Current status of artificial intelligence methods for skin cancer survival analysis: a scoping review

Skin cancer mortality rates continue to rise, and survival analysis is increasingly needed to understand who is at risk and what interventions improve outcomes. However, current statistical methods are limited by inability to synthesize multiple data types, such as patient genetics, clinical history, demographics, and pathology and reveal significant multimodal relationships through predictive algorithms. Advances in computing power and data science enabled the rise of artificial intelligence (AI), which synthesizes vast amounts of data and applies algorithms that enable personalized diagnostic approaches. Here, we analyze AI methods used in skin cancer survival analysis, focusing on supervised learning, unsupervised learning, deep learning, and natural language processing. We illustrate strengths and weaknesses of these approaches with examples. Our PubMed search yielded 14 publications meeting inclusion criteria for this scoping review. Most publications focused on melanoma, particularly histopathologic interpretation with deep learning. Such concentration on a single type of skin cancer amid increasing focus on deep learning highlight growing areas for innovation; however, it also demonstrates opportunity for additional analysis that addresses other types of cutaneous malignancies and expands the scope of prognostication to combine both genetic, histopathologic, and clinical data. Moreover, researchers may leverage multiple AI methods for enhanced benefit in analyses. Expanding AI to this arena may enable improved survival analysis, targeted treatments, and outcomes.

Inborn Errors of Immunity Contribute to the Burden of Skin Disease and Create Opportunities for Improving the Practice of Dermatology

Opportunities to improve the clinical management of skin disease are being created by advances in genomic medicine. Large-scale sequencing increasingly challenges notions about single-gene disorders. It is now apparent that monogenic etiologies make appreciable contributions to the population burden of disease and that they are underrecognized in clinical practice. A genetic diagnosis informs on molecular pathology and may direct targeted treatments and tailored prevention strategies for patients and family members. It also generates knowledge about disease pathogenesis and management that is relevant to patients without rare pathogenic variants. Inborn errors of immunity are a large class of monogenic etiologies that have been well-studied and contribute to the population burden of inflammatory diseases. To further delineate the contributions of inborn errors of immunity to the pathogenesis of skin disease, we performed a set of analyses that identified 316 inborn errors of immunity associated with skin pathologies, including common skin diseases. These data suggest that clinical sequencing is underutilized in dermatology. We next use these data to derive a network that illuminates the molecular relationships of these disorders and suggests an underlying etiological organization to immune-mediated skin disease. Our results motivate the further development of a molecularly derived and data-driven reorganization of clinical diagnoses of skin disease.

Estimating the heritability of SARS-CoV-2 susceptibility and COVID-19 severity

SARS-CoV-2 has infected over 340 million people, prompting therapeutic research. While genetic studies can highlight potential drug targets, understanding the heritability of SARS-CoV-2 susceptibility and COVID-19 severity can contextualize their results. To date, loci from meta-analyses explain 1.2% and 5.8% of variation in susceptibility and severity respectively. Here we estimate the importance of shared environment and additive genetic variation to SARS-CoV-2 susceptibility and COVID-19 severity using pedigree data, PCR results, and hospitalization information. The relative importance of genetics and shared environment for susceptibility shifted during the study, with heritability ranging from 33% (95% CI: 20%-46%) to 70% (95% CI: 63%-74%). Heritability was greater for days hospitalized with COVID-19 (41%, 95% CI: 33%-57%) compared to shared environment (33%, 95% CI: 24%-38%). While our estimates suggest these genetic architectures are not fully understood, the shift in susceptibility estimates highlights the challenge of estimation during a pandemic, given environmental fluctuations and vaccine introduction.

SynTwin: A graph-based approach for predicting clinical outcomes using digital twins derived from synthetic patients

The concept of a digital twin came from the engineering, industrial, and manufacturing domains to create virtual objects or machines that could inform the design and development of real objects. This idea is appealing for precision medicine where digital twins of patients could help inform healthcare decisions. We have developed a methodology for generating and using digital twins for clinical outcome prediction. We introduce a new approach that combines synthetic data and network science to create digital twins (i.e. SynTwin) for precision medicine. First, our approach starts by estimating the distance between all subjects based on their available features. Second, the distances are used to construct a network with subjects as nodes and edges defining distance less than the percolation threshold. Third, communities or cliques of subjects are defined. Fourth, a large population of synthetic patients are generated using a synthetic data generation algorithm that models the correlation structure of the data to generate new patients. Fifth, digital twins are selected from the synthetic patient population that are within a given distance defining a subject community in the network. Finally, we compare and contrast community-based prediction of clinical endpoints using real subjects, digital twins, or both within and outside of the community. Key to this approach are the digital twins defined using patient similarity that represent hypothetical unobserved patients with patterns similar to nearby real patients as defined by network distance and community structure. We apply our SynTwin approach to predicting mortality in a population-based cancer registry (n=87,674) from the Surveillance, Epidemiology, and End Results (SEER) program from the National Cancer Institute (USA). Our results demonstrate that nearest network neighbor prediction of mortality in this study is significantly improved with digital twins (AUROC=0.864, 95% CI=0.857-0.872) over just using real data alone (AUROC=0.791, 95% CI=0.781-0.800). These results suggest a network-based digital twin strategy using synthetic patients may add value to precision medicine efforts.

Discovering Venom-Derived Drug Candidates Using Differential Gene Expression

Venoms are a diverse and complex group of natural toxins that have been adapted to treat many types of human disease, but rigorous computational approaches for discovering new therapeutic activities are scarce. We have designed and validated a new platform-named VenomSeq-to systematically identify putative associations between venoms and drugs/diseases via high-throughput transcriptomics and perturbational differential gene expression analysis. In this study, we describe the architecture of VenomSeq and its evaluation using the crude venoms from 25 diverse animal species and 9 purified teretoxin peptides. By integrating comparisons to public repositories of differential expression, associations between regulatory networks and disease, and existing knowledge of venom activity, we provide a number of new therapeutic hypotheses linking venoms to human diseases supported by multiple layers of preliminary evidence.

Association between neighborhood socioeconomic status, built environment and SARS-CoV-2 infection among cancer patients treated at a Tertiary Cancer Center in New York City

BACKGROUND

Racial and ethnic minority groups experience a disproportionate burden of SARS-CoV-2 illness and studies suggest that cancer patients are at a particular risk for severe SARS-CoV-2 infection.

AIMS

The objective of this study was examine the association between neighborhood characteristics and SARS-CoV-2 infection among patients with cancer.

METHODS AND RESULTS

We performed a cross-sectional study of New York City residents receiving treatment for cancer at a tertiary cancer center. Patients were linked by their address to data from the US Census Bureau's American Community Survey and to real estate tax data from New York's Department of City Planning. Models were used to both to estimate odds ratios (ORs) per unit increase and to predict probabilities (and 95% CI) of SARS-CoV2 infection. We identified 2350 New York City residents with cancer receiving treatment. Overall, 214 (9.1%) were infected with SARS-CoV-2. In adjusted models, the percentage of Hispanic/Latino population (aOR = 1.01; 95% CI, 1.005-1.02), unemployment rate (aOR = 1.10; 95% CI, 1.05-1.16), poverty rates (aOR = 1.02; 95% CI, 1.0002-1.03), rate of >1 person per room (aOR = 1.04; 95% CI, 1.01-1.07), average household size (aOR = 1.79; 95% CI, 1.23-2.59) and population density (aOR = 1.86; 95% CI, 1.27-2.72) were associated with SARS-CoV-2 infection.

CONCLUSION

Among cancer patients in New York City receiving anti-cancer therapy, SARS-CoV-2 infection was associated with neighborhood- and building-level markers of larger household membership, household crowding, and low socioeconomic status.

