Abstract
Acute myocardial infarction (AMI) is a major cause of death worldwide. In the USA, there are approximately 0.8 million persons suffering from AMI annually with a death rate of 27%. The risk factors of AMI include hypertension, family history, smoking habits, diabetes, serenity, obesity, cholesterol, alcoholism, coronary artery disease, and so forth. In this study, data acquired from a subset of the National Health Insurance Research Database (NHIRD) of Taiwan were used to develop a clinical decision support system (CDSS) to predict AMI. The integrated genetic algorithm and support vector machine (IGS) and deep neural network (DNN) were both applied to design the predictive models. A balanced dataset (6087 AMI patients and 6087 non-AMI patients) and an imbalanced dataset (6,087 AMI patients and 12,174 non-AMI patients) with each patient record including 74 features were retrieved to design the predictive models. Tenfold cross-validation was used to obtain the optimal model with best prediction performance during training. The experimental results showed that the CDSSs reached a prediction performance with accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of 79.75–84.4%, 68.29–83.7%, 82.45–92.07%, and 0.8424–0.9089, respectively, for models designed based on the balanced dataset, as well as 81.86–86.27%, 52.65–81.22%, 84.29–96.47%, and 0.8503–0.9098, respectively, for models implemented based on the imbalanced dataset. The IGS and DNN algorithms and a combination of age, presence of related comorbidities, and other comorbidity-related features, including diagnosed age and annual physician visits of individual comorbidities, have been shown to be promising in designing strong predictive models in detecting patients who are more likely to develop AMI in the near future as well as for realizing mobile-health (m-Health) systems in managing their comorbidities to prevent occurrence of AMI events. Future work will focus on realizing an ensemble model by combining the model designed based on the long-term NHIRD dataset and the model based on the short-term EMR data and the real-time IoT sensor data, as well as implementing a transfer learning model by transferring the knowledge learned from the long-term model for training the short-term model, so that the predictive performance can be enhanced.
Similar content being viewed by others
References
World Health Organization. Accessed from https://www.who.int/cardiovascular_diseases/about_cvd/en/
Ministry of Health and Welfare of Taiwan. Accessed from https://www.mohw.gov.tw/cp-16-48057-1.html
Boateng S, Sanborn T (2013) Acute myocardial infarction. Dis Mon 59:83–96
Lanas F, Avezum A, Bautista LE, Diaz R, Luna M, Islam S et al (2007) Risk factors for acute myocardial infarction in Latin America: the INTERHEART Latin American study. Circulation 115:1067–1074
Kumar A (2012) Cardiovascular risk factors in elderly normolipidaemic acute myocardial infarct patients. In: Atiq M (ed) Recent advances in cardiovascular risk factors. IntechOpen, Croatia
Isiozor NM, Kunutsor SK, Voutilainen A, Kurl S, Kauhanen J, Laukkanen JA (2019) Ideal cardiovascular health and risk of acute myocardial infarction among Finnish men. Atherosclerosis 289:126–131
Yamada Y, Izawa H, Ichihara S, Takatsu F, Ishihara H, Hirayama H et al (2002) Prediction of the risk of myocardial infarction from polymorphisms in candidate genes. N Engl J Med 347:1916–1923
Garg AX, Adhikari NK, McDonald H, Rosas-Arellano MP, Devereaux P, Beyene J et al (2005) Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review. JAMA 293:1223–1238
Porat T, Kostopoulou O, Woolley A, Delaney BC (2016) Eliciting user decision requirements for designing computerized diagnostic support for family physicians. J Cognit Eng Decis Mak 10:57–73
Horng S, Sontag DA, Halpern Y, Jernite Y, Shapiro NI, Nathanson LA (2017) Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning. PloS one 12:e0174708
Hsu JC, Chen YF, Chung WS, Tan TH, Chen TS, Chiang JY (2013) Clinical verification of a clinical decision support system for ventilator weaning. Biomed Eng Online 12:S4
