gGATLDA: lncRNA-disease association prediction based on graph-level graph attention network

Background Long non-coding RNAs (lncRNAs) are related to human diseases by regulating gene expression. Identifying lncRNA-disease associations (LDAs) will contribute to diagnose, treatment, and prognosis of diseases. However, the identification of LDAs by the biological experiments is time-consuming, costly and inefficient. Therefore, the development of efficient and high-accuracy computational methods for predicting LDAs is of great significance. Results In this paper, we propose a novel computational method (gGATLDA) to predict LDAs based on graph-level graph attention network. Firstly, we extract the enclosing subgraphs of each lncRNA-disease pair. Secondly, we construct the feature vectors by integrating lncRNA similarity and disease similarity as node attributes in subgraphs. Finally, we train a graph neural network (GNN) model by feeding the subgraphs and feature vectors to it, and use the trained GNN model to predict lncRNA-disease potential association scores. The experimental results show that our method can achieve higher area under the receiver operation characteristic curve (AUC), area under the precision recall curve (AUPR), accuracy and F1-Score than the state-of-the-art methods in five fold cross-validation. Case studies show that our method can effectively identify lncRNAs associated with breast cancer, gastric cancer, prostate cancer, and renal cancer. Conclusion The experimental results indicate that our method is a useful approach for predicting potential LDAs.

Heterogeneous Types of miRNA-Disease Associations Stratified by Multi-Layer Network Embedding and Prediction

Abnormal miRNA functions are widely involved in many diseases recorded in the database of experimentally supported human miRNA-disease associations (HMDD). Some of the associations are complicated: There can be up to five heterogeneous association types of miRNA with the same disease, including genetics type, epigenetics type, circulating miRNAs type, miRNA tissue expression type and miRNA-target interaction type. When one type of association is known for an miRNA-disease pair, it is important to predict any other types of the association for a better understanding of the disease mechanism. It is even more important to reveal associations for currently unassociated miRNAs and diseases. Methods have been recently proposed to make predictions on the association types of miRNA-disease pairs through restricted Boltzman machines, label propagation theories and tensor completion algorithms. None of them has exploited the non-linear characteristics in the miRNA-disease association network to improve the performance. We propose to use attributed multi-layer heterogeneous network embedding to learn the latent representations of miRNAs and diseases from each association type and then to predict the existence of the association type for all the miRNA-disease pairs. The performance of our method is compared with two newest methods via 10-fold cross-validation on the database HMDD v3.2 to demonstrate the superior prediction achieved by our method under different settings. Moreover, our real predictions made beyond the HMDD database can be all validated by NCBI literatures, confirming that our method is capable of accurately predicting new associations of miRNAs with diseases and their association types as well.

Drug target gene-based analyses of drug repositionability in rare and intractable diseases

Drug development for rare and intractable diseases has been challenging for decades due to the low prevalence and insufficient information on these diseases. Drug repositioning is increasingly being used as a promising option in drug development. We aimed to analyze the trend of drug repositioning and inter-disease drug repositionability among rare and intractable diseases. We created a list of rare and intractable diseases based on the designated diseases in Japan. Drug information extracted from clinical trial data were integrated with information of drug target genes, which represent the mechanism of drug action. We obtained 753 drugs and 551 drug target genes from 8307 clinical trials for 189 diseases or disease groups. Trend analysis of drug sharing between a disease pair revealed that 1676 drug repositioning events occurred in 4401 disease pairs. A score, Rgene, was invented to investigate the proportion of drug target genes shared between a disease pair. Annual changes of Rgene corresponded to the trend of drug repositioning and predicted drug repositioning events occurring within a year or two. Drug target gene-based analyses well visualized the drug repositioning landscape. This approach facilitates drug development for rare and intractable diseases.

