Predicting Chronic Myocardial Ischemia Using CCTA-Based Radiomics Machine Learning Nomogram.

BACKGROUND: Coronary computed tomography angiography (CCTA) is a well-established non-invasive diagnostic test for the assessment of coronary artery diseases (CAD). CCTA not only provides information on luminal stenosis but also permits non-invasive assessment and quantitative measurement of stenosis based on radiomics. PURPOSE: This study is aimed to develop and validate a CT-based radiomics machine learning for predicting chronic myocardial ischemia (MIS). METHODS: CCTA and SPECT-myocardial perfusion imaging (MPI) of 154 patients with CAD were retrospectively analyzed and 94 patients were diagnosed with MIS. The patients were randomly divided into two sets: training (n = 107) and test (n = 47). Features were extracted for each CCTA cross-sectional image to identify myocardial segments. Multivariate logistic regression was used to establish a radiomics signature after feature dimension reduction. Finally, the radiomics nomogram was built based on a predictive model of MIS which in turn was constructed by machine learning combined with the clinically related factors. We then validated the model using data from 49 CAD patients and included 18 MIS patients from another medical center. The receiver operating characteristic curve evaluated the diagnostic accuracy of the nomogram based on the training set and was validated by the test and validation set. Decision curve analysis (DCA) was used to validate the clinical practicability of the nomogram. RESULTS: The accuracy of the nomogram for the prediction of MIS in the training, test and validation sets was 0.839, 0.832, and 0.816, respectively. The diagnosis accuracy of the nomogram, signature, and vascular stenosis were 0.824, 0.736 and 0.708, respectively. A significant difference in the number of patients with MIS between the high and low-risk groups was identified based on the nomogram (P < .05). The DCA curve demonstrated that the nomogram was clinically feasible. CONCLUSION: The radiomics nomogram constructed based on the image of CCTA act as a non-invasive tool for predicting MIS that helps to identify high-risk patients with coronary artery disease.

Prediction of the progression from mild cognitive impairment to Alzheimer's disease using a radiomics-integrated model.

OBJECTIVE: This study aimed to build and validate a radiomics-integrated model with whole-brain magnetic resonance imaging (MRI) to predict the progression of mild cognitive impairment (MCI) to Alzheimer's disease (AD). METHODS: 357 patients with MCI were selected from the ADNI database, which is an open-source database for AD with multicentre cooperation, of which 154 progressed to AD during the 48-month follow-up period. Subjects were divided into a training and test group. For each patient, the baseline T1WI MR images were automatically segmented into white matter, gray matter and cerebrospinal fluid (CSF), and radiomics features were extracted from each tissue. Based on the data from the training group, a radiomics signature was built using logistic regression after dimensionality reduction. The radiomics signatures, in combination with the apolipoprotein E4 (APOE4) and baseline neuropsychological scales, were used to build an integrated model using machine learning. The receiver operating characteristics (ROC) curve and data of the test group were used to evaluate the diagnostic accuracy and reliability of the model, respectively. In addition, the clinical prognostic efficacy of the model was evaluated based on the time of progression from MCI to AD. RESULTS: Stepwise logistic regression analysis showed that the APOE4, clinical dementia rating, AD assessment scale, and radiomics signature were independent predictors of MCI progression to AD. The integrated model was constructed based on independent predictors using machine learning. The ROC curve showed that the accuracy of the model in the training and the test sets was 0.814 and 0.807, with a specificity of 0.671 and 0.738, and a sensitivity of 0.822 and 0.745, respectively. In addition, the model had the most significant diagnostic efficacy in predicting MCI progression to AD within 12 months, with an AUC of 0.814, sensitivity of 0.726, and specificity of 0.798. CONCLUSION: The integrated model based on whole-brain radiomics can accurately identify and predict the high-risk population of MCI patients who may progress to AD. Radiomics biomarkers are practical in the precursory stage of such disease.

[Evaluation of therapeutic effects of the ultramicro needle knife combined with cervical spine fine adjusting on youth cervical curvature abnormality case].

