1
|
Forrest IS, Petrazzini BO, Duffy Á, Park JK, Marquez-Luna C, Jordan DM, Rocheleau G, Cho JH, Rosenson RS, Narula J, Nadkarni GN, Do R. Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts. Lancet 2023; 401:215-225. [PMID: 36563696 PMCID: PMC10069625 DOI: 10.1016/s0140-6736(22)02079-7] [Citation(s) in RCA: 29] [Impact Index Per Article: 29.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Revised: 10/05/2022] [Accepted: 10/18/2022] [Indexed: 12/24/2022]
Abstract
BACKGROUND Binary diagnosis of coronary artery disease does not preserve the complexity of disease or quantify its severity or its associated risk with death; hence, a quantitative marker of coronary artery disease is warranted. We evaluated a quantitative marker of coronary artery disease derived from probabilities of a machine learning model. METHODS In this cohort study, we developed and validated a coronary artery disease-predictive machine learning model using 95 935 electronic health records and assessed its probabilities as in-silico scores for coronary artery disease (ISCAD; range 0 [lowest probability] to 1 [highest probability]) in participants in two longitudinal biobank cohorts. We measured the association of ISCAD with clinical outcomes-namely, coronary artery stenosis, obstructive coronary artery disease, multivessel coronary artery disease, all-cause death, and coronary artery disease sequelae. FINDINGS Among 95 935 participants, 35 749 were from the BioMe Biobank (median age 61 years [IQR 18]; 14 599 [41%] were male and 21 150 [59%] were female; 5130 [14%] were with diagnosed coronary artery disease) and 60 186 were from the UK Biobank (median age 62 [15] years; 25 031 [42%] male and 35 155 [58%] female; 8128 [14%] with diagnosed coronary artery disease). The model predicted coronary artery disease with an area under the receiver operating characteristic curve of 0·95 (95% CI 0·94-0·95; sensitivity of 0·94 [0·94-0·95] and specificity of 0·82 [0·81-0·83]) and 0·93 (0·92-0·93; sensitivity of 0·90 [0·89-0·90] and specificity of 0·88 [0·87-0·88]) in the BioMe validation and holdout sets, respectively, and 0·91 (0·91-0·91; sensitivity of 0·84 [0·83-0·84] and specificity of 0·83 [0·82-0·83]) in the UK Biobank external test set. ISCAD captured coronary artery disease risk from known risk factors, pooled cohort equations, and polygenic risk scores. Coronary artery stenosis increased quantitatively with ascending ISCAD quartiles (increase per quartile of 12 percentage points), including risk of obstructive coronary artery disease, multivessel coronary artery disease, and stenosis of major coronary arteries. Hazard ratios (HRs) and prevalence of all-cause death increased stepwise over ISCAD deciles (decile 1: HR 1·0 [95% CI 1·0-1·0], 0·2% prevalence; decile 6: 11 [3·9-31], 3·1% prevalence; and decile 10: 56 [20-158], 11% prevalence). A similar trend was observed for recurrent myocardial infarction. 12 (46%) undiagnosed individuals with high ISCAD (≥0·9) had clinical evidence of coronary artery disease according to the 2014 American College of Cardiology/American Heart Association Task Force guidelines. INTERPRETATION Electronic health record-based machine learning was used to generate an in-silico marker for coronary artery disease that can non-invasively quantify atherosclerosis and risk of death on a continuous spectrum, and identify underdiagnosed individuals. FUNDING National Institutes of Health.
Collapse
Affiliation(s)
- Iain S Forrest
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Medical Scientist Training Program, Icahn School of Medicine at Mount Sinai, New York, NY, USA; The BioMe Phenomics Center, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Ben O Petrazzini
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Áine Duffy
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Joshua K Park
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Medical Scientist Training Program, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Carla Marquez-Luna
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Daniel M Jordan
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Ghislain Rocheleau
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Judy H Cho
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; The BioMe Phenomics Center, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Robert S Rosenson
- Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Metabolism and Lipids Unit, Zena and Michael A Wiener Cardiovascular Institute, Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Jagat Narula
- Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Girish N Nadkarni
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; The BioMe Phenomics Center, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Division of Data-Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Ron Do
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA; The BioMe Phenomics Center, Icahn School of Medicine at Mount Sinai, New York, NY, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
| |
Collapse
|
2
|
Abstract
Missed opportunities refer to incidents where different actions by those involved could result in more desirable outcomes. While missed opportunities are not an established concept in coronary artery disease (CAD), they are important because CAD is common and potentially life-threatening. Treatment of CAD has the potential to prevent poor patient outcomes which can have a downstream consequence on resource utilization and costs for healthcare providers. The missed opportunities in CAD could be divided into those related to prevention, early detection, diagnosis and treatment. The primary prevention opportunities include the management of patients with risk factors and comorbidities. In terms of diagnosis, a proportion of patients who have underlying CAD are admitted beforehand with symptoms which may be attributed to CAD. However, some may have been misdiagnosed with other conditions and are subsequently readmitted with a delayed diagnosis of acute coronary syndrome. In acute coronary syndrome, there is a need for acute treatment and missed opportunities may arise from delay in diagnosis and missed reperfusion therapy. Finally, after coronary revascularization or medication management, there may be missed opportunities for patients related to secondary prevention such as smoking cessation, exercise, weight loss, attendance at cardiac rehabilitation and receipt evidenced-based therapies including antihypertensives, antiplatelet and statin therapy. Our review finds that missed opportunities can become apparent if looked for in the care of patients with CAD. While the term is nonspecific, it should be contextualized and described as those which are related to prevention, diagnosis and treatment. Only through reflection on clinical activities in relation to patient outcomes and the use of healthcare services can missed opportunities be identified so that better care can be delivered.
Collapse
|