Ischemic and haemorrhagic stroke risk estimation using a machine-learning-based retinal image analysis.

Background: Stroke is the second leading cause of death worldwide, causing a considerable disease burden. Ischemic stroke is more frequent, but haemorrhagic stroke is responsible for more deaths. The clinical management and treatment are different, and it is advantageous to classify their risk as early as possible for disease prevention. Furthermore, retinal characteristics have been associated with stroke and can be used for stroke risk estimation. This study investigated machine learning approaches to retinal images for risk estimation and classification of ischemic and haemorrhagic stroke. Study design: A case-control study was conducted in the Shenzhen Traditional Chinese Medicine Hospital. According to the computerized tomography scan (CT) or magnetic resonance imaging (MRI) results, stroke patients were classified as either ischemic or hemorrhage stroke. In addition, a control group was formed using non-stroke patients from the hospital and healthy individuals from the community. Baseline demographic and medical information was collected from participants' hospital medical records. Retinal images of both eyes of each participant were taken within 2 weeks of admission. Classification models using a machine-learning approach were developed. A 10-fold cross-validation method was used to validate the results. Results: 711 patients were included, with 145 ischemic stroke patients, 86 haemorrhagic stroke patients, and 480 controls. Based on 10-fold cross-validation, the ischemic stroke risk estimation has a sensitivity and a specificity of 91.0% and 94.8%, respectively. The area under the ROC curve for ischemic stroke is 0.929 (95% CI 0.900 to 0.958). The haemorrhagic stroke risk estimation has a sensitivity and a specificity of 93.0% and 97.1%, respectively. The area under the ROC curve is 0.951 (95% CI 0.918 to 0.983). Conclusion: A fast and fully automatic method can be used for stroke subtype risk assessment and classification based on fundus photographs alone.

Risk Assessment of CHD Using Retinal Images with Machine Learning Approaches for People with Cardiometabolic Disorders.

BACKGROUND: Coronary heart disease (CHD) is the leading cause of death worldwide, constituting a growing health and social burden. People with cardiometabolic disorders are more likely to develop CHD. Retinal image analysis is a novel and noninvasive method to assess microvascular function. We aim to investigate whether retinal images can be used for CHD risk estimation for people with cardiometabolic disorders. METHODS: We have conducted a case-control study at Shenzhen Traditional Chinese Medicine Hospital, where 188 CHD patients and 128 controls with cardiometabolic disorders were recruited. Retinal images were captured within two weeks of admission. The retinal characteristics were estimated by the automatic retinal imaging analysis (ARIA) algorithm. Risk estimation models were established for CHD patients using machine learning approaches. We divided CHD patients into a diabetes group and a non-diabetes group for sensitivity analysis. A ten-fold cross-validation method was used to validate the results. RESULTS: The sensitivity and specificity were 81.3% and 88.3%, respectively, with an accuracy of 85.4% for CHD risk estimation. The risk estimation model for CHD with diabetes performed better than the model for CHD without diabetes. CONCLUSIONS: The ARIA algorithm can be used as a risk assessment tool for CHD for people with cardiometabolic disorders.

Estimation of stroke severity with National Institutes of Health Stroke Scale grading and retinal features: A cross-sectional study.

ABSTRACT: To estimate National Institutes of Health Stroke Scale (NIHSS) grading of stroke patients with retinal characteristics.A cross-sectional study was conducted in Shenzhen Traditional Chinese Medicine Hospital. Baseline information and retinal photos were collected within 2 weeks of admission. An NIHSS score was measured for each patient by trained doctors. Patients were classified into 0 to 4 score group and 5 to 42 score group for analysis. Three multivariate logistic models, with traditional clinical characteristics alone, with retinal characteristics alone, and with both, were built.For clinical characteristics, hypertension duration is statistically significantly associated with higher NIHSS score (P = .014). Elevated total homocysteine levels had an OR of 0.456 (P = .029). For retinal characteristics, the fractal dimension of the arteriolar network had an OR of 0.245 (P < .001) for the left eyes, and an OR of 0.417 (P = .009) for right eyes. The bifurcation coefficient of the arteriole of the left eyes had an OR of 2.931 (95% CI 1.573-5.46, P = .001), the nipping of the right eyes had an OR of 0.092 (P = .003) showed statistical significance in the model.The area under receiver-operating characteristic curve increased from 0.673, based on the model with clinical characteristics alone, to 0.896 for the model with retinal characteristics alone and increased to 0.931 for the model with both clinical and retinal characteristics combined.Retinal characteristics provided more information than clinical characteristics in estimating NIHSS grading and can provide us with an objective method for stroke severity estimation.

