Natural Language Processing in a Clinical Decision Support System for the Identification of Venous Thromboembolism: Algorithm Development and Validation.

BACKGROUND: It remains unknown whether capturing data from electronic health records (EHRs) using natural language processing (NLP) can improve venous thromboembolism (VTE) detection in different clinical settings. OBJECTIVE: The aim of this study was to validate the NLP algorithm in a clinical decision support system for VTE risk assessment and integrated care (DeVTEcare) to identify VTEs from EHRs. METHODS: All inpatients aged ≥18 years in the Sixth Medical Center of the Chinese People's Liberation Army General Hospital from January 1 to December 31, 2021, were included as the validation cohort. The sensitivity, specificity, positive and negative likelihood ratios (LR+ and LR-, respectively), area under the receiver operating characteristic curve (AUC), and F1-scores along with their 95% CIs were used to analyze the performance of the NLP tool, with manual review of medical records as the reference standard for detecting deep vein thrombosis (DVT) and pulmonary embolism (PE). The primary end point was the performance of the NLP approach embedded into the EHR for VTE identification. The secondary end points were the performances to identify VTE among different hospital departments with different VTE risks. Subgroup analyses were performed among age, sex, and the study season. RESULTS: Among 30,152 patients (median age 56 [IQR 41-67] years; 14,247/30,152, 47.3% females), the prevalence of VTE, PE, and DVT was 2.1% (626/30,152), 0.6% (177/30,152), and 1.8% (532/30,152), respectively. The sensitivity, specificity, LR+, LR-, AUC, and F1-score of NLP-facilitated VTE detection were 89.9% (95% CI 87.3%-92.2%), 99.8% (95% CI 99.8%-99.9%), 483 (95% CI 370-629), 0.10 (95% CI 0.08-0.13), 0.95 (95% CI 0.94-0.96), and 0.90 (95% CI 0.90-0.91), respectively. Among departments of surgery, internal medicine, and intensive care units, the highest specificity (100% vs 99.7% vs 98.8%, respectively), LR+ (3202 vs 321 vs 77, respectively), and F1-score (0.95 vs 0.89 vs 0.92, respectively) were in the surgery department (all P<.001). Among low, intermediate, and high VTE risks in hospital departments, the low-risk department had the highest AUC (1.00 vs 0.94 vs 0.96, respectively) and F1-score (0.97 vs 0.90 vs 0.90, respectively) as well as the lowest LR- (0.00 vs 0.13 vs 0.08, respectively) (DeLong test for AUC; all P<.001). Subgroup analysis of the age, sex, and season demonstrated consistently good performance of VTE detection with >87% sensitivity and specificity and >89% AUC and F1-score. The NLP algorithm performed better among patients aged ≤65 years than among those aged >65 years (F1-score 0.93 vs 0.89, respectively; P<.001). CONCLUSIONS: The NLP algorithm in our DeVTEcare identified VTE well across different clinical settings, especially in patients in surgery units, departments with low-risk VTE, and patients aged ≤65 years. This algorithm can help to inform accurate in-hospital VTE rates and enhance risk-classified VTE integrated care in future research.

Comparison of diagnostic accuracy of dual-axis rotational versus standard coronary angiography.

