Machine Learning Prediction Models for In-Hospital Mortality After Transcatheter Aortic Valve Replacement

Hernández-Suárez, Dagmar F.; Kim, Yeunjung; Villablanca, Pedro A.; Gupta, Tanush; Wiley, Jose; Nieves-Rodriguez, Brenda G.; Rodríguez-Maldonado, Jovaniel; Maldonado, Roberto Feliu; Sant’Ana, Istoni da Luz; Sanina, Cristina; Cox‐Alomar, Pedro; Ramakrishna, Harish; López‐Candales, Angel; O’Neill, William W.; Pinto, Duane S.; Latib, Azeem; Roche-Lima, Abiel

doi:10.1016/j.jcin.2019.06.013

Cited by 93 publications

(79 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies have consistently demonstrated the ANN model’s superiority relative to the KNN, SVM, NBC, or MLR models 22 – 24 . Furthermore, statistical analyses have proven the advantages of the ANN model 23 .…”

Section: Discussionmentioning

confidence: 99%

“…When we used actual validation data sets to compare performance among forecasting models based on pCR occurrence, the ANN model significantly outperformed www.nature.com/scientificreports/ the KNN, SVM, NBC, and MLR models, which were constructed using the same limited number of clinical parameters. Recent studies have consistently demonstrated the ANN model's superiority relative to the KNN, SVM, NBC, or MLR models [22][23][24] . Furthermore, statistical analyses have proven the advantages of the ANN model 23 .…”

Section: Discussionmentioning

confidence: 99%

“…In addition, nonnormally distributed and highly correlated data can be used to develop nonlinear and linear ANN models, with extensive application in medical big data analysis. Clinical studies have commonly used ANN models for prognosis prediction 11,22,24 . This study's comparison of various models indicated that the ANN model had the best performance in terms of expanding the set of predictive variables; this facilitates evaluation of the effectiveness of research methods and enables comprehensive prediction of pCR occurrence.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy

Huang

Tsai

et al. 2020

Sci Rep

View full text Add to dashboard Cite

For patients with locally advanced rectal cancer (LARC), achieving a pathological complete response (pCR) after neoadjuvant chemoradiotherapy (CRT) provides them with the optimal prognosis. However, no reliable prediction model is presently available. We evaluated the performance of an artificial neural network (ANN) model in pCR prediction in patients with LARC. Predictive accuracy was compared between the ANN, k-nearest neighbor (KNN), support vector machine (SVM), naïve Bayes classifier (NBC), and multiple logistic regression (MLR) models. Data from two hundred seventy patients with LARC were used to compare the efficacy of the forecasting models. We trained the model with an estimation data set and evaluated model performance with a validation data set. The ANN model significantly outperformed the KNN, SVM, NBC, and MLR models in pCR prediction. Our results revealed that the post-CRT carcinoembryonic antigen is the most influential pCR predictor, followed by intervals between CRT and surgery, chemotherapy regimens, clinical nodal stage, and clinical tumor stage. The ANN model was a more accurate pCR predictor than other conventional prediction models. The predictors of pCR can be used to identify which patients with LARC can benefit from watch-and-wait approaches. Neoadjuvant chemoradiotherapy (CRT) has benefited patients with locally advanced rectal cancer (LARC) with specific respect to improvements in local control, disease-free survival, and sphincter preservation rates 1-3. However, the patterns of tumor regression after neoadjuvant CRT vary widely, ranging from a pathological complete response (pCR) to disease progression. Patients with a pCR have the most favorable survival and tumor control, but only 10-30% of patients with LARC achieve a pCR to neoadjuvant CRT 4-7. Furthermore, mounting evidence has demonstrated that in patients who achieve a pCR, radical surgery can be omitted without compromising

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy

Huang

Tsai

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In addition, we can use non-normally distributed and highly correlated data to develop nonlinear and linear ANN models, with extensive applications in medical big data analysis. In medicine, clinical studies have commonly used the ANN model for prognosis prediction [11,22,24]. This study's comparison of various models indicated that the ANN model exhibited the best performance of expanding the set of predictive variables; this facilitates the evaluation of the effectiveness of research methods and comprehensive prediction of pCR occurrence.…”

