Predicting conversion of brain ß-amyloid positivity in amyloid-negative individuals.

BACKGROUND: Cortical deposition of ß-amyloid (Aß) plaque is one of the main hallmarks of Alzheimer's disease (AD). While Aß positivity has been the main concern so far, predicting whether Aß (-) individuals will convert to Aß (+) has become crucial in clinical and research aspects. In this study, we aimed to develop a classifier that predicts the conversion from Aß (-) to Aß (+) using artificial intelligence. METHODS: Data were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort regarding patients who were initially Aß (-). We developed an artificial neural network-based classifier with baseline age, gender, APOE ε4 genotype, and global and regional standardized uptake value ratios (SUVRs) from positron emission tomography. Ten times repeated 10-fold cross-validation was performed for model measurement, and the feature importance was assessed. To validate the prediction model, we recruited subjects at the Samsung Medical Center (SMC). RESULTS: A total of 229 participants (53 converters) from the ADNI dataset and a total of 40 subjects (10 converters) from the SMC dataset were included. The average area under the receiver operating characteristic values of three developed models are as follows: Model 1 (age, gender, APOE ε4) of 0.674, Model 2 (age, gender, APOE ε4, global SUVR) of 0.814, and Model 3 (age, gender, APOE ε4, global and regional SUVR) of 0.841. External validation result showed an AUROC of 0.900. CONCLUSION: We developed prediction models regarding Aß positivity conversion. With the growing recognition of the need for earlier intervention in AD, the results of this study are expected to contribute to the screening of early treatment candidates.

Potential Applications of Artificial Intelligence in Clinical Trials for Alzheimer's Disease.

Clinical trials for Alzheimer's disease (AD) face multiple challenges, such as the high screen failure rate and the even allocation of heterogeneous participants. Artificial intelligence (AI), which has become a potent tool of modern science with the expansion in the volume, variety, and velocity of biological data, offers promising potential to address these issues in AD clinical trials. In this review, we introduce the current status of AD clinical trials and the topic of machine learning. Then, a comprehensive review is focused on the potential applications of AI in the steps of AD clinical trials, including the prediction of protein and MRI AD biomarkers in the prescreening process during eligibility assessment and the likelihood stratification of AD subjects into rapid and slow progressors in randomization. Finally, this review provides challenges, developments, and the future outlook on the integration of AI into AD clinical trials.

Toxocariasis-Associated Acute Perimyocarditis with Cardiogenic Shock: A Case Report.

BACKGROUND Toxocariasis is an infection due to ingestion of the helminth parasite larvae found in dogs (Toxocara canis) or cats (Toxocara cati). Symptoms vary from being asymptomatic to shock, depending on the organ invaded by the parasite. However, cardiac involvement with shock in toxocariasis is very rare. CASE REPORT A 21-year-old woman without any history of underlying conditions visited the Emergency Department because of epigastric pain, vomiting, headache, and dizziness. Her blood pressure was 80/60 mmHg. Computed tomography (CT) of the brain showed no abnormal lesions. The abdominal-pelvic CT with contrast showed right pleural effusion, pericardial effusion, and focal ascites in the pelvic cavity. Laboratory tests revealed an elevation of eosinophils (40%) and cardiac enzymes (creatinine kinase-MB 27.6 ng/mL, high-sensitive cardiac troponin T 1.21 ng/mL). The transthoracic echocardiogram showed left ventricular systolic dysfunction (ejection fraction 44%) and moderate pericardial effusion. She was presumptively diagnosed with hypereosinophilic perimyocarditis and admitted to the Intensive Care Unit for shock. The pericardial effusion increased during treatment; therefore, pericardiocentesis was performed. Analysis of the pericardial effusion showed eosinophilia (eosinophils 90%) and the serologic test for parasites was positive for Toxocara and Sparganum. A combination therapy of albendazole, praziquantel, and corticosteroid resolved the pericardial effusion and the peripheral blood eosinophil count normalized. She was discharged without any other complications. At Outpatient Clinic follow-ups and observations over the next 2 years there were no abnormal findings, including pericardial effusion or eosinophilia. CONCLUSIONS Toxocariasis rarely causes perimyocarditis with cardiogenic shock. Patients who present with pericardial effusion and eosinophilia need to be evaluated for parasitic infection.

Ten-year clinical outcomes of an intermediate coronary lesion; prognosis and predictors of major adverse cardiovascular events.

