Diagnostic signature for Heart Failure with Preserved Ejection Fraction (HFpEF): A Machine Learning Approach Using Multi-Modality Electronic Health Record Data

Aims: Heart failure with preserved ejection fraction (HFpEF) is thought to be highly prevalent yet remains underdiagnosed. We sought to develop a data-driven diagnostic model to predict from electronic health records (EHR) the likelihood of HFpEF among patients with unexplained dyspnea and preserved left ventricular EF. Methods & Results: The derivation cohort comprised patients with dyspnea and echocardiography results. Structured and unstructured data were extracted using an automated informatics pipeline. Patients were retrospectively diagnosed as HFpEF (cases), non-HF (control cohort I), or HF with reduced EF (HFrEF; control cohort II). The ability of clinical parameters and investigations to discriminate cases from controls was evaluated by extreme gradient boosting. A likelihood scoring system was developed and validated in a separate test cohort. The derivation cohort included 1585 consecutive patients: 133 cases of HFpEF (9%), 194 non-HF cases (Control cohort I) and 1258 HFrEF cases (Control cohort II). Two HFpEF diagnostic signatures were derived, comprising symptoms, diagnoses and investigation results. A final prediction model was generated based on the averaged likelihood scores from these two models. In a validation cohort consisting of 269 consecutive patients (with 66 HFpEF cases (24.5%)), the diagnostic power of detecting HFpEF had an AUROC of 90% (P<0.001) and average precision (AP) of 74%. Conclusion: This diagnostic signature enables discrimination of HFpEF from non-cardiac dyspnea or HFrEF from EHR and can assist in the diagnostic evaluation in patients with unexplained dyspnea.

Blood Circulating miRNA Pairs as a Robust Signature for Early Detection of Esophageal Cancer

Esophageal cancer (EC) is a common malignant tumor in the digestive system which is often diagnosed at the middle and late stages. Noninvasive diagnosis using circulating miRNA as biomarkers enables accurate detection of early-stage EC to reduce mortality. We built a diagnostic signature consisting of four miRNA pairs for the early detection of EC using individualized Pairwise Analysis of Gene Expression (iPAGE). Profiling of miRNA expression identified 496 miRNA pairs with significant relative expression change. Four miRNA pairs consistently selected from LASSO were used to construct the final diagnostic model. The performance of the signature was validated using two independent datasets, yielding both AUCs and PRCs over 0.99. Furthermore, precision, recall, and F-score were also evaluated for clinical application, when a fixed threshold is given, resulting in all the scores are larger than 0.92 in the training set, test set, and two validation sets. Our results suggested that the 4-miRNA signature is a new biomarker for the early diagnosis of patients with EC. The clinical use of this signature would have improved the detection of EC for earlier therapy and more favorite prognosis.

Long non-coding RNA pairs to assist in diagnosing sepsis

Background Sepsis is the major cause of death in Intensive Care Unit (ICU) globally. Molecular detection enables rapid diagnosis that allows early intervention to minimize the death rate. Recent studies showed that long non-coding RNAs (lncRNAs) regulate proinflammatory genes and are related to the dysfunction of organs in sepsis. Identifying lncRNA signature with absolute abundance is challenging because of the technical variation and the systematic experimental bias. Results Cohorts (n = 768) containing whole blood lncRNA profiling of sepsis patients in the Gene Expression Omnibus (GEO) database were included. We proposed a novel diagnostic strategy that made use of the relative expressions of lncRNA pairs, which are reversed between sepsis patients and normal controls (eg. lncRNAi > lncRNAj in sepsis patients and lncRNAi < lncRNAj in normal controls), to identify 14 lncRNA pairs as a sepsis diagnostic signature. The signature was then applied to independent cohorts (n = 644) to evaluate its predictive performance across different ages and normalization methods. Comparing to common machine learning models and existing signatures, SepSigLnc consistently attains better performance on the validation cohorts from the same age group (AUC = 0.990 & 0.995 in two cohorts) and across different groups (AUC = 0.878 on average), as well as cohorts processed by an alternative normalization method (AUC = 0.953 on average). Functional analysis demonstrates that the lncRNA pairs in SepsigLnc are functionally similar and tend to implicate in the same biological processes including cell fate commitment and cellular response to steroid hormone stimulus. Conclusion Our study identified 14 lncRNA pairs as signature that can facilitate the diagnosis of septic patients at an intervenable point when clinical manifestations are not dramatic. Also, the computational procedure can be generalized to a standard procedure for discovering diagnostic molecule signatures.

Transcriptomic analysis and Novel gene pair-based signatures for Hepatitis B-related hepatocellular carcinoma

Background: Hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC) misses the opportunity for surgery because it is not detected early. The molecular mechanism of hepatitis B-related liver cancer needs further understanding, and effective diagnostic and prognostic models are in urgent need. Methods: Expression profiles from the Cancer Genome Atlas (TCGA) Liver Hepatocellular Carcinoma (LIHC), GSE121248, GSE94660 GSE76724 from Gene Expression Omnibus (GEO) database were obtained. Differentially expressed genes (DEGs) between normal and tumor HBV-related HCC samples based on GSE121248 and GSE94660. Gene pairs are generated by comparing the expression levels of every two DEGs. A diagnostic signature of pairs of DEGs was built using cross-validation Lasso and Best Subset Selection regression. Hub genes and significant modules were screened by Cytoscape, and potential drugs were predicted by DGIdb. A prognostic signature was established and xCell and ssGSEA were utilized to reveal the cell composition and cancer hallmarks to get an elucidation for the risk.Results: 457 DEGs were screened. A powerful diagnostic signature of 2 pairs of DEGs was built and validated in TCGA-LIHC and GEO datasets repeatedly with assured performance. 10 Hub genes were found and fostamatinib was predicted to have potential therapeutic effect on HBV-related HCC. A prognostic signature with good efficiency (Log-rank P value<0.05, AUC=93.1%) were established, with stromal score and several hallmarks related to the risk Conclusion: Taken together, the study provided sight into the molecular mechanism as well as a novel strategy for the early diagnosis and prognosis for HBV-related HCC.

Circulating exosomal mRNA profiling identifies novel signatures for the detection of prostate cancer

The landscape and characteristics of circulating exosomal messenger RNAs (emRNAs) are poorly understood, which hampered the accurate detection of circulating emRNAs. Through comparing RNA sequencing data of circulating exosomes with the corresponding data in tissues, we illustrated the different characteristics of emRNAs compared to tissue mRNAs. We then developed an improved strategy for emRNA detection based on the features of circulating emRNAs. Using the optimized detection strategy, we further validated prostate cancer (PCa) associated emRNAs discovered by emRNA-seq in a large cohort of patients and identified emRNA signatures for PCa screening and diagnosis using logistic regression analysis. The receiver operating characteristic curve (ROC) analysis showed that the circulating emRNA-based screening signature yielded an area under the ROC curve (AUC) of 0.948 in distinguishing PCa patients from healthy controls. The circulating emRNA-based diagnostic signature also showed a great performance in predicting prostate biopsy results (AUC: 0.851). In conclusion, our study developed an optimized emRNA detection strategy and identified novel emRNA signatures for the detection of PCa.