Identifying diagnosis evidence of cardiogenic stroke from Chinese echocardiograph reports

Left atrial myxoma as a rare cause of stroke

Cerebrovascular events may attribute to the fragmentation of a cardiac tumor. Due to the small number of reported cases of large vascular occlusion-acute ischemic stroke (LVO-AIS) associated with atrial myxoma, current guidelines still follow the principle of intravenous thrombolysis priority, even if LVO-AIS patients are eligible for mechanical thrombectomy, and have not recommended the timing of cardiac surgery or preoperative anticoagulation and antithrombotic therapy. Surgical removal is the definitive therapy for cardiac myxomas, especially for left-sided myxomas. With this case, we aim to demonstrate the main challenges that clinicians may encounter when dealing with patients with AIS secondary to cardiac myxoma: the difficulties with clinical diagnosis, strategies for reperfusion therapy, and therapeutic management of cardiac myxoma.

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

BACKGROUND

TOAST subtype classification is important for diagnosis and research of ischemic stroke. Limited by experience of neurologist and time-consuming manual adjudication, it is a big challenge to finish TOAST classification effectively. We propose a novel active deep learning architecture to classify TOAST.

METHODS

To simulate the diagnosis process of neurologists, we drop the valueless features by XGB algorithm and rank the remaining ones. Utilizing active learning framework, we propose a novel causal CNN, in which it combines with a mixed active selection criterion to optimize the uncertainty of samples adaptively. Meanwhile, KL-focal loss derived from the enhancement of Focal loss by KL regularization is introduced to accelerate the iterative fine-tuning of the model.

RESULTS

To evaluate the proposed method, we construct a dataset which consists of totally 2310 patients. In a series of sequential experiments, we verify the effectiveness of each contribution by different evaluation metrics. Experimental results show that the proposed method achieves competitive results on each evaluation metric. In this task, the improvement of AUC is the most obvious, reaching 77.4.

CONCLUSIONS

We construct a backbone causal CNN to simulate the neurologist process of that could enhance the internal interpretability. The research on clinical data also indicates the potential application value of this model in stroke medicine. Future work we would consider various data types and more comprehensive patient types to achieve fully automated subtype classification.