Luo G, Nkoy FL, Gesteland PH, Glasgow TS, Stone BL (2014) A systematic review of predictive modeling for bronchiolitis. Int J Med Informatics 83:691–714
Dunn Lopez K, Gephart SM, Raszewski R, Sousa V, Shehorn LE, Abraham J (2017) Integrative review of clinical decision support for registered nurses in acute care settings. J Am Med Inform Assoc 24:441–450
Scheepers-Hoeks A-MJ, Grouls RJ, Neef C, Ackerman EW, Korsten EH (2013) Physicians’ responses to clinical decision support on an intensive care unit—comparison of four different alerting methods. Artif Intell Med 59:33–38
Otto AK, Dyer AA, Warren CM, Walkner M, Smith BM, Gupta RS (2017) The development of a clinical decision support system for the management of pediatric food allergy. Clin Pediatr 56:571–578
Ammenwerth E, Schnell-Inderst P, Machan C, Siebert U (2008) The effect of electronic prescribing on medication errors and adverse drug events: a systematic review. J Am Med Inform Assoc 15:585–600
Baypinar F, Kingma HJ, van der Hoeven RT, Becker ML (2017) Physicians’ compliance with a clinical decision support system alerting during the prescribing process. J Med Syst 41:96
Chen YF, Huang PC, Lin KC, Lin HH, Wang LE, Cheng CC et al (2013) Semi-automatic segmentation and classification of pap smear cells. IEEE J Biomed Health Inform 18:94–108
Chen YF, Lin CS, Wang KA, Rahman LOA, Lee DJ, Chung WS et al (2018) Design of a clinical decision support system for fracture prediction using imbalanced dataset. J Healthcare Eng 2018:9621640
Lai HJ, Lin HH, Tan TH, Lin CS, Chen YF. Designing a clinical decision support system to predict readmissions for patients admitted with all-cause conditions. J Ambient Intell Humaniz Comput, in press
Chen YF, Lin CS, Hong CF, Lee DJ, Sun C, Lin HH (2018) Design of a clinical decision support system for predicting erectile dysfunction in men using NHIRD dataset. IEEE J Biomed Health Inform 23:2127–2137
Rau H-H, Hsu C-Y, Lin Y-A, Atique S, Fuad A, Wei L-M et al (2016) Development of a web-based liver cancer prediction model for type II diabetes patients by using an artificial neural network. Comput Methods Programs Biomed 125:58–65
Lee H-A, Chao LR, Hsu C-Y (2021) A 10-year probability deep neural network prediction model for lung cancer. Cancers 13:928
Chien K-L, Lin H-J, Su T-C, Chen Y-Y, Chen P-C (2018) Comparing the consistency and performance of various coronary heart disease prediction models for primary prevention using a national representative cohort in Taiwan. Circ J, pp. CJ-17–0910
Abdar M, Acharya UR, Sarrafzadegan N, Makarenkov V (2019) NE-nu-SVC: A new nested ensemble clinical decision support system for effective diagnosis of coronary artery disease. IEEE Access 7:167605–167620
Ali L, Niamat A, Khan JA, Golilarz NA, Xingzhong X, Noor A et al (2019) An optimized stacked support vector machines based expert system for the effective prediction of heart failure. IEEE Access 7:54007–54014
Gupta A, Kumar R, Arora HS, Raman B (2019) MIFH: a machine intelligence framework for heart disease diagnosis. IEEE Access 8:14659–14674
Nasarian E, Abdar M, Fahami MA, Alizadehsani R, Hussain S, Basiri ME et al (2020) Association between work-related features and coronary artery disease: A heterogeneous hybrid feature selection integrated with balancing approach. Pattern Recogn Lett 133:33–40
Yahyaie M, Tarokh MJ, Mahmoodyar MA (2019) Use of Internet of Things to provide a new model for remote heart attack prediction. Telemed e-Health 25:499–510
Than MP, Pickering JW, Sandoval Y, Shah AS, Tsanas A, Apple FS et al (2019) Machine learning to predict the likelihood of acute myocardial infarction. Circulation 140:899–909
Wu FH, Lin HH, Chan PC, Tseng CM, Chen YF, Lin CS (2020) Clinical decision support systems for predicting patients liable to acquire acute myocardial infarctions. In: International conference on pattern recognition and artificial intelligence, pp 622–634
