1
|
Pingitore A, Zhang C, Vassalle C, Ferragina P, Landi P, Mastorci F, Sicari R, Tommasi A, Zavattari C, Prencipe G, Sîrbu A. Machine learning to identify a composite indicator to predict cardiac death in ischemic heart disease. Int J Cardiol 2024; 404:131981. [PMID: 38527629 DOI: 10.1016/j.ijcard.2024.131981] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Revised: 03/13/2024] [Accepted: 03/17/2024] [Indexed: 03/27/2024]
Abstract
BACKGROUND Machine learning (ML) employs algorithms that learn from data, building models with the potential to predict events by aggregating a large number of variables and assessing their complex interactions. The aim of this study is to assess ML potential in identifying patients with ischemic heart disease (IHD) at high risk of cardiac death (CD). METHODS 3987 (mean age 68 ± 11) hospitalized IHD patients were enrolled. We implemented and compared various ML models and their combination into ensembles. Model output constitutes a new ML indicator to be employed for stratification. Primary variable importance was assessed with ablation tests. RESULTS An ensemble classifier combining three ML models achieved the best performance to predict CD (AUROC of 0.830, F1-macro of 0.726). ML indicator use through Cox survival analysis outperformed the 18 variables individually, producing a better stratification compared to standard multivariate analysis (improvement of ∼20%). Patients in the low risk group defined through ML indicator had a significantly higher survival (88.8% versus 29.1%). The main variables identified were Dyslipidemia, LVEF, Previous CABG, Diabetes, Previous Myocardial Infarction, Smoke, Documented resting or exertional ischemia, with an AUROC of 0.791 and an F1-score of 0.674, lower than that of 18 variables. Both code and clinical data are freely available with this article. CONCLUSION ML may allow a faster, low-cost and reliable evaluation of IHD patient prognosis by inclusion of more predictors and identification of those more significant, improving outcome prediction towards the development of precision medicine in this clinical field.
Collapse
Affiliation(s)
| | - Chenxiang Zhang
- Computer Science Department, University of Pisa, Pisa, Italy
| | | | - Paolo Ferragina
- Computer Science Department, University of Pisa, Pisa, Italy
| | | | | | - Rosa Sicari
- Clinical Physiology Institute, CNR, Pisa, Italy
| | | | | | | | - Alina Sîrbu
- Computer Science Department, University of Pisa, Pisa, Italy
| |
Collapse
|
2
|
Elvas LB, Nunes M, Ferreira JC, Dias MS, Rosário LB. AI-Driven Decision Support for Early Detection of Cardiac Events: Unveiling Patterns and Predicting Myocardial Ischemia. J Pers Med 2023; 13:1421. [PMID: 37763188 PMCID: PMC10533089 DOI: 10.3390/jpm13091421] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Revised: 09/18/2023] [Accepted: 09/19/2023] [Indexed: 09/29/2023] Open
Abstract
Cardiovascular diseases (CVDs) account for a significant portion of global mortality, emphasizing the need for effective strategies. This study focuses on myocardial infarction, pulmonary thromboembolism, and aortic stenosis, aiming to empower medical practitioners with tools for informed decision making and timely interventions. Drawing from data at Hospital Santa Maria, our approach combines exploratory data analysis (EDA) and predictive machine learning (ML) models, guided by the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. EDA reveals intricate patterns and relationships specific to cardiovascular diseases. ML models achieve accuracies above 80%, providing a 13 min window to predict myocardial ischemia incidents and intervene proactively. This paper presents a Proof of Concept for real-time data and predictive capabilities in enhancing medical strategies.
Collapse
Affiliation(s)
- Luís B. Elvas
- ISTAR, Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, Portugal; (M.N.); (J.C.F.); (M.S.D.)
- Inov Inesc Inovação—Instituto de Novas Tecnologias, 1000-029 Lisbon, Portugal
| | - Miguel Nunes
- ISTAR, Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, Portugal; (M.N.); (J.C.F.); (M.S.D.)
| | - Joao C. Ferreira
- ISTAR, Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, Portugal; (M.N.); (J.C.F.); (M.S.D.)
