Unsupervised deep representation learning enables phenotype discovery for genetic association studies of brain imaging.

Understanding the genetic architecture of brain structure is challenging, partly due to difficulties in designing robust, non-biased descriptors of brain morphology. Until recently, brain measures for genome-wide association studies (GWAS) consisted of traditionally expert-defined or software-derived image-derived phenotypes (IDPs) that are often based on theoretical preconceptions or computed from limited amounts of data. Here, we present an approach to derive brain imaging phenotypes using unsupervised deep representation learning. We train a 3-D convolutional autoencoder model with reconstruction loss on 6130 UK Biobank (UKBB) participants' T1 or T2-FLAIR (T2) brain MRIs to create a 128-dimensional representation known as Unsupervised Deep learning derived Imaging Phenotypes (UDIPs). GWAS of these UDIPs in held-out UKBB subjects (n = 22,880 discovery and n = 12,359/11,265 replication cohorts for T1/T2) identified 9457 significant SNPs organized into 97 independent genetic loci of which 60 loci were replicated. Twenty-six loci were not reported in earlier T1 and T2 IDP-based UK Biobank GWAS. We developed a perturbation-based decoder interpretation approach to show that these loci are associated with UDIPs mapped to multiple relevant brain regions. Our results established unsupervised deep learning can derive robust, unbiased, heritable, and interpretable brain imaging phenotypes.

Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records.

Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROCPyTorch_EHR = 0.911, AUROCLR = 0.857, AUROCLGBM = 0.892). External validation with 393,713 patient events from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset in Boston confirms its superior accuracy (AUROCPyTorch_EHR = 0.859, AUROCLR = 0.816, AUROCLGBM = 0.838). Our model effectively stratifies patients into high-, medium-, and low-risk categories, potentially optimizing antimicrobial therapy and reducing unnecessary MRSA-specific antimicrobials. This highlights the advantage of deep learning models in predicting MRSA positive cultures, surpassing traditional machine learning models and supporting clinicians' judgments.

Dynamic Prognosis Prediction for Patients on DAPT After Drug-Eluting Stent Implantation: Model Development and Validation.

BACKGROUND: The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. METHODS AND RESULTS: We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum's de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were designated as our primary forecasting interval, further segmented into 6 sequential prediction windows. We evaluated 5 distinct AI algorithms for their precision in predicting ischemic and bleeding risks. Model discriminative accuracy was assessed using the area under the receiver operating characteristic curve, among other metrics. The weighted light gradient boosting machine stood out as the preeminent model, thus earning its place as our AI-DAPT model. The AI-DAPT demonstrated peak accuracy in the 30 to 36 months window, charting an area under the receiver operating characteristic curve of 90% [95% CI, 88%-92%] for ischemia and 84% [95% CI, 82%-87%] for bleeding predictions. CONCLUSIONS: Our AI-DAPT excels in formulating iterative, refined dynamic predictions by assimilating ongoing updates from patients' clinical profiles, holding value as a novel smart clinical tool to facilitate optimal DAPT duration management with high accuracy and adaptability.

FiMAP: A fast identity-by-descent mapping test for biobank-scale cohorts.

Although genome-wide association studies (GWAS) have identified tens of thousands of genetic loci, the genetic architecture is still not fully understood for many complex traits. Most GWAS and sequencing association studies have focused on single nucleotide polymorphisms or copy number variations, including common and rare genetic variants. However, phased haplotype information is often ignored in GWAS or variant set tests for rare variants. Here we leverage the identity-by-descent (IBD) segments inferred from a random projection-based IBD detection algorithm in the mapping of genetic associations with complex traits, to develop a computationally efficient statistical test for IBD mapping in biobank-scale cohorts. We used sparse linear algebra and random matrix algorithms to speed up the computation, and a genome-wide IBD mapping scan of more than 400,000 samples finished within a few hours. Simulation studies showed that our new method had well-controlled type I error rates under the null hypothesis of no genetic association in large biobank-scale cohorts, and outperformed traditional GWAS single-variant tests when the causal variants were untyped and rare, or in the presence of haplotype effects. We also applied our method to IBD mapping of six anthropometric traits using the UK Biobank data and identified a total of 3,442 associations, 2,131 (62%) of which remained significant after conditioning on suggestive tag variants in the ± 3 centimorgan flanking regions from GWAS.

Fast and accurate local ancestry inference with Recomb-Mix.

