1
|
Apostolopoulos ID, Papandrianos NI, Papathanasiou ND, Papageorgiou EI. Fuzzy Cognitive Map Applications in Medicine over the Last Two Decades: A Review Study. Bioengineering (Basel) 2024; 11:139. [PMID: 38391626 PMCID: PMC10886348 DOI: 10.3390/bioengineering11020139] [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: 12/16/2023] [Revised: 01/18/2024] [Accepted: 01/27/2024] [Indexed: 02/24/2024] Open
Abstract
Fuzzy Cognitive Maps (FCMs) have become an invaluable tool for healthcare providers because they can capture intricate associations among variables and generate precise predictions. FCMs have demonstrated their utility in diverse medical applications, from disease diagnosis to treatment planning and prognosis prediction. Their ability to model complex relationships between symptoms, biomarkers, risk factors, and treatments has enabled healthcare providers to make informed decisions, leading to better patient outcomes. This review article provides a thorough synopsis of using FCMs within the medical domain. A systematic examination of pertinent literature spanning the last two decades forms the basis of this overview, specifically delineating the diverse applications of FCMs in medical realms, including decision-making, diagnosis, prognosis, treatment optimisation, risk assessment, and pharmacovigilance. The limitations inherent in FCMs are also scrutinised, and avenues for potential future research and application are explored.
Collapse
Affiliation(s)
| | - Nikolaos I Papandrianos
- Department of Energy Systems, University of Thessaly, Gaiopolis Campus, 41500 Larisa, Greece
| | | | - Elpiniki I Papageorgiou
- Department of Energy Systems, University of Thessaly, Gaiopolis Campus, 41500 Larisa, Greece
| |
Collapse
|
2
|
Calderón-Díaz M, Silvestre Aguirre R, Vásconez JP, Yáñez R, Roby M, Querales M, Salas R. Explainable Machine Learning Techniques to Predict Muscle Injuries in Professional Soccer Players through Biomechanical Analysis. SENSORS (BASEL, SWITZERLAND) 2023; 24:119. [PMID: 38202981 PMCID: PMC10780883 DOI: 10.3390/s24010119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/27/2023] [Revised: 11/25/2023] [Accepted: 12/18/2023] [Indexed: 01/12/2024]
Abstract
There is a significant risk of injury in sports and intense competition due to the demanding physical and psychological requirements. Hamstring strain injuries (HSIs) are the most prevalent type of injury among professional soccer players and are the leading cause of missed days in the sport. These injuries stem from a combination of factors, making it challenging to pinpoint the most crucial risk factors and their interactions, let alone find effective prevention strategies. Recently, there has been growing recognition of the potential of tools provided by artificial intelligence (AI). However, current studies primarily concentrate on enhancing the performance of complex machine learning models, often overlooking their explanatory capabilities. Consequently, medical teams have difficulty interpreting these models and are hesitant to trust them fully. In light of this, there is an increasing need for advanced injury detection and prediction models that can aid doctors in diagnosing or detecting injuries earlier and with greater accuracy. Accordingly, this study aims to identify the biomarkers of muscle injuries in professional soccer players through biomechanical analysis, employing several ML algorithms such as decision tree (DT) methods, discriminant methods, logistic regression, naive Bayes, support vector machine (SVM), K-nearest neighbor (KNN), ensemble methods, boosted and bagged trees, artificial neural networks (ANNs), and XGBoost. In particular, XGBoost is also used to obtain the most important features. The findings highlight that the variables that most effectively differentiate the groups and could serve as reliable predictors for injury prevention are the maximum muscle strength of the hamstrings and the stiffness of the same muscle. With regard to the 35 techniques employed, a precision of up to 78% was achieved with XGBoost, indicating that by considering scientific evidence, suggestions based on various data sources, and expert opinions, it is possible to attain good precision, thus enhancing the reliability of the results for doctors and trainers. Furthermore, the obtained results strongly align with the existing literature, although further specific studies about this sport are necessary to draw a definitive conclusion.