NOVELTY AND IMPACT

We performed a cross-sectional analysis of residents of New York City receiving treatment for cancer in which we linked subjects to census and real estate date. This linkage is a novel way to examine the neighborhood characteristics that influence SARS-COV-2 infection. We found that among patients receiving anti-cancer therapy, SARS-CoV-2 infection was associated with building and neighborhood-level markers of household crowding, larger household membership, and low socioeconomic status. With ongoing surges of SARS-CoV-2 infections, these data may help in the development of interventions to decrease the morbidity and mortality associated with SARS-CoV-2 among cancer patients.

Structured deep embedding model to generate composite clinical indices from electronic health records for early detection of pancreatic cancer

The high-dimensionality, complexity, and irregularity of electronic health records (EHR) data create significant challenges for both simplified and comprehensive health assessments, prohibiting an efficient extraction of actionable insights by clinicians. If we can provide human decision-makers with a simplified set of interpretable composite indices (i.e., combining information about groups of related measures into single representative values), it will facilitate effective clinical decision-making. In this study, we built a structured deep embedding model aimed at reducing the dimensionality of the input variables by grouping related measurements as determined by domain experts (e.g., clinicians). Our results suggest that composite indices representing liver function may consistently be the most important factor in the early detection of pancreatic cancer (PC). We propose our model as a basis for leveraging deep learning toward developing composite indices from EHR for predicting health outcomes, including but not limited to various cancers, with clinically meaningful interpretations.

Mural Wnt/β-catenin signaling regulates Lama2 expression to promote neurovascular unit maturation

Neurovascular unit and barrier maturation rely on vascular basement membrane (vBM) composition. Laminins, a major vBM component, are crucial for these processes, yet the signaling pathway(s) that regulate their expression remain unknown. Here, we show that mural cells have active Wnt/β-catenin signaling during central nervous system development in mice. Bulk RNA sequencing and validation using postnatal day 10 and 14 wild-type versus adenomatosis polyposis coli downregulated 1 (Apcdd1-/-) mouse retinas revealed that Lama2 mRNA and protein levels are increased in mutant vasculature with higher Wnt/β-catenin signaling. Mural cells are the main source of Lama2, and Wnt/β-catenin activation induces Lama2 expression in mural cells in vitro. Markers of mature astrocytes, including aquaporin 4 (a water channel in astrocyte endfeet) and integrin-α6 (a laminin receptor), are upregulated in Apcdd1-/- retinas with higher Lama2 vBM deposition. Thus, the Wnt/β-catenin pathway regulates Lama2 expression in mural cells to promote neurovascular unit and barrier maturation.

Alterations in the kallikrein-kinin system predict death after heart transplant

Heart transplantation remains the definitive treatment for end stage heart failure. Because availability is limited, risk stratification of candidates is crucial for optimizing both organ allocations and transplant outcomes. Here we utilize proteomics prior to transplant to identify new biomarkers that predict post-transplant survival in a multi-institutional cohort. Microvesicles were isolated from serum samples and underwent proteomic analysis using mass spectrometry. Monte Carlo cross-validation (MCCV) was used to predict survival after transplant incorporating select recipient pre-transplant clinical characteristics and serum microvesicle proteomic data. We identified six protein markers with prediction performance above AUROC of 0.6, including Prothrombin (F2), anti-plasmin (SERPINF2), Factor IX, carboxypeptidase 2 (CPB2), HGF activator (HGFAC) and low molecular weight kininogen (LK). No clinical characteristics demonstrated an AUROC > 0.6. Putative biological functions and pathways were assessed using gene set enrichment analysis (GSEA). Differential expression analysis identified enriched pathways prior to transplant that were associated with post-transplant survival including activation of platelets and the coagulation pathway prior to transplant. Specifically, upregulation of coagulation cascade components of the kallikrein-kinin system (KKS) and downregulation of kininogen prior to transplant were associated with survival after transplant. Further prospective studies are warranted to determine if alterations in the KKS contributes to overall post-transplant survival.

A database of pediatric drug effects to evaluate ontogenic mechanisms from child growth and development

BACKGROUND

Adverse drug effects (ADEs) in children are common and may result in disability and death, necessitating post-marketing monitoring of their use. Evaluating drug safety is especially challenging in children due to the processes of growth and maturation, which can alter how children respond to treatment. Current drug safety-signal-detection methods do not account for these dynamics.

METHODS

We recently developed a method called disproportionality generalized additive models (dGAMs) to better identify safety signals for drugs across child-development stages.

FINDINGS

We used dGAMs on a database of 264,453 pediatric adverse-event reports and found 19,438 ADEs signals associated with development and validated these signals against a small reference set of pediatric ADEs. Using our approach, we can hypothesize on the ontogenic dynamics of ADE signals, such as that montelukast-induced psychiatric disorders appear most significant in the second year of life. Additionally, we integrated pediatric enzyme expression data and found that pharmacogenes with dynamic childhood expression, such as CYP2C18 and CYP27B1, are associated with pediatric ADEs.

CONCLUSIONS

We curated KidSIDES, a database of pediatric drug safety signals, for the research community and developed the Pediatric Drug Safety portal (PDSportal) to facilitate evaluation of drug safety signals across childhood growth and development.

FUNDING

This study was supported by grants from the National Institutes of Health (NIH).

Deep learning on time series laboratory test results from electronic health records for early detection of pancreatic cancer

The multi-modal and unstructured nature of observational data in Electronic Health Records (EHR) is currently a significant obstacle for the application of machine learning towards risk stratification. In this study, we develop a deep learning framework for incorporating longitudinal clinical data from EHR to infer risk for pancreatic cancer (PC). This framework includes a novel training protocol, which enforces an emphasis on early detection by applying an independent Poisson-random mask on proximal-time measurements for each variable. Data fusion for irregular multivariate time-series features is enabled by a "grouped" neural network (GrpNN) architecture, which uses representation learning to generate a dimensionally reduced vector for each measurement set before making a final prediction. These models were evaluated using EHR data from Columbia University Irving Medical Center-New York Presbyterian Hospital. Our framework demonstrated better performance on early detection (AUROC 0.671, CI 95% 0.667 - 0.675, p < 0.001) at 12 months prior to diagnosis compared to a logistic regression, xgboost, and a feedforward neural network baseline. We demonstrate that our masking strategy results greater improvements at distal times prior to diagnosis, and that our GrpNN model improves generalizability by reducing overfitting relative to the feedforward baseline. The results were consistent across reported race. Our proposed algorithm is potentially generalizable to other diseases including but not limited to cancer where early detection can improve survival.

Snapshots of nascent RNA reveal cell- and stimulus-specific responses to acute kidney injury

The current strategy to detect acute injury of kidney tubular cells relies on changes in serum levels of creatinine. Yet serum creatinine (sCr) is a marker of both functional and pathological processes and does not adequately assay tubular injury. In addition, sCr may require days to reach diagnostic thresholds, yet tubular cells respond with programs of damage and repair within minutes or hours. To detect acute responses to clinically relevant stimuli, we created mice expressing Rosa26-floxed-stop uracil phosphoribosyltransferase (Uprt) and inoculated 4-thiouracil (4-TU) to tag nascent RNA at selected time points. Cre-driven 4-TU-tagged RNA was isolated from intact kidneys and demonstrated that volume depletion and ischemia induced different genetic programs in collecting ducts and intercalated cells. Even lineage-related cell types expressed different genes in response to the 2 stressors. TU tagging also demonstrated the transient nature of the responses. Because we placed Uprt in the ubiquitously active Rosa26 locus, nascent RNAs from many cell types can be tagged in vivo and their roles interrogated under various conditions. In short, 4-TU labeling identifies stimulus-specific, cell-specific, and time-dependent acute responses that are otherwise difficult to detect with other technologies and are entirely obscured when sCr is the sole metric of kidney damage.