The data about the accuracy of dual-axis rotational coronary angiography (DARCA) in detecting coronary artery disease (CAD) is scare. This study aimed to compare the diagnostic accuracy of DARCA versus standard coronary angiography (SA). 70 patients with possible CAD underwent SA following by DARCA were prospectively enrolled. The primary endpoint was the non-inferiority comparison of the two modalities regarding diagnosis of CAD. Coronary lesion assessment, quantitative coronary angiography (QCA) analysis, and screening adequacy comparisons were performed. All images were analyzed by two independent reviewers except QCA analysis that was analyzed by the third independent reviewer. Radiation dose, contrast usage and procedural time were recorded. This trial is registered with ClinicalTrials.gov, Number NCT01776866. 63 of 70 patients were analyzed. DARCA was non-inferior to SA regarding the diagnosis of CAD (reviewer one-positive agreement: 100%, negative agreement: 100%, p = 1; p = 0.003 for non-inferiority; reviewer two-positive agreement: 96%, negative agreement: 95%, p = 1; p = 0.016 for non-inferiority). All reviewers showed good agreement between the two modalities for the diagnosis of CAD, coronary lesion assessment, QCA analysis, and screening adequacy, as reflected by kappa coefficients between 0.61 and 1.00. DARCA was associated with 41% reduction in radiation dose, 30% in contrast usage and 29% in procedure time (all p < 0.001). DARCA is clinically comparable to SA concerning the diagnostic accuracy for CAD, while markedly reduces radiation dose, contrast usage and procedure time.

Antiplatelet Effect of Different Loading Doses of Ticagrelor in Patients With Non-ST-Elevation Acute Coronary Syndrome Undergoing Percutaneous Coronary Intervention: The APELOT Trial.

BACKGROUND: We hypothesized that a high ticagrelor loading dose (LD) may improve platelet inhibition in patients with non-ST-elevation acute coronary syndrome (NSTE-ACS) undergoing percutaneous coronary intervention (PCI). METHODS: This interventional multicentre open-label trial randomized 278 patients with NSTE-ACS to a high (360 mg) or conventional (180 mg) ticagrelor LD. The primary outcome was the platelet reactivity index (PRI) 1 hour after administration of the LD. Secondary outcomes included PRI at 0.5 hour, 1 hour, 8 hours, and 24 hours; periprocedural myocardial infarction (PMI); major cardiac adverse events; and bleeding events. RESULTS: Two hundred sixty-two patients completed the major end points. PRI was lower in the high-LD group than in the conventional-LD group at any time point (all, P < 0.05), including at 1 hour (12.2% vs 16.7%; P = 0.023). At 0.5 hour, the high-LD group showed a lower high-platelet reactivity rate (49.6% vs 60.2%; P = 0.013) and a higher low-platelet reactivity rate (24.8% vs 12.8%; P = 0.017) than did the conventional LD group. No significant differences in the bleeding rates were found between the 2 groups (14% vs 14.3%). Four cases of PMI and 1 death in each group, as well as 1 acute myocardial infarction in the conventional LD group, occurred. There was no stroke, target lesion revascularization, or target vessel revascularization. CONCLUSIONS: Doubling the ticagrelor LD achieved faster onset and greater platelet inhibition without an increase in adverse events in patients with NSTE-ACS undergoing PCI.

Five-year outcomes of ST-elevation myocardial infarction versus non-ST-elevation acute coronary syndrome treated with biodegradable polymer-coated sirolimus-eluting stents: Insights from the CREATE trial.

BACKGROUND: Long-term outcome of drug-eluting stents (DES) for ST-elevation myocardial infarction (STEMI) versus non-ST-elevation acute coronary syndrome (NSTE-ACS) remains unclear. This study sought to compare the long-term outcomes of biodegradable polymer-coated DES in patients with STEMI versus NSTE-ACS. METHODS: We explored a post hoc analysis of the 5-year outcome of the CREATE trial in the subgroup of patients with STEMI (n=318) versus NSTE-ACS (n=1223) who were implanted with biodegradable polymer-coated DES. The primary outcome was the rate of major adverse cardiac events (MACE) at 5 years. Clopidogrel and aspirin for 6 months followed by chronic aspirin therapy were recommended. RESULTS: STEMI patients showed a trend of increase in MACE (8.7% vs. 6.8%, log rank p=0.289) compared to NSTE-ACS patients at 5 years, and a greater risk of cardiac death (5.4% vs. 2.1%, log rank p=0.003), mainly driven by the higher cardiac death rate within the first month after stent placement (log rank p=0.003) and the last year of follow-up (log rank p=0.001). No significant difference in stent thrombosis was found between them (3.1% vs. 2.5%, log rank p=0.653). Prolonged clopidogrel therapy (>6 months) showed no effect on risk of MACE or stent thrombosis between the two groups (both p for interaction >0.1). CONCLUSIONS: STEMI patients have a higher risk of cardiac mortality compared with NSTE-ACS patients after biodegradable polymer-coated DES placement, primarily attribute to more cardiac deaths that happened within the first month after the event and the last year of follow-up.

