Con&Net: A Cross-Network Anchor Link Discovery Method Based on Embedding Representation

Cross-network anchor link discovery is an important research problem and has many applications in heterogeneous social network. Existing schemes of cross-network anchor link discovery can provide reasonable link discovery results, but the quality of these results depends on the features of the platform. Therefore, there is no theoretical guarantee to the stability. This article employs user embedding feature to model the relationship between cross-platform accounts, that is, the more similar the user embedding features are, the more similar the two accounts are. The similarity of user embedding features is determined by the distance of the user features in the latent space. Based on the user embedding features, this article proposes an embedding representation-based method Con&Net(Content and Network) to solve cross-network anchor link discovery problem. Con&Net combines the user’s profile features, user-generated content (UGC) features, and user’s social structure features to measure the similarity of two user accounts. Con&Net first trains the user’s profile features to get profile embedding. Then it trains the network structure of the nodes to get structure embedding. It connects the two features through vector concatenating, and calculates the cosine similarity of the vector based on the embedding vector. This cosine similarity is used to measure the similarity of the user accounts. Finally, Con&Net predicts the link based on similarity for account pairs across the two networks. A large number of experiments in Sina Weibo and Twitter networks show that the proposed method Con&Net is better than state-of-the-art method. The area under the curve (AUC) value of the receiver operating characteristic (ROC) curve predicted by the anchor link is 11% higher than the baseline method, and Precision@30 is 25% higher than the baseline method.

A Minimalist Method Toward Severity Assessment and Progression Monitoring of Obstructive Sleep Apnea on the Edge

Artificial Intelligence-enabled applications on edge devices have the potential to revolutionize disease detection and monitoring in future smart health (sHealth) systems. In this study, we investigated a minimalist approach for the severity classification, severity estimation, and progression monitoring of obstructive sleep apnea (OSA) in a home environment using wearables. We used the recursive feature elimination technique to select the best feature set of 70 features from a total of 200 features extracted from polysomnogram. We used a multi-layer perceptron model to investigate the performance of OSA severity classification with all the ranked features to a subset of features available from either Electroencephalography or Heart Rate Variability (HRV) and time duration of SpO2 level. The results indicate that using only computationally inexpensive features from HRV and SpO2, an area under the curve of 0.91 and an accuracy of 83.97% can be achieved for the severity classification of OSA. For estimation of the apnea-hypopnea index, the accuracy of RMSE = 4.6 and R-squared value = 0.71 have been achieved in the test set using only ranked HRV and SpO2 features. The Wilcoxon-signed-rank test indicates a significant change (p < 0.05) in the selected feature values for a progression in the disease over 2.5 years. The method has the potential for integration with edge computing for deployment on everyday wearables. This may facilitate the preliminary severity estimation, monitoring, and management of OSA patients and reduce associated healthcare costs as well as the prevalence of untreated OSA.

Temporal Patterns of Glucagon and Its Relationships with Glucose and Insulin following Ingestion of Different Classes of Macronutrients

Background: glucagon secretion and inhibition should be mainly determined by glucose and insulin levels, but the relative relevance of each factor is not clarified, especially following ingestion of different macronutrients. We aimed to investigate the associations between plasma glucagon, glucose, and insulin after ingestion of single macronutrients or mixed-meal. Methods: thirty-six participants underwent four metabolic tests, based on administration of glucose, protein, fat, or mixed-meal. Glucagon, glucose, insulin, and C-peptide were measured at fasting and for 300 min following food ingestion. We analyzed relationships between time samples of glucagon, glucose, and insulin in each individual, as well as between suprabasal area-under-the-curve of the same variables (ΔAUCGLUCA, ΔAUCGLU, ΔAUCINS) over the whole participants’ cohort. Results: in individuals, time samples of glucagon and glucose were related in only 26 cases (18 direct, 8 inverse relationships), whereas relationship with insulin was more frequent (60 and 5, p < 0.0001). The frequency of significant relationships was different among tests, especially for direct relationships (p ≤ 0.006). In the whole cohort, ΔAUCGLUCA was weakly related to ΔAUCGLU (p ≤ 0.02), but not to ΔAUCINS, though basal insulin secretion emerged as possible covariate. Conclusions: glucose and insulin are not general and exclusive determinants of glucagon secretion/inhibition after mixed-meal or macronutrients ingestion.

Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer

Background Liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. Nevertheless, there is still no effective model to predict the risk of LM in T1 CRC patients. Hence, we aim to construct an accurate predictive model and an easy-to-use tool clinically. Methods We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER, training dataset) and Xijing hospital (testing dataset). Artificial intelligence (AI) and machine learning (ML) methods were adopted to establish the predictive model. Results A total of 16,785 and 326 T1 CRC patients from SEER database and Xijing hospital were incorporated respectively into the study. Every single ML model demonstrated great predictive capability, with an area under the curve (AUC) close to 0.95 and a stacking bagging model displaying the best performance (AUC = 0.9631). Expectedly, the stacking model exhibited a favorable discriminative ability and precisely screened out all eight LM cases from 326 T1 patients in the outer validation cohort. In the subgroup analysis, the stacking model also demonstrated a splendid predictive ability for patients with tumor size ranging from one to50mm (AUC = 0.956). Conclusion We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in the external dataset. Ultimately, we designed a novel and easy-to-use decision tree, which only incorporated four fundamental parameters and could be successfully applied in clinical practice.

The Serum Concentration of Vancomycin as a Diagnostic Predictor of Nephrotoxic Acute Kidney Injury in Critically Ill Patients

The impact of serum concentrations of vancomycin is a controversial topic. Results: 182 critically ill patients were evaluated using vancomycin and 63 patients were included in the study. AKI occurred in 44.4% of patients on the sixth day of vancomycin use. Vancomycin higher than 17.53 mg/L between the second and the fourth days of use was a predictor of AKI, preceding AKI diagnosis for at least two days, with an area under the curve of 0.806 (IC 95% 0.624–0.987, p = 0.011). Altogether, 46.03% of patients died, and in the Cox analysis, the associated factors were age, estimated GFR, CPR, and vancomycin between the second and the fourth days. Discussion: The current 2020 guidelines recommend using Bayesian-derived AUC monitoring rather than trough concentrations. However, due to the higher number of laboratory analyses and the need for an application to calculate the AUC, many centers still use therapeutic trough levels between 15 and 20 mg/L. Conclusion: The results of this study suggest that a narrower range of serum concentration of vancomycin was a predictor of AKI in critically ill septic patients, preceding the diagnosis of AKI by at least 48 h, and it can be a useful monitoring tool when AUC cannot be used.

AK098656: a new biomarker of coronary stenosis severity in hypertensive and coronary heart disease patients

Background AK098656 may be an adverse factor for coronary heart disease (CHD), especially in patients with hypertension. This study aimed to analyze the effect of AK098656 on CHD and CHD with various complications. Methods A total of 117 CHD patients and 27 healthy control subjects were enrolled in the study. Plasma AK098656 expression was determined using the quantitative real-time polymerase chain reaction. Student’s t-test was used to compare AK098656 expression levels in different groups. Receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to quantify the discrimination ability between CHD patients and health controls and between CHD and CHD + complications patients. The relationship between AK098656 and coronary stenosis was analyzed using Spearman’s correlation. Results AK098656 expression was remarkably higher in CHD patients than in healthy controls (P = 0.03). The ROC curve revealed an effective predictive AK098656 expression value for CHD risk, with an AUC of 0.656 (95% CI 0.501–0.809). Moreover, AK098656 expression was increased in CHD + complications patients compared to CHD patients alone (P = 0.005), especially in patients with hypertension (CHD + hHTN, P = 0.030). The ROC curve revealed a predictive AK098656 prognostic value for discriminating between CHD and CHD + hHTN patients, with an AUC of 0.666 (95% CI 0.528–0.805). There was no significant difference in AK098656 expression in CHD patients with diabetes mellitus compared to CHD patients alone. In addition, AK098656 expression in CHD patients was positively correlated with stenosis severity (R = 0.261, P = 0.006). Conclusion AK098656 expression was significantly increased in patients with CHD, especially those with hypertension, and its expression level was positively correlated with the degree of coronary stenosis. This implied that AK098656 may be a risk factor for CHD and can potentially be applied in clinical diagnosis or provide a novel target for treatment.

