Search

Machine learning provides increasingly reliable assistance for medical experts in diagnosing coronary heart disease. This study proposes a deep learning hybrid model based coronary heart disease (CAD) prediction method, which can significantly improve the prediction accuracy compared to traditional solutions. This research scheme is based on the data of 7291 patients and proposes a hybrid model, which uses two different deep neural network models and a recurrent neural network model as the main model for training. The prediction results based on the main model training use a k-nearest neighbor model for secondary training so as to improve the accuracy of coronary heart disease prediction. The comparison between the model prediction results and the clinical diagnostic results shows that the prediction model has a prediction accuracy rate of 82.8%, a prediction precision rate of 87.08%, a prediction recall rate of 88.57%, a prediction F1-score of 87.82%, and an area under the curve value of 0.8 in the test set. Compared to single model machine learning predictions, the hybrid model has a significantly improved accuracy and has effectively solved the problem of overfitting. A deep learning based CAD prediction hybrid model that combines multiple weak models into a strong model can fully explore the complex inter-relationships between various features under limited feature values and sample size, improve the evaluation indicators of the prediction model, and provide effective auxiliary support for CAD diagnosis., (© 2024 Author(s). Published under an exclusive license by AIP Publishing.)

Background: Impairment of coronary flow reserve (CFR) has been generally demonstrated in diabetic patients and animals with microvascular complications but without obvious obstructive coronary atherosclerosis. There have been few studies investigating CFR in cases of relatively well-controlled therapy. The purpose of this study is to evaluate the effect of treatment with a Sphingosine-1-phosphate (S1P) receptor potent agonist, FTY720, on early diabetic rats in terms of CFR. METHODS AND RESULTS: Male Sprague-Dawley (SD) rats were divided into 3 groups: (1) streptozotocin-uninjected rats (control rats); (2) streptozotocin-injected hyperglycemic rats (diabetic group); and (3) FTY720-fed and streptozotocin-injected hyperglycemic rats. FTY720 (1.25 mg/kg per day orally) was administrated for 9 weeks in SD rats (from 6 weeks old to 15 weeks old). CFR was evaluated by (13)NH3-positron emission tomography. No obvious pathological changes of macrovascular atherosclerosis were observed in each group. Diabetic rats had impaired CFR compared with the control group (1.39±0.26 vs. 1.94±0.24, P<0.05). Treatment with FTY720 for 9 weeks attenuated the heart histological changes and improved CFR in 32% of diabetic rats (1.84±0.36 vs. 1.39±0.26, P<0.05)., Conclusions: In summary, long-term therapy with the Sphingosine-1-phosphate receptor agonist, FTY720, improved CFR by attenuating the heart histological changes, and it might have a beneficial effect on coronary microvascular function in diabetic rats.