Correlation between dual-axis rotational coronary angiography and intravascular ultrasound in a coronary lesion assessment.

The purpose of this study was to evaluate the accuracy of dual-axis rotational coronary angiography (DARCA) for coronary lesion assessment by directly comparing with intravascular ultrasound (IVUS). From October 2014 to December 2015, 40 patients (58 lesions) who had undergone both DARCA and IVUS were included in the image analysis. The minimum lumen diameter (MLD), lesion length, reference vessel diameter (RVD) and percent diameter stenosis at the same lesion, were identified and assessed. Significant correlation with IVUS was found for DARCA in either lesion length (r = 0.90, P < 0.001) or RVD (r = 0.81, P < 0.001) comparison. DARCA had fair correlation with IVUS for both MLD (r = 0.65, P < 0.001) and diameter stenosis (r = 0.48, P < 0.001). From the Bland-Altman plots, there was a good agreement between DARCA and IVUS regarding MLD (mean difference: -0.23 mm, 95 % limits of agreement: -0.96 to 0.50 mm) and RVD (mean difference: -0.15 mm, 95 % limits of agreement: -0.85 to 0.55 mm), while lesser agreement was found on lesion length (mean difference: -3.39 mm, 95 % limits of agreement: -12.63 to 5.85 mm) and diameter stenosis (mean difference: 4.82 %, 95 % limits of agreement: -17.05 to 26.68 %). There is an adequate correlation and agreement between DARCA and IVUS in coronary lesion assessment.

Design and Rationale of the APELOT Trial: A Randomized, Open-Label, Multicenter, Phase IV Study to Evaluate the Antiplatelet Effect of Different Loading Dose of Ticagrelor in Patients With Non-ST Acute Coronary Syndrome Undergoing Percutaneous Coronary Intervention.

Ticagrelor is a direct acting on the P2Y12 receptor blocker, which provides faster and greater platelet inhibition than clopidogrel. However, several studies suggested that in ST-segment elevation myocardial infarction patients undergoing percutaneous coronary intervention (PCI), ticagrelor exhibits initial delay in the onset of antiplatelet action. Unlike ST-segment elevation myocardial infarction, in non-ST-segment elevation acute coronary syndrome (NSTE-ACS), management pathways are highly variable, and some patients may require surgery. Effect of higher loading dose (LD) of ticagrelor in patients with NSTE-ACS in providing faster and stronger inhibition of platelet aggregation is unknown and needs to be explored further.The AntiPlatelet Effect of different Loading dOse of Ticagrelor trial is an interventional, randomized, open-label, multicenter, phase IV trial designed to evaluate whether a high LD (360 mg) of ticagrelor compared with the conventional LD (180 mg) will result in a higher inhibition of platelet aggregation without increasing bleeding events in NSTE-ACS participants undergoing PCI.A total of 250 NSTE-ACS participants will be randomized to receive a ticagrelor LD (360 or 180 mg), followed by a maintenance dose of 90 mg twice a day (bid) starting 12 hours after the LD. The primary endpoint is platelet reactivity index measured by vasodilator-stimulated phosphoprotein phosphorylation 2 hours after the LD, and the secondary endpoints include occurrence of periprocedural myocardial infarction and bleeding events.The AntiPlatelet Effect of different Loading dOse of Ticagrelor trial will provide important information on the risks and benefits of a high LD (360 mg) of ticagrelor in achieving a faster and stronger platelet inhibition compared with the conventional LD (180 mg) in NSTE-ACS patients undergoing PCI.