Cerebrospinal fluid neurofilament light chain differentiates behavioural variant frontotemporal dementia progressors from phenocopy non-progressors

Background: Distinguishing behavioural variant frontotemporal dementia (bvFTD) from non-neurodegenerative non-progressor, phenocopy mimics of frontal lobe dysfunction, can be one of the most challenging clinical dilemmas. A biomarker of neuronal injury, neurofilament light chain (NfL), could reduce misdiagnosis and delay. Methods: Cerebrospinal fluid (CSF) NfL, amyloid beta 1-42 (AB42), total and phosphorylated tau (T-tau, P-tau) levels were examined in patients with an initial diagnosis of bvFTD. Based on follow up information, patients were categorised as Progressors. Non-Progressors were subtyped in to Phenocopy Non-Progressors (non-neurological/neurodegenerative final diagnosis), and Static Non-Progressors (static deficits, not fully explained by non-neurological/neurodegenerative causes). Results: Forty-three patients were included: 20 Progressors, 23 Non-Progressors (15 Phenocopy, 8 Static), 20 controls. NfL concentrations were lower in Non-Progressors (Non-Progressors Mean, M=554pg/mL, 95%CI:[461, 675], Phenocopy Non-Progressors M=459pg/mL, 95%CI:[385, 539], Static Non-Progressors M=730pg/mL, 95%CI:[516, 940]), compared to bvFTD Progressors (M=2397pg/mL, 95%CI:[1607, 3332]). NfL distinguished Progressors from Non-Progressors with the highest accuracy (area under the curve 0.92, 90%/87% sensitivity/specificity, 86%/91% positive/negative predictive value, 88% accuracy). Static Non-Progressors tended to have higher T-tau and P-tau levels compared to Phenocopy Non-Progressors. Conclusion: This study demonstrated strong diagnostic utility of CSF NfL to distinguish bvFTD from phenocopy non-progressor variants, at baseline, with high accuracy, in a real-world clinical setting. This has important clinical implications, to improve outcomes for patients and clinicians facing this challenging clinical dilemma, as well as for healthcare services, and clinical trials. Further research is required to investigate heterogeneity within the non-progressor group and potential diagnostic algorithms, and prospective studies are underway assessing plasma NfL

Development of a radiomics model to diagnose pheochromocytoma preoperatively: a multicenter study with prospective validation

Background Preoperative diagnosis of pheochromocytoma (PHEO) accurately impacts preoperative preparation and surgical outcome in PHEO patients. Highly reliable model to diagnose PHEO is lacking. We aimed to develop a magnetic resonance imaging (MRI)-based radiomic-clinical model to distinguish PHEO from adrenal lesions. Methods In total, 305 patients with 309 adrenal lesions were included and divided into different sets. The least absolute shrinkage and selection operator (LASSO) regression model was used for data dimension reduction, feature selection, and radiomics signature building. In addition, a nomogram incorporating the obtained radiomics signature and selected clinical predictors was developed by using multivariable logistic regression analysis. The performance of the radiomic-clinical model was assessed with respect to its discrimination, calibration, and clinical usefulness. Results Seven radiomics features were selected among the 1301 features obtained as they could differentiate PHEOs from other adrenal lesions in the training (area under the curve [AUC], 0.887), internal validation (AUC, 0.880), and external validation cohorts (AUC, 0.807). Predictors contained in the individualized prediction nomogram included the radiomics signature and symptom number (symptoms include headache, palpitation, and diaphoresis). The training set yielded an AUC of 0.893 for the nomogram, which was confirmed in the internal and external validation sets with AUCs of 0.906 and 0.844, respectively. Decision curve analyses indicated the nomogram was clinically useful. In addition, 25 patients with 25 lesions were recruited for prospective validation, which yielded an AUC of 0.917 for the nomogram. Conclusion We propose a radiomic-based nomogram incorporating clinically useful signatures as an easy-to-use, predictive and individualized tool for PHEO diagnosis.

