage adjuster and patient-specific case-mix factors to a base rate to calculate a per-patient, per treatment payment unit. We have modeled the proposed bundle and entered clinical and financial data for 118 Medicare patients dialyzed at a suburban dialysis center in New York State during 2006. Under the proposed bundled system, we stand to lose as much as $118,000 per year in revenue, and we find the case-mix adjusters appear to be poor predictors of our actual costs. We conclude that the proposed bundle places the small dialysis provider at significant financial risk.

Rituximab treatment of dysproteinemias affecting the kidney: a review of three cases.

The renal diseases associated with monoclonal immunoglobulin deposits constitute a diverse range of clinical and pathological entities. Renal prognosis is variable, and there currently are no standard treatment regimens. We describe the effect of rituximab treatment on 3 patients with renal insufficiency and proteinuria with monoclonal immunoglobulin deposits associated with glomerulonephritis on renal biopsy. Two patients with hypertension and chronic lymphocytic leukemia had a membranoproliferative glomerulonephritis pattern on kidney biopsy associated with monoclonal immunoglobulin G deposits. Both patients experienced partial remission of their disease and 1 patient was able to come off hemodialysis therapy after treatment with 7 and 11 biweekly doses of rituximab, 375 mg/m(2), in addition to angiotensin-converting enzyme inhibitor and angiotensin receptor blocker. Both patients subsequently experienced relapse of their hematologic and renal diseases and eventually progressed to end-stage renal disease and death. A third patient had diffuse proliferative glomerulonephritis with immunoglobulin G lambda deposits on renal biopsy. She was treated with an angiotensin receptor blocker and two 1,000-mg infusions of rituximab separated by 2 weeks, with sustained partial remission at 18 months' follow-up. Rituximab therapy, in addition to corticosteroids and angiotensin blockade, may improve the clinical course of patients with renal diseases associated with dysproteinemias, delaying the onset of end-stage renal failure or other adverse outcomes. Additional clinical studies should be planned.