System-wide transcriptome damage and tissue identity loss in COVID-19 patients

The molecular mechanisms underlying the clinical manifestations of coronavirus disease 2019 (COVID-19), and what distinguishes them from common seasonal influenza virus and other lung injury states such as acute respiratory distress syndrome, remain poorly understood. To address these challenges, we combine transcriptional profiling of 646 clinical nasopharyngeal swabs and 39 patient autopsy tissues to define body-wide transcriptome changes in response to COVID-19. We then match these data with spatial protein and expression profiling across 357 tissue sections from 16 representative patient lung samples and identify tissue-compartment-specific damage wrought by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, evident as a function of varying viral loads during the clinical course of infection and tissue-type-specific expression states. Overall, our findings reveal a systemic disruption of canonical cellular and transcriptional pathways across all tissues, which can inform subsequent studies to combat the mortality of COVID-19 and to better understand the molecular dynamics of lethal SARS-CoV-2 and other respiratory infections.

Characterizing shared and distinct symptom clusters in common chronic conditions through natural language processing of nursing notes

Data-driven characterization of symptom clusters in chronic conditions is essential for shared cluster detection and physiological mechanism discovery. This study aims to computationally describe symptom documentation from electronic nursing notes and compare symptom clusters among patients diagnosed with four chronic conditions-chronic obstructive pulmonary disease (COPD), heart failure, type 2 diabetes mellitus, and cancer. Nursing notes (N = 504,395; 133,977 patients) were obtained for the 2016 calendar year from a single medical center. We used NimbleMiner, a natural language processing application, to identify the presence of 56 symptoms. We calculated symptom documentation prevalence by note and patient for the corpus. Then, we visually compared documentation for a subset of patients (N = 22,657) diagnosed with COPD (n = 3339), heart failure (n = 6587), diabetes (n = 12,139), and cancer (n = 7269) and conducted multiple correspondence analysis and hierarchical clustering to discover underlying groups of patients who have similar symptom profiles (i.e., symptom clusters) for each condition. As expected, pain was the most frequently documented symptom. All conditions had a group of patients characterized by no symptoms. Shared clusters included cardiovascular symptoms for heart failure and diabetes; pain and other symptoms for COPD, diabetes, and cancer; and a newly-identified cognitive and neurological symptom cluster for heart failure, diabetes, and cancer. Cancer (gastrointestinal symptoms and fatigue) and COPD (mental health symptoms) each contained a unique cluster. In summary, we report both shared and distinct, as well as established and novel, symptom clusters across chronic conditions. Findings support the use of electronic health record-derived notes and NLP methods to study symptoms and symptom clusters to advance symptom science.

Pediatric data from the All of Us research program: demonstration of pediatric obesity over time

OBJECTIVE

To describe and demonstrate use of pediatric data collected by the All of Us Research Program.

MATERIALS AND METHODS

All of Us participant physical measurements and electronic health record (EHR) data were analyzed including investigation of trends in childhood obesity and correlation with adult body mass index (BMI).

RESULTS

We identified 19 729 participants with legacy pediatric EHR data including diagnoses, prescriptions, visits, procedures, and measurements gathered since 1980. We found an increase in pediatric obesity diagnosis over time that correlates with BMI measurements recorded in participants' adult EHRs and those physical measurements taken at enrollment in the research program.

DISCUSSION

We highlight the availability of retrospective pediatric EHR data for nearly 20 000 All of Us participants. These data are relevant to current issues such as the rise in pediatric obesity.

CONCLUSION

All of Us contains a rich resource of retrospective pediatric EHR data to accelerate pediatric research studies.

Predictions, Pivots, and a Pandemic: a Review of 2020's Top Translational Bioinformatics Publications

OBJECTIVES

Provide an overview of the emerging themes and notable papers which were published in 2020 in the field of Bioinformatics and Translational Informatics (BTI) for the International Medical Informatics Association Yearbook.

METHODS

A team of 16 individuals scanned the literature from the past year. Using a scoring rubric, papers were evaluated on their novelty, importance, and objective quality. 1,224 Medical Subject Headings (MeSH) terms extracted from these papers were used to identify themes and research focuses. The authors then used the scoring results to select notable papers and trends presented in this manuscript.

RESULTS

The search phase identified 263 potential papers and central themes of coronavirus disease 2019 (COVID-19), machine learning, and bioinformatics were examined in greater detail.

CONCLUSIONS

When addressing a once in a centruy pandemic, scientists worldwide answered the call, with informaticians playing a critical role. Productivity and innovations reached new heights in both TBI and science, but significant research gaps remain.

Evaluating risk detection methods to uncover ontogenic-mediated adverse drug effect mechanisms in children

BACKGROUND

Identifying adverse drugs effects (ADEs) in children, overall and within pediatric age groups, is essential for preventing disability and death from marketed drugs. At the same time, however, detection is challenging due to dynamic biological processes during growth and maturation, called ontogeny, that alter pharmacokinetics and pharmacodynamics. As a result, methodologies in pediatric drug safety have been limited to event surveillance and have not focused on investigating adverse event mechanisms. There is an opportunity to identify drug event patterns within observational databases for evaluating ontogenic-mediated adverse event mechanisms. The first step of which is to establish statistical models that can identify temporal trends of adverse effects across childhood.

RESULTS

Using simulation, we evaluated a population stratification method (the proportional reporting ratio or PRR) and a population modeling method (the generalized additive model or GAM) to identify and quantify ADE risk at varying reporting rates and dynamics. We found that GAMs showed improved performance over the PRR in detecting dynamic drug event reporting across child development stages. Moreover, GAMs exhibited normally distributed and robust ADE risk estimation at all development stages by sharing information across child development stages.

CONCLUSIONS

Our study underscores the opportunity for using population modeling techniques, which leverage drug event reporting across development stages, as biologically-inspired detection methods for evaluating ontogenic mechanisms.

Plasma kallikrein predicts primary graft dysfunction after heart transplant

BACKGROUND

Primary graft dysfunction (PGD) is the leading cause of early mortality after heart transplant. Pre-transplant predictors of PGD remain elusive and its etiology remains unclear.

METHODS

Microvesicles were isolated from 88 pre-transplant serum samples and underwent proteomic evaluation using TMT mass spectrometry. Monte Carlo cross validation (MCCV) was used to predict the occurrence of severe PGD after transplant using recipient pre-transplant clinical characteristics and serum microvesicle proteomic data. Putative biological functions and pathways were assessed using gene set enrichment analysis (GSEA) within the MCCV prediction methodology.

RESULTS

Using our MCCV prediction methodology, decreased levels of plasma kallikrein (KLKB1), a critical regulator of the kinin-kallikrein system, was the most predictive factor identified for PGD (AUROC 0.6444 [0.6293, 0.6655]; odds 0.1959 [0.0592, 0.3663]. Furthermore, a predictive panel combining KLKB1 with inotrope therapy achieved peak performance (AUROC 0.7181 [0.7020, 0.7372]) across and within (AUROCs of 0.66-0.78) each cohort. A classifier utilizing KLKB1 and inotrope therapy outperforms existing composite scores by more than 50 percent. The diagnostic utility of the classifier was validated on 65 consecutive transplant patients, resulting in an AUROC of 0.71 and a negative predictive value of 0.92-0.96. Differential expression analysis revealed a enrichment in inflammatory and immune pathways prior to PGD.

CONCLUSIONS

Pre-transplant level of KLKB1 is a robust predictor of post-transplant PGD. The combination with pre-transplant inotrope therapy enhances the prediction of PGD compared to pre-transplant KLKB1 levels alone and the resulting classifier equation validates within a prospective validation cohort. Inflammation and immune pathway enrichment characterize the pre-transplant proteomic signature predictive of PGD.

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.

Identifying Symptom Information in Clinical Notes Using Natural Language Processing

BACKGROUND

Symptoms are a core concept of nursing interest. Large-scale secondary data reuse of notes in electronic health records (EHRs) has the potential to increase the quantity and quality of symptom research. However, the symptom language used in clinical notes is complex. A need exists for methods designed specifically to identify and study symptom information from EHR notes.