OBJECTIVE: To study the therapeutic effects of the ultramicro needle-knife combine with cervical spine fine adjusting on youth cervical curvature abnormality case. METHODS: From November 2016 to October 2018, 88 young patients with abnormal curvature of cervical spine were treated. Due to loss of follow up, 86 cases were actually completely including 37 males and 49 females, ranging in age from 20 to 40 years old, with an average of (30.55±5.21) years old, and the course of disease ranged from 1 to 42 months, with a mean of (14.21±7.38) months. All the patients were divided into two groups:treatment group (44 cases) and control group (42 cases). The patients in the treatment group were treated with ultramicro needle-knife and cervical spine fine adjusting, and the patients in the control group were treated with conventional acupuncture and manipulation. The treatments were done 1 time per week in the treatment group while 3 times per week in control group every week, with a duration of 3 weeks for both groups. Before treatment, 3 weeks after treatment, and at the end of 1 month follow-up, the score of neck pain questionnaire(NPQ), range of the motion(ROM) in the cervical region and the D values of cervical physiological curvature were recorded. The efficacy at the end of treatment and in the follow up was evaluated. During the treatment, the patients were also required to correct the bad posture in daily life, to sleep in a low pillow position, and put a moderately columnar pillow behind the neck for 0.5 hours every morning and evening. RESULTS: Two patients in the control group were dropped out after 3 weeks treatment. No adverse reactions were found in the 2 groups during the treatment period. Compared with those before treatment, all scores at all the observation time points were significantly improved between two groups after treatment(all P<0.05). The NPQ scores of cervical symptoms were different significantly between two groups(all P<0.05). The changing range of the the NPQ score of cervical symptoms and cervical spine alignment curve of the treatment group were better than those of the control group (P<0.05).There was statistical difference in NPQ scores between different time points, in the other words, there was time effect(F=203.63, P=0.000). There was interaction between time factor and group factor(F=4.964, P=0.012). There was no statistical difference in the changing range of the ROM score between two groups (all P>0.05). There was statistical difference in ROM scores between different time points, there was time effect (F=240.32), P=0.000). There was no interaction between time factor and group factor (F=0.311, P=0.734). The effective rate of the treatment group and control group were 90.91%(40 / 44) and 80.95%(34 / 42) respectively, the treatment group was more effective than the control group (P<0.05). During the follow-up period, the effective rate of the treatment group and the control group were 84.09%(37 / 44) and 76.19%(32 / 42) respectively. Obviously, the difference of total effective rate between two groups had no statistical signification(P>0.05) in the follow-up duration. CONCLUSION: The method of needle knife combined with cervical spine fine adjusting has a better therapeutic efficiency than conventional acupuncturecombined with manipulation in treating youth cervical curvature abnormality patients. Because this novel method can recover the cervical curvature, relieve the neck pain, and improve cervical mobility.

Radiomics nomogram based on MRI for predicting white matter hyperintensity progression in elderly adults.

BACKGROUND: White matter hyperintensity (WMH) is widely observed in aging brain and is associated with various diseases. A pragmatic and handy method in the clinic to assess and follow up white matter disease is strongly in need. PURPOSE: To develop and validate a radiomics nomogram for the prediction of WMH progression. STUDY TYPE: Retrospective. POPULATION: Brain images of 193 WMH patients from the Picture Archiving and Communication Systems (PACS) database in the A Medical Center (Zhejiang Provincial People's Hospital). MRI data of 127 WMH patients from the PACS database in the B Medical Center (Zhejiang Lishui People's Hospital) were included for external validation. All of the patients were at least 60 years old. FIELD STRENGTH/SEQUENCE: T1 -fluid attenuated inversion recovery images were acquired using a 3T scanner. ASSESSMENT: WMH was evaluated utilizing the Fazekas scale based on MRI. WMH progression was assessed with a follow-up MRI using a visual rating scale. Three neuroradiologists, who were blinded to the clinical data, assessed the images independently. Moreover, interobserver and intraobserver reproducibility were performed for the regions of interest for segmentation and feature extraction. STATISTICAL TESTS: A receiver operating characteristic (ROC) curve, the area under the curve (AUC) of the ROC was calculated, along with sensitivity and specificity. Also, a Hosmer-Lemeshow test was performed. RESULTS: The AUC of radiomics signature in the primary, internal validation cohort, external validation cohort were 0.886, 0.816, and 0.787, respectively; the specificity were 71.79%, 72.22%, and 81%, respectively; the sensitivity were 92.68%, 87.94% and 78.3%, respectively. The radiomics nomogram in the primary cohort (AUC = 0.899) and the internal validation cohort (AUC = 0.84). The Hosmer-Lemeshow test showed no significant difference between the primary cohort and the internal validation cohort (P > 0.05). The AUC of the radiomics nomogram, radiomics signature, and hyperlipidemia in all patients from the primary and internal validation cohort was 0.878, 0.848, and 0.626, respectively. DATA CONCLUSION: This multicenter study demonstrated the use of a radiomics nomogram in predicting the progression of WMH with elderly adults (an age of at least 60 years) based on conventional MRI. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:535-546.