Collapse
Affiliation(s)
- Mailyn Calderón-Díaz
- Faculty of Engineering, Universidad Andres Bello, Santiago 7550196, Chile;
- Ph.D. Program in Health Sciences and Engineering, Universidad de Valparaiso, Valparaiso 2362735, Chile
- Millennium Institute for Intelligent Healthcare Engineering (iHealth), Valparaiso 2362735, Chile
| | - Rony Silvestre Aguirre
- Laboratorio de Biomecánica, Centro de Innovación Clínica MEDS, Santiago 7691236, Chile; (R.S.A.); (R.Y.); (M.R.)
| | - Juan P. Vásconez
- Faculty of Engineering, Universidad Andres Bello, Santiago 7550196, Chile;
| | - Roberto Yáñez
- Laboratorio de Biomecánica, Centro de Innovación Clínica MEDS, Santiago 7691236, Chile; (R.S.A.); (R.Y.); (M.R.)
| | - Matías Roby
- Laboratorio de Biomecánica, Centro de Innovación Clínica MEDS, Santiago 7691236, Chile; (R.S.A.); (R.Y.); (M.R.)
| | - Marvin Querales
- School of Medical Technology, Universidad de Valparaiso, Valparaiso 2362735, Chile;
| | - Rodrigo Salas
- Ph.D. Program in Health Sciences and Engineering, Universidad de Valparaiso, Valparaiso 2362735, Chile
- Millennium Institute for Intelligent Healthcare Engineering (iHealth), Valparaiso 2362735, Chile
- School of Biomedical Engineering, Universidad de Valparaiso, Valparaiso 2362735, Chile
| |
Collapse
|
3
|
Obot O, John A, Udo I, Attai K, Johnson E, Udoh S, Nwokoro C, Akwaowo C, Dan E, Umoh U, Uzoka FM. Modelling Differential Diagnosis of Febrile Diseases with Fuzzy Cognitive Map. Trop Med Infect Dis 2023; 8:352. [PMID: 37505648 PMCID: PMC10386044 DOI: 10.3390/tropicalmed8070352] [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: 03/23/2023] [Revised: 05/26/2023] [Accepted: 06/28/2023] [Indexed: 07/29/2023] Open
Abstract
The report of the World Health Organization (WHO) about the poor accessibility of people living in low-to-middle-income countries to medical facilities and personnel has been a concern to both professionals and nonprofessionals in healthcare. This poor accessibility has led to high morbidity and mortality rates in tropical regions, especially when such a disease presents itself with confusable symptoms that are not easily differentiable by inexperienced doctors, such as those found in febrile diseases. This prompted the development of the fuzzy cognitive map (FCM) model to serve as a decision-support tool for medical health workers in the diagnosis of febrile diseases. With 2465 datasets gathered from four states in the febrile diseases-prone regions in Nigeria with the aid of 60 medical doctors, 10 of those doctors helped in weighting and fuzzifying the symptoms, which were used to generate the FCM model. Results obtained from computations to predict diagnosis results for the 2465 patients, and those diagnosed by the physicians on the field, showed an average of 87% accuracy for the 11 febrile diseases used in the study. The number of comorbidities of diseases with varying degrees of severity for most patients in the study also covary strongly with those found by the physicians in the field.
Collapse
Affiliation(s)
- Okure Obot
- Department of Computer Science, University of Uyo, Uyo 520103, Nigeria
| | - Anietie John
- Department of Mathematics and Computer Science, Ritman University, Ikot Ekpene 530101, Nigeria
| | - Iberedem Udo
- Department of Computer Science, University of Uyo, Uyo 520103, Nigeria
| | - Kingsley Attai
- Department of Mathematics and Computer Science, Ritman University, Ikot Ekpene 530101, Nigeria
| | - Ekemini Johnson
- Department of Mathematics and Computer Science, Ritman University, Ikot Ekpene 530101, Nigeria
| | - Samuel Udoh
- Department of Computer Science, University of Uyo, Uyo 520103, Nigeria
| | - Chukwudi Nwokoro
- Department of Computer Science, University of Uyo, Uyo 520103, Nigeria
| | - Christie Akwaowo
- Health Systems Research Hub, University of Uyo Teaching Hospital, Uyo 520103, Nigeria
| | - Emem Dan
- Health Systems Research Hub, University of Uyo Teaching Hospital, Uyo 520103, Nigeria
| | - Uduak Umoh
- Department of Computer Science, University of Uyo, Uyo 520103, Nigeria
| | - Faith-Michael Uzoka
- Department of Mathematics and Computing, Mount Royal University, Calgary, AB T3E 6K6, Canada
| |
Collapse
|
4
|
Samaras AD, Moustakidis S, Apostolopoulos ID, Papandrianos N, Papageorgiou E. Classification models for assessing coronary artery disease instances using clinical and biometric data: an explainable man-in-the-loop approach. Sci Rep 2023; 13:6668. [PMID: 37095118 PMCID: PMC10125978 DOI: 10.1038/s41598-023-33500-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Accepted: 04/13/2023] [Indexed: 04/26/2023] Open
Abstract