OBJECTIVES

We aim to describe a method that combines standardized vocabularies, clinical expertise, and natural language processing to generate comprehensive symptom vocabularies and identify symptom information in EHR notes. We piloted this method with five diverse symptom concepts: constipation, depressed mood, disturbed sleep, fatigue, and palpitations.

METHODS

First, we obtained synonym lists for each pilot symptom concept from the Unified Medical Language System. Then, we used two large bodies of text (clinical notes from Columbia University Irving Medical Center and PubMed abstracts containing Medical Subject Headings or key words related to the pilot symptoms) to further expand our initial vocabulary of synonyms for each pilot symptom concept. We used NimbleMiner, an open-source natural language processing tool, to accomplish these tasks and evaluated NimbleMiner symptom identification performance by comparison to a manually annotated set of nurse- and physician-authored common EHR note types.

RESULTS

Compared to the baseline Unified Medical Language System synonym lists, we identified up to 11 times more additional synonym words or expressions, including abbreviations, misspellings, and unique multiword combinations, for each symptom concept. Natural language processing system symptom identification performance was excellent.

DISCUSSION

Using our comprehensive symptom vocabularies and NimbleMiner to label symptoms in clinical notes produced excellent performance metrics. The ability to extract symptom information from EHR notes in an accurate and scalable manner has the potential to greatly facilitate symptom science research.

Medical records-based chronic kidney disease phenotype for clinical care and "big data" observational and genetic studies

Chronic Kidney Disease (CKD) represents a slowly progressive disorder that is typically silent until late stages, but early intervention can significantly delay its progression. We designed a portable and scalable electronic CKD phenotype to facilitate early disease recognition and empower large-scale observational and genetic studies of kidney traits. The algorithm uses a combination of rule-based and machine-learning methods to automatically place patients on the staging grid of albuminuria by glomerular filtration rate ("A-by-G" grid). We manually validated the algorithm by 451 chart reviews across three medical systems, demonstrating overall positive predictive value of 95% for CKD cases and 97% for healthy controls. Independent case-control validation using 2350 patient records demonstrated diagnostic specificity of 97% and sensitivity of 87%. Application of the phenotype to 1.3 million patients demonstrated that over 80% of CKD cases are undetected using ICD codes alone. We also demonstrated several large-scale applications of the phenotype, including identifying stage-specific kidney disease comorbidities, in silico estimation of kidney trait heritability in thousands of pedigrees reconstructed from medical records, and biobank-based multicenter genome-wide and phenome-wide association studies.

No population left behind: Improving paediatric drug safety using informatics and systems biology

Adverse drugs effects (ADEs) in children are common and may result in disability and death. The current paediatric drug safety landscape, including clinical trials, is limited as it rarely includes children and relies on extrapolation from adults. Children are not small adults but go through an evolutionarily conserved and physiologically dynamic process of growth and maturation. Novel quantitative approaches, integrating observations from clinical trials and drug safety databases with dynamic mechanisms, can be used to systematically identify ADEs unique to childhood. In this perspective, we discuss three critical research directions using systems biology methodologies and novel informatics to improve paediatric drug safety, namely child versus adult drug safety profiles, age-dependent drug toxicities and genetic susceptibility of ADEs across childhood. We argue that a data-driven framework that leverages observational data, biomedical knowledge and systems biology modelling will reveal previously unknown mechanisms of pediatric adverse drug events and lead to improved paediatric drug safety.

Comparative analysis, applications, and interpretation of electronic health record-based stroke phenotyping methods

BACKGROUND

Accurate identification of acute ischemic stroke (AIS) patient cohorts is essential for a wide range of clinical investigations. Automated phenotyping methods that leverage electronic health records (EHRs) represent a fundamentally new approach cohort identification without current laborious and ungeneralizable generation of phenotyping algorithms. We systematically compared and evaluated the ability of machine learning algorithms and case-control combinations to phenotype acute ischemic stroke patients using data from an EHR.

MATERIALS AND METHODS

Using structured patient data from the EHR at a tertiary-care hospital system, we built and evaluated machine learning models to identify patients with AIS based on 75 different case-control and classifier combinations. We then estimated the prevalence of AIS patients across the EHR. Finally, we externally validated the ability of the models to detect AIS patients without AIS diagnosis codes using the UK Biobank.

RESULTS

Across all models, we found that the mean AUROC for detecting AIS was 0.963 ± 0.0520 and average precision score 0.790 ± 0.196 with minimal feature processing. Classifiers trained with cases with AIS diagnosis codes and controls with no cerebrovascular disease codes had the best average F1 score (0.832 ± 0.0383). In the external validation, we found that the top probabilities from a model-predicted AIS cohort were significantly enriched for AIS patients without AIS diagnosis codes (60-150 fold over expected).

CONCLUSIONS

Our findings support machine learning algorithms as a generalizable way to accurately identify AIS patients without using process-intensive manual feature curation. When a set of AIS patients is unavailable, diagnosis codes may be used to train classifier models.

Association of Neighborhood Deprivation Index With Success in Cancer Care Crowdfunding

Importance

Financial toxicity resulting from cancer care poses a substantial public health concern, leading some patients to turn to online crowdfunding. However, the practice may exacerbate existing socioeconomic cancer disparities by privileging those with access to interpersonal wealth and digital media literacy.

Objective

To test the hypotheses that higher county-level socioeconomic status and the presence (vs absence) of text indicators of beneficiary worth in campaign descriptions are associated with amount raised from cancer crowdfunding.

Design, Setting, and Participants

This cross-sectional analysis examined US cancer crowdfunding campaigns conducted between 2010 and 2019 and data from the American Community Survey (2013-2017). Data analysis was performed from December 2019 to March 2020.

Exposures

Neighborhood deprivation index of campaign location and campaign text features indicating the beneficiary's worth.

Main Outcomes and Measures

Amount of money raised.

Results

This study analyzed 144 061 US cancer crowdfunding campaigns. Campaigns in counties with higher neighborhood deprivation raised less (-26.07%; 95% CI, -27.46% to -24.65%; P < .001) than those in counties with less neighborhood deprivation. Campaigns raised more funds when legitimizing details were provided, including clinical details about the cancer type (9.58%; 95% CI, 8.00% to 11.18%; P < .001) and treatment type (6.58%; 95% CI, 5.44% to 7.79%; P < .001) and financial details, such as insurance status (1.39%; 95% CI, 0.20% to 2.63%; P = .02) and out-of-pocket costs (7.36%; 95% CI, 6.18% to 8.55%; P < .001). Campaigns raised more money when beneficiaries were described as warm (13.80%; 95% CI, 12.30% to 15.26%; P < .001), brave (15.40%; 95% CI, 14.11% to 16.65%; P < .001), or self-reliant (5.23%; 95% CI, 3.77% to 6.72%; P < .001).

Conclusions and Relevance

These findings suggest that cancer crowdfunding success ay disproportionately benefit those in high-socioeconomic status areas and those with the internet literacy necessary to portray beneficiaries as worthy. By rewarding those with existing socioeconomic advantage, cancer crowdfunding may perpetuate socioeconomic disparities in cancer care access. The findings also underscore the widespread nature of financial toxicity resulting from cancer care.

Where Have All the Emergencies Gone? The Impact of the COVID-19 Pandemic on Obstetric and Gynecologic Procedures and Consults at a New York City Hospital

Study Objective

The purpose of this study was to assess the impact of the coronavirus disease 2019 (COVID-19) pandemic on surgical volume and emergency department (ED) consults across obstetrics-gynecology (OB-GYN) services at a New York City hospital.

Design

Retrospective cohort study.

Setting

Tertiary care academic medical center in New York City.

Patients

Women undergoing OB-GYN ED consults or surgeries between February 1, 2020 and April 15, 2020.