Identification of the most specific markers to differentiate primary pulmonary carcinoma from metastatic gastrointestinal carcinoma to the lung

Background A number of biomarkers have the potential of differentiating between primary lung tumours and secondary lung tumours from the gastrointestinal tract, however, a standardised panel for that purpose does not exist yet. We aimed to identify the smallest panel that is most sensitive and specific at differentiating between primary lung tumours and secondary lung tumours from the gastrointestinal tract. Methods A total of 170 samples were collected, including 140 primary and 30 non-primary lung tumours and staining for CK7, Napsin-A, TTF1, CK20, CDX2, and SATB2 was performed via tissue microarray. The data was then analysed using univariate regression models and a combination of multivariate regression models and Receiver Operating Characteristic (ROC) curves. Results Univariate regression models confirmed the 6 biomarkers’ ability to independently predict the primary outcome (p < 0.001). Multivariate models of 2-biomarker combinations identified 11 combinations with statistically significant odds ratios (ORs) (p < 0.05), of which TTF1/CDX2 had the highest area under the curve (AUC) (0.983, 0.960–1.000 95% CI). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 75.7, 100, 100, and 37.5% respectively. Multivariate models of 3-biomarker combinations identified 4 combinations with statistically significant ORs (p < 0.05), of which CK7/CK20/SATB2 had the highest AUC (0.965, 0.930–1.000 95% CI). The sensitivity, specificity, PPV, and NPV were 85.1, 100, 100, and 41.7% respectively. Multivariate models of 4-biomarker combinations did not identify any combinations with statistically significant ORs (p < 0.05). Conclusions The analysis identified the combination of CK7/CK20/SATB2 to be the smallest panel with the highest sensitivity (85.1%) and specificity (100%) for predicting tumour origin with an ROC AUC of 0.965 (p < 0.001; SE: 0.018, 0.930–1.000 95% CI).

Study of the sensitivity and specificity of smell and taste disorders as a predictive factor of SARS-CoV-2 infection among primary care healthcare professionals

Backgroundamong the manifestations of COVID-19 are Taste and Smell Disorders (TSDs).AimThe aim of the study is to evaluate the sensitivity and specificity of TSDs and other associated symptoms to estimate predictive values for determining SARS-CoV-2 infection.Design and settingRetrospective observational study.Methodsa study of the sensitivity and specificity of TSDs has been carried out using the Polymerase Chain Reaction (PCR) test for the diagnosis of SARS-CoV-2 as the Gold Standard value. Logistic regressions adjusted for age and sex were performed to identify additional symptoms that might be associated with COVID-19.Resultsthe results are based on 226 healthcare workers with clinical symptoms suggestive of COVID-19, 116 with positive PCR and 111 with negative PCR. TSDs had an OR of 12.43 (CI 0.95 6.33–26.19), sensitivity 60.34% and specificity 89.09%. In the logistic regression model, the association of TSD, fever or low-grade fever, shivering, dyspnoea, arthralgia and myalgia obtained an area under the curve of 85.7% (CI 0.95: 80.7 % - 90.7 %), sensitivity 82.8 %, specificity 80% and positive predictive values 81.4% and negative 81.5%.ConclusionsTSDs are a strong predictor of COVID-19. The association of TSD, fever, low-grade fever or shivering, dyspnoea, arthralgia and myalgia correctly predicts 85.7% of the results of the COVID-19 test.