Kojuri J, Boostani R, Dehghani P, Nowroozipour F, Saki N (2015) Prediction of acute myocardial infarction with artificial neural networks in patients with nondiagnostic electrocardiogram. J Cardiovasc Dis Res 6:51–59
Hamidi H, Daraie A (2016) A new hybrid method for improving the performance of myocardial infarction prediction. J Commun Health Res 5:110–120
Lin HH, Ho FM, Chen YF, Tseng CM, Ho CC, Chung WS (2015) Increased risk of erectile dysfunction among patients with sleep disorders: a nationwide population-based cohort study. Int J Clin Pract 69:846–852
Chen YF, Lin HH, Lu CC, Hung CT, Lee MH, Hsu CY et al (2015) Gout and a subsequent increased risk of erectile dysfunction in men aged 64 and under: a nationwide cohort study in Taiwan. J Rheumatol 42:1898–1905
Thompson IM, Tangen CM, Goodman PJ, Probstfield JL, Moinpour CM, Coltman CA (2005) Erectile dysfunction and subsequent cardiovascular disease. JAMA 294:2996–3002
Speel T, Van Langen H, Meuleman E (2003) The risk of coronary heart disease in men with erectile dysfunction. Eur Urol 44:366–371
Shen BJ, Avivi YE, Todaro JF, Spiro A, Laurenceau J-P, Ward KD et al (2008) Anxiety characteristics independently and prospectively predict myocardial infarction in men: the unique contribution of anxiety among psychologic factors. J Am Coll Cardiol 51:113–119
Seftel AD, Sun P, Swindle R (2004) The prevalence of hypertension, hyperlipidemia, diabetes mellitus and depression in men with erectile dysfunction. J Urol 171:2341–2345
Andersen YM, Egeberg A, Gislason GH, Hansen PR, Skov L, Thyssen JP (2016) Risk of myocardial infarction, ischemic stroke, and cardiovascular death in patients with atopic dermatitis. J Allergy Clin Immunol 138:310–312
Silverberg JI (2015) Association between adult atopic dermatitis, cardiovascular disease, and increased heart attacks in three population-based studies. Allergy 70:1300–1308
Su VYF, Chen TJ, Yeh CM, Chou KT, Hung MH, Chu SY et al (2014) Atopic dermatitis and risk of ischemic stroke: a nationwide population-based study. Ann Med 46:84–89
Chang CC, Liao CC, Chen TL (2016) Perioperative medicine and Taiwan National Health Insurance Research Database. Acta Anaesthesiol Taiwan 54:93–96
Decoste D, Schölkopf B (2002) Training invariant support vector machines. Mach Learn 46:161–190
LeCun Y, Jackel L, Bottou L, Brunot A, Cortes C, Denker J, et al. (1995) Comparison of learning algorithms for handwritten digit recognition. In: International Conference on Artificial Neural Networks, Perth, Australia, 1995, pp. 53–60
Lillywhite K, Tippetts B, Lee DJ (2012) Self-tuned Evolution-COnstructed features for general object recognition. Pattern Recogn 45:241–251
Tao P, Sun Z, Sun Z (2018) An improved intrusion detection algorithm based on GA and SVM. IEEE Access 6:13624–13631
Tao Z, Huiling L, Wenwen W, Xia Y (2019) GA-SVM based feature selection and parameter optimization in hospitalization expense modeling. Appl Soft Comput 75:323–332
Hung C-Y, Lin C-H, Lan T-H, Peng G-S, Lee C-C (2019) Development of an intelligent decision support system for ischemic stroke risk assessment in a population-based electronic health record database. PloS one 14:e0213007
Kumar NM, Manjula R (2019) Design of multi-layer perceptron for the diagnosis of diabetes mellitus using Keras in deep learning. In: Smart intelligent computing and applications, ed: Springer, 2019, pp. 703–711
Ortiz A, Munilla J, Gorriz JM, Ramirez J (2016) Ensembles of deep learning architectures for the early diagnosis of the Alzheimer’s disease. Int J Neural Syst 26:1650025
Ge Y, Wang Q, Wang L, Wu H, Peng C, Wang J et al (2019) Predicting post-stroke pneumonia using deep neural network approaches. Int J Med Inform 132:103986
Hong W, Xiong Z, Zheng N, Weng Y (2019) A medical-history-based potential disease prediction algorithm. IEEE Access 7:131094–131101
Haq AU, Li J, Memon MH, Khan J, Din SU, Ahad I, et al. (2018) Comparative analysis of the classification performance of machine learning classifiers and deep neural network classifier for prediction of Parkinson disease. In: 2018 15th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), pp. 101–106