Interventions

March 16 institutional moratorium on elective surgeries.

Measurements and Main Results

The volume and types of surgeries and ED consults were compared before and after the COVID-19 moratorium. During the pandemic, the average weekly volume of ED consults and gynecology (GYN) surgeries decreased, whereas obstetric (OB) surgeries remained stable. The proportions of OB-GYN ED consults, GYN surgeries, and OB surgeries relative to all ED consults, all surgeries, and all labor and delivery patients were 1.87%, 13.8%, 54.6% in the pre–COVID-19 time frame (February 1–March 15) vs 1.53%, 21.3%, 79.7% in the COVID-19 time frame (March 16–April 15), representing no significant difference in proportions of OB-GYN ED consults (p = .464) and GYN surgeries (p = .310) before and during COVID-19, with a proportionate increase in OB surgeries (p <.002). The distribution of GYN surgical case types changed significantly during the pandemic with higher proportions of emergent surgeries for ectopic pregnancies, miscarriages, and concern for cancer (p <.001). Alternatively, the OB surgery distribution of case types remained relatively constant.

Conclusion

This study highlights how the pandemic has affected the ways that patients in OB-GYN access and receive care. Institutional policies suspending elective surgeries during the pandemic decreased GYN surgical volume and affected the types of cases performed. This decrease was not appreciated for OB surgical volume, reflecting the nonelective and time-sensitive nature of obstetric care. A decrease in ED consults was noted during the pandemic begging the question “Where have all the emergencies gone?” Although the moratorium on elective procedures was necessary, “elective” GYN surgeries remain medically indicated to address symptoms such as pain and bleeding and to prevent serious medical sequelae such as severe anemia requiring transfusion. As we continue to battle COVID-19, we must not lose sight of those patients whose care has been deferred.

Associations between blood type and COVID-19 infection, intubation, and death

The rapid global spread of the novel coronavirus SARS-CoV-2 has strained healthcare and testing resources, making the identification and prioritization of individuals most at-risk a critical challenge. Recent evidence suggests blood type may affect risk of severe COVID-19. Here, we use observational healthcare data on 14,112 individuals tested for SARS-CoV-2 with known blood type in the New York Presbyterian (NYP) hospital system to assess the association between ABO and Rh blood types and infection, intubation, and death. We find slightly increased infection prevalence among non-O types. Risk of intubation was decreased among A and increased among AB and B types, compared with type O, while risk of death was increased for type AB and decreased for types A and B. We estimate Rh-negative blood type to have a protective effect for all three outcomes. Our results add to the growing body of evidence suggesting blood type may play a role in COVID-19.

Recent evidence has suggested that blood type may be associated with severe COVID-19. Here, the authors use data from ~14,000 individuals tested for SARS-CoV-2 at a New York City hospital, and find that certain ABO and Rh blood types are associated with infection, intubation, and death.

Using Machine Learning to Identify Adverse Drug Effects Posing Increased Risk to Women

Adverse drug reactions are the fourth leading cause of death in the US. Although women take longer to metabolize medications and experience twice the risk of developing adverse reactions compared with men, these sex differences are not comprehensively understood. Real-world clinical data provide an opportunity to estimate safety effects in otherwise understudied populations, i.e., women. These data, however, are subject to confounding biases and correlated covariates. We present AwareDX, a pharmacovigilance algorithm that leverages advances in machine learning to predict sex risks. Our algorithm mitigates these biases and quantifies the differential risk of a drug causing an adverse event in either men or women. AwareDX demonstrates high precision during validation against clinical literature and pharmacogenetic mechanisms. We present a resource of 20,817 adverse drug effects posing sex-specific risks. AwareDX, and this resource, present an opportunity to minimize adverse events by tailoring drug prescription and dosage to sex.

Immune complement and coagulation dysfunction in adverse outcomes of SARS-CoV-2 infection

Understanding the pathophysiology of SARS-CoV-2 infection is critical for therapeutic and public health strategies. Viral-host interactions can guide discovery of disease regulators, and protein structure function analysis points to several immune pathways, including complement and coagulation, as targets of coronaviruses. To determine whether conditions associated with dysregulated complement or coagulation systems impact disease, we performed a retrospective observational study and found that history of macular degeneration (a proxy for complement-activation disorders) and history of coagulation disorders (thrombocytopenia, thrombosis and hemorrhage) are risk factors for SARS-CoV-2-associated morbidity and mortality-effects that are independent of age, sex or history of smoking. Transcriptional profiling of nasopharyngeal swabs demonstrated that in addition to type-I interferon and interleukin-6-dependent inflammatory responses, infection results in robust engagement of the complement and coagulation pathways. Finally, in a candidate-driven genetic association study of severe SARS-CoV-2 disease, we identified putative complement and coagulation-associated loci including missense, eQTL and sQTL variants of critical complement and coagulation regulators. In addition to providing evidence that complement function modulates SARS-CoV-2 infection outcome, the data point to putative transcriptional genetic markers of susceptibility. The results highlight the value of using a multimodal analytical approach to reveal determinants and predictors of immunity, susceptibility and clinical outcome associated with infection.

Testing the association between blood type and COVID-19 infection, intubation, and death

The rapid global spread of the novel coronavirus SARS-CoV-2 has strained healthcare and testing resources, making the identification and prioritization of individuals most at-risk a critical challenge. Recent evidence suggests blood type may affect risk of severe COVID-19. We used observational healthcare data on 14,112 individuals tested for SARS-CoV-2 with known blood type in the New York Presbyterian (NYP) hospital system to assess the association between ABO and Rh blood types and infection, intubation, and death. We found slightly increased infection prevalence among non-O types. Risk of intubation was decreased among A and increased among AB and B types, compared with type O, while risk of death was increased for type AB and decreased for types A and B. We estimated Rh-negative blood type to have a protective effect for all three outcomes. Our results add to the growing body of evidence suggesting blood type may play a role in COVID-19.

Identification of Immune complement function as a determinant of adverse SARS-CoV-2 infection outcome

Understanding the pathophysiology of SARS-CoV-2 infection is critical for therapeutics and public health intervention strategies. Viral-host interactions can guide discovery of regulators of disease outcomes, and protein structure function analysis points to several immune pathways, including complement and coagulation, as targets of the coronavirus proteome. To determine if conditions associated with dysregulation of the complement or coagulation systems impact adverse clinical outcomes, we performed a retrospective observational study of 11,116 patients who presented with suspected SARS-CoV-2 infection. We found that history of macular degeneration (a proxy for complement activation disorders) and history of coagulation disorders (thrombocytopenia, thrombosis, and hemorrhage) are risk factors for morbidity and mortality in SARS-CoV-2 infected patients - effects that could not be explained by age, sex, or history of smoking. Further, transcriptional profiling of nasopharyngeal (NP) swabs from 650 control and SARS-CoV-2 infected patients demonstrated that in addition to innate Type-I interferon and IL-6 dependent inflammatory immune responses, infection results in robust engagement and activation of the complement and coagulation pathways. Finally, we conducted a candidate driven genetic association study of severe SARS-CoV-2 disease. Among the findings, our scan identified putative complement and coagulation associated loci including missense, eQTL and sQTL variants of critical regulators of the complement and coagulation cascades. In addition to providing evidence that complement function modulates SARS-CoV-2 infection outcome, the data point to putative transcriptional genetic markers of susceptibility. The results highlight the value of using a multi-modal analytical approach, combining molecular information from virus protein structure-function analysis with clinical informatics, transcriptomics, and genomics to reveal determinants and predictors of immunity, susceptibility, and clinical outcome associated with infection.