Association of dysglycemia and all-cause mortality across the spectrum of coronary artery disease.

OBJECTIVE: To assess the association between fasting plasma glucose (FPG) and all-cause mortality across the spectrum of coronary artery disease (CAD). PATIENTS AND METHODS: The study included 18,999 patients during a study period of April 1, 2004, through October 31, 2010. The primary end points were in-hospital and follow-up all-cause mortality. According to the quartiles of FPG levels, patients were categorized into 4 groups: quartile 1, less than 5.1 mmol/L; quartile 2, 5.1 to less than 5.9 mmol/L; quartile 3, 5.9 to less than 7.5 mmol/L; and quartile 4, 7.5 mmol/L or greater. The conversion factor for units of plasma glucose is 1.00 mmol/L equals 18 mg/dL. Presented as mg/dL, the 4 quartile ranges of plasma glucose concentrations used in our data analysis are ≤90.0 mg/dL, 90.1-106.0 mg/dL, 106.1 mg/dL-135.0 mg/dL and ≥135.1 mg/dL. Quartile 1 was recognized as the lower glycemic group, quartiles 2 and 3 as the normoglycemic groups, and quartile 4 as the higher glycemic group. RESULTS: In patients with acute myocardial infarction, all-cause mortality for the dysglycemic groups was higher than for the normoglycemic groups: in-hospital mortality for quartiles 1, 2, 3, and 4 was 1.0%, 0.9%, 0.2%, and 1.5%, respectively (P=.001); follow-up mortality for quartiles 1, 2, 3, and 4 was 1.7%, 0.9%, 0.3%, and 1.8%, respectively (P<.001). In patients with stable CAD, no significant differences in mortality were found among groups. However, in patients with unstable angina pectoris, the normoglycemic groups had lower follow-up mortality and roughly equal in-hospital mortality compared with the dysglycemic groups. After adjusting for confounding factors, this observation persisted. CONCLUSION: The association between lower FPG level and mortality differed across the spectrum of CAD. In patients with acute myocardial infarction, there was a U-shaped relationship. In patients with stable CAD or unstable angina pectoris, mildly to moderately decreasing FPG level was associated with neither higher nor lower all-cause mortality.

[2-(2-Chloro-phen-yl)-2-hy-droxy-eth-yl](isoprop-yl)ammonium 4-hy-droxy-benzoate.

The title molecular salt, C(11)H(17)ClNO(+)·C(7)H(5)O(3) (-), was obtained by the reaction of racemic clorprenaline and 4-hy-droxy-benzoic acid. In the crystal, the components are connected by O-H⋯O and N-H⋯O hydrogen bonds, resulting in a two-dimensional hydrogen-bonded network.

[The effect of different dosage of aspirin on inflammatory biomarkers and prognosis in acute coronary syndrome.].