Association of technologically assisted integrated care with clinical outcomes in type 2 diabetes in Hong Kong using the prospective JADE Program: A retrospective cohort analysis.

BACKGROUND: Diabetes outcomes are influenced by host factors, settings, and care processes. We examined the association of data-driven integrated care assisted by information and communications technology (ICT) with clinical outcomes in type 2 diabetes in public and private healthcare settings. METHODS AND FINDINGS: The web-based Joint Asia Diabetes Evaluation (JADE) platform provides a protocol to guide data collection for issuing a personalized JADE report including risk categories (1-4, low-high), 5-year probabilities of cardiovascular-renal events, and trends and targets of 4 risk factors with tailored decision support. The JADE program is a prospective cohort study implemented in a naturalistic environment where patients underwent nurse-led structured evaluation (blood/urine/eye/feet) in public and private outpatient clinics and diabetes centers in Hong Kong. We retrospectively analyzed the data of 16,624 Han Chinese patients with type 2 diabetes who were enrolled in 2007-2015. In the public setting, the non-JADE group (n = 3,587) underwent structured evaluation for risk factors and complications only, while the JADE (n = 9,601) group received a JADE report with group empowerment by nurses. In a community-based, nurse-led, university-affiliated diabetes center (UDC), the JADE-Personalized (JADE-P) group (n = 3,436) received a JADE report, personalized empowerment, and annual telephone reminder for reevaluation and engagement. The primary composite outcome was time to the first occurrence of cardiovascular-renal diseases, all-site cancer, and/or death, based on hospitalization data censored on 30 June 2017. During 94,311 person-years of follow-up in 2007-2017, 7,779 primary events occurred. Compared with the JADE group (136.22 cases per 1,000 patient-years [95% CI 132.35-140.18]), the non-JADE group had higher (145.32 [95% CI 138.68-152.20]; P = 0.020) while the JADE-P group had lower event rates (70.94 [95% CI 67.12-74.91]; P < 0.001). The adjusted hazard ratios (aHRs) for the primary composite outcome were 1.22 (95% CI 1.15-1.30) and 0.70 (95% CI 0.66-0.75), respectively, independent of risk profiles, education levels, drug usage, self-care, and comorbidities at baseline. We reported consistent results in propensity-score-matched analyses and after accounting for loss to follow-up. Potential limitations include its nonrandomized design that precludes causal inference, residual confounding, and participation bias. CONCLUSIONS: ICT-assisted integrated care was associated with a reduction in clinical events, including death in type 2 diabetes in public and private healthcare settings.

Clinical risk factors associated with recurrence of ischemic stroke within two years: A cohort study.

To identify the clinical risk factors and investigate the efficacy of a classification model based on the identified factors for predicting 2-year recurrence after ischemic stroke.From June 2017 to January 2019, 358 patients with first-ever ischemic stroke were enrolled and followed up in Shenzhen Traditional Chinese Medicine Hospital. Demographic and clinical characteristics were recorded by trained medical staff. The outcome was defined as recurrence within 2 years. A multivariate logistic regression model with risk factors and their interaction effects was established and evaluated.The mean (standard deviation) age of the participants was 61.6 (12.1) years, and 101 (28.2%) of the 358 patients were female. The common comorbidities included hypertension (286 patients, 79.9%), diabetes (148 patients, 41.3%), and hyperlipidemia (149 patients, 41.6%). The 2-year recurrence rate was 30.7%. Of the 23 potential risk factors, 10 were significantly different between recurrent and non-recurrent subjects in the univariate analysis. A multivariate logistic regression model was developed based on 10 risk factors. The significant variables include diabetes mellitus, smoking status, peripheral artery disease, hypercoagulable state, depression, 24 h minimum systolic blood pressure, 24 h maximum diastolic blood pressure, age, family history of stroke, NIHSS score status. The area under the receiver operating characteristic curve (ROC) was 0.78 (95% confidence interval: 0.726-0.829) with a sensitivity of 0.61 and a specificity of 0.81, indicating a potential predictive ability.Ten risk factors were identified, and an effective classification model was built. This may aid clinicians in identifying high-risk patients who would benefit most from intensive follow-up and aggressive risk factor reduction.The clinical trial registration number: ChiCTR1800019647.

