Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data
Abstract Background Heart failure with preserved ejection fraction (HFpEF) is thought to be highly prevalent yet remains underdiagnosed. Evidence-based treatments are available that increase quality of life and decrease hospitalization. We sought to develop a data-driven diagnostic model to predict ...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | BMC Cardiovascular Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12872-022-03005-w |
| _version_ | 1828083549354328064 |
|---|---|
| author | Nazli Farajidavar Kevin O’Gallagher Daniel Bean Adam Nabeebaccus Rosita Zakeri Daniel Bromage Zeljko Kraljevic James T. H. Teo Richard J. Dobson Ajay M. Shah |
| author_facet | Nazli Farajidavar Kevin O’Gallagher Daniel Bean Adam Nabeebaccus Rosita Zakeri Daniel Bromage Zeljko Kraljevic James T. H. Teo Richard J. Dobson Ajay M. Shah |
| author_sort | Nazli Farajidavar |
| collection | DOAJ |
| description | Abstract Background Heart failure with preserved ejection fraction (HFpEF) is thought to be highly prevalent yet remains underdiagnosed. Evidence-based treatments are available that increase quality of life and decrease hospitalization. We sought to develop a data-driven diagnostic model to predict from electronic health records (EHR) the likelihood of HFpEF among patients with unexplained dyspnea and preserved left ventricular EF. Methods and results The derivation cohort comprised patients with dyspnea and echocardiography results. Structured and unstructured data were extracted using an automated informatics pipeline. Patients were retrospectively diagnosed as HFpEF (cases), non-HF (control cohort I), or HF with reduced EF (HFrEF; control cohort II). The ability of clinical parameters and investigations to discriminate cases from controls was evaluated by extreme gradient boosting. A likelihood scoring system was developed and validated in a separate test cohort. The derivation cohort included 1585 consecutive patients: 133 cases of HFpEF (9%), 194 non-HF cases (Control cohort I) and 1258 HFrEF cases (Control cohort II). Two HFpEF diagnostic signatures were derived, comprising symptoms, diagnoses and investigation results. A final prediction model was generated based on the averaged likelihood scores from these two models. In a validation cohort consisting of 269 consecutive patients [with 66 HFpEF cases (24.5%)], the diagnostic power of detecting HFpEF had an AUROC of 90% (P < 0.001) and average precision of 74%. Conclusion This diagnostic signature enables discrimination of HFpEF from non-cardiac dyspnea or HFrEF from EHR and can assist in the diagnostic evaluation in patients with unexplained dyspnea. This approach will enable identification of HFpEF patients who may then benefit from new evidence-based therapies. |
| first_indexed | 2024-04-11T04:09:00Z |
| format | Article |
| id | doaj.art-ca4a25815785445ebf16cbaf26aa26af |
| institution | Directory Open Access Journal |
| issn | 1471-2261 |
| language | English |
| last_indexed | 2024-04-11T04:09:00Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cardiovascular Disorders |
| spelling | doaj.art-ca4a25815785445ebf16cbaf26aa26af2023-01-01T12:12:39ZengBMCBMC Cardiovascular Disorders1471-22612022-12-0122111310.1186/s12872-022-03005-wDiagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record dataNazli Farajidavar0Kevin O’Gallagher1Daniel Bean2Adam Nabeebaccus3Rosita Zakeri4Daniel Bromage5Zeljko Kraljevic6James T. H. Teo7Richard J. Dobson8Ajay M. Shah9King’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonDepartment of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King’s College LondonKing’s College Hospital NHS Foundation TrustKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonKing’s College London British Heart Foundation Centre of Excellence, School of Cardiovascular and Metabolic Medicine and Sciences, King’s College LondonAbstract Background Heart failure with preserved ejection fraction (HFpEF) is thought to be highly prevalent yet remains underdiagnosed. Evidence-based treatments are available that increase quality of life and decrease hospitalization. We sought to develop a data-driven diagnostic model to predict from electronic health records (EHR) the likelihood of HFpEF among patients with unexplained dyspnea and preserved left ventricular EF. Methods and results The derivation cohort comprised patients with dyspnea and echocardiography results. Structured and unstructured data were extracted using an automated informatics pipeline. Patients were retrospectively diagnosed as HFpEF (cases), non-HF (control cohort I), or HF with reduced EF (HFrEF; control cohort II). The ability of clinical parameters and investigations to discriminate cases from controls was evaluated by extreme gradient boosting. A likelihood scoring system was developed and validated in a separate test cohort. The derivation cohort included 1585 consecutive patients: 133 cases of HFpEF (9%), 194 non-HF cases (Control cohort I) and 1258 HFrEF cases (Control cohort II). Two HFpEF diagnostic signatures were derived, comprising symptoms, diagnoses and investigation results. A final prediction model was generated based on the averaged likelihood scores from these two models. In a validation cohort consisting of 269 consecutive patients [with 66 HFpEF cases (24.5%)], the diagnostic power of detecting HFpEF had an AUROC of 90% (P < 0.001) and average precision of 74%. Conclusion This diagnostic signature enables discrimination of HFpEF from non-cardiac dyspnea or HFrEF from EHR and can assist in the diagnostic evaluation in patients with unexplained dyspnea. This approach will enable identification of HFpEF patients who may then benefit from new evidence-based therapies.https://doi.org/10.1186/s12872-022-03005-wHFpEFMachine learningDyspnea |
| spellingShingle | Nazli Farajidavar Kevin O’Gallagher Daniel Bean Adam Nabeebaccus Rosita Zakeri Daniel Bromage Zeljko Kraljevic James T. H. Teo Richard J. Dobson Ajay M. Shah Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data BMC Cardiovascular Disorders HFpEF Machine learning Dyspnea |
| title | Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data |
| title_full | Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data |
| title_fullStr | Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data |
| title_full_unstemmed | Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data |
| title_short | Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data |
| title_sort | diagnostic signature for heart failure with preserved ejection fraction hfpef a machine learning approach using multi modality electronic health record data |
| topic | HFpEF Machine learning Dyspnea |
| url | https://doi.org/10.1186/s12872-022-03005-w |
| work_keys_str_mv | AT nazlifarajidavar diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT kevinogallagher diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT danielbean diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT adamnabeebaccus diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT rositazakeri diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT danielbromage diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT zeljkokraljevic diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT jamesthteo diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT richardjdobson diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata AT ajaymshah diagnosticsignatureforheartfailurewithpreservedejectionfractionhfpefamachinelearningapproachusingmultimodalityelectronichealthrecorddata |