Similarity-based prediction of ejection fraction in heart failure patients
Biomedical research is increasingly employing real world evidence (RWE) to foster discoveries of novel clinical phenotypes and to better characterize long term effect of medical treatments. However, due to limitations inherent in the collection process, RWE often lacks key features of patients, part...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914822001770 |
| _version_ | 1811211573593636864 |
|---|---|
| author | Jamie Wallis Andres Azqueta-Gavaldon Thanusha Ananthakumar Robert Dürichen Luca Albergante |
| author_facet | Jamie Wallis Andres Azqueta-Gavaldon Thanusha Ananthakumar Robert Dürichen Luca Albergante |
| author_sort | Jamie Wallis |
| collection | DOAJ |
| description | Biomedical research is increasingly employing real world evidence (RWE) to foster discoveries of novel clinical phenotypes and to better characterize long term effect of medical treatments. However, due to limitations inherent in the collection process, RWE often lacks key features of patients, particularly when these features cannot be directly encoded using data standards such as ICD-10. Here, we propose a novel data-driven statistical machine learning approach, named Feature Imputation via Local Likelihood (FILL), designed to infer missing features by exploiting feature similarity between patients. We test our method using a particularly challenging problem: differentiating heart failure patients with reduced versus preserved ejection fraction (HFrEF and HFpEF respectively). The complexity of the task stems from three aspects: the two share many common characteristics and treatments, only part of the relevant diagnoses may have been recorded, and the information on ejection fraction is often missing from RWE datasets. Despite these difficulties, our method is shown to be capable of inferring heart failure patients with HFpEF with a precision above 80% when considering multiple scenarios across two RWE datasets containing 11,950 and 10,051 heart failure patients. This is an improvement when compared to classical approaches such as logistic regression and random forest which were only able to achieve a precision < 73%. Finally, this approach allows us to analyse which features are commonly associated with HFpEF patients. For example, we found that specific diagnostic codes for atrial fibrillation and personal history of long-term use of anticoagulants are often key in identifying HFpEF patients. |
| first_indexed | 2024-04-12T05:15:02Z |
| format | Article |
| id | doaj.art-9e0a2467ee4c4ecebc5dc5c433e3505b |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-04-12T05:15:02Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-9e0a2467ee4c4ecebc5dc5c433e3505b2022-12-22T03:46:39ZengElsevierInformatics in Medicine Unlocked2352-91482022-01-0132101035Similarity-based prediction of ejection fraction in heart failure patientsJamie Wallis0Andres Azqueta-Gavaldon1Thanusha Ananthakumar2Robert Dürichen3Luca Albergante4Corresponding author.; Sensyne Health Plc, Oxford, UKSensyne Health Plc, Oxford, UKSensyne Health Plc, Oxford, UKSensyne Health Plc, Oxford, UKSensyne Health Plc, Oxford, UKBiomedical research is increasingly employing real world evidence (RWE) to foster discoveries of novel clinical phenotypes and to better characterize long term effect of medical treatments. However, due to limitations inherent in the collection process, RWE often lacks key features of patients, particularly when these features cannot be directly encoded using data standards such as ICD-10. Here, we propose a novel data-driven statistical machine learning approach, named Feature Imputation via Local Likelihood (FILL), designed to infer missing features by exploiting feature similarity between patients. We test our method using a particularly challenging problem: differentiating heart failure patients with reduced versus preserved ejection fraction (HFrEF and HFpEF respectively). The complexity of the task stems from three aspects: the two share many common characteristics and treatments, only part of the relevant diagnoses may have been recorded, and the information on ejection fraction is often missing from RWE datasets. Despite these difficulties, our method is shown to be capable of inferring heart failure patients with HFpEF with a precision above 80% when considering multiple scenarios across two RWE datasets containing 11,950 and 10,051 heart failure patients. This is an improvement when compared to classical approaches such as logistic regression and random forest which were only able to achieve a precision < 73%. Finally, this approach allows us to analyse which features are commonly associated with HFpEF patients. For example, we found that specific diagnostic codes for atrial fibrillation and personal history of long-term use of anticoagulants are often key in identifying HFpEF patients.http://www.sciencedirect.com/science/article/pii/S2352914822001770 |
| spellingShingle | Jamie Wallis Andres Azqueta-Gavaldon Thanusha Ananthakumar Robert Dürichen Luca Albergante Similarity-based prediction of ejection fraction in heart failure patients Informatics in Medicine Unlocked |
| title | Similarity-based prediction of ejection fraction in heart failure patients |
| title_full | Similarity-based prediction of ejection fraction in heart failure patients |
| title_fullStr | Similarity-based prediction of ejection fraction in heart failure patients |
| title_full_unstemmed | Similarity-based prediction of ejection fraction in heart failure patients |
| title_short | Similarity-based prediction of ejection fraction in heart failure patients |
| title_sort | similarity based prediction of ejection fraction in heart failure patients |
| url | http://www.sciencedirect.com/science/article/pii/S2352914822001770 |
| work_keys_str_mv | AT jamiewallis similaritybasedpredictionofejectionfractioninheartfailurepatients AT andresazquetagavaldon similaritybasedpredictionofejectionfractioninheartfailurepatients AT thanushaananthakumar similaritybasedpredictionofejectionfractioninheartfailurepatients AT robertdurichen similaritybasedpredictionofejectionfractioninheartfailurepatients AT lucaalbergante similaritybasedpredictionofejectionfractioninheartfailurepatients |