Electroacupuncture and splinting versus splinting alone to treat carpal tunnel syndrome: a randomized controlled trial.

BACKGROUND: The effectiveness of acupuncture for managing carpal tunnel syndrome is uncertain, particularly in patients already receiving conventional treatments (e.g., splinting). We aimed to assess the effects of electroacupuncture combined with splinting. METHODS: We conducted a randomized parallel-group assessor-blinded 2-arm trial on patients with clinically diagnosed primary carpal tunnel syndrome. The treatment group was offered 13 sessions of electroacupuncture over 17 weeks. The treatment and control groups both received continuous nocturnal wrist splinting. RESULTS: Of 181 participants randomly assigned to electroacupuncture combined with splinting (n = 90) or splinting alone (n = 91), 174 (96.1%) completed all follow-up. The electroacupuncture group showed greater improvements at 17 weeks in symptoms (primary outcome of Symptom Severity Scale score mean difference [MD] -0.20, 95% confidence interval [CI] -0.36 to -0.03), disability (Disability of Arm, Shoulder and Hand Questionnaire score MD -6.72, 95% CI -10.9 to -2.57), function (Functional Status Scale score MD -0.22, 95% CI -0.38 to -0.05), dexterity (time to complete blinded pick-up test MD -6.13 seconds, 95% CI -10.6 to -1.63) and maximal tip pinch strength (MD 1.17 lb, 95% CI 0.48 to 1.86). Differences between groups were small and clinically unimportant for reduction in pain (numerical rating scale -0.70, 95% CI -1.34 to -0.06), and not significant for sensation (first finger monofilament test -0.08 mm, 95% CI -0.22 to 0.06). INTERPRETATION: For patients with primary carpal tunnel syndrome, chronic mild to moderate symptoms and no indication for surgery, electroacupuncture produces small changes in symptoms, disability, function, dexterity and pinch strength when added to nocturnal splinting. TRIAL REGISTRATION: Chinese Clinical Trial Register no. ChiCTR-TRC-11001655 (www.chictr.org.cn/showprojen.aspx?proj=7890); subsequently deposited in the World Health Organization International Clinical Trials Registry Platform (apps.who.int/trialsearch/Trial2.aspx?TrialID=ChiCTR-TRC-11001655).

Randomized Phase II Study of the X-linked Inhibitor of Apoptosis (XIAP) Antisense AEG35156 in Combination With Sorafenib in Patients With Advanced Hepatocellular Carcinoma (HCC).

OBJECTIVES: This multicenter, randomized, open-label, phase II trial evaluated the efficacy and safety of AEG35156 in addition to sorafenib in patients with advanced hepatocellular carcinoma (HCC), as compared with sorafenib alone. METHODS: Eligible patients were randomly assigned in a 2:1 ratio to receive AEG35156 (300 mg weekly intravenous infusion) in combination with sorafenib (400 mg twice daily orally) or sorafenib alone. The primary endpoint was progression-free survival (PFS). Other endpoints include overall survival (OS), objective response rates (ORR), and safety profile. RESULTS: A total of 51 patients were enrolled; of them, 48 were evaluable. At a median follow-up of 16.2 months, the median PFS and OS were 4.0 months (95% CI, 1.2-4.1) and 6.5 months (95% CI, 3.9-11.5) for combination arm, and 2.6 (95% CI, 1.2-5.4) and 5.4 months (95% CI, 4.3-11.2) for sorafenib arm. Patients who had the study treatment interrupted or had dose modifications according to protocol did significantly better, in terms of PFS and OS, than those who had no dose reduction in combination arm and those in sorafenib arm. The ORR based on Choi and RECIST criteria were 16.1% and 9.7% in combination arm, respectively. The ORR was 0 in control arm. One drug-related serious adverse event of hypersensitivity occurred in the combination arm, whereas 2 gastrointestinal serious adverse events in the sorafenib arm. CONCLUSION: AEG35156 in combination with sorafenib showed additional activity in terms of ORR and was well tolerated. The benefit on PFS is moderate but more apparent in the dose-reduced subgroups.