The main goal driving this work is to develop computer-aided classification models relying on clinical data to identify coronary artery disease (CAD) instances with high accuracy while incorporating the expert's opinion as input, making it a "man-in-the-loop" approach. CAD is traditionally diagnosed in a definite manner by Invasive Coronary Angiography (ICA). A dataset was created using biometric and clinical data from 571 patients (21 total features, 43% ICA-confirmed CAD instances) along with the expert's diagnostic yield. Five machine learning classification algorithms were applied to the dataset. For the selection of the best feature set for each algorithm, three different parameter selection algorithms were used. Each ML model's performance was evaluated using common metrics, and the best resulting feature set for each is presented. A stratified ten-fold validation was used for the performance evaluation. This procedure was run both using the assessments of experts/doctors as input and without them. The significance of this paper lies in its innovative approach of incorporating the expert's opinion as input in the classification process, making it a "man-in-the-loop" approach. This approach not only increases the accuracy of the models but also provides an added layer of explainability and transparency, allowing for greater trust and confidence in the results. Maximum achievable accuracy, sensitivity, and specificity are 83.02%, 90.32%, and 85.49% when using the expert's diagnosis as input, compared to 78.29%, 76.61%, and 86.07% without the expert's diagnosis. The results of this study demonstrate the potential for this approach to improve the diagnosis of CAD and highlight the importance of considering the role of human expertise in the development of computer-aided classification models.
Collapse
Affiliation(s)
| | - Serafeim Moustakidis
- Department of Energy Systems, University of Thessaly, Larisa, Greece.
- AIDEAS OÜ, Tallinn, Estonia.
| | - Ioannis D Apostolopoulos
- Department of Energy Systems, University of Thessaly, Larisa, Greece
- Department of Medical Physics, School of Medicine, University of Patras, Patras, Greece
| | | | | |
Collapse
|
5
|
Determination of Significant Parameters on the Basis of Methods of Mathematical Statistics, and Boolean and Fuzzy Logic. MATHEMATICS 2022. [DOI: 10.3390/math10071133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
Among the set of parameters for which data are collected for decision-making based on artificial intelligence methods, often only some of the parameters are significant. This article compares methods for determining the significant parameters based on the theory of mathematical statistics, and fuzzy and boolean logic. The testing was conducted on several test data sets with a different number of parameters and different variability of parameter values. It was shown that for data sets with a small number of parameters (<5), the most accurate result was given for a method based on the theory of mathematical statistics and boolean logic. For a data set with a large number of parameters—the most suitable is the method of fuzzy logic.
Collapse
|
6
|
Groumpos PP, Apostolopoulos ID. Modeling the spread of dangerous pandemics with the utilization of a hybrid-statistical–Advanced-Fuzzy-Cognitive-Map algorithm: the example of COVID-19. RESEARCH ON BIOMEDICAL ENGINEERING 2021. [PMCID: PMC8475432 DOI: 10.1007/s42600-021-00182-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
Purpose The novel Coronavirus SARS-coV-2 outbreak late in 2019 and early 2020, known today as the COVID-19 pandemic, has spread fast throughout the world. It has considerably affected the lives of all people around the globe while the number of deaths related to the pandemic keeps increasing worldwide. Being able to predict the spread of the pandemic has been very helpful to governments to decide on actions. Statistical prediction models are capable of modeling a single snapshot but have several well-known weaknesses, such as linear assumptions between pandemic variables, while they cannot confirm the actual causality between studied factors. In the present work, the authors propose a state space Advanced Fuzzy Cognitive Maps (AFCM) approach model to predict the spread of the pandemic, using dynamic cause and effect relationships between pre-defined factors. Methods State-Space Advanced Fuzzy Cognitive Maps are proposed for modeling the spread of the pandemic, utilizing several social, policy, and healthcare factors. Statistical data from Greece, South Korea, and Germany are gathered to evaluate the performance of the proposed model. Results The proposed methodology was able to predict the pandemic trend in the studied countries, in terms of the total number of confirmed patient cases, yielding a coefficient of determination of 0.99, 0.94, and 0.97 respectively. The Pearson’s correlation coefficient was found to be 0.99, 0.97, and 0.98 respectively. Conclusion The results demonstrate the effectiveness and the advantages of the proposed methodology when modeling uncertain and dynamic situations, like novel pandemics.
Collapse
|