Randomized study on the safety and efficacy of dual-axis rotational versus standard coronary angiography in.

BACKGROUND: Dual-axis rotational coronary angiography (DARCA) was developed as an innovative adaptation of rotational angiography (RA), but it requires a longer coronary injection compared to standard coronary angiography (SA). As the body of the average Chinese patient is smaller than that of most western patients, with the same contrast injection time, the risk of complications from the contrast agent is increased in this population. The purpose of this study was to assess the clinical safety and efficacy of DARCA in the diagnosis of coronary artery disease (CAD) in the Chinese population by directly comparing it to SA. METHODS: Two hundred Chinese patients were randomized to either the SA group (n = 100) or DARCA group (n = 100). Contrast utilization, radiation exposure and procedure time were recorded for each modalities. Blood pressure (BP), heart rate (HR) pre and post injection symptoms and any arrhythmias were recorded. RESULTS: Compared to the SA group, there was a 42% reduction in contrast utilization, 55% reduction in radiation exposure and a 31% shorter procedure time in the DARCA group. In both groups, there were slight declines in the systolic BP values in the left coronary artery (LCA) post injection (P < 0.01). Moreover, post injection HRs for the LCA were also reduced in the DARCA group (P < 0.01). But all of these changes were small, transient and without clinical importance. Only one patient (1%) in the DARCA group had an attack of ventricular tachycardia immediately post injection and it resolved by itself during LCA angiography. No arrhythmias occurred in the SA group. CONCLUSION: DARCA is a safe, efficient, and clinically comparable alternative to SA in the diagnosis of coronary artery disease in the Chinese population with less contrast utilized, which is less radiation exposure and a shorter procedure time than SA.

Long-term effects of biodegradable versus durable polymer-coated sirolimus-eluting stents on coronary arterial wall morphology assessed by virtual histology intravascular ultrasound.

BACKGROUND: The durable presence of polymer coating on drug-eluting stent (DES) surface may be one of the principal reasons for stent thrombosis. The long-term coronary arterial response to biodegradable polymer-coated sirolimus-eluting stent (BSES) in vivo remained unclear. METHODS: Forty-one patients were enrolled in this study and virtual histology intravascular ultrasound (VH-IVUS) was performed to assess the native artery vascular responses to BSES compared with durable polymer-coated SES (DSES) during long-term follow-up (median: 8 months). The incidence of necrotic core abutting to the lumen was evaluated at follow-up. RESULTS: With similar in-stent late luminal loss (0.15 mm (0.06-0.30 mm) vs. 0.19 mm (0.03-0.30 mm), P = 0.772), the overall incidence of necrotic core abutting to the lumen was significantly less in BSES group than in DSES group (44% vs. 63%, P < 0.05) (proximal 18%, stented site 14% and distal 12% in BSES group, proximal 19%, stented site 28% and distal 16% in DSES group). The DSES-treated segments had a significant higher incidence of necrotic core abutting to the lumen through the stent struts (73% vs. 36%, P < 0.01). In addition, more multiple necrotic core abutting to the lumen was observed in DSES group (overall: 63% vs. 36%, P < 0.05). Furthermore, when the stented segments with necrotic core abutting to the lumen had been taken into account only, DSES-treated lesions tended to contain more multiple necrotic core abutting to the lumen through the stent struts than BSES-treated lesions (74% vs. 33%), although there was no statistically significant difference between them (P = 0.06). CONCLUSIONS: By VH-IVUS analysis at follow-up, a greater frequency of stable lesion morphometry was shown in lesions treated with BSESs compared with lesions treated with DSESs. The major reason was BSES produced less toxicity to the arterial wall and facilitated neointimal healing as a result of polymer coating on DES surface biodegraded as time went by.