Rate of sepsis hospitalizations after misdiagnosis in adult emergency department patients: a look-forward analysis with administrative claims data using Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) methodology in an integrated health system

Objectives Delays in sepsis diagnosis can increase morbidity and mortality. Previously, we performed a Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) “look-back” analysis to identify symptoms at risk for delayed sepsis diagnosis. We found treat-and-release emergency department (ED) encounters for fluid and electrolyte disorders (FED) and altered mental status (AMS) were associated with downstream sepsis hospitalizations. In this “look-forward” analysis, we measure the potential misdiagnosis-related harm rate for sepsis among patients with these symptoms. Methods Retrospective cohort study using electronic health record and claims data from Kaiser Permanente Mid-Atlantic States (2013–2018). Patients ≥18 years with ≥1 treat-and-release ED encounter for FED or AMS were included. Observed greater than expected sepsis hospitalizations within 30 days of ED treat-and-release encounters were considered potential misdiagnosis-related harms. Temporal analyses were employed to differentiate case and comparison (superficial injury/contusion ED encounters) cohorts. Results There were 4,549 treat-and-release ED encounters for FED or AMS, 26 associated with a sepsis hospitalization in the next 30 days. The observed (0.57%) minus expected (0.13%) harm rate was 0.44% (absolute) and 4.5-fold increased over expected (relative). There was a spike in sepsis hospitalizations in the week following FED/AMS ED visits. There were fewer sepsis hospitalizations and no spike in admissions in the week following superficial injury/contusion ED visits. Potentially misdiagnosed patients were older and more medically complex. Conclusions Potential misdiagnosis-related harms from sepsis are infrequent but measurable using SPADE. This look-forward analysis validated our previous look-back study, demonstrating the SPADE approach can be used to study infectious disease syndromes.

Antecedent treat-and-release diagnoses prior to sepsis hospitalization among adult emergency department patients: a look-back analysis employing insurance claims data using Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) methodology

Objectives The aim of this study was to identify delays in early pre-sepsis diagnosis in emergency departments (ED) using the Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) approach. Methods SPADE methodology was employed using electronic health record and claims data from Kaiser Permanente Mid-Atlantic States (KPMAS). Study cohort included KPMAS members ≥18 years with ≥1 sepsis hospitalization 1/1/2013–12/31/2018. A look-back analysis identified treat-and-release ED visits in the month prior to sepsis hospitalizations. Top 20 diagnoses associated with these ED visits were identified; two diagnosis categories were distinguished as being linked to downstream sepsis hospitalizations. Observed-to-expected (O:E) and temporal analyses were performed to validate the symptom selection; results were contrasted to a comparison group. Demographics of patients that did and did not experience sepsis misdiagnosis were compared. Results There were 3,468 sepsis hospitalizations during the study period and 766 treat-and-release ED visits in the month prior to hospitalization. Patients discharged from the ED with fluid and electrolyte disorders (FED) and altered mental status (AMS) were most likely to have downstream sepsis hospitalizations (O:E ratios of 2.66 and 2.82, respectively). Temporal analyses revealed that these symptoms were overrepresented and temporally clustered close to the hospitalization date. Approximately 2% of sepsis hospitalizations were associated with prior FED or AMS ED visits. Conclusions Treat-and-release ED encounters for FED and AMS may represent harbingers for downstream sepsis hospitalizations. The SPADE approach can be used to develop performance measures that identify pre-sepsis.

Missed acute myocardial infarction in the emergency department–standardizing measurement of misdiagnosis-related harms using the SPADE method

ObjectivesDiagnostic error is a serious public health problem. Measuring diagnostic performance remains elusive. We sought to measure misdiagnosis-related harms following missed acute myocardial infarctions (AMI) in the emergency department (ED) using the symptom-disease pair analysis of diagnostic error (SPADE) method.MethodsRetrospective administrative data analysis (2009–2017) from a single, integrated health system using International Classification of Diseases (ICD) coded discharge diagnoses. We looked back 30 days from AMI hospitalizations for antecedent ED treat-and-release visits to identify symptoms linked to probable missed AMI (observed > expected). We then looked forward from these ED discharge diagnoses to identify symptom-disease pair misdiagnosis-related harms (AMI hospitalizations within 30-days, representing diagnostic adverse events).ResultsA total of 44,473 AMI hospitalizations were associated with 2,874 treat-and-release ED visits in the prior 30 days. The top plausibly-related ED discharge diagnoses were “chest pain” and “dyspnea” with excess treat-and-release visit rates of 9.8% (95% CI 8.5–11.2%) and 3.4% (95% CI 2.7–4.2%), respectively. These represented 574 probable missed AMIs resulting in hospitalization (adverse event rate per AMI 1.3%, 95% CI 1.2–1.4%). Looking forward, 325,088 chest pain or dyspnea ED discharges were followed by 508 AMI hospitalizations (adverse event rate per symptom discharge 0.2%, 95% CI 0.1–0.2%).ConclusionsThe SPADE method precisely quantifies misdiagnosis-related harms from missed AMIs using administrative data. This approach could facilitate future assessment of diagnostic performance across health systems. These results correspond to ∼10,000 potentially-preventable harms annually in the US. However, relatively low error and adverse event rates may pose challenges to reducing harms for this ED symptom-disease pair.

Multimorbidity among Two Million Adults in China

To explore the multimorbidity prevalence and patterns among middle-aged and older adults from China. Data on thirteen chronic diseases were collected from 2,097,150 participants aged over 45 years between January 1st 2011 and December 31st 2015 from Beijing Medical Claim Data for Employees. Association rule mining and hierarchical cluster analysis were applied to assess multimorbidity patterns. Multimorbidity prevalence was 51.6% and 81.3% in the middle-aged and older groups, respectively. The most prevalent disease pair was that of osteoarthritis and rheumatoid arthritis (OARA) with hypertension (HT) (middle-aged: 22.5%; older: 41.8%). Ischaemic heart disease (IHD), HT, and OARA constituted the most common triad combination (middle-aged: 11.0%; older: 31.2%). Among the middle-aged group, the strongest associations were found in a combination of cerebrovascular disease (CBD), OARA, and HT with IHD in males (lift = 3.49), and CBD, OARA, and COPD with IHD in females (lift = 3.24). Among older patients, glaucoma and cataracts in females (lift = 2.95), and IHD, OARA, and glaucoma combined with cataracts in males (lift = 2.45) were observed. Visual impairment clusters, a mixed cluster of OARA, IHD, COPD, and cardiometabolic clusters were detected. Multimorbidity is prevalent among middle-aged and older Chinese individuals. The observations of multimorbidity patterns have implications for improving preventive care and developing appropriate guidelines for morbidity treatment.

Predicting drug−disease associations via sigmoid kernel-based convolutional neural networks

Background In the process of drug development, computational drug repositioning is effective and resource-saving with regards to its important functions on identifying new drug–disease associations. Recent years have witnessed a great progression in the field of data mining with the advent of deep learning. An increasing number of deep learning-based techniques have been proposed to develop computational tools in bioinformatics. Methods Along this promising direction, we here propose a drug repositioning computational method combining the techniques of Sigmoid Kernel and Convolutional Neural Network (SKCNN) which is able to learn new features effectively representing drug–disease associations via its hidden layers. Specifically, we first construct similarity metric of drugs using drug sigmoid similarity and drug structural similarity, and that of disease using disease sigmoid similarity and disease semantic similarity. Based on the combined similarities of drugs and diseases, we then use SKCNN to learn hidden representations for each drug-disease pair whose labels are finally predicted by a classifier based on random forest. Results A series of experiments were implemented for performance evaluation and their results show that the proposed SKCNN improves the prediction accuracy compared with other state-of-the-art approaches. Case studies of two selected disease are also conducted through which we prove the superior performance of our method in terms of the actual discovery of potential drug indications. Conclusion The aim of this study was to establish an effective predictive model for finding new drug–disease associations. These experimental results show that SKCNN can effectively predict the association between drugs and diseases.

A Mendelian randomization study of IL6 signaling in cardiovascular diseases, immune-related disorders and longevity

Growing evidence suggests that inflammation is a significant contributor to different cardiovascular diseases (CVDs). Mendelian randomization (MR) was performed to assess the causal inference between plasma soluble IL6 receptor (sIL6R), a negative regulator of IL6 signaling, and different cardiovascular and immune-related disorders. Cis-MR with multiple instrumental variables showed an inverse association of sIL6R with rheumatoid arthritis, atrial fibrillation, stroke, coronary artery disease, and abdominal aortic aneurysm. However, genetically-determined sIL6R level was positively associated with atopic dermatitis and asthma. Also, sIL6R level was associated with longevity, as evaluated by parental age at death, a heritable trait. Gene-based association analysis with S-PrediXcan by using tissues from GTExV7 showed that IL6R tissue expression-disease pair associations were consistent with the directional effect of IL6 signaling identified in MR. Genetically-determined reduced IL6 signaling lowers the risk of multiple CVDs and is associated with increased longevity, but at the expense of higher atopic risk.