- Inov Inesc Inovação—Instituto de Novas Tecnologias, 1000-029 Lisbon, Portugal
| | - Miguel Sales Dias
- ISTAR, Instituto Universitário de Lisboa (ISCTE-IUL), 1649-026 Lisbon, Portugal; (M.N.); (J.C.F.); (M.S.D.)
| | - Luís Brás Rosário
- Faculty of Medicine, Lisbon University, Hospital Santa Maria/CHULN, CCUL, 1649-028 Lisbon, Portugal;
| |
Collapse
|
3
|
Shimizu T. Twelve tips for physicians’ mastering expertise in diagnostic excellence. MEDEDPUBLISH 2023. [DOI: 10.12688/mep.19618.1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/08/2023] Open
Abstract
Diagnostic errors, which account for a large proportion of medical errors, are a global medical challenge. The slogan of reducing diagnostic errors has recently shifted to a new strategy of diagnostic excellence, the core of which is the importance of improving the multidisciplinary diagnostic process. Many of the elements and strategies necessary for diagnostic excellence have been presented. In the context of this diagnostic improvement, some reports have been structured to improve the quality of performance of individual physicians as players. Still, surprisingly, only a few reports have focused on specific day-to-day training strategies for the diagnostic thinking process as expertise. This paper focuses on this point and proposes strategies for refining the diagnostic thinking expertise of frontline physicians in the new era, based on the following four elements: knowledge and experience, diagnostic thinking strategies, information management skills, and calibration and reflection.
Collapse
|
4
|
Tasin I, Nabil TU, Islam S, Khan R. Diabetes prediction using machine learning and explainable AI techniques. Healthc Technol Lett 2023; 10:1-10. [PMID: 37077883 PMCID: PMC10107388 DOI: 10.1049/htl2.12039] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2022] [Revised: 11/23/2022] [Accepted: 11/29/2022] [Indexed: 12/15/2022] Open
Abstract
Globally, diabetes affects 537 million people, making it the deadliest and the most common non-communicable disease. Many factors can cause a person to get affected by diabetes, like excessive body weight, abnormal cholesterol level, family history, physical inactivity, bad food habit etc. Increased urination is one of the most common symptoms of this disease. People with diabetes for a long time can get several complications like heart disorder, kidney disease, nerve damage, diabetic retinopathy etc. But its risk can be reduced if it is predicted early. In this paper, an automatic diabetes prediction system has been developed using a private dataset of female patients in Bangladesh and various machine learning techniques. The authors used the Pima Indian diabetes dataset and collected additional samples from 203 individuals from a local textile factory in Bangladesh. Feature selection algorithm mutual information has been applied in this work. A semi-supervised model with extreme gradient boosting has been utilized to predict the insulin features of the private dataset. SMOTE and ADASYN approaches have been employed to manage the class imbalance problem. The authors used machine learning classification methods, that is, decision tree, SVM, Random Forest, Logistic Regression, KNN, and various ensemble techniques, to determine which algorithm produces the best prediction results. After training on and testing all the classification models, the proposed system provided the best result in the XGBoost classifier with the ADASYN approach with 81% accuracy, 0.81 F1 coefficient and AUC of 0.84. Furthermore, the domain adaptation method has been implemented to demonstrate the versatility of the proposed system. The explainable AI approach with LIME and SHAP frameworks is implemented to understand how the model predicts the final results. Finally, a website framework and an Android smartphone application have been developed to input various features and predict diabetes instantaneously. The private dataset of female Bangladeshi patients and programming codes are available at the following link: https://github.com/tansin-nabil/Diabetes-Prediction-Using-Machine-Learning.
