Preventing unnecessary imaging in patients suspect of coronary artery disease through machine learning of electronic health records

Abstract Aims With the ageing European population, the incidence of coronary artery disease (CAD) is expected to rise. This will likely result in an increased imaging use. Symptom recognition can be complicated, as symptoms caused by CAD can be atypical, particularly in women. Early CAD exclusion may help to optimize use of diagnostic resources and thus improve the sustainability of the healthcare system. To develop sex-stratified algorithms, trained on routinely available electronic health records (EHRs), raw electrocardiograms, and haematology data to exclude CAD in patients upfront. Methods and results We trained XGBoost algorithms on data from patients from the Utrecht Patient-Oriented Database, who underwent coronary computed tomography angiography (CCTA), and/or stress cardiac magnetic resonance (CMR) imaging, or stress single-photon emission computerized tomography (SPECT) in the UMC Utrecht. Outcomes were extracted from radiology reports. We aimed to maximize negative predictive value (NPV) to minimize the false negative risk with acceptable specificity. Of 6808 CCTA patients (31% female), 1029 females (48%) and 1908 males (45%) had no diagnosis of CAD. Of 3053 CMR/SPECT patients (45% female), 650 females (47%) and 881 males (48%) had no diagnosis of CAD. On the train and test set, the CCTA models achieved NPVs and specificities of 0.95 and 0.19 (females) and 0.96 and 0.09 (males). The CMR/SPECT models achieved NPVs and specificities of 0.75 and 0.041 (females) and 0.92 and 0.026 (males). Conclusion Coronary artery disease can be excluded from EHRs with high NPV. Our study demonstrates new possibilities to reduce unnecessary imaging in women and men suspected of CAD.

[1]  E. Hagström,et al.  Mortality in STEMI patients without standard modifiable risk factors: a sex-disaggregated analysis of SWEDEHEART registry data , 2021, The Lancet.

[2]  Anouk L. M. Eikendal,et al.  Cardiovascular imaging of women and men visiting the outpatient clinic with chest pain or discomfort: design and rationale of the ARGUS Study , 2020, BMJ Open.

[3]  G. Figtree,et al.  Taking the next steps to implement polygenic risk scoring for improved risk stratification and primary prevention of coronary artery disease. , 2020, European journal of preventive cardiology.

[4]  Jeroen J. Bax,et al.  Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry. , 2019, European heart journal.

[5]  Weiguo Fan,et al.  Review of Medical Decision Support and Machine-Learning Methods , 2019, Veterinary pathology.

[6]  Michael T. Lu,et al.  Pretest probability for patients with suspected obstructive coronary artery disease: re-evaluating Diamond-Forrester for the contemporary era and clinical implications: insights from the PROMISE trial. , 2018, European heart journal cardiovascular Imaging.

[7]  T. K. J. Groenhofa,et al.  Data mining information from electronic health records produced high yield and accuracy for current smoking status , 2019 .

[8]  B. Buğan,et al.  Level of Anxiety and Depression in Cardiac Syndrome X , 2018, Medical Principles and Practice.

[9]  T. Leiner,et al.  Routinely measured hematological parameters and prediction of recurrent vascular events in patients with clinically manifest vascular disease , 2018, PloS one.

[10]  I. Išgum,et al.  Commonly available hematological biomarkers are associated with the extent of coronary calcifications. , 2018, Atherosclerosis.

[11]  M. Ward,et al.  Increasing proportion of ST elevation myocardial infarction patients with coronary atherosclerosis poorly explained by standard modifiable risk factors , 2017, European journal of preventive cardiology.

[12]  M. Pencina,et al.  Prognostic Value of Noninvasive Cardiovascular Testing in Patients With Stable Chest Pain: Insights From the PROMISE Trial (Prospective Multicenter Imaging Study for Evaluation of Chest Pain) , 2017, Circulation.

[13]  L. Rohde,et al.  Cost-effectiveness of anatomical and functional test strategies for stable chest pain: public health perspective from a middle-income country , 2017, BMJ Open.

[14]  H. D. den Ruijter,et al.  Routinely analyzed leukocyte characteristics improve prediction of mortality after coronary angiography , 2016, European journal of preventive cardiology.

[15]  L. Rohde,et al.  Long‐term Cost‐Effectiveness of Diagnostic Tests for Assessing Stable Chest Pain: Modeled Analysis of Anatomical and Functional Strategies , 2016, Clinical cardiology.

[16]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[17]  M. Voskuil,et al.  Hematological Parameters Improve Prediction of Mortality and Secondary Adverse Events in Coronary Angiography Patients , 2015, Medicine.

[18]  P. Stella,et al.  Elevated mean neutrophil volume represents altered neutrophil composition and reflects damage after myocardial infarction , 2015, Basic Research in Cardiology.

[19]  R. Strasser,et al.  Mental symptoms in patients with cardiac symptoms and normal coronary arteries , 2014, Open Heart.

[20]  Carl J Pepine,et al.  Adverse outcomes among women presenting with signs and symptoms of ischemia and no obstructive coronary artery disease: findings from the National Heart, Lung, and Blood Institute-sponsored Women's Ischemia Syndrome Evaluation (WISE) angiographic core laboratory. , 2013, American heart journal.

[21]  Erik Jørgensen,et al.  Stable angina pectoris with no obstructive coronary artery disease is associated with increased risks of major adverse cardiovascular events. , 2012, European heart journal.

[22]  Hatem Alkadhi,et al.  A clinical prediction rule for the diagnosis of coronary artery disease: validation, updating, and extension. , 2011, European heart journal.

[23]  V. Fuster,et al.  Contemporary Reviews in Cardiovascular Medicine Cellular Senescence, Vascular Disease, and Aging Part 2 of a 2-Part Review: Clinical Vascular Disease in the Elderly , 2011 .

[24]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

[25]  M. Piegza,et al.  [Cardiac syndrome X from a psychosomatic point of view]. , 2008, Psychiatria polska.

[26]  F. Crea,et al.  Coronary microvascular dysfunction. , 2013, The New England journal of medicine.

[27]  A. Egberts,et al.  Linking laboratory and medication data: new opportunities for pharmacoepidemiological research , 2007, Clinical chemistry and laboratory medicine.

[28]  K. Smith,et al.  Abnormal Coronary Vasomotion as a Prognostic Indicator of Cardiovascular Events in Women: Results From the National Heart, Lung, and Blood Institute–Sponsored Women’s Ischemia Syndrome Evaluation (WISE) , 2004, Circulation.

[29]  Eric J Topol,et al.  Prevalence of conventional risk factors in patients with coronary heart disease. , 2003, JAMA.

[30]  H. Tunstall-Pedoe,et al.  Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project. , 2003, European heart journal.

[31]  Pepine,et al.  Coronary microvascular dysfunction is highly prevalent in women with chest pain in the absence of coronary artery disease: results from the NHLBI WISE study. , 2001, American heart journal.

[32]  D. Berman,et al.  The economic consequences of available diagnostic and prognostic strategies for the evaluation of stable angina patients: an observational assessment of the value of precatheterization ischemia. Economics of Noninvasive Diagnosis (END) Multicenter Study Group. , 1999, Journal of the American College of Cardiology.

[33]  J. Rumberger,et al.  Coronary calcification by electron beam computed tomography and obstructive coronary artery disease: a model for costs and effectiveness of diagnosis as compared with conventional cardiac testing methods. , 1999, Journal of the American College of Cardiology.