Machine Learning Prediction of Stroke Mechanism in Embolic Strokes of Undetermined Source

Kamel, Hooman; Navi, Babak B.; Parikh, Neal S; Merkler, Alexander E; Okin, Peter M.; Devereux, Richard B.; Weinsaft, Jonathan W.; Kim, Jiwon; Cheung, Jim W.; Kim, Luke K.; Casadei, Barbara; Iadecola, Costantino; Sabuncu, Mert R.; Gupta, Ajay; Díaz, Iván

doi:10.1161/strokeaha.120.029305

Cited by 42 publications

(34 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“… 109 proposed a model to be used especially when typical risk factors are unknown to improve stroke screening efficiency, while Kamel et al . 110 studied the associations between cardioembolic stroke and AF. A study from Akça et al .…”

Section: Risk Prediction Modelling With Ai/ml Methodsmentioning

confidence: 99%

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

Olier

Ortega‐Martorell

Pieroni

et al. 2021

Cardiovascular Research

View full text Add to dashboard Cite

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centered on applying ML for detecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modeling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centered in aims such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g., blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.

show abstract

Section: Risk Prediction Modelling With Ai/ml Methodsmentioning

confidence: 99%

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

Olier

Ortega‐Martorell

Pieroni

et al. 2021

Cardiovascular Research

View full text Add to dashboard Cite

show abstract

“…Para autores como Bruffaerts (2018) y Kamel, Navi, Parikh, Merkler & Díaz (2020), la amplia gama de aplicaciones y extensiones que posee el machine learning, se hace cada vez más extensa, pues en cualquier entorno o contexto en el que sea posible estudiar patrones conductuales, ahí �ene cabida el machine learning, dado que es una herramienta que está basada en incorporar toda la compleja algorítmica de los mecanismos de aprendizaje del ser humano, en medir cómo funcionamos desde el condicionamiento clásico o pavloviano y desde el condicionamiento operante, por lo que resulta mucho más sencillo para los procesadores de las grandes corporaciones como Google, Amazon, Facebook, YouTube, Apple, Microso�, entre muchas otras & Sormani, 2020; Zaharchuk, Gong, Wintermark, Rubin & Langlotz, 2018).…”

Section: Marco Teóricounclassified

Neurooncología y su relación con las herramientas de Machine Learning: Un estudio de revisión.

Parra-Bolaños¹,

Benjumea-Garcés²,

Ocampo³

2021

ids

View full text Add to dashboard Cite

La neurooncología es una disciplina cientifica que en la actualidad está haciendo uso constante del machine learning. En este estudio de revisión se hace una pesquisa por varias de las mejores y más rigurosas bases de datos del mundo, con el objetivo de entender cómo el machine learning, que es una herramienta devenida de las nuevas tecnologías de la información y la comunicación para conseguir generar algoritmos y tecnologías basadas en el aprendizaje humano para, desde los principios más básicos y elementales del condicionamiento clásico y operante, hacer una emulación primitiva y rudimentaria de los mecanismos de aprendizaje automatiados en grandes servidores computacionales que se han puesto al servicio de la mayor parte de ciencias existentes. Esta investigación de revisión ha encontrado que el machine learning se está convirtiendo en una herramienta cada vez más usada por los expertos en neurooncología de todo el mundo, con la perspectiva de generar marcadores predictivos mucho más precisos y ambiciosos.

show abstract

“…Acute ischemic stroke (AIS) is a disturbance in cerebral blood flow and has been the leading cause of serious disability and death worldwide ( Khandelwal et al, 2016 ; Kamel et al, 2020 ). As an acute emergency, AIS is estimated to lead to a loss of 1.9 million neurons per minute, causing irreversible brain injury around the infarction area ( Saver, 2006 ).…”

Section: Introductionmentioning

confidence: 99%

Predicting 1-Hour Thrombolysis Effect of r-tPA in Patients With Acute Ischemic Stroke Using Machine Learning Algorithm

et al. 2022

View full text Add to dashboard Cite

Background: Thrombolysis with r-tPA is recommended for patients after acute ischemic stroke (AIS) within 4.5 h of symptom onset. However, only a few patients benefit from this therapeutic regimen. Thus, we aimed to develop an interpretable machine learning (ML)–based model to predict the thrombolysis effect of r-tPA at the super-early stage.Methods: A total of 353 patients with AIS were divided into training and test data sets. We then used six ML algorithms and a recursive feature elimination (RFE) method to explore the relationship among the clinical variables along with the NIH stroke scale score 1 h after thrombolysis treatment. Shapley additive explanations and local interpretable model–agnostic explanation algorithms were applied to interpret the ML models and determine the importance of the selected features.Results: Altogether, 353 patients with an average age of 63.0 (56.0–71.0) years were enrolled in the study. Of these patients, 156 showed a favorable thrombolysis effect and 197 showed an unfavorable effect. A total of 14 variables were enrolled in the modeling, and 6 ML algorithms were used to predict the thrombolysis effect. After RFE screening, seven variables under the gradient boosting decision tree (GBDT) model (area under the curve = 0.81, specificity = 0.61, sensitivity = 0.9, and F1 score = 0.79) demonstrated the best performance. Of the seven variables, activated partial thromboplastin clotting time (time), B-type natriuretic peptide, and fibrin degradation products were the three most important clinical characteristics that might influence r-tPA efficiency.Conclusion: This study demonstrated that the GBDT model with the seven variables could better predict the early thrombolysis effect of r-tPA.

show abstract

Machine Learning Prediction of Stroke Mechanism in Embolic Strokes of Undetermined Source

Cited by 42 publications

References 29 publications

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

Neurooncología y su relación con las herramientas de Machine Learning: Un estudio de revisión.

Predicting 1-Hour Thrombolysis Effect of r-tPA in Patients With Acute Ischemic Stroke Using Machine Learning Algorithm

Contact Info

Product

Resources

About