Collapse
Affiliation(s)
- Isfafuzzaman Tasin
- Electrical and Computer EngineeringNorth South UniversityDhakaBangladesh
| | - Tansin Ullah Nabil
- Electrical and Computer EngineeringNorth South UniversityDhakaBangladesh
| | - Sanjida Islam
- Electrical and Computer EngineeringNorth South UniversityDhakaBangladesh
| | - Riasat Khan
- Electrical and Computer EngineeringNorth South UniversityDhakaBangladesh
| |
Collapse
|
5
|
Hassannataj Joloudari J, Mojrian S, Nodehi I, Mashmool A, Kiani Zadegan Z, Khanjani Shirkharkolaie S, Alizadehsani R, Tamadon T, Khosravi S, Akbari Kohnehshari M, Hassannatajjeloudari E, Sharifrazi D, Mosavi A, Loh HW, Tan RS, Acharya UR. Application of artificial intelligence techniques for automated detection of myocardial infarction: a review. Physiol Meas 2022; 43. [PMID: 35803247 DOI: 10.1088/1361-6579/ac7fd9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Accepted: 07/08/2022] [Indexed: 11/11/2022]
Abstract
Myocardial infarction (MI) results in heart muscle injury due to receiving insufficient blood flow. MI is the most common cause of mortality in middle-aged and elderly individuals worldwide. To diagnose MI, clinicians need to interpret electrocardiography (ECG) signals, which requires expertise and is subject to observer bias. Artificial intelligence-based methods can be utilized to screen for or diagnose MI automatically using ECG signals. In this work, we conducted a comprehensive assessment of artificial intelligence-based approaches for MI detection based on ECG and some other biophysical signals, including machine learning (ML) and deep learning (DL) models. The performance of traditional ML methods relies on handcrafted features and manual selection of ECG signals, whereas DL models can automate these tasks. The review observed that deep convolutional neural networks (DCNNs) yielded excellent classification performance for MI diagnosis, which explains why they have become prevalent in recent years. To our knowledge, this is the first comprehensive survey of artificial intelligence techniques employed for MI diagnosis using ECG and some other biophysical signals.
Collapse
Affiliation(s)
- Javad Hassannataj Joloudari
- Computer Engineering, University of Birjand, South Khorasan Province, Birjand, Iran, Birjand, South Khorasan, 9717434765, Iran (the Islamic Republic of)
| | - Sanaz Mojrian
- Mazandaran University of Science and Technology, Mazandaran Province, Babol, Danesh 5, No. Sheykh Tabarasi, Iran, Babol, 47166-85635, Iran (the Islamic Republic of)
| | - Issa Nodehi
- University of Qom, Qom, shahid khodakaram blvd، Iran, Qom, Qom, 1519-37195, Iran (the Islamic Republic of)
| | - Amir Mashmool
- University of Geneva, Via del Molo, 65, 16128 Genova GE, Italy, Geneva, Geneva, 16121, ITALY
| | - Zeynab Kiani Zadegan
- University of Birjand, South Khorasan Province, Birjand, Iran, Birjand, 9717434765, Iran (the Islamic Republic of)
| | - Sahar Khanjani Shirkharkolaie
- Mazandaran University of Science and Technology, Mazandaran Province, Babol, Danesh 5, No. Sheykh Tabarasi, Iran, Babol, 47166-85635, Iran (the Islamic Republic of)
| | - Roohallah Alizadehsani
- Deakin University - Geelong Waterfront Campus, IISRI, Geelong, Victoria, 3220, AUSTRALIA
| | - Tahereh Tamadon
- University of Birjand, South Khorasan Province, Birjand, Iran, Birjand, 9717434765, Iran (the Islamic Republic of)
| | - Samiyeh Khosravi
- University of Birjand, South Khorasan Province, Birjand, Iran, Birjand, 9717434765, Iran (the Islamic Republic of)
| | - Mitra Akbari Kohnehshari
- Bu Ali Sina University, QFRQ+V8H District 2, Hamedan, Iran, Hamedan, Hamedan, 6516738695, Iran (the Islamic Republic of)
| | - Edris Hassannatajjeloudari
- Maragheh University of Medical Sciences, 87VG+9J6, Maragheh, East Azerbaijan Province, Iran, Maragheh, East Azerbaijan, 55158-78151, Iran (the Islamic Republic of)
| | - Danial Sharifrazi
- Islamic Azad University Shiraz, Shiraz University, Iran, Shiraz, Fars, 74731-71987, Iran (the Islamic Republic of)
| | - Amir Mosavi
- Faculty of Informatics, Obuda University, Faculty of Informatics, Obuda University, Budapest, Hungary, Budapest, 1034, HUNGARY
| | - Hui Wen Loh
- Singapore University of Social Sciences, SG, Clementi Rd, 463, Singapore 599494, Singapore, 599491, SINGAPORE
| | - Ru-San Tan
- Department of Cardiology, National Heart Centre Singapore, 5 Hospital Dr, Singapore 169609, Singapore, 168752, SINGAPORE
| | - U Rajendra Acharya
- Electronic Computer Engineering Division, Ngee Ann Polytechnic, 535 Clementi Road, Singapore 599489, Singapore, 599489, SINGAPORE
| |
Collapse
|