OBJECTIVE: To observe and assess the effect of different dosages of aspirin on inflammatory biomarkers, hemorheology (platelet aggregation rate) and clinical prognosis in patients with acute coronary syndrome (ACS). METHODS: ACS patients were randomly assigned to receive different dosages of aspirin treatment orally. Patients in group A, B and C took 100 mg, 500 mg and 1000 mg of aspirin per day respectively. They were treated and followed-up for 1 year. High-sensitivity C-reactive protein (hsCRP), IL-6, tumor necrosis TNFalpha and platelet aggregation rate were examined and major adverse cardiac events (MACE) were recorded. RESULTS: A total of 312 patients with ACS were enrolled in the study. The baseline characteristics of the three groups were not different with respect to age, gender, cardiovascular risk profile, level of inflammatory biomarkers and concomitant treatment before and after randomization. The levels of baseline serum hsCRP, IL-6 and TNFalpha were higher in subjects of the study as compared with normal reference value (P < 0.05, < 0.05, < 0.01) and they decreased significantly after therapy with 3 different doses of aspirin (detected at 30 days, 6 months and 12 months, P < 0.001), but there were no significant differences among the three groups (P > 0.05). Rehospitalization, MACE and the change of platelet aggregation ratio were not significantly different among the three groups. The incidence of gastrointestinal complaints was significantly higher in groups B and C than in group A (P < 0.05). CONCLUSIONS: The levels of serum inflammatory biomarker increase in patients with ACS. Aspirin therapy may decrease the level of inflammatory markers significantly, but increasing the dosage of aspirin from 100 mg to 1000 mg daily does not decrease the level of inflammatory markers and the clinical MACEs further. However, the incidence of gastrointestinal complaints increase significantly with the increase of aspirin dosage.

[Effects of transcatheter closure of perimembranous ventricular septal defects: intermediate and long-term follow-up of 68 cases].

OBJECTIVE: To evaluate the curative effects of transcatheter closure on perimembranous ventricular septal defects (PMVSDs) using unbalanced Amplatzer asymmetric ventricular septal defect occluder (AAVSDO). METHODS: The data of 68 patients of PMVSDs with a diameter of 6.7 mm (3 to 12 mm) and the diameter of ventricular septal rim below the aortic valve of 2.7 +/- 1.1 mm (1-5 mm), 27 males and 41 females, aged 15.6 +/- 11.5 (1.5-44), weighing 42.8 +/- 15.2 kg (10-72 kg), treated with AAVSDO, the diameter of which was 1-2 mm larger than the largest diameter of the defects determined by angled left ventriculography, from September 2002 to January 2005 were prospectively analyzed. The patients were followed up for 221 +/- 130 days (90 to 750 days). RESULTS: Seventy-one procedures were performed. The device was implanted successfully in 65 of the 68 patients (95.6%). The selected device diameter was 8.4 mm (4 to 14 mm). Device was lost in one patient during the procedure, which was successfully managed by recapturing the device with a snare device and redeploying it. During the procedure, transient complete left bundle branch block and right bundle branch block occurred in 6 and 5 patients respectively. On follow-up evaluation, transient junctional rhythm occurred in one patient, and accelerated ventricular rhythm in 1. After deployment of the device, the immediate complete closure rate was 43% (28/68), increased to 81.5% (53/68) on the day next to the procedure, and reached 100% 6 months after. One patient adopted surgical reparation because hemolysis occurred after the device implanted. The hospitalization time was 4.5 +/- 3.6 days (2-8 days). The X-ray exposure time was 14.8 +/- 10.7 min (6-48 min). The procedure time 72.6 +/- 38.7 min (35-186 min). One patient was diagnosed as with deep vein thrombosis because of right leg swelling at the seventh day after the procedure. The symptoms disappeared after anticoagulation treatment with low molecule weight heparin. During the scheduled long-term follow-up all patients were doing well. No episode of endocarditis, procedure-related death, or wire disruption was recorded. CONCLUSION: The initial and long-term follow-up results of transcatheter closure of PMVSDs are promising with high success and occlusion rates. Transcatheter closure of PMVSDs using AAVSDO appears to be the first line choice for suitable patients with such defects.

[The characteristics during exercise test in long QT syndrome patients and the effects of left cardiac sympathetic denervation].

