Dataset Information

Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement.

ABSTRACT: Cerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. Predictive variables were selected by recursive feature reduction to train an autoencoder predictive model. Area under the curve (AUC) represented the model's performance to predict 30-day CVE. Among 2279 patients included between 2007 and 2019, both clinical and imaging data were available in 1492 patients. Median age was 83 years and STS score was 4.6%. Acute (< 24 h) and subacute (day 2-30) CVE occurred in 19 (1.3%) and 36 (2.4%) patients, respectively. The occurrence of CVE was associated with an increased risk of death (HR [95% CI] 2.62 [1.82-3.78]). The constructed predictive model uses less than 107 clinical and imaging variables and has an AUC of 0.79 (0.65-0.93). TAVR-related CVE can be predicted using a deep learning-based predictive algorithm. The model is implemented online for broad usage.

SUBMITTER: Okuno T

PROVIDER: S-EPMC8455675 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement.

Okuno Taishi T Overtchouk Pavel P Asami Masahiko M Tomii Daijiro D Stortecky Stefan S Praz Fabien F Lanz Jonas J Siontis George C M GCM Gräni Christoph C Windecker Stephan S Pilgrim Thomas T

Scientific reports 20210921 1

Cerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. ...[more]

PMID: 34548574

Similar Datasets

Project description:BACKGROUNDA series of models have been developed to identify patients at high risk for poor outcomes after transcatheter aortic valve replacement (TAVR) to help guide treatment choices, offer patients realistic expectations of long-term outcomes, and support decision making.OBJECTIVESThis study examined the performance of the previously developed TAVR Poor Outcome risk models in an external dataset and explored the incremental contribution of geriatric domains to model performance.METHODSPoor outcome after TAVR was defined as death, poor quality of life (QOL), or decline in QOL, as assessed using the Kansas City Cardiomyopathy Questionnaire. We tested 4 TAVR Poor Outcome risk models: 6-month and 1-year full and clinical (reduced) models. We examined each model's discrimination and calibration in the CoreValve trial dataset, and then tested the incremental contribution of frailty and disability markers to the model's discrimination using the incremental discrimination index.RESULTSAmong 2,830 patients who underwent TAVR in the CoreValve US Pivotal Extreme and High Risk trials and associated continued access registries, 31.2% experienced a poor outcome at 6 months following TAVR (death, 17.6%; very poor QOL, 11.6%; QOL decline, 2.0%) and 50.8% experienced a poor outcome at 1 year (death, 30.2%; poor QOL, 19.6%; QOL, decline 1.0%). The models demonstrated similar discrimination as in the Placement of Aortic Transcatheter Valves Trial cohorts (c-indexes, 0.637 to 0.665) and excellent calibration. Adding frailty as a syndrome increased the c-indexes by 0.000 to 0.004 (incremental discrimination index, p < 0.01 for all except the 1-year clinical model), with the most important individual components being disability and unintentional weight loss.CONCLUSIONSAlthough discrimination of the TAVR Poor Outcome risk models was generally moderate, calibration was excellent among patients with different risk profiles and treated with a different TAVR device. These findings demonstrated the value of these models for individualizing outcome predictions in high-risk patients undergoing TAVR.

Project description:ImportanceReducing postprocedural stroke is important to improve the safety of transcatheter aortic valve replacement (TAVR).ObjectiveThis study evaluated the trends of stroke occurring within 30 days after the procedure during the first 5 years TAVR was used in the United States, the association of stroke with 30-day mortality, and the association of medical therapy with 30-day stroke risk.Design, setting, and participantsRetrospective cohort study including 101 430 patients who were treated with femoral and nonfemoral TAVR at 521 US hospitals in the Society of Thoracic Surgeons/American College of Cardiology Transcatheter Valve Therapies Registry from November 9, 2011, through May 31, 2017. Thirty-day follow-up ended June 30, 2017.ExposuresTAVR.Main outcomes and measuresThe rates of 30-day transient ischemic attack and stroke were assessed. Association of stroke with 30-day mortality and association of antithrombotic medical therapies with postdischarge 30-day stroke were assessed with a Cox proportional hazards model and propensity-score matching, respectively.ResultsAmong 101 430 patients included in the study (median age, 83 years [interquartile range {IQR}, 76-87 years]; 47 797 women [47.1%]; and 85 147 patients [83.9%] treated via femoral access), 30-day postprocedure follow-up data was assessed in all patients. At day 30, there were 2290 patients (2.3%) with a stroke of any kind (95% CI, 2.2%-2.4%), and 373 patients (0.4%) with transient ischemic attacks (95% CI, 0.3%-0.4%) . During the study period, 30-day stroke rates were stable without an increasing or decreasing trend in all patients (P for trend = .22) and in the large femoral access subgroup (P trend = .47). Among cases of stroke within 30 days, 1119 strokes (48.9%) occurred within the first day and 1567 (68.4%) within 3 days following TAVR. The occurrence of stroke was associated with a significant increase in 30-day mortality: 383 patients (16.7%) of 2290 who had a stroke vs 3662 patients (3.7%) of 99 140 who did not have a stroke died (P < .001; risk-adjusted hazard ratio [HR], 6.1 [95% CI, 5.4-6.8]; P < .001). After propensity-score matching, 30-day stroke risk was not associated with whether patients in the femoral cohort were (0.55%) or were not (0.52%) treated with dual antiplatelet therapy at hospital discharge (HR, 1.04; 95% CI, 0.74-1.46) nor was it associated with whether patients in the nonfemoral cohort were (0.71%) or were not (0.69%) treated with dual antiplatelet therapy (HR, 1.02; 95% CI, 0.54-1.95). Similarly, 30-day stroke risk was not associated with whether patients in the femoral cohort were (0.57%) or were not (0.55) treated with oral anticoagulant therapy at hospital discharge (HR, 1.03; 95% CI, 0.73-1.46) nor was it associated with whether patients in the nonfemoral cohort were (0.75%) or were not (0.82%) treated with an oral anticoagulant (HR, 0.93; 95% CI, 0.47-1.83).Conclusions and relevanceBetween 2011 and 2017, the rate of 30-day stroke following transcatheter aortic valve replacement in a US registry population remained stable.

Dataset Information

Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement.

Publications

Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets