Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis
Background Accurate mortality prediction following transcatheter aortic valve implantation (TAVI) is essential for mitigating risk, shared decision-making and periprocedural planning. Surgical risk models have demonstrated modest discriminative value for patients undergoing TAVI and are typically po...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2025-01-01
|
| Series: | Open Heart |
| Online Access: | https://openheart.bmj.com/content/12/1/e002779.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590863408037888 |
|---|---|
| author | Clara K Chow Aravinda Thiagalingam Rohan Jayasinghe Sarah Zaman Stephen Bacchi Justin Chan Aashray Gupta Shaun Evans Pramesh Kovoor Brandon Stretton Jayme Bennetts Ammar Zaka Naim Mridha Joshua Kovoor Gopal Sivagangabalan Cecil Mustafiz Daud Mutahar Shreyans Sinhal James Gorcilov Benjamin Muston Fabio Ramponi Dale J Murdoch |
| author_facet | Clara K Chow Aravinda Thiagalingam Rohan Jayasinghe Sarah Zaman Stephen Bacchi Justin Chan Aashray Gupta Shaun Evans Pramesh Kovoor Brandon Stretton Jayme Bennetts Ammar Zaka Naim Mridha Joshua Kovoor Gopal Sivagangabalan Cecil Mustafiz Daud Mutahar Shreyans Sinhal James Gorcilov Benjamin Muston Fabio Ramponi Dale J Murdoch |
| author_sort | Clara K Chow |
| collection | DOAJ |
| description | Background Accurate mortality prediction following transcatheter aortic valve implantation (TAVI) is essential for mitigating risk, shared decision-making and periprocedural planning. Surgical risk models have demonstrated modest discriminative value for patients undergoing TAVI and are typically poorly calibrated, with incremental improvements seen in TAVI-specific models. Machine learning (ML) models offer an alternative risk stratification that may offer improved predictive accuracy.Methods PubMed, EMBASE, Web of Science and Cochrane databases were searched until 16 December 2023 for studies comparing ML models with traditional statistical methods for event prediction after TAVI. The primary outcome was comparative discrimination measured by C-statistics with 95% CIs between ML models and traditional methods in estimating the risk of all-cause mortality at 30 days and 1 year.Results Nine studies were included (29 608 patients). The summary C-statistic of the top performing ML models was 0.79 (95% CI 0.71 to 0.86), compared with traditional methods 0.68 (95% CI 0.61 to 0.76). The difference in C-statistic between all ML models and traditional methods was 0.11 (p<0.00001). Of the nine studies, two studies provided externally validated models and three studies reported calibration. Prediction Model Risk of Bias Assessment Tool tool demonstrated high risk of bias for all studies.Conclusion ML models outperformed traditional risk scores in the discrimination of all-cause mortality following TAVI. While integration of ML algorithms into electronic healthcare systems may improve periprocedural risk stratification, immediate implementation in the clinical setting remains uncertain. Further research is required to overcome methodological and validation limitations. |
| format | Article |
| id | doaj-art-0efc5b449dd6498a9b716323d194759a |
| institution | Kabale University |
| issn | 2053-3624 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | Open Heart |
| spelling | doaj-art-0efc5b449dd6498a9b716323d194759a2025-01-23T05:30:09ZengBMJ Publishing GroupOpen Heart2053-36242025-01-0112110.1136/openhrt-2024-002779Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysisClara K Chow0Aravinda Thiagalingam1Rohan Jayasinghe2Sarah Zaman3Stephen Bacchi4Justin Chan5Aashray Gupta6Shaun Evans7Pramesh Kovoor8Brandon Stretton9Jayme Bennetts10Ammar Zaka11Naim Mridha12Joshua Kovoor13Gopal Sivagangabalan14Cecil Mustafiz15Daud Mutahar16Shreyans Sinhal17James Gorcilov18Benjamin Muston19Fabio Ramponi20Dale J Murdoch21The George Institute for Global Health, Sydney, New South Wales, AustraliaWestmead Hospital, Westmead, New South Wales, AustraliaGold Coast Hospital and Health Service, Southport, Queensland, AustraliaWestmead Hospital, Westmead, New South Wales, AustraliaMassachusetts General Hospital, Boston, Massachusetts, USANew York University Grossman School of Medicine, New York, New York, USARoyal North Shore Hospital, St Leonards, New South Wales, AustraliaRoyal Adelaide Hospital, Adelaide, South Australia, AustraliaUniversity of Sydney, Westmead Hospital, Sydney, New South Wales, AustraliaRoyal Adelaide Hospital, Adelaide, South Australia, AustraliaMonash University, Melbourne, Victoria, AustraliaGold Coast Hospital and Health Service, Southport, Queensland, AustraliaThe Prince Charles Hospital, Chermside, Queensland, AustraliaThe University of Sydney Westmead Applied Research Centre, Westmead, New South Wales, AustraliaCardiology Department, Westmead Hospital, Westmead, New South Wales, AustraliaGriffith University, Brisbane, Queensland, AustraliaBond University Faculty of Health Sciences and Medicine, Gold Coast, Queensland, AustraliaThe