OBJECTIVE: To explore the mechanism of the left cardiac sympathetic denervation (LCSD) surgery to reduce the incidence of cardiac events for long QT syndrome (LQTS) patients. METHODS: 12 LQTS patients were selected to do exercise test (ET) to mimic sympathetic activation. The dynamic alterations on ECG during exercise and recovery phases (Rec) were observed and the exercise test characteristics for LQTS patients before and after surgery were summarized and compared. RESULTS: The QTc at resting was shortened from 0.54 s +/- 0.04 s to 0.50 s +/- 0.04 s, P = 0.026, while the maximum heart rate during exercise decreased from 141 beat/min +/- 18 beat/min to 124 beat/min +/- 14 beat/min, P = 0.003. QTc was shortened during exercise, however, it was prolonged during the early recovery phase (before ET 0.54 s +/- 0.02 s, ET 10 min 0.46 s +/- 0.02 s, Rec 4 min 0.55 s +/- 0.03 s); LCSD could reduce such abrupt alteration of QTc during early recovery phase (after surgery: before ET 0.53 s +/- 0.03 s, ET 10 min 0.48 s +/- 0.03 s, Rec 4 min 0.53 s +/- 0.05 s). QT/RR interval slope, representing the adaptation response of QT interval to heart rate, became steeper after exercise (from 0.61 +/- 0.06 to 0.71 +/- 0.07 after exercise, P < 0.01). LCSD made the slopes become less steep both before exercise (from 0.61 +/- 0.06 before surgery to 0.55 +/- 0.07 after surgery, P = 0.013) and after exercise (from 0.71 +/- 0.07 before surgery to 0.66 +/- 0.06 after surgery, P = 0.018). Notched T wave alterations occurred in 7 patients at the end of exercise and/or during early recovery phase before surgery, and LCSD diminished such alteration in 4 patients. CONCLUSION: The slope between QT and RR both the pre-exercise and post-exercise slopes, interval becomes less steep after LCSD, which suggests that exaggerated delay in repolarization with decreasing heart rate for LQTS patients is improved by LCSD. This may be one of the mechanisms of LCSD efficacy for treating LQTS patients. Exercise test is one of tools to evaluate the effect of LCSD on LQTS patients.

[The predictive value of risk scoring system in myocardial infarction in long-term prognosis of patients referred to direct percutaneous coronary intervention].

OBJECTIVE: To evaluate the predicting values of thrombolysis in myocardial infarction (TIMI) risk scoring system for long-term prognosis in patients with ST segment elevation myocardial infarction (STEMI) referred for primary percutaneous coronary intervention (PCI). METHODS: Eight clinical variables and their relative value of score derived from TIMI risk scoring system were used to determine individual's risk score. The patients with STEMI were evaluated during the period of in-hospital and followed-up at a mean of (23.9 +/- 3.8) months for major adverse cardiovascular events (MACE), including nonfatal heart failure, nonfatal re-infarction, target vessel revascularization and cardiac mortality and the predicting value of TIMI risk scores at hospital admission for total MACE were analyzed. RESULTS: Out of 373 patients with STEMI referred for primary PCI, 89 patients were presented with MACE during the period of follow-up (average incidence: 23.9%). The presentation of the total MACE increased progressively with the rising TIMI risk scores (P < 0.05 for trends in increase of MACE). The incidence of total MACE in patients with a score > or = 8 was 9 times those with a score 0. The incidence of cardiac mortality was higher (25% vs 0, P < 0.01) and the combined incidence of cardiac mortality and nonfatal re-infarction also increased significantly (36.7% vs 2.6%, P < 0.01) in patients with a score > or = 6 than in those with a score < 6 respectively. The risk of adverse cardiovascular events increased with rising in TIMI risk scores in patients with either high or normal TnI level. CONCLUSIONS: The higher the TIMI risk score at admission, the worse the prognosis. This TIMI risk scoring system is likely to be a simple and practical tool at the bedside in quantitative risk evaluation and long-term prognosis prediction in patients with STEMI referred for primary PCI.