Enhanced Detection of Heart Valve Disease Using Integrated Artificial Intelligence at Scale.

BACKGROUND: Undertreatment of heart valve disease creates unnecessary patient risk. Poorly integrated healthcare data systems are unequipped to solve this problem. A software program using a rules-based algorithm to search the electronic health record for heart valve disease among patients treated by healthcare systems in the United States may provide a solution. METHODS: A software interface allowed concurrent access to picture archiving communication systems, the electronic health record, and other sources. The software platform was created to programmatically run a rules engine to search structured and unstructured data for identification of moderate or severe heart valve disease using guideline-reported values. Incidence and progression of disease as well as compliance with a care pathway were assessed. RESULTS: In 2 health institutions in the United States 60,145 patients had 77,215 echocardiograms. Moderate or severe aortic stenosis (AS) was identified at a rate of 9.1% of patients (5474 and 6910 echocardiograms) in this population. The precision and accuracy of the algorithm for the detection of moderate or severe AS was 92.9% and 98.6%, respectively. Thirty-five percent of patients (441/1265) with moderate stenosis and a subsequent echocardiogram progressed to severe stenosis (mean interval, 358 days). In 1 sample 70.3% of moderate AS patients lacked a 6-month echocardiogram or appointment. The platform enabled 100% accountability for all patients with severe AS. CONCLUSIONS: A rules-based software program enhances detection of heart valve disease and can be used to measures disease progression and care pathway compliance.

Outcomes in the Randomized CoreValve US Pivotal High Risk Trial in Patients With a Society of Thoracic Surgeons Risk Score of 7% or Less.

Importance: Transcatheter aortic valve replacement (TAVR) is now a well-accepted alternative to surgical AVR (SAVR) for patients with symptomatic aortic stenosis at increased operative risk. There is interest in whether TAVR would benefit patients at lower risk. Objective: The Society of Thoracic Surgeons Predicted Risk of Mortality (STS PROM) has trended downward in US TAVR trials and the STS/American College of Cardiology Transcatheter Valve Therapy Registry. We hypothesized that if the Society of Thoracic Surgeons Predicted Risk of Mortality (STS PROM) alone is sufficient to define decreased risk, the contribution to survival based on the degree of invasiveness of the TAVR procedure will decrease, making it more difficult to show improved survival and benefit over SAVR. Design, Setting, and Participants: The CoreValve US Pivotal High Risk Trial was a multicenter, randomized, noninferiority trial. This retrospective analysis evaluated patients who underwent an attempted implant and had an STS PROM of 7% or less. The trial was performed at 45 US sites. Patients had severe aortic stenosis and were at increased surgical risk based on their STS PROM score and other risk factors. Interventions: Eligible patients were randomly assigned (1:1) to self-expanding TAVR or to SAVR. Main Outcomes and Measures: We retrospectively stratified patients by the overall median STS PROM score (7%) and analyzed clinical outcomes and quality of life using the Kansas City Cardiomyopathy Questionnaire in patients with an STS PROM score of 7% or less. Results: The mean (SD) ages were 81.5 (7.6) years for the TAVR group and 81.2 years (6.6) for the SAVR group. A little more than half were men (57.9% in the TAVR group and 55.8% in the SAVR group). Of 750 patients who underwent attempted implantation, 383 (202 TAVR and 181 SAVR) had an STS PROM of 7% or less (median [interquartile range]: TAVR, 5.3% [4.3%-6.1%]; SAVR, 5.3% [4.1%-5.9%]). Two-year all-cause mortality for TAVR vs SAVR was 15.0% (95% CI, 8.9-10.0) vs 26.3% (95% CI, 19.7-33.0) (log rank P = .01). The 2-year rate of stroke for TAVR vs SAVR was 11.3% vs 15.1% (log rank P = .50). Quality of life by the Kansas City Cardiomyopathy Questionnaire summary score showed significant and equivalent increases in both groups at 2 years (mean [SD] TAVR, 20.0 [25.0]; SAVR, 18.6 [23.6]; P = .71; both P < .001 compared with baseline). Medical benefit, defined as alive with a Kansas City Cardiomyopathy Questionnaire summary score of at least 60 and a less than 10-point decrease from baseline, was similar between groups at 2 years (TAVR, 51.0%; SAVR, 44.4%; P = .28). Conclusions and Relevance: Self-expanding TAVR compares favorably with SAVR in high-risk patients with STS PROM scores traditionally considered intermediate risk. Trial Registration: Clinicaltrials.gov Identifier: NCT01240902.