The availability of large genotyped cohorts brings new opportunities for revealing high-resolution genetic structure of admixed populations, via local ancestry inference (LAI), the process of identifying the ancestry of each segment of an individual haplotype. Though current methods achieve high accuracy in standard cases, LAI is still challenging when reference populations are more similar (e.g., intra-continental), when the number of reference populations is too numerous, or when the admixture events are deep in time, all of which are increasingly unavoidable in large biobanks. Here, we present a new LAI method, Recomb-Mix. Adopting the commonly used site-based formulation based on the classic Li and Stephens' model, Recomb-Mix integrates the elements of existing methods and introduces a new graph collapsing to simplify counting paths with the same ancestry label readout. Through comprehensive benchmarking on various simulated datasets, we show that Recomb-Mix is more accurate than existing methods in diverse sets of scenarios while being competitive in terms of resource efficiency. We expect that Recomb-Mix will be a useful method for advancing genetics studies of admixed populations.

Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies.

Genome-wide association studies (GWAS) are used to identify relationships between genetic variations and specific traits. When applied to high-dimensional medical imaging data, a key step is to extract lower-dimensional, yet informative representations of the data as traits. Representation learning for imaging genetics is largely under-explored due to the unique challenges posed by GWAS in comparison to typical visual representation learning. In this study, we tackle this problem from the mutual information (MI) perspective by identifying key limitations of existing methods. We introduce a trans-modal learning framework Genetic InfoMax (GIM), including a regularized MI estimator and a novel genetics-informed transformer to address the specific challenges of GWAS. We evaluate GIM on human brain 3D MRI data and establish standardized evaluation protocols to compare it to existing approaches. Our results demonstrate the effectiveness of GIM and a significantly improved performance on GWAS.

Minimal positional substring cover is a haplotype threading alternative to Li and Stephens model.

The Li and Stephens (LS) hidden Markov model (HMM) models the process of reconstructing a haplotype as a mosaic copy of haplotypes in a reference panel. For small panels, the probabilistic parameterization of LS enables modeling the uncertainties of such mosaics. However, LS becomes inefficient when sample size is large, because of its linear time complexity. Recently the PBWT, an efficient data structure capturing the local haplotype matching among haplotypes, was proposed to offer a fast method for giving some optimal solution (Viterbi) to the LS HMM. Previously, we introduced the minimal positional substring cover (MPSC) problem as an alternative formulation of LS whose objective is to cover a query haplotype by a minimum number of segments from haplotypes in a reference panel. The MPSC formulation allows the generation of a haplotype threading in time constant to sample size (O(N)). This allows haplotype threading on very large biobank-scale panels on which the LS model is infeasible. Here, we present new results on the solution space of the MPSC. In addition, we derived a number of optimal algorithms for MPSC, including solution enumerations, the length maximal MPSC, and h-MPSC solutions. In doing so, our algorithms reveal the solution space of LS for large panels. We show that our method is informative in terms of revealing the characteristics of biobank-scale data sets and can improve genotype imputation.

Fast inference of genetic recombination rates in biobank scale data.

Although rates of recombination events across the genome (genetic maps) are fundamental to genetic research, the majority of current studies only use one standard map. There is evidence suggesting population differences in genetic maps, and thus estimating population-specific maps, are of interest. Although the recent availability of biobank-scale data offers such opportunities, current methods are not efficient at leveraging very large sample sizes. The most accurate methods are still linkage disequilibrium (LD)-based methods that are only tractable for a few hundred samples. In this work, we propose a fast and memory-efficient method for estimating genetic maps from population genotyping data. Our method, FastRecomb, leverages the efficient positional Burrows-Wheeler transform (PBWT) data structure for counting IBD segment boundaries as potential recombination events. We used PBWT blocks to avoid redundant counting of pairwise matches. Moreover, we used a panel-smoothing technique to reduce the noise from errors and recent mutations. Using simulation, we found that FastRecomb achieves state-of-the-art performance at 10-kb resolution, in terms of correlation coefficients between the estimated map and the ground truth. This is mainly because FastRecomb can effectively take advantage of large panels comprising more than hundreds of thousands of haplotypes. At the same time, other methods lack the efficiency to handle such data. We believe further refinement of FastRecomb would deliver more accurate genetic maps for the genetics community.

RaPID-Query for fast identity by descent search and genealogical analysis.

