METHODS: This is a retrospective cohort study utilizing data from the National Cardiovascular Disease (NCVD)-PCI registry. The data collected (N = 28,007) were split into training set (n = 24,409) and testing set (n = 3598). Four predictive models (logistic regression [LR], random forest method, support vector machine [SVM], and artificial neural network) were developed and validated. The outcome on risk prediction were compared.
RESULTS: The demographic and clinical features of patients in the training and testing cohorts were similar. Patients had mean age ± standard deviation of 58.15 ± 10.13 years at admission with a male majority (82.66%). In over half of the procedures (50.61%), patients had chronic stable angina. Within 1 year of follow up mortality, target vessel revascularization (TVR), and composite event of mortality and TVR were 3.92%, 9.48%, and 12.98% respectively. LR was the best model in predicting mortality event within 1-year post-PCI (AUC: 0.820). SVM had the highest discrimination power for both TVR event (AUC: 0.720) and composite event of mortality and TVR (AUC: 0.720).
CONCLUSIONS: This study successfully identified optimal prediction models with the good discriminatory ability for mortality outcome and good discrimination ability for TVR and composite event of mortality and TVR with a simple machine learning framework.
METHODS: Two detection architectures, Single Shot Multibox Detector (SSD) and Faster Regional based Convolutional Neural Network (R-CNN) with various feature extractors were trained on echocardiography images from 33 patients. Thereafter, the models were tested on 10 echocardiography videos.
RESULTS: Faster R-CNN Inception v2 had shown the highest accuracy (98.6%) followed closely by SSD Mobilenet v2. In terms of speed, SSD Mobilenet v2 resulted in a loss of 46.81% in framesper- second (fps) during real-time detection but managed to perform better than the other neural network models. Additionally, SSD Mobilenet v2 used the least amount of Graphic Processing Unit (GPU) but the Central Processing Unit (CPU) usage was relatively similar throughout all models.
CONCLUSION: Our findings provide a foundation for implementing a convolutional detection system to echocardiography for medical purposes.
METHODS: This was a retrospective study. Data were extracted from the hybrid medical records of patients from the Institut Jantung Negara (IJN), Malaysia. Adults with established diagnosis of hypertension and on prescription of Val-based SPC therapies as part of routine medical care from 1 January 2013 to 31 December 2018, with ≥ 1 year of follow-up were included. Primary endpoint was proportion of patients achieving therapeutic BP control (BP < 140/90 mmHg). Secondary outcomes included change from baseline (CFB) in systolic BP (SBP) and diastolic BP (DBP), and subgroup analysis was based on baseline SBP categories and presence of diabetes.
RESULTS: Study included 409 hypertensive patients. The mean (standard deviation [SD]) age of the population was 65.1 (10.6) years old, with male predominance (61.6%). Proportion of patients achieving target BP between baseline and follow-up were 57.0% (P < 0.001). Mean CFB in SBP and DBP were recorded as 19.52 mmHg and 7.47 mmHg, respectively. Over half of the patients achieved the target BP in all subgroups categorised by SBP at baseline, except the subgroup of SBP 160 mmHg-179 mmHg. SPC therapies were continued in 97.3% of patients at 1-year follow-up.
CONCLUSION: Patients using Val-based SPC therapies had significant reduction in BP with good tolerability, with 57% of patients achieving target BP over a prolonged 1-year follow-up period. Uptake of SPC therapy is warranted to improve patient care and outcomes in hypertension.
METHODS: The Malaysian subpopulation of two all-comers observational studies based on the same protocol (ClinicalTrials.gov Identifiers: NCT02629575 and NCT02905214) were combined and compared to a Malaysian-only cohort which was treated with a later-generation PF-SES. The PF-SES's used differed only in their bare-metal backbone architecture, with otherwise identical sirolimus coating. The primary endpoint was the accumulated target lesion revascularization (TLR) rate at 12 months. The rates of major adverse cardiac events (MACE), stent thrombosis (ST) and myocardial infarction (MI) were part of the secondary endpoints.
RESULTS: A total of 643 patients were treated with either the first-generation PF-SES (413 patients) or second-generation PF-SES (230 patients). Patient demographics were similar in terms of age (p = 0.744), male gender (0.987), diabetes mellitus (p = 0.293), hypertension (p = 0.905) and acute coronary syndrome (ACS, 44.8% vs. 46.1%, p = 0.752) between groups. There were no differences between treatment groups in terms of lesion length (20.8 ± 7.3 mm vs. 22.9 ± 7.9, p = 0.111) or vessel diameter (2.87 ± 0.39 vs. 2.93 ± 0.40, p = 0.052) despite numerically smaller diameters in the first-generation PF-SES group. The second-generation PF-SES tended to have more complex lesions as characterized by calcification (10.3% vs. 16.2%, p = 0.022), severe tortuosity (3.5% vs. 6.9%, p = 0.041) and B2/C lesions (49.2% vs. 62.8%, p
METHODS: We studied the systematic use of SBA with a low profile, non-slip element device prior to DCB angioplasty in an unselected, non-randomized patient population. This prospective, all-comers study enrolled patients with de novo lesions as well as in-stent restenotic lesions in bare metal stents (BMS-ISR) and drug-eluting stents (DES-ISR). The primary endpoint was the target lesion failure (TLF) rate at 9 months (ClinicalTrials.gov Identifier NCT02554292).
RESULTS: A total of 481 patients (496 lesions) were recruited to treat de novo lesions (78.4%, 377), BMS-ISR (4.0%, 19), and DES-ISR (17.6%, 85). Overall risk factors were acute coronary syndrome (ACS, 20.6%, 99), diabetes mellitus (46.8%, 225), and atrial fibrillation (8.5%, 41). Average lesion lengths were 16.7 ± 10.4 mm in the de novo group, and 20.1 ± 8.9 mm (BMS-ISR) and 16.2 ± 9.8 mm (DES-ISR) in the ISR groups. Scoring balloon diameters were 2.43 ± 0.41 mm (de novo), 2.71 ± 0.31 mm (BMS-ISR), and 2.92 ± 0.42 mm (DES-ISR) whereas DCB diameters were 2.60 ± 0.39 mm (de novo), 3.00 ± 0.35 mm (BMS-ISR), and 3.10 ± 0.43 mm (DES-ISR), respectively. The overall accumulated TLF rate of 3.0% (14/463) was driven by significantly higher target lesion revascularization rates in the BMS-ISR (5.3%, 1/19) and the DES-ISR group (6.0%, 5/84). In de novo lesions, the TLF rate was 1.1% (4/360) without differences between calcified and non-calcified lesions (p = 0.158) and small vs. large reference vessel diameters with a cutoff value of 3.0 mm (p = 0.901).
CONCLUSIONS: The routine use of a non-slip element scoring balloon catheter to prepare lesions suitable for drug-coated balloon angioplasty is associated with high procedural success rates and low TLF rates in de novo lesions.