An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation
<i>Background</i>: Early safety outcomes following transcatheter aortic valve implantation (TAVI) for severe aortic stenosis are critical for patient prognosis. Accurate prediction of adverse events can enhance patient management and improve outcomes. <i>Aim</i>: This study a...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/61/3/374 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849343142149488640 |
|---|---|
| author | Abilkhair Kurmanaliyev Kristina Sutiene Rima Braukylienė Ali Aldujeli Martynas Jurenas Rugile Kregzdyte Laurynas Braukyla Rassul Zhumagaliyev Serik Aitaliyev Nurlan Zhanabayev Rauan Botabayeva Yerlan Orazymbetov Ramunas Unikas |
| author_facet | Abilkhair Kurmanaliyev Kristina Sutiene Rima Braukylienė Ali Aldujeli Martynas Jurenas Rugile Kregzdyte Laurynas Braukyla Rassul Zhumagaliyev Serik Aitaliyev Nurlan Zhanabayev Rauan Botabayeva Yerlan Orazymbetov Ramunas Unikas |
| author_sort | Abilkhair Kurmanaliyev |
| collection | DOAJ |
| description | <i>Background</i>: Early safety outcomes following transcatheter aortic valve implantation (TAVI) for severe aortic stenosis are critical for patient prognosis. Accurate prediction of adverse events can enhance patient management and improve outcomes. <i>Aim</i>: This study aimed to develop a machine learning model to predict early safety outcomes in patients with severe aortic stenosis undergoing TAVI. <i>Methods</i>: We conducted a retrospective single-centre study involving 224 patients with severe aortic stenosis who underwent TAVI. Seventy-seven clinical and biochemical variables were collected for analysis. To handle unbalanced classification problems, an adaptive synthetic (ADASYN) sampling approach was used. A fined-tuned random forest (RF) machine learning model was developed to predict early safety outcomes, defined as all-cause mortality, stroke, life-threatening bleeding, acute kidney injury (stage 2 or 3), coronary artery obstruction requiring intervention, major vascular complications, and valve-related dysfunction requiring repeat procedures. Shapley Additive Explanations (SHAPs) were used to explain the output of the machine learning model by attributing each variable’s contribution to the final prediction of early safety outcomes. <i>Results</i>: The random forest model identified left femoral artery diameter and aortic valve calcification volume as the most influential predictors of early safety outcomes. SHAPs analysis demonstrated that smaller left femoral artery diameter and higher aortic valve calcification volume were associated with poorer early safety prognoses. <i>Conclusions</i>: The machine learning model highlights of early safety outcomes after TAVI. These findings suggest that incorporating these variables into pre-procedural assessments may improve risk stratification and inform clinical decision-making to enhance patient care. |
| format | Article |
| id | doaj-art-21d3e18fa6974af39d655f9fcb1b7f85 |
| institution | Kabale University |
| issn | 1010-660X 1648-9144 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj-art-21d3e18fa6974af39d655f9fcb1b7f852025-08-20T03:43:10ZengMDPI AGMedicina1010-660X1648-91442025-02-0161337410.3390/medicina61030374An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve ImplantationAbilkhair Kurmanaliyev0Kristina Sutiene1Rima Braukylienė2Ali Aldujeli3Martynas Jurenas4Rugile Kregzdyte5Laurynas Braukyla6Rassul Zhumagaliyev7Serik Aitaliyev8Nurlan Zhanabayev9Rauan Botabayeva10Yerlan Orazymbetov11Ramunas Unikas12Department of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Mathematical Modeling, Kaunas University of Technology, Studentų Str. 50–143, LT-50009 Kaunas, LithuaniaDepartment of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiac, Thoracic and Vascular Surgery, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiac, Thoracic and Vascular Surgery, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaSouth Kazakhstan Medical Academy, 1 Al-Farabi Square, Shymkent 160019, KazakhstanSouth Kazakhstan Medical Academy, 1 Al-Farabi Square, Shymkent 160019, KazakhstanDepartment of Cardiac, Thoracic and Vascular Surgery, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, LithuaniaDepartment of Cardiology, Hospital of Lithuanian University of Health Sciences Kauno Klinikos, Lithuanian University of Health Sciences, 2 Eivenių Str., LT-50009 Kaunas, Lithuania<i>Background</i>: Early safety outcomes following transcatheter aortic valve implantation (TAVI) for severe aortic stenosis are critical for patient prognosis. Accurate prediction of adverse events can enhance patient management and improve outcomes. <i>Aim</i>: This study aimed to develop a machine learning model to predict early safety outcomes in patients with severe aortic stenosis undergoing TAVI. <i>Methods</i>: We conducted a retrospective single-centre study involving 224 patients with severe aortic stenosis who underwent TAVI. Seventy-seven clinical and biochemical variables were collected for analysis. To handle unbalanced classification problems, an adaptive synthetic (ADASYN) sampling approach was used. A fined-tuned random forest (RF) machine learning model was developed to predict early safety outcomes, defined as all-cause mortality, stroke, life-threatening bleeding, acute kidney injury (stage 2 or 3), coronary artery obstruction requiring intervention, major vascular complications, and valve-related dysfunction requiring repeat procedures. Shapley Additive Explanations (SHAPs) were used to explain the output of the machine learning model by attributing each variable’s contribution to the final prediction of early safety outcomes. <i>Results</i>: The random forest model identified left femoral artery diameter and aortic valve calcification volume as the most influential predictors of early safety outcomes. SHAPs analysis demonstrated that smaller left femoral artery diameter and higher aortic valve calcification volume were associated with poorer early safety prognoses. <i>Conclusions</i>: The machine learning model highlights of early safety outcomes after TAVI. These findings suggest that incorporating these variables into pre-procedural assessments may improve risk stratification and inform clinical decision-making to enhance patient care.https://www.mdpi.com/1648-9144/61/3/374aortic stenosistranscatheter aortic valve implantationearly safety outcomesADASYNrandom forestSHAP |
| spellingShingle | Abilkhair Kurmanaliyev Kristina Sutiene Rima Braukylienė Ali Aldujeli Martynas Jurenas Rugile Kregzdyte Laurynas Braukyla Rassul Zhumagaliyev Serik Aitaliyev Nurlan Zhanabayev Rauan Botabayeva Yerlan Orazymbetov Ramunas Unikas An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation Medicina aortic stenosis transcatheter aortic valve implantation early safety outcomes ADASYN random forest SHAP |
| title | An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation |
| title_full | An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation |
| title_fullStr | An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation |
| title_full_unstemmed | An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation |
| title_short | An Integrative Machine Learning Model for Predicting Early Safety Outcomes in Patients Undergoing Transcatheter Aortic Valve Implantation |
| title_sort | integrative machine learning model for predicting early safety outcomes in patients undergoing transcatheter aortic valve implantation |
| topic | aortic stenosis transcatheter aortic valve implantation early safety outcomes ADASYN random forest SHAP |
| url | https://www.mdpi.com/1648-9144/61/3/374 |
| work_keys_str_mv | AT abilkhairkurmanaliyev anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT kristinasutiene anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rimabraukyliene anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT alialdujeli anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT martynasjurenas anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rugilekregzdyte anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT laurynasbraukyla anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rassulzhumagaliyev anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT serikaitaliyev anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT nurlanzhanabayev anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rauanbotabayeva anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT yerlanorazymbetov anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT ramunasunikas anintegrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT abilkhairkurmanaliyev integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT kristinasutiene integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rimabraukyliene integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT alialdujeli integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT martynasjurenas integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rugilekregzdyte integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT laurynasbraukyla integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rassulzhumagaliyev integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT serikaitaliyev integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT nurlanzhanabayev integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT rauanbotabayeva integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT yerlanorazymbetov integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation AT ramunasunikas integrativemachinelearningmodelforpredictingearlysafetyoutcomesinpatientsundergoingtranscatheteraorticvalveimplantation |