MOTIVATION: Due to the rapid growth of the genetic database size, genealogical search, a process of inferring familial relatedness by identifying DNA matches, has become a viable approach to help individuals finding missing family members or law enforcement agencies locating suspects. A fast and accurate method is needed to search an out-of-database individual against millions of individuals. Most existing approaches only offer all-versus-all within panel match. Some prototype algorithms offer one-versus-all query from out-of-panel individual, but they do not tolerate errors. RESULTS: A new method, random projection-based identity-by-descent (IBD) detection (RaPID) query, is introduced to make fast genealogical search possible. RaPID-Query identifies IBD segments between a query haplotype and a panel of haplotypes. By integrating matches over multiple PBWT indexes, RaPID-Query manages to locate IBD segments quickly with a given cutoff length while allowing mismatched sites. A single query against all UK biobank autosomal chromosomes was completed within 2.76 seconds on average, with the minimum length 7 cM and 700 markers. RaPID-Query achieved a 0.016 false negative rate and a 0.012 false positive rate simultaneously on a chromosome 20 sequencing panel having 86 265 sites. This is comparable to the state-of-the-art IBD detection method TPBWT(out-of-sample) and Hap-IBD. The high-quality IBD segments yielded by RaPID-Query were able to distinguish up to fourth degree of the familial relatedness for a given individual pair, and the area under the receiver operating characteristic curve values are at least 97.28%. AVAILABILITY AND IMPLEMENTATION: The RaPID-Query program is available at https://github.com/ucfcbb/RaPID-Query.

Prediction of Brain Metastases Development in Patients With Lung Cancer by Explainable Artificial Intelligence From Electronic Health Records.

PURPOSE: Early detection of brain metastases (BMs) is critical for prompt treatment and optimal control of the disease. In this study, we seek to predict the risk of developing BM among patients diagnosed with lung cancer on the basis of electronic health record (EHR) data and to understand what factors are important for the model to predict BM development through explainable artificial intelligence approaches accurately. MATERIALS AND METHODS: We trained a recurrent neural network model, REverse Time AttentIoN (RETAIN), to predict the risk of developing BM using structured EHR data. To interpret the model's decision process, we analyzed the attention weights in the RETAIN model and the SHAP values from a feature attribution method, Kernel SHAP, to identify the factors contributing to BM prediction. RESULTS: We developed a high-quality cohort with 4,466 patients with BM from the Cerner Health Fact database, which contains over 70 million patients from more than 600 hospitals. RETAIN uses this data set to achieve the best area under the receiver operating characteristic curve at 0.825, a significant improvement over the baseline model. We also extended a feature attribution method, Kernel SHAP, to structured EHR data for model interpretation. Both RETAIN and Kernel SHAP can identify important features related to BM prediction. CONCLUSION: To the best of our knowledge, this is the first study to predict BM using structured EHR data. We achieved decent prediction performance for BM prediction and identified factors highly relevant to BM development. The sensitivity analysis demonstrated that both RETAIN and Kernel SHAP could discriminate unrelated features and put more weight on the features important to BM. Our study explored the potential of applying explainable artificial intelligence for future clinical applications.

Minimal Positional Substring Cover: A Haplotype Threading Alternative to Li & Stephens Model.

The Li & Stephens (LS) hidden Markov model (HMM) models the process of reconstructing a haplotype as a mosaic copy of haplotypes in a reference panel (haplotype threading). For small panels the probabilistic parameterization of LS enables modeling the uncertainties of such mosaics, and has been the foundational model for haplotype phasing and imputation. However, LS becomes inefficient when sample size is large (tens of thousands to millions), because of its linear time complexity ( O ( MN ), where M is the number of haplotypes and N is the number of sites in the panel). Recently the PBWT, an efficient data structure capturing the local haplotype matching among haplotypes, was proposed to offer fast methods for giving some optimal solution (Viterbi) to the LS HMM. But the solution space of the LS for large panels is still elusive. Previously we introduced the Minimal Positional Substring Cover (MPSC) problem as an alternative formulation of LS whose objective is to cover a query haplotype by a minimum number of segments from haplotypes in a reference panel. The MPSC formulation allows the generation of a haplotype threading in time constant to sample size ( O ( N )). This allows haplotype threading on very large biobank scale panels on which the LS model is infeasible. Here we present new results on the solution space of the MPSC by first identifying a property that any MPSC will have a set of required regions, and then proposing a MPSC graph. In addition, we derived a number of optimal algorithms for MPSC, including solution enumerations, the Length Maximal MPSC, and h -MPSC solutions. In doing so, our algorithms reveal the solution space of LS for large panels. Even though we only solved an extreme case of LS where the emission probability is 0, our algorithms can be made more robust by PBWT smoothing. We show that our method is informative in terms of revealing the characteristics of biobank-scale data sets and can improve genotype imputation.

