Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study
Abstract BackgroundTranscatheter aortic valve replacement (TAVR) is a commonly used treatment for severe aortic stenosis. As degenerative aortic stenosis is primarily a disease afflicting older adults, a frailty assessment is essential to patient selection and optimal periproc...
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | English |
| Publicado: |
JMIR Publications
2024-11-01
|
| Colección: | JMIR Aging |
| Acceso en línea: | https://aging.jmir.org/2024/1/e58980 |
| _version_ | 1826949232160931840 |
|---|---|
| author | Mamoun T Mardini Chen Bai Anthony A Bavry Ahmed Zaghloul R David Anderson Catherine E Crenshaw Price Mohammad A Z Al-Ani |
| author_facet | Mamoun T Mardini Chen Bai Anthony A Bavry Ahmed Zaghloul R David Anderson Catherine E Crenshaw Price Mohammad A Z Al-Ani |
| author_sort | Mamoun T Mardini |
| collection | DOAJ |
| description |
Abstract
BackgroundTranscatheter aortic valve replacement (TAVR) is a commonly used treatment for severe aortic stenosis. As degenerative aortic stenosis is primarily a disease afflicting older adults, a frailty assessment is essential to patient selection and optimal periprocedural outcomes.
ObjectiveThis study aimed to enhance frailty assessments of TAVR candidates by integrating real-world structured and unstructured data.
MethodsThis study analyzed data from 14,000 patients between January 2018 and December 2019 to assess frailty in TAVR patients at the University of Florida. Frailty was identified using the Fried criteria, which includes weight loss, exhaustion, walking speed, grip strength, and physical activity. Latent Dirichlet allocation for topic modeling and Extreme Gradient Boosting for frailty prediction were applied to unstructured clinical notes and structured electronic health record (EHR) data. We also used least absolute shrinkage and selection operator regression for feature selection. Model performance was rigorously evaluated using nested cross-validation, ensuring the generalizability of the findings.
ResultsModel performance was significantly improved by combining unstructured clinical notes with structured EHR data, achieving an area under the receiver operating characteristic curve of 0.82 (SD 0.07), which surpassed the EHR-only model’s area under the receiver operating characteristic curve of 0.64 (SD 0.08). The Shapley Additive Explanations analysis found that congestive heart failure management, back problems, and atrial fibrillation were the top frailty predictors. Additionally, the latent Dirichlet allocation topic modeling identified 7 key topics, highlighting the role of specific medical treatments in predicting frailty.
ConclusionsIntegrating unstructured clinical notes and structured EHR data led to a notable enhancement in predicting frailty. This method shows great potential for standardizing frailty assessments using real-world data and improving patient selection for TAVR. |
| first_indexed | 2025-02-17T22:05:20Z |
| format | Article |
| id | doaj.art-c8ab3efa9dfa418e91dda3adb7d4626c |
| institution | Directory Open Access Journal |
| issn | 2561-7605 |
| language | English |
| last_indexed | 2025-02-17T22:05:20Z |
| publishDate | 2024-11-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Aging |
| spelling | doaj.art-c8ab3efa9dfa418e91dda3adb7d4626c2024-12-04T22:16:34ZengJMIR PublicationsJMIR Aging2561-76052024-11-017e58980e5898010.2196/58980Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence StudyMamoun T Mardinihttp://orcid.org/0000-0002-5345-8811Chen Baihttp://orcid.org/0000-0003-0961-1927Anthony A Bavryhttp://orcid.org/0000-0002-3731-1457Ahmed Zaghloulhttp://orcid.org/0000-0002-3647-7404R David Andersonhttp://orcid.org/0000-0003-3490-3286Catherine E Crenshaw Pricehttp://orcid.org/0000-0001-5994-0644Mohammad A Z Al-Anihttp://orcid.org/0000-0002-7220-1114 Abstract BackgroundTranscatheter aortic valve replacement (TAVR) is a commonly used treatment for severe aortic stenosis. As degenerative aortic stenosis is primarily a disease afflicting older adults, a frailty assessment is essential to patient selection and optimal periprocedural outcomes. ObjectiveThis study aimed to enhance frailty assessments of TAVR candidates by integrating real-world structured and unstructured data. MethodsThis study analyzed data from 14,000 patients between January 2018 and December 2019 to assess frailty in TAVR patients at the University of Florida. Frailty was identified using the Fried criteria, which includes weight loss, exhaustion, walking speed, grip strength, and physical activity. Latent Dirichlet allocation for topic modeling and Extreme Gradient Boosting for frailty prediction were applied to unstructured clinical notes and structured electronic health record (EHR) data. We also used least absolute shrinkage and selection operator regression for feature selection. Model performance was rigorously evaluated using nested cross-validation, ensuring the generalizability of the findings. ResultsModel performance was significantly improved by combining unstructured clinical notes with structured EHR data, achieving an area under the receiver operating characteristic curve of 0.82 (SD 0.07), which surpassed the EHR-only model’s area under the receiver operating characteristic curve of 0.64 (SD 0.08). The Shapley Additive Explanations analysis found that congestive heart failure management, back problems, and atrial fibrillation were the top frailty predictors. Additionally, the latent Dirichlet allocation topic modeling identified 7 key topics, highlighting the role of specific medical treatments in predicting frailty. ConclusionsIntegrating unstructured clinical notes and structured EHR data led to a notable enhancement in predicting frailty. This method shows great potential for standardizing frailty assessments using real-world data and improving patient selection for TAVR.https://aging.jmir.org/2024/1/e58980 |
| spellingShingle | Mamoun T Mardini Chen Bai Anthony A Bavry Ahmed Zaghloul R David Anderson Catherine E Crenshaw Price Mohammad A Z Al-Ani Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study JMIR Aging |
| title | Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study |
| title_full | Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study |
| title_fullStr | Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study |
| title_full_unstemmed | Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study |
| title_short | Enhancing Frailty Assessments for Transcatheter Aortic Valve Replacement Patients Using Structured and Unstructured Data: Real-World Evidence Study |
| title_sort | enhancing frailty assessments for transcatheter aortic valve replacement patients using structured and unstructured data real world evidence study |
| url | https://aging.jmir.org/2024/1/e58980 |
| work_keys_str_mv | AT mamountmardini enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy AT chenbai enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy AT anthonyabavry enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy AT ahmedzaghloul enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy AT rdavidanderson enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy AT catherineecrenshawprice enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy AT mohammadazalani enhancingfrailtyassessmentsfortranscatheteraorticvalvereplacementpatientsusingstructuredandunstructureddatarealworldevidencestudy |