University of Adelaide Faculty of Health and Medical Sciences, Adelaide, South Australia, AustraliaRoyal Adelaide Hospital, Adelaide, South Australia, AustraliaRoyal Prince Alfred Hospital, Camperdown, New South Wales, AustraliaYale School of Medicine, New Haven, Connecticut, USAThe Prince Charles Hospital, Chermside, Queensland, AustraliaBackground Accurate mortality prediction following transcatheter aortic valve implantation (TAVI) is essential for mitigating risk, shared decision-making and periprocedural planning. Surgical risk models have demonstrated modest discriminative value for patients undergoing TAVI and are typically poorly calibrated, with incremental improvements seen in TAVI-specific models. Machine learning (ML) models offer an alternative risk stratification that may offer improved predictive accuracy.Methods PubMed, EMBASE, Web of Science and Cochrane databases were searched until 16 December 2023 for studies comparing ML models with traditional statistical methods for event prediction after TAVI. The primary outcome was comparative discrimination measured by C-statistics with 95% CIs between ML models and traditional methods in estimating the risk of all-cause mortality at 30 days and 1 year.Results Nine studies were included (29 608 patients). The summary C-statistic of the top performing ML models was 0.79 (95% CI 0.71 to 0.86), compared with traditional methods 0.68 (95% CI 0.61 to 0.76). The difference in C-statistic between all ML models and traditional methods was 0.11 (p<0.00001). Of the nine studies, two studies provided externally validated models and three studies reported calibration. Prediction Model Risk of Bias Assessment Tool tool demonstrated high risk of bias for all studies.Conclusion ML models outperformed traditional risk scores in the discrimination of all-cause mortality following TAVI. While integration of ML algorithms into electronic healthcare systems may improve periprocedural risk stratification, immediate implementation in the clinical setting remains uncertain. Further research is required to overcome methodological and validation limitations.https://openheart.bmj.com/content/12/1/e002779.full |
| spellingShingle | Clara K Chow Aravinda Thiagalingam Rohan Jayasinghe Sarah Zaman Stephen Bacchi Justin Chan Aashray Gupta Shaun Evans Pramesh Kovoor Brandon Stretton Jayme Bennetts Ammar Zaka Naim Mridha Joshua Kovoor Gopal Sivagangabalan Cecil Mustafiz Daud Mutahar Shreyans Sinhal James Gorcilov Benjamin Muston Fabio Ramponi Dale J Murdoch Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis Open Heart |
| title | Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis |
| title_full | Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis |
| title_fullStr | Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis |
| title_full_unstemmed | Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis |
| title_short | Machine-learning versus traditional methods for prediction of all-cause mortality after transcatheter aortic valve implantation: a systematic review and meta-analysis |
| title_sort | machine learning versus traditional methods for prediction of all cause mortality after transcatheter aortic valve implantation a systematic review and meta analysis |
| url | https://openheart.bmj.com/content/12/1/e002779.full |
| work_keys_str_mv | AT clarakchow machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT aravindathiagalingam machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT rohanjayasinghe machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT sarahzaman machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT stephenbacchi machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT justinchan machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT aashraygupta machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT shaunevans machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT prameshkovoor machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT brandonstretton machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT jaymebennetts machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT ammarzaka machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT naimmridha machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT joshuakovoor machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT gopalsivagangabalan machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT cecilmustafiz machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT daudmutahar machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT shreyanssinhal machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT jamesgorcilov machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT benjaminmuston machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT fabioramponi machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis AT dalejmurdoch machinelearningversustraditionalmethodsforpredictionofallcausemortalityaftertranscatheteraorticvalveimplantationasystematicreviewandmetaanalysis |