Predicting Phenotypic Polymyxin Resistance in Klebsiella pneumoniae through Machine Learning Analysis of Genomic Data

Polymyxins are used as treatments of last resort for Gram-negative bacterial infections. Their increased use has led to concerns about emerging polymyxin resistance (PR). Phenotypic polymyxin susceptibility testing is resource intensive and difficult to perform accurately. The complex polygenic nature of PR and our incomplete understanding of its genetic basis make it difficult to predict PR using detection of resistance determinants. We therefore applied machine learning (ML) to whole-genome sequencing data from >600 Klebsiella pneumoniae clonal group 258 (CG258) genomes to predict phenotypic PR. Using a reference-based representation of genomic data with ML outperformed a rule-based approach that detected variants in known PR genes (area under receiver-operator curve [AUROC], 0.894 versus 0.791, P = 0.006). We noted modest increases in performance by using a bacterial genome-wide association study to filter relevant genomic features and by integrating clinical data in the form of prior polymyxin exposure. Conversely, reference-free representation of genomic data as k-mers was associated with decreased performance (AUROC, 0.692 versus 0.894, P = 0.015). When ML models were interpreted to extract genomic features, six of seven known PR genes were correctly identified by models without prior programming and several genes involved in stress responses and maintenance of the cell membrane were identified as potential novel determinants of PR. These findings are a proof of concept that whole-genome sequencing data can accurately predict PR in K. pneumoniae CG258 and may be applicable to other forms of complex antimicrobial resistance.IMPORTANCE Polymyxins are last-resort antibiotics used to treat highly resistant Gram-negative bacteria. There are increasing reports of polymyxin resistance emerging, raising concerns of a postantibiotic era. Polymyxin resistance is therefore a significant public health threat, but current phenotypic methods for detection are difficult and time-consuming to perform. There have been increasing efforts to use whole-genome sequencing for detection of antibiotic resistance, but this has been difficult to apply to polymyxin resistance because of its complex polygenic nature. The significance of our research is that we successfully applied machine learning methods to predict polymyxin resistance in Klebsiella pneumoniae clonal group 258, a common health care-associated and multidrug-resistant pathogen. Our findings highlight that machine learning can be successfully applied even in complex forms of antibiotic resistance and represent a significant contribution to the literature that could be used to predict resistance in other bacteria and to other antibiotics.

No Increased Risk of Colorectal Adenomas in Spouses of Patients with Colorectal Neoplasia

Although genetic factors such as family history have been associated with increased risk of developing colorectal cancer (CRC), multiple lifestyle and environmental risk factors for CRC have been identified, including smoking, diet, obesity, and physical activity.1,2 Although couples typically have different genetic backgrounds, spouses are likely to share lifestyle and environmental exposures over the course of years, including similar home environments, geographical locations of residence, dietary exposures, and smoking exposures.3 As such, one might expect that an increased CRC incidence would be seen among spouses of patients with CRC; however, studies on this topic have inconsistent results.3-6 By using a large cohort of spouses who have undergone colonoscopy, we aimed to determine whether the risk of colorectal adenomas is increased among spouses of those with colorectal neoplasia (CRN) on colonoscopy.

PatientExploreR: an extensible application for dynamic visualization of patient clinical history from electronic health records in the OMOP common data model

MOTIVATION

Electronic health records (EHRs) are quickly becoming omnipresent in healthcare, but interoperability issues and technical demands limit their use for biomedical and clinical research. Interactive and flexible software that interfaces directly with EHR data structured around a common data model (CDM) could accelerate more EHR-based research by making the data more accessible to researchers who lack computational expertise and/or domain knowledge.

RESULTS

We present PatientExploreR, an extensible application built on the R/Shiny framework that interfaces with a relational database of EHR data in the Observational Medical Outcomes Partnership CDM format. PatientExploreR produces patient-level interactive and dynamic reports and facilitates visualization of clinical data without any programming required. It allows researchers to easily construct and export patient cohorts from the EHR for analysis with other software. This application could enable easier exploration of patient-level data for physicians and researchers. PatientExploreR can incorporate EHR data from any institution that employs the CDM for users with approved access. The software code is free and open source under the MIT license, enabling institutions to install and users to expand and modify the application for their own purposes.

AVAILABILITY AND IMPLEMENTATION

PatientExploreR can be freely obtained from GitHub: https://github.com/BenGlicksberg/PatientExploreR. We provide instructions for how researchers with approved access to their institutional EHR can use this package. We also release an open sandbox server of synthesized patient data for users without EHR access to explore: http://patientexplorer.ucsf.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Pathway analysis of genomic pathology tests for prognostic cancer subtyping

Genomic test results collected during the provision of medical care and stored in Electronic Health Record (EHR) systems represent an opportunity for clinical research into disease heterogeneity and clinical outcomes. In this paper, we evaluate the use of genomic test reports ordered for cancer patients in order to derive cancer subtypes and to identify biological pathways predictive of poor survival outcomes. A novel method is proposed to calculate patient similarity based on affected biological pathways rather than gene mutations. We demonstrate that this approach identifies subtypes of prognostic value and biological pathways linked to survival, with implications for precision treatment selection and a better understanding of the underlying disease. We also share lessons learned regarding the opportunities and challenges of secondary use of observational genomic data to conduct such research.

Molecular nephrology: types of acute tubular injury

The acute loss of kidney function has been diagnosed for many decades using the serum concentration of creatinine - a muscle metabolite that is an insensitive and non-specific marker of kidney function, but is now used for the very definition of acute kidney injury (AKI). Fortunately, myriad new tools have now been developed to better understand the relationship between acute tubular injury and elevation in serum creatinine (SCr). These tools include unbiased gene and protein expression analyses in kidney, urine and blood, the localization of specific gene transcripts in pathological biopsy samples by rapid in-situ RNA technology and single-cell RNA-sequencing analyses. However, this molecular approach to AKI has produced a series of unexpected problems, because the expression of specific kidney-derived molecules that are indicative of injury often do not correlate with SCr levels. This discrepancy between kidney injury markers and SCr level can be reconciled by the recognition that many separate subtypes of AKI exist, each with distinct patterning of molecular markers of tubular injury and SCr data. In this Review, we describe the weaknesses of isolated SCr-based diagnoses, the clinical and molecular subtyping of acute tubular injury, and the role of non-invasive biomarkers in clinical phenotyping. We propose a conceptual model that synthesizes molecular and physiological data along a time course spanning from acute cellular injury to organ failure.

Translational medicine in the Age of Big Data

The ability to collect, store and analyze massive amounts of molecular and clinical data is fundamentally transforming the scientific method and its application in translational medicine. Collecting observations has always been a prerequisite for discovery, and great leaps in scientific understanding are accompanied by an expansion of this ability. Particle physics, astronomy and climate science, for example, have all greatly benefited from the development of new technologies enabling the collection of larger and more diverse data. Unlike medicine, however, each of these fields also has a mature theoretical framework on which new data can be evaluated and incorporated-to say it another way, there are no 'first principals' from which a healthy human could be analytically derived. The worry, and it is a valid concern, is that, without a strong theoretical underpinning, the inundation of data will cause medical research to devolve into a haphazard enterprise without discipline or rigor. The Age of Big Data harbors tremendous opportunity for biomedical advances, but will also be treacherous and demanding on future scientists.

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.

Challenges with quality of race and ethnicity data in observational databases

OBJECTIVE

We sought to assess the quality of race and ethnicity information in observational health databases, including electronic health records (EHRs), and to propose patient self-recording as an improvement strategy.

MATERIALS AND METHODS

We assessed completeness of race and ethnicity information in large observational health databases in the United States (Healthcare Cost and Utilization Project and Optum Labs), and at a single healthcare system in New York City serving a racially and ethnically diverse population. We compared race and ethnicity data collected via administrative processes with data recorded directly by respondents via paper surveys (National Health and Nutrition Examination Survey and Hospital Consumer Assessment of Healthcare Providers and Systems). Respondent-recorded data were considered the gold standard for the collection of race and ethnicity information.