Health-related quality of life after aneurysmal subarachnoid hemorrhage: profile and clinical factors.

BACKGROUND: Health-related quality of life has recently been suggested as a supplement to the traditional neurological outcome measures from the patient's perspective according to the World Health Organization model and may capture the effects of other factors such as posttraumatic stress disorder and neuroendocrine dysfunction. OBJECTIVE: To explore the profile and clinical factors of quality of life after aneurysmal subarachnoid hemorrhage using the data we obtained from the recently completed Intravenous Magnesium Sulphate After Aneurysmal Subarachnoid Hemorrhage (IMASH) trial. METHODS: This study was registered at www.strokecenter.org/trials and www.ClinicalTrials.gov (NCT00124150). Data from a patient cohort obtained with the Short Form-36 questionnaire completed at 6 months were used for analysis. RESULTS: Patients with aneurysmal subarachnoid hemorrhage demonstrated a decrease in quality of life according to the Short Form-36 at 6 months. The physical and mental health scores correlated with the Extended Glasgow Outcome Scale and had the potential to avoid the ceiling effect. Multiple regression analyses showed that the physical component scores were related to age, World Federation of Neurological Surgeons grade, and chronic hydrocephalus and that the mental component scores were not related to the traditional prognostic factors. CONCLUSION: Subarachnoid hemorrhage caused a decrease in quality of life. Chronic hydrocephalus is related to a decrease in physical health quality of life.

Curcumin effects on blood lipid profile in a 6-month human study.

Studies in animals and a short-term human study have suggested that curcumin, a polyphenolic compound concentrated in the curry spice turmeric, decreases serum cholesterol concentration. However, no controlled human trials have examined the effect of curcumin on cholesterol. This study investigated the effects of consuming curcumin on the serum lipid profile in men and women. Elderly subjects (n=36) consumed 4 g/d curcumin, 1g/d curcumin, or placebo in a 6-month, randomized, double-blind trial. Plasma curcumin and its metabolites were measured at 1 month, and the serum lipid profile was measured at baseline, 1 month, and 6 months. The plasma curcumin concentration reached a mean of 490 nmol/L. The curcumin concentration was greater after capsule than powder administration. Consumption of either dose of curcumin did not significantly affect triacylglycerols, or total, LDL, and HDL cholesterol over 1 month or 6 months. However, the concentrations of plasma curcumin and serum cholesterol were positively and significantly correlated. Curcumin consumption does not appear to have a significant effect on the serum lipid profile, unless the absorbed concentration of curcumin is considered, in which case curcumin may modestly increase cholesterol.

Irofulven as first line therapy in recurrent or metastatic gastric cancer: a phase II multicenter study by the Cancer Therapeutics Research Group (CTRG).

BACKGROUND: The purpose of this study was to evaluate the tolerability and efficacy of irofulven, a DNA interacting acylfulvene analog, as first line therapy for patients with recurrent or metastatic gastric cancer. PATIENTS AND METHODS: Twenty-three patients with recurrent or metastatic gastric cancer received irofulven at a dose of 0.45 mg/kg administered intravenously over 30-min infusion (up to a maximum of 50 mg), on days 1 and 8, every 3 weeks. RESULTS: The median number of cycles delivered per patient was 2 (range 1-6). Two patients (9%) had >or= 1-week delay in administration of subsequent cycle of chemotherapy. For the day 8 chemotherapy, dose reductions were required in seven patients (30%); dose omitting occurred in five patients (22%). Grade 3/4 anemia and neutropenia occurred in 22 and 17% of patients, respectively. There was no grade 4 thrombocytopenia and no neutropenic fever was observed. Of the 20 evaluable patients, there were no responses observed, 3 patients had stable disease after 2 cycles of treatment which was not confirmed by a further assessment. Median overall survival was 6.05 months (95% CI 4.55-9.39). CONCLUSIONS: Irofulven was tolerated at the dose of 0.45 mg/kg on days 1 and 8, every 3 weeks but showed no evidence of antitumor activity in patients with advanced gastric cancer.