AIMS: The natural history of intermediate coronary lesions (30 to 70% angiographic stenosis) and the prognostic predictors in predicting very long-term clinical outcomes is unknown. METHODS: Patients (n = 82, mean 60 years old) with intermediate non-culprit coronary lesions (NCL, n = 86), evaluated by virtual histology-intravascular ultrasound (VH-IVUS), were followed for 10 years. Major adverse cardiovascular events (MACE; all-cause death, myocardial infarction, stroke, and revascularization) were collected over follow-up period and stratified by culprit lesion (CL)-related, NCL-related and indeterminate/unrelated to CL or NCL lesions. NCL-related MACE was further stratified into intermediate and minimal NCL-related events. RESULTS: Twenty two (25.6%) out of 86 intermediate NCL were associated with MACE in 20/82 (24.4%) study patients. Ten-year cumulative intermediate NCL-related MACE rate was twice (25.6% vs. 12.8%) compared to treated culprit lesion (CL)-related MACE. Ten-year cumulative revascularization rate of the intermediate NCL lesions was similar (17.4% vs. 15.1%) to those of CL, but higher than that of minimal (stenosed <30% at baseline) NCL (8.1%). Important intermediate NCL VH-IVUS predictor for MACE was area stenosis ≥50%, and for revascularization were percent diameter stenosis, plaque burden ≥70%, and fibrofatty area. CONCLUSIONS: Ten-year MACE rate of intermediate NCL was double that of CL and ten-year revascularization rate of intermediate NCL was similar or slightly higher than that of CL. VH-IVUS may play an important role in determining the very long-term clinical outcomes in patients with intermediate NCL. This study suggests that Intermediate NCL can be safely followed up in terms of revascularization risk.

In-stent restenosis-prone coronary plaque composition: A retrospective virtual histology-intravascular ultrasound study.

BACKGROUND: The mechanism of in-stent restenosis (ISR) is multifactorial, which includes biological, mechanical and technical factors. This study hypothesized that increased inflammatory reaction, which is known to be an important atherosclerotic process, at a culprit lesion may lead to higher restenosis rates. METHODS: The study population consisted of 241 patients who had undergone percutaneous coronary intervention with virtual histology-intravascular ultrasound (VH-IVUS) and a 9-month follow-up coronary angiography. Compared herein is the coronary plaque composition between patients with ISR and those without ISR. RESULTS: Patients with ISR (n = 27) were likely to be older (66.2 ± 9.5 years vs. 58.7 ± 11.7 years, p = 0.002) and have higher levels of high-sensitivity C-reactive protein (hs-CRP, 1.60 ± 3.59 mg/dL vs. 0.31 ± 0.76 mg/dL, p < 0.001) than those without ISR (n = 214). VH-IVUS examination showed that percent necrotic core volume (14.3 ± 8.7% vs. 19.5 ± 9.1%, p = 0.005) was higher in those without ISR than those with ISR. Multivariate analysis revealed that hs-CRP (odds ratio [OR] 3.334, 95% con-fidence interval [CI] 1.158-9.596, p = 0.026) and age (OR 3.557, 95% CI 1.242-10.192, p = 0.018) were associated with ISR. CONCLUSIONS: This study suggests that ISR is not associated with baseline coronary plaque composition but is associated with old age and increased expression of the inflammatory marker of hs-CRP. (Cardiol J 2018; 25, 1: 7-13).

Analysis of Plaque Composition in Coronary Chronic Total Occlusion Lesion Using Virtual Histology-Intravascular Ultrasound.

BACKGROUND AND OBJECTIVES: Success rates of chronic total occlusion (CTO) percutaneous coronary intervention (PCI) have recently been reported to range from 80% to 90%. A better understanding of the pathologic characteristics of the CTO lesion may helpful to improving CTO PCI success rates. We evaluated the CTO lesion in patients with stable angina (SA) by virtual histology-intravascular ultrasound (VH-IVUS). SUBJECTS AND METHODS: The study population consisted of 149 consecutive patients with SA underwent VH-IVUS examination. We analyzed demographic and VH-IVUS findings in 22 CTO patients (17 males; mean, 62.3 years old) compared with 127 non-CTO patients (82 males; mean, 61.3 years old). RESULTS: A significantly lower ejection fraction (57.6±13.0% vs. 65.4±8.8%, p=0.007) was detected in the CTO group compared with the non-CTO group. Reference vessel lumen area of the proximal and distal segment was significantly less in CTO group than in non-CTO group. The lesion length of the CTO group was significantly longer than those of the non-CTO group (24.4±9.6 mm vs. 17.2±7.4 mm, p<0.001). Total atheroma volume (224±159 mm(3) vs. 143±86 mm(3), p=0.006) and percent atheroma volume (63.2±9.6% vs. 55.8±8.5%, p=0.011) of the CTO group were also significantly greater than those of non-CTO group. However, the lesion length adjusted plaque composition of the CTO group was not significantly different compared with that of the non-CTO group. CONCLUSION: CTO lesions had a longer lesion length and greater plaque burden than the non-CTO lesion in patients with SA. However, lesion length adjusted plaque composition showed similar between the two groups. These results support that plaque characteristics of CTO lesions are similar to non-CTO lesions in patients with SA.