RESULTS

Among the 160 million patients from the Healthcare Cost and Utilization Project and Optum Labs datasets, race or ethnicity was unknown for 25%. Among the 2.4 million patients in the single New York City healthcare system's EHR, race or ethnicity was unknown for 57%. However, when patients directly recorded their race and ethnicity, 86% provided clinically meaningful information, and 66% of patients reported information that was discrepant with the EHR.

DISCUSSION

Race and ethnicity data are critical to support precision medicine initiatives and to determine healthcare disparities; however, the quality of this information in observational databases is concerning. Patient self-recording through the use of patient-facing tools can substantially increase the quality of the information while engaging patients in their health.

CONCLUSIONS

Patient self-recording may improve the completeness of race and ethnicity information.

Informatics and Computational Methods in Natural Product Drug Discovery: A Review and Perspectives

The discovery of new pharmaceutical drugs is one of the preeminent tasks-scientifically, economically, and socially-in biomedical research. Advances in informatics and computational biology have increased productivity at many stages of the drug discovery pipeline. Nevertheless, drug discovery has slowed, largely due to the reliance on small molecules as the primary source of novel hypotheses. Natural products (such as plant metabolites, animal toxins, and immunological components) comprise a vast and diverse source of bioactive compounds, some of which are supported by thousands of years of traditional medicine, and are largely disjoint from the set of small molecules used commonly for discovery. However, natural products possess unique characteristics that distinguish them from traditional small molecule drug candidates, requiring new methods and approaches for assessing their therapeutic potential. In this review, we investigate a number of state-of-the-art techniques in bioinformatics, cheminformatics, and knowledge engineering for data-driven drug discovery from natural products. We focus on methods that aim to bridge the gap between traditional small-molecule drug candidates and different classes of natural products. We also explore the current informatics knowledge gaps and other barriers that need to be overcome to fully leverage these compounds for drug discovery. Finally, we conclude with a "road map" of research priorities that seeks to realize this goal.

The Next Generation of Drug Safety Science: Coupling Detection, Corroboration, and Validation to Discover Novel Drug Effects and Drug-Drug Interactions

Rare adverse drug reactions and drug-drug interactions (DDIs) are difficult to detect in randomized trials and impossible to prove using observational studies. We must ascribe to a new way of conducting research that has the efficiency of a retrospective analysis and the rigor of a prospective trial. This can be achieved by integrating observational data from humans with laboratory experiments in model systems. The former establishes clinical significance and the latter supports causality.

ROMOP: a light-weight R package for interfacing with OMOP-formatted electronic health record data

OBJECTIVES

Electronic health record (EHR) data are increasingly used for biomedical discoveries. The nature of the data, however, requires expertise in both data science and EHR structure. The Observational Medical Out-comes Partnership (OMOP) common data model (CDM) standardizes the language and structure of EHR data to promote interoperability of EHR data for research. While the OMOP CDM is valuable and more attuned to research purposes, it still requires extensive domain knowledge to utilize effectively, potentially limiting more widespread adoption of EHR data for research and quality improvement.

MATERIALS AND METHODS

We have created ROMOP: an R package for direct interfacing with EHR data in the OMOP CDM format.

RESULTS

ROMOP streamlines typical EHR-related data processes. Its functions include exploration of data types, extraction and summarization of patient clinical and demographic data, and patient searches using any CDM vocabulary concept.

CONCLUSION

ROMOP is freely available under the Massachusetts Institute of Technology (MIT) license and can be obtained from GitHub (http://github.com/BenGlicksberg/ROMOP). We detail instructions for setup and use in the Supplementary Materials. Additionally, we provide a public sandbox server containing synthesized clinical data for users to explore OMOP data and ROMOP (http://romop.ucsf.edu).

Low Screening Rates for Diabetes Mellitus Among Family Members of Affected Relatives

Cardiovascular disease is the leading cause of death in the United States, and abnormal blood glucose is an important risk factor. Delayed diagnosis of diabetes mellitus can increase patients' morbidity. In an urban academic medical center with a large clinical data warehouse, we used a novel algorithm to identify 56,794 family members of diabetic patients that were eligible for disease screening. We found that 30.6% of patients did not receive diabetes screening as recommended by current guidelines. Further, our analysis showed that having more than one family member affected and being a female were important contributors to being screened for diabetes mellitus. This study demonstrates that informatics methods applied to electronic health record data can be used to identify patients at risk for disease development, and therefore support clinical care.

Pathogen population structure can explain hospital outbreaks

Hospitalized patients are at risk for increased length of stay, illness, or death due to hospital acquired infections. The majority of hospital transmission models describe dynamics on the level of the host rather than on the level of the pathogens themselves. Accordingly, epidemiologists often cannot complete transmission chains without direct evidence of either host-host contact or a large reservoir population. Here, we propose an ecology-based model to explain the transmission of pathogens in hospitals. The model is based upon metapopulation biology, which describes a group of interacting localized populations and island biogeography, which provides a basis for how pathogens may be moving between locales. Computational simulation trials are used to assess the applicability of the model. Results indicate that pathogens survive for extended periods without the need for large reservoirs by living in localized ephemeral populations while continuously transmitting pathogens to new seed populations. Computational simulations show small populations spending significant portions of time at sizes too small to be detected by most surveillance protocols and that the number and type of these ephemeral populations enable the overall pathogen population to be sustained. By modeling hospital pathogens as a metapopulation, many observations characteristic of hospital acquired infection outbreaks for which there has previously been no sufficient biological explanation, including how and why empirically successful interventions work, can now be accounted for using population dynamic hypotheses. Epidemiological links between temporally isolated outbreaks are explained via pathogen population dynamics and potential outbreak intervention targets are identified.

Columbia Open Health Data, clinical concept prevalence and co-occurrence from electronic health records

Columbia Open Health Data (COHD) is a publicly accessible database of electronic health record (EHR) prevalence and co-occurrence frequencies between conditions, drugs, procedures, and demographics. COHD was derived from Columbia University Irving Medical Center's Observational Health Data Sciences and Informatics (OHDSI) database. The lifetime dataset, derived from all records, contains 36,578 single concepts (11,952 conditions, 12,334 drugs, and 10,816 procedures) and 32,788,901 concept pairs from 5,364,781 patients. The 5-year dataset, derived from records from 2013-2017, contains 29,964 single concepts (10,159 conditions, 10,264 drugs, and 8,270 procedures) and 15,927,195 concept pairs from 1,790,431 patients. Exclusion of rare concepts (count ≤ 10) and Poisson randomization enable data sharing by eliminating risks to patient privacy. EHR prevalences are informative of healthcare consumption rates. Analysis of co-occurrence frequencies via relative frequency analysis and observed-expected frequency ratio are informative of associations between clinical concepts, useful for biomedical research tasks such as drug repurposing and pharmacovigilance. COHD is publicly accessible through a web application-programming interface (API) and downloadable from the Figshare repository. The code is available on GitHub.