Section: Discussionmentioning

confidence: 95%

“…Recent studies have consistently demonstrated the ANN model's superiority relative to the KNN, SVM, NBC, or MLR models [22][23][24]. Statistical analyses have proved the advantages of the ANN model as well [23].…”

Section: Discussionmentioning

confidence: 98%

Machine Learning for Predicting Pathological Complete Response in Patients with Locally Advanced Rectal Cancer after Neoadjuvant Chemoradiotherapy

Huang

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND For patients with locally advanced rectal cancer (LARC), achieving pathological complete response (pCR) after neoadjuvant chemoradiotherapy (CRT) results in best prognosis. So far, no reliable prediction model has been available. We aim to evaluate the performance of an artificial neural network (ANN) model in the prediction of pCR in patients with LARC. METHODS Predictive accuracy was compared between the ANN, k-earest neighbor (KNN), support vector machines (SVM), naïve Bayes classifier (NBC), and multiple logistic regression (MLR) models. RESULTS A total of 236 patients with LARC were used to compare the forecasting models. We trained the model with an estimation data set, and evaluated model performance with a validation data set. The ANN model significantly outperformed the KNN, SVM, NBC, and MLR models in predicting pCR. Our results revealed that post-CRT carcinoembryonic antigen was the most influential predictor of pCR, followed by intervals between CRT and surgery, chemotherapy regimens, clinical nodal stage, and clinical tumor stage. CONCLUSIONS Compared with conventional prediction models, the ANN model was more accurate in the prediction of pCR. The predictors of pCR can be used to identify which patients with LARC can benefit from watch-and-wait approaches.

show abstract

Safety of same‐day discharge after uncomplicated, minimalist transcatheter aortic valve replacement in the COVID‐19 era

Perdoncin

Greenbaum

Grubb

et al. 2020

Cathet Cardio Intervent

View full text Add to dashboard Cite

Objectives We sought to evaluate the safety, efficacy and feasibility of same‐day discharge after uncomplicated, minimalist TAVR. Background At the start of the COVID‐19 pandemic, we created a same‐day discharge (SDD) pathway after conscious sedation, transfemoral (minimalist) TAVR to help minimize risk of viral transmission and conserve hospital resources. Studies support that next‐day discharge (NDD) for carefully selected patients following minimalist TAVR is safe and feasible. There is a paucity of data regarding the safety of SDD after TAVR. Methods In‐hospital and 30 day outcomes of consecutive patients meeting pre‐specified criteria for SDD after minimalist TAVR at our institution between March and July of 2020 were reviewed. Outcomes were compared to a NDD cohort from July 2018 through July 2020 that would have met SDD criteria. Primary endpoints were mortality, delayed pacemaker placement, stroke and cardiovascular readmission at 30 days. Results Twenty nine patients were discharged via the SDD pathway after TAVR. 128 prior NDD patients were identified who met all criteria for SDD. The STS scores were similar between the two groups (SDD 2.6% ±1.5 vs. NDD 2.3% ± 1.2). There were no deaths at 30 days in either group. There was no significant difference in delayed pacemaker placement (SDD 0% vs. NDD 0.8%, p > .99) or cardiovascular readmission (SDD 0% vs. NDD 5.5%, p = .35) at 30 days. Conclusions Same day discharge following uncomplicated, minimalist TAVR in selected patients appears to be safe, achieving similar 30 day outcomes as a cohort of next day discharge patients.

show abstract

Machine Learning Prediction Models for In-Hospital Mortality After Transcatheter Aortic Valve Replacement

Cited by 93 publications

References 27 publications

Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy

Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy

Machine Learning for Predicting Pathological Complete Response in Patients with Locally Advanced Rectal Cancer after Neoadjuvant Chemoradiotherapy

Safety of same‐day discharge after uncomplicated, minimalist transcatheter aortic valve replacement in the COVID‐19 era

Contact Info

Product

Resources

About