Longitudinal profiling of circulating miRNA during cardiac allograft rejection: a proof-of-concept study.

AIMS: Allograft rejection following heart transplantation (HTx) is a serious complication even in the era of modern immunosuppressive regimens and causes up to a third of early deaths after HTx. Allograft rejection is mediated by a cascade of immune mechanisms leading to acute cellular rejection (ACR) and/or antibody-mediated rejection (AMR). The gold standard for monitoring allograft rejection is invasive endomyocardial biopsy that exposes patients to complications. Little is known about the potential of circulating miRNAs as biomarkers to detect cardiac allograft rejection. We here present a systematic analysis of circulating miRNAs as biomarkers and predictors for allograft rejection after HTx using next-generation small RNA sequencing. METHODS AND RESULTS: We used next-generation small RNA sequencing to investigate circulating miRNAs among HTx recipients (10 healthy controls, 10 heart failure patients, 13 ACR, and 10 AMR). MiRNA profiling was performed at different time points before, during, and after resolution of the rejection episode. We found three miRNAs with significantly increased serum levels in patients with biopsy-proven cardiac rejection when compared with patients without rejection: hsa-miR-139-5p, hsa-miR-151a-5p, and hsa-miR-186-5p. We identified miRNAs that may serve as potential predictors for the subsequent development of ACR: hsa-miR-29c-3p (ACR) and hsa-miR-486-5p (AMR). Overall, hsa-miR-486-5p was most strongly associated with acute rejection episodes. CONCLUSIONS: Monitoring cardiac allograft rejection using circulating miRNAs might represent an alternative strategy to invasive endomyocardial biopsy.

Artificial Intelligence for Drug Toxicity and Safety.

Interventional pharmacology is one of medicine's most potent weapons against disease. These drugs, however, can result in damaging side effects and must be closely monitored. Pharmacovigilance is the field of science that monitors, detects, and prevents adverse drug reactions (ADRs). Safety efforts begin during the development process, using in vivo and in vitro studies, continue through clinical trials, and extend to postmarketing surveillance of ADRs in real-world populations. Future toxicity and safety challenges, including increased polypharmacy and patient diversity, stress the limits of these traditional tools. Massive amounts of newly available data present an opportunity for using artificial intelligence (AI) and machine learning to improve drug safety science. Here, we explore recent advances as applied to preclinical drug safety and postmarketing surveillance with a specific focus on machine and deep learning (DL) approaches.

Disease Heritability Inferred from Familial Relationships Reported in Medical Records.

Heritability is essential for understanding the biological causes of disease but requires laborious patient recruitment and phenotype ascertainment. Electronic health records (EHRs) passively capture a wide range of clinically relevant data and provide a resource for studying the heritability of traits that are not typically accessible. EHRs contain next-of-kin information collected via patient emergency contact forms, but until now, these data have gone unused in research. We mined emergency contact data at three academic medical centers and identified 7.4 million familial relationships while maintaining patient privacy. Identified relationships were consistent with genetically derived relatedness. We used EHR data to compute heritability estimates for 500 disease phenotypes. Overall, estimates were consistent with the literature and between sites. Inconsistencies were indicative of limitations and opportunities unique to EHR research. These analyses provide a validation of the use of EHRs for genetics and disease research.

Serum exosomal protein profiling for the non-invasive detection of cardiac allograft rejection.

BACKGROUND: Exosomes are cell-derived circulating vesicles that play an important role in cell-cell communication. Exosomes are actively assembled and carry messenger RNAs, microRNAs and proteins. The "gold standard" for cardiac allograft surveillance is endomyocardial biopsy (EMB), an invasive technique with a distinct complication profile. The development of novel, non-invasive methods for the early diagnosis of allograft rejection is warranted. We hypothesized that the exosomal proteome is altered in acute rejection, allowing for a distinction between non-rejection and rejection episodes. METHODS: Serum samples were collected from heart transplant (HTx) recipients with no rejection, acute cellular rejection (ACR) and antibody-mediated rejection (AMR). Liquid chromatography-tandem mass spectrometry (LC-MS/MS) analysis of serum exosome was performed using a mass spectrometer (Orbitrap Fusion Tribrid). RESULTS: Principal component analysis (PCA) revealed a clustering of 3 groups: (1) control and heart failure (HF); (2) HTx without rejection; and (3) ACR and AMR. A total of 45 proteins were identified that could distinguish between groups (q < 0.05). Comparison of serum exosomal proteins from control, HF and non-rejection HTx revealed 17 differentially expressed proteins in at least 1 group (q < 0.05). Finally, comparisons of non-rejection HTx, ACR and AMR serum exosomes revealed 15 differentially expressed proteins in at least 1 group (q < 0.05). Of these 15 proteins, 8 proteins are known to play a role in the immune response. Of note, the majority of proteins identified were associated with complement activation, adaptive immunity such as immunoglobulin components and coagulation. CONCLUSIONS: Characterizing of circulating exosomal proteome in different cardiac disease states reveals unique protein expression patterns indicative of the respective pathologies. Our data suggest that HTx and allograft rejection alter the circulating exosomal protein content. Exosomal protein analysis could be a novel approach to detect and monitor acute transplant rejection and lead to the development of predictive and prognostic biomarkers.

PREDICTIVE MODELING OF HOSPITAL READMISSION RATES USING ELECTRONIC MEDICAL RECORD-WIDE MACHINE LEARNING: A CASE-STUDY USING MOUNT SINAI HEART FAILURE COHORT.