Structural and functional cardiac profile after prolonged duration of mechanical unloading: potential implications for myocardial recovery

Clinical and experimental studies have suggested that the duration of left ventricular assist device (LVAD) support may affect remodeling of the failing heart. We aimed to 1) characterize the changes in Ca2+/calmodulin-dependent protein kinase type-IIδ (CaMKIIδ), growth signaling, structural proteins, fibrosis, apoptosis, and gene expression before and after LVAD support and 2) assess whether the duration of support correlated with improvement or worsening of reverse remodeling. Left ventricular apex tissue and serum pairs were collected in patients with dilated cardiomyopathy ( n = 25, 23 men and 2 women) at LVAD implantation and after LVAD support at cardiac transplantation/LVAD explantation. Normal cardiac tissue was obtained from healthy hearts ( n = 4) and normal serum from age-matched control hearts ( n = 4). The duration of LVAD support ranged from 48 to 1,170 days (median duration: 270 days). LVAD support was associated with CaMKIIδ activation, increased nuclear myocyte enhancer factor 2, sustained histone deacetylase-4 phosphorylation, increased circulating and cardiac myostatin (MSTN) and MSTN signaling mediated by SMAD2, ongoing structural protein dysregulation and sustained fibrosis and apoptosis (all P < 0.05). Increased CaMKIIδ phosphorylation, nuclear myocyte enhancer factor 2, and cardiac MSTN significantly correlated with the duration of support. Phosphorylation of SMAD2 and apoptosis decreased with a shorter duration of LVAD support but increased with a longer duration of LVAD support. Further study is needed to define the optimal duration of LVAD support in patients with dilated cardiomyopathy. NEW & NOTEWORTHY A long duration of left ventricular assist device support may be detrimental for myocardial recovery, based on myocardial tissue experiments in patients with prolonged support showing significantly worsened activation of Ca2+/calmodulin-dependent protein kinase-IIδ, increased nuclear myocyte enhancer factor 2, increased myostatin and its signaling by SMAD2, and apoptosis as well as sustained histone deacetylase-4 phosphorylation, structural protein dysregulation, and fibrosis.

Pharmacological risk factors associated with hospital readmission rates in a psychiatric cohort identified using prescriptome data mining

BACKGROUND

Worldwide, over 14% of individuals hospitalized for psychiatric reasons have readmissions to hospitals within 30 days after discharge. Predicting patients at risk and leveraging accelerated interventions can reduce the rates of early readmission, a negative clinical outcome (i.e., a treatment failure) that affects the quality of life of patient. To implement individualized interventions, it is necessary to predict those individuals at highest risk for 30-day readmission. In this study, our aim was to conduct a data-driven investigation to find the pharmacological factors influencing 30-day all-cause, intra- and interdepartmental readmissions after an index psychiatric admission, using the compendium of prescription data (prescriptome) from electronic medical records (EMR).

METHODS

The data scientists in the project received a deidentified database from the Mount Sinai Data Warehouse, which was used to perform all analyses. Data was stored in a secured MySQL database, normalized and indexed using a unique hexadecimal identifier associated with the data for psychiatric illness visits. We used Bayesian logistic regression models to evaluate the association of prescription data with 30-day readmission risk. We constructed individual models and compiled results after adjusting for covariates, including drug exposure, age, and gender. We also performed digital comorbidity survey using EMR data combined with the estimation of shared genetic architecture using genomic annotations to disease phenotypes.

RESULTS

Using an automated, data-driven approach, we identified prescription medications, side effects (primary side effects), and drug-drug interaction-induced side effects (secondary side effects) associated with readmission risk in a cohort of 1275 patients using prescriptome analytics. In our study, we identified 28 drugs associated with risk for readmission among psychiatric patients. Based on prescription data, Pravastatin had the highest risk of readmission (OR = 13.10; 95% CI (2.82, 60.8)). We also identified enrichment of primary side effects (n = 4006) and secondary side effects (n = 36) induced by prescription drugs in the subset of readmitted patients (n = 89) compared to the non-readmitted subgroup (n = 1186). Digital comorbidity analyses and shared genetic analyses further reveals that cardiovascular disease and psychiatric conditions are comorbid and share functional gene modules (cardiomyopathy and anxiety disorder: shared genes (n = 37; P = 1.06815E-06)).

CONCLUSIONS

Large scale prescriptome data is now available from EMRs and accessible for analytics that could improve healthcare outcomes. Such analyses could also drive hypothesis and data-driven research. In this study, we explored the utility of prescriptome data to identify factors driving readmission in a psychiatric cohort. Converging digital health data from EMRs and systems biology investigations reveal a subset of patient populations that have significant comorbidities with cardiovascular diseases are more likely to be readmitted. Further, the genetic architecture of psychiatric illness also suggests overlap with cardiovascular diseases. In summary, assessment of medications, side effects, and drug-drug interactions in a clinical setting as well as genomic information using a data mining approach could help to find factors that could help to lower readmission rates in patients with mental illness.

Tissue-Specific Analysis of Pharmacological Pathways

Understanding the downstream consequences of pharmacologically targeted proteins is essential to drug design. Current approaches investigate molecular effects under tissue‐naïve assumptions. Many target proteins, however, have tissue‐specific expression. A systematic study connecting drugs to target pathways in in vivo human tissues is needed. We introduced a data‐driven method that integrates drug‐target relationships with gene expression, protein‐protein interaction, and pathway annotation data. We applied our method to four independent genomewide expression datasets and built 467,396 connections between 1,034 drugs and 954 pathways in 259 human tissues or cell lines. We validated our results using data from L1000 and Pharmacogenomics Knowledgebase (PharmGKB), and observed high precision and recall. We predicted and tested anticoagulant effects of 22 compounds experimentally that were previously unknown, and used clinical data to validate these effects retrospectively. Our systematic study provides a better understanding of the cellular response to drugs and can be applied to many research topics in systems pharmacology.

A Pharmacovigilance Signaling System Based on FDA Regulatory Action and Post-Marketing Adverse Event Reports

INTRODUCTION

Many serious drug adverse events (AEs) only manifest well after regulatory approval. Therefore, the development of signaling methods to use with post-approval AE databases appears vital to comprehensively assess real-world drug safety. However, with millions of potential drug-AE pairs to analyze, the issue of focus is daunting.

OBJECTIVE

Our objective was to develop a signaling platform that focuses on AEs with historically demonstrated regulatory interest and to analyze such AEs with a disproportional reporting method that offers broad signal detection and acceptable false-positive rates.

METHODS

We analyzed over 1500 US FDA regulatory actions (safety communications and drug label changes) from 2008 to 2015 to construct a list of eligible signal AEs. The FDA Adverse Event Reporting System (FAERS) was used to evaluate disproportional reporting rates, constrained by minimum case counts and confidence interval limits, of these selected AEs for 109 training drugs. This step led to 45 AEs that appeared to have a low likelihood of being added to a label by FDA, so they were removed from the signal eligible list. We measured disproportional reporting for the final group of eligible AEs on a test group of 29 drugs that were not used in either the eligible list construction or the training steps.

RESULTS

In a group of 29 test drugs, our model reduced the number of potential drug-AE signals from 41,834 to 97 and predicted 73 % of individual drug label changes. The model also predicted at least one AE-drug pair label change in 66 % of all the label changes for the test drugs.

CONCLUSIONS

By concentrating on AE types with already demonstrated interest to FDA, we constructed a signaling system that provided focus regarding drug-AE pairs and suitable accuracy with regard to the issuance of FDA labeling changes. We suggest that focus on historical regulatory actions may increase the utility of pharmacovigilance signaling systems.

Development of A Machine Learning Algorithm to Classify Drugs Of Unknown Fetal Effect

Many drugs commonly prescribed during pregnancy lack a fetal safety recommendation - called FDA 'category C' drugs. This study aims to classify these drugs into harmful and safe categories using knowledge gained from chemoinformatics (i.e., pharmacological similarity with drugs of known fetal effect) and empirical data (i.e., derived from Electronic Health Records). Our fetal loss cohort contains 14,922 affected and 33,043 unaffected pregnancies and our congenital anomalies cohort contains 5,658 affected and 31,240 unaffected infants. We trained a random forest to classify drugs of unknown pregnancy class into harmful or safe categories, focusing on two distinct outcomes: fetal loss and congenital anomalies. Our models achieved an out-of-bag accuracy of 91% for fetal loss and 87% for congenital anomalies outperforming null models. Fifty-seven 'category C' medications were classified as harmful for fetal loss and eleven for congenital anomalies. This includes medications with documented harmful effects, including naproxen, ibuprofen and rubella live vaccine. We also identified several novel drugs, e.g., haloperidol, that increased the risk of fetal loss. Our approach provides important information on the harmfulness of 'category C' drugs. This is needed, as no FDA recommendation exists for these drugs' fetal safety.