Ayon SI, Islam M (2019) Diabetes prediction: a deep learning approach. Int J Inf Eng Electron Bus 11(21):2019
Kayal CK, Bagchi S, Dhar D, Maitra T, S. Chatterjee S (2019) Hepatocellular carcinoma survival prediction using deep neural network. In: Proceedings of International Ethical Hacking Conference 2018, pp. 349–358
Ashraf M, Rizvi M, Sharma H (2019) Improved heart disease prediction using deep neural network. Asian J Comput Sci Technol 8:49–54
Anderson A, Gregg D (2018) Optimal DNN primitive selection with partitioned boolean quadratic programming. In: Proceedings of the 2018 International Symposium on Code Generation and Optimization, 2018, pp. 340–351
Grover S, Bhartia S, Yadav A, Seeja K (2018) Predicting severity of Parkinson’s disease using deep learning. Procedia Comput Sci 132:1788–1794
Goyal M (2017) Prediction of stroke using deep learning model. In: International Conference on Neural Information Processing, pp. 774–781
Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30:1145–1159
Cortes C, Mohri M (2004) AUC optimization vs. error rate minimization. In: Advances in neural information processing systems, pp. 313–320
Trifonova O, Lokhov P, Archakov A (2013) Metabolic profiling of human blood. Biochem Moscow Suppl Ser B: Biomed Chem 7:179–186
Cholongitas E, Senzolo M, Patch D, Shaw S, Hui C, Burroughs A (2006) Scoring systems for assessing prognosis in critically ill adult cirrhotics. Aliment Pharmacol Ther 24:453–464
Wu TY, Majeed A, Kuo KN (2010) An overview of the healthcare system in Taiwan. London J Prim Care 3:115–119
Wu MH, Wu MJ, Chou LF, Chen TJ (2014) Patterns of nonemergent visits to different healthcare facilities on the same day: a nationwide analysis in Taiwan. Sci World J 2014:1–8
Hatipoğlu U, Wells BJ, Chagin K, Joshi D, Milinovich A, Rothberg MB (2018) Predicting 30-day all-cause readmission risk for subjects admitted with pneumonia at the point of care. Respir Care 63:43–49
Cai X, Perez-Concha O, Coiera E, Martin-Sanchez F, Day R, Roffe D et al (2015) Real-time prediction of mortality, readmission, and length of stay using electronic health record data. J Am Med Inform Assoc 23:553–561
Jamei M, Nisnevich A, Wetchler E, Sudat S, Liu E (2017) Predicting all-cause risk of 30-day hospital readmission using artificial neural networks. PloS one 12:e0181173
Smith LN, Makam AN, Darden D, Mayo H, Das SR, Halm EA et al (2018) Acute myocardial infarction readmission risk prediction models: a systematic review of model performance. Circ Cardiovasc Qual Outcomes 11:e003885
Muzny M, Henriksen A, Giordanengo A, Muzik J, Grøttland A, Blixgård H et al (2019) Wearable sensors with possibilities for data exchange: analyzing status and needs of different actors in mobile health monitoring systems. Int J Med Inform 133:104017
Khan MA (2020) An IoT framework for heart disease prediction based on MDCNN classifier. IEEE Access 8:34717–34727
Angelo R (2020) The internet of things (IoT), electronic health record (EHR), and federal legislation: the case for a national electronic personal health information (EPHI) record system. Issues Inform Syst vol. 21
Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H et al (2020) A comprehensive survey on transfer learning. Proc IEEE 109:43–76
Feuz KD, Cook DJ (2017) Collegial activity learning between heterogeneous sensors. Knowl Inf Syst 53:337–364
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was funded in part by Central Taiwan University of Science and Technology (Grant CTU108-P-019) and Ministry of Science and Technology of Taiwan (Grants MOST 107-2410-H-166-003 & MOST 105-2410-H-166-006). Fu-Hsing Wu, Huey-Jen Lai, and Hsuan-Hung Lin contributed equally to this work.
Rights and permissions
About this article
Cite this article
Wu, FH., Lai, HJ., Lin, HH. et al. Predictive models for detecting patients more likely to develop acute myocardial infarctions. J Supercomput 78, 2043–2071 (2022). https://doi.org/10.1007/s11227-021-03916-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-021-03916-z