Reduction of preventable hospital readmissions that result from chronic or acute conditions like stroke, heart failure, myocardial infarction and pneumonia remains a significant challenge for improving the outcomes and decreasing the cost of healthcare delivery in the United States. Patient readmission rates are relatively high for conditions like heart failure (HF) despite the implementation of high-quality healthcare delivery operation guidelines created by regulatory authorities. Multiple predictive models are currently available to evaluate potential 30-day readmission rates of patients. Most of these models are hypothesis driven and repetitively assess the predictive abilities of the same set of biomarkers as predictive features. In this manuscript, we discuss our attempt to develop a data-driven, electronic-medical record-wide (EMR-wide) feature selection approach and subsequent machine learning to predict readmission probabilities. We have assessed a large repertoire of variables from electronic medical records of heart failure patients in a single center. The cohort included 1,068 patients with 178 patients were readmitted within a 30-day interval (16.66% readmission rate). A total of 4,205 variables were extracted from EMR including diagnosis codes (n=1,763), medications (n=1,028), laboratory measurements (n=846), surgical procedures (n=564) and vital signs (n=4). We designed a multistep modeling strategy using the Naïve Bayes algorithm. In the first step, we created individual models to classify the cases (readmitted) and controls (non-readmitted). In the second step, features contributing to predictive risk from independent models were combined into a composite model using a correlation-based feature selection (CFS) method. All models were trained and tested using a 5-fold cross-validation method, with 70% of the cohort used for training and the remaining 30% for testing. Compared to existing predictive models for HF readmission rates (AUCs in the range of 0.6-0.7), results from our EMR-wide predictive model (AUC=0.78; Accuracy=83.19%) and phenome-wide feature selection strategies are encouraging and reveal the utility of such datadriven machine learning. Fine tuning of the model, replication using multi-center cohorts and prospective clinical trial to evaluate the clinical utility would help the adoption of the model as a clinical decision system for evaluating readmission status.

Mechanical Signals Inhibit Growth of a Grafted Tumor In Vivo: Proof of Concept.

In the past ten years, many studies have shown that malignant tissue has been "normalized" in vitro using mechanical signals. We apply the principles of physical oncology (or mechanobiology) in vivo to show the effect of a "constraint field" on tumor growth. The human breast cancer cell line, MDA MB 231, admixed with ferric nanoparticles was grafted subcutaneously in Nude mice. The magnetizable particles rapidly surrounded the growing tumor. Two permanent magnets located on either side of the tumor created a gradient of magnetic field. Magnetic energy is transformed into mechanical energy by the particles acting as "bioactuators", applying a constraint field and, by consequence, biomechanical stress to the tumor. This biomechanical treatment was applied 2 hours/day during 21 days, from Day 18 to Day 39 following tumor implantation. The study lasted 74 days. Palpable tumor was measured two times a week. There was a significant in vivo difference between the median volume of treated tumors and untreated controls in the mice measured up to D 74 (D 59 + population): (529 [346; 966] mm3 vs 1334 [256; 2106] mm3; p = 0.015), treated mice having smaller tumors. The difference was not statistically significant in the group of mice measured at least to D 59 (D 59 population). On ex vivo examination, the surface of the tumor mass, measured on histologic sections, was less in the treated group, G1, than in the control groups: G2 (nanoparticles, no magnetic field), G3 (magnetic field, no nanoparticles), G4 (no nanoparticles, no magnetic field) in the D 59 population (Median left surface was significantly lower in G1 (5.6 [3.0; 42.4] mm2, p = 0.005) than in G2 (20.8 [4.9; 34.3]), G3 (16.5 [13.2; 23.2]) and G4 (14.8 [1.8; 55.5]); Median right surface was significantly lower in G1 (4.7 [1.9; 29.2] mm2, p = 0.015) than in G2 (25.0 [5.2; 55.0]), G3 (18.0 [14.6; 35.2]) and G4 (12.5 [1.5; 51.8]). There was no statistically significant difference in the day 59+ population. This is the first demonstration of the effect of stress on tumor growth in vivo suggesting that biomechanical intervention may have a high translational potential as a therapy in locally advanced tumors like pancreatic cancer or primary hepatic carcinoma for which no effective therapy is currently available.

A knowledge-based, automated method for phenotyping in the EHR using only clinical pathology reports.

The secondary use of electronic health records (EHR) represents unprecedented opportunities for biomedical discovery. Central to this goal is, EHR-phenotyping, also known as cohort identification, which remains a significant challenge. Complex phenotypes often require multivariate and multi-scale analyses, ultimately leading to manually created phenotype definitions. We present Ontology-driven Reports-based Phenotyping from Unique Signatures (ORPheUS), an automated approach to EHR-phenotyping. To do this we identify unique signatures of abnormal clinical pathology reports that correspond to pre-defined medical terms from biomedical ontologies. By using only the clinical pathology, or "lab", reports we are able to mitigate clinical biases enabling researchers to explore other dimensions of the EHR. We used ORPheUS to generate signatures for 858 diseases and validated against reference cohorts for Type 2 Diabetes Mellitus (T2DM) and Atrial Fibrillation (AF). Our results suggest that our approach, using solely clinical pathology reports, is an effective as a primary screening tool for automated clinical phenotyping.