O'Hair DP, Gada H, Sotelo MR, Wagner L, Feind CM, Brigman L, Rogers C, Kohli NS. Enhanced Detection of Heart Valve Disease Using Integrated Artificial Intelligence at Scale.
Ann Thorac Surg 2021;
113:1499-1504. [PMID:
34139187 DOI:
10.1016/j.athoracsur.2021.04.106]
[Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/06/2020] [Revised: 04/20/2021] [Accepted: 04/27/2021] [Indexed: 11/29/2022]
Abstract
BACKGROUND
Undertreatment of heart valve disease creates unnecessary patient risk. Poorly integrated healthcare data systems are unequipped to solve this problem. A software program utilizing a rules-based algorithm to search the electronic health record (EHR) 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 (PACS), the electronic health record (EHR) 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
60,145 patients had 77,215 echocardiograms in two health institutions in the United States. Moderate or severe aortic stenosis (AS) was identified at a rate of 9.1% (5,474) of patients (6,910 echoes) in this population. The precision and accuracy of the algorithm for the detection of moderate or severe aortic stenosis was 92.9% and 98.6%, respectively. Thirty five percent (441/1,265) of patients with moderate stenosis and a subsequent echocardiogram progressed to severe (mean interval 358 days). In one sample, 70.3% of moderate AS patients lacked a 6-month echo or appointment. The platform enabled 100% accountability for all patients with severe aortic stenosis.
CONCLUSIONS
A rules-based software program enhances detection of heart valve disease and can be used to measures disease progression and care pathway compliance.
Collapse