Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures
<i>Background</i>: Osteoporosis is a socio-economic problem of modern aging societies. Bone fractures and the related treatments generate the highest costs. The occurrence of osteoporotic fractures is a cause of chronic disability, many complications, reduced quality of life, and often p...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/13/8/1738 |
| _version_ | 1797584083215187968 |
|---|---|
| author | Dorota Lis-Studniarska Marta Lipnicka Marcin Studniarski Robert Irzmański |
| author_facet | Dorota Lis-Studniarska Marta Lipnicka Marcin Studniarski Robert Irzmański |
| author_sort | Dorota Lis-Studniarska |
| collection | DOAJ |
| description | <i>Background</i>: Osteoporosis is a socio-economic problem of modern aging societies. Bone fractures and the related treatments generate the highest costs. The occurrence of osteoporotic fractures is a cause of chronic disability, many complications, reduced quality of life, and often premature death. <i>Aim of the study:</i> The aim of the study was to determine which of the patient’s potential risk factors pertaining to various diseases and lifestyle have an essential impact on the occurrence of low-energy fractures and the hierarchy of these factors. <i>Methods:</i> The study was retrospective. The documentation of 222 patients (206 women and 16 men) from an osteoporosis treatment clinic in Łódź, Poland was analyzed. Each patient was described by a vector consisting of 27 features, where each feature was a different risk factor. Using artificial neural networks, an attempt was made to create a model that, based on the available data, would be able to predict whether the patient would be exposed to low-energy fractures. We developed a neural network model that achieved the best result for the testing data. In addition, we used other methods to solve the classification problem, i.e., correctly dividing patients into two groups: those with fractures and those without fractures. These methods were logistic regression, <i>k</i>-nearest neighbors and SVM. <i>Results:</i> The obtained results gave us the opportunity to assess the effectiveness of various methods and the importance of the features describing patients. Using logistic regression and the recursive elimination of features, a ranking of risk factors was obtained in which the most important were age, chronic kidney disease, neck T-score, and serum phosphate level. Then, we repeated the learning procedure of the neural network considering only these four most important features. The average mean squared error on the test set was about <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>27</mn><mo>%</mo></mrow></semantics></math></inline-formula> for the best variant of the model. <i>Conclusions:</i> The comparison of the rankings with different numbers of patients shows that the applied method is very sensitive to changes in the considered data (adding new patients significantly changes the result). Further cohort studies with more patients and more advanced methods of machine learning may be needed to identify other significant risk factors and to develop a reliable fracture risk system. The obtained results may contribute to the improved identification patients at risk of low-energy fractures and early implementation of comprehensive treatment. |
| first_indexed | 2024-03-10T23:47:15Z |
| format | Article |
| id | doaj.art-2d8a880555ab40c6b7c12a316158ab87 |
| institution | Directory Open Access Journal |
| issn | 2075-1729 |
| language | English |
| last_indexed | 2024-03-10T23:47:15Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj.art-2d8a880555ab40c6b7c12a316158ab872023-11-19T01:54:55ZengMDPI AGLife2075-17292023-08-01138173810.3390/life13081738Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic FracturesDorota Lis-Studniarska0Marta Lipnicka1Marcin Studniarski2Robert Irzmański3Central Clinical Hospital, Medical University of Łódź, Pomorska 251, 92-213 Łódź, PolandFaculty of Mathematics and Computer Science, University of Łódź, Banacha 22, 90-238 Łódź, PolandFaculty of Mathematics and Computer Science, University of Łódź, Banacha 22, 90-238 Łódź, PolandDepartment of Internal Medicine, Rehabilitation and Physical Medicine, Medical University of Łódź, plac Gen. Józefa Hallera 1, 90-645 Łódź, Poland<i>Background</i>: Osteoporosis is a socio-economic problem of modern aging societies. Bone fractures and the related treatments generate the highest costs. The occurrence of osteoporotic fractures is a cause of chronic disability, many complications, reduced quality of life, and often premature death. <i>Aim of the study:</i> The aim of the study was to determine which of the patient’s potential risk factors pertaining to various diseases and lifestyle have an essential impact on the occurrence of low-energy fractures and the hierarchy of these factors. <i>Methods:</i> The study was retrospective. The documentation of 222 patients (206 women and 16 men) from an osteoporosis treatment clinic in Łódź, Poland was analyzed. Each patient was described by a vector consisting of 27 features, where each feature was a different risk factor. Using artificial neural networks, an attempt was made to create a model that, based on the available data, would be able to predict whether the patient would be exposed to low-energy fractures. We developed a neural network model that achieved the best result for the testing data. In addition, we used other methods to solve the classification problem, i.e., correctly dividing patients into two groups: those with fractures and those without fractures. These methods were logistic regression, <i>k</i>-nearest neighbors and SVM. <i>Results:</i> The obtained results gave us the opportunity to assess the effectiveness of various methods and the importance of the features describing patients. Using logistic regression and the recursive elimination of features, a ranking of risk factors was obtained in which the most important were age, chronic kidney disease, neck T-score, and serum phosphate level. Then, we repeated the learning procedure of the neural network considering only these four most important features. The average mean squared error on the test set was about <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>27</mn><mo>%</mo></mrow></semantics></math></inline-formula> for the best variant of the model. <i>Conclusions:</i> The comparison of the rankings with different numbers of patients shows that the applied method is very sensitive to changes in the considered data (adding new patients significantly changes the result). Further cohort studies with more patients and more advanced methods of machine learning may be needed to identify other significant risk factors and to develop a reliable fracture risk system. The obtained results may contribute to the improved identification patients at risk of low-energy fractures and early implementation of comprehensive treatment.https://www.mdpi.com/2075-1729/13/8/1738osteoporosisfracturesrisk factorsmedical recordsartificial neural networkslogistic regression |
| spellingShingle | Dorota Lis-Studniarska Marta Lipnicka Marcin Studniarski Robert Irzmański Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures Life osteoporosis fractures risk factors medical records artificial neural networks logistic regression |
| title | Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures |
| title_full | Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures |
| title_fullStr | Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures |
| title_full_unstemmed | Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures |
| title_short | Applications of Artificial Intelligence Methods for the Prediction of Osteoporotic Fractures |
| title_sort | applications of artificial intelligence methods for the prediction of osteoporotic fractures |
| topic | osteoporosis fractures risk factors medical records artificial neural networks logistic regression |
| url | https://www.mdpi.com/2075-1729/13/8/1738 |
| work_keys_str_mv | AT dorotalisstudniarska applicationsofartificialintelligencemethodsforthepredictionofosteoporoticfractures AT martalipnicka applicationsofartificialintelligencemethodsforthepredictionofosteoporoticfractures AT marcinstudniarski applicationsofartificialintelligencemethodsforthepredictionofosteoporoticfractures AT robertirzmanski applicationsofartificialintelligencemethodsforthepredictionofosteoporoticfractures |