FastRecomb: Fast inference of genetic recombination rates in biobank scale data.

While rates of recombination events across the genome (genetic maps) are fundamental to genetic research, the majority of current studies only use one standard map. There is evidence suggesting population differences in genetic maps, and thus estimating population-specific maps are of interest. While the recent availability of biobank-scale data offers such opportunities, current methods are not efficient at leveraging very large sample sizes. The most accurate methods are still linkage-disequilibrium (LD)-based methods that are only tractable for a few hundred samples. In this work, we propose a fast and memory-efficient method for estimating genetic maps from population genotyping data. Our method, FastRecomb, leverages the efficient positional Burrows-Wheeler transform (PBWT) data structure for counting IBD segment boundaries as potential recombination events. We used PBWT blocks to avoid redundant counting of pairwise matches. Moreover, we used a panel smoothing technique to reduce the noise from errors and recent mutations. Using simulation, we found that FastRecomb achieves state-of-the-art performance at 10k resolution, in terms of correlation coefficients between the estimated map and the ground truth. This is mainly due to the fact that FastRecomb can effectively take advantage of large panels comprising more than hundreds of thousands of haplotypes. At the same time, other methods lack the efficiency to handle such data. We believe further refinement of FastRecomb would deliver more accurate genetic maps for the genetics community.

Syllable-PBWT for space-efficient haplotype long-match query.

MOTIVATION: The positional Burrows-Wheeler transform (PBWT) has led to tremendous strides in haplotype matching on biobank-scale data. For genetic genealogical search, PBWT-based methods have optimized the asymptotic runtime of finding long matches between a query haplotype and a predefined panel of haplotypes. However, to enable fast query searches, the full-sized panel and PBWT data structures must be kept in memory, preventing existing algorithms from scaling up to modern biobank panels consisting of millions of haplotypes. In this work, we propose a space-efficient variation of PBWT named Syllable-PBWT, which divides every haplotype into syllables, builds the PBWT positional prefix arrays on the compressed syllabic panel, and leverages the polynomial rolling hash function for positional substring comparison. With the Syllable-PBWT data structures, we then present a long match query algorithm named Syllable-Query. RESULTS: Compared to the most time- and space-efficient previously published solution to the long match query problem, Syllable-Query reduced the memory use by a factor of over 100 on both the UK Biobank genotype data and the 1000 Genomes Project sequence data. Surprisingly, the smaller size of our syllabic data structures allows for more efficient iteration and CPU cache usage, granting Syllable-Query even faster runtime than existing solutions. AVAILABILITY AND IMPLEMENTATION: https://github.com/ZhiGroup/Syllable-PBWT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Open-source benchmarking of IBD segment detection methods for biobank-scale cohorts.

In the recent biobank era of genetics, the problem of identical-by-descent (IBD) segment detection received renewed interest, as IBD segments in large cohorts offer unprecedented opportunities in the study of population and genealogical history, as well as genetic association of long haplotypes. While a new generation of efficient methods for IBD segment detection becomes available, direct comparison of these methods is difficult: existing benchmarks were often evaluated in different datasets, with some not openly accessible; methods benchmarked were run under suboptimal parameters; and benchmark performance metrics were not defined consistently. Here, we developed a comprehensive and completely open-source evaluation of the power, accuracy, and resource consumption of these IBD segment detection methods using realistic population genetic simulations with various settings. Our results pave the road for fair evaluation of IBD segment detection methods and provide an practical guide for users.

MetaRNN: differentiating rare pathogenic and rare benign missense SNVs and InDels using deep learning.

Multiple computational approaches have been developed to improve our understanding of genetic variants. However, their ability to identify rare pathogenic variants from rare benign ones is still lacking. Using context annotations and deep learning methods, we present pathogenicity prediction models, MetaRNN and MetaRNN-indel, to help identify and prioritize rare nonsynonymous single nucleotide variants (nsSNVs) and non-frameshift insertion/deletions (nfINDELs). We use independent test sets to demonstrate that these new models outperform state-of-the-art competitors and achieve a more interpretable score distribution. Importantly, prediction scores from both models are comparable, enabling easy adoption of integrated genotype-phenotype association analysis methods. All pre-computed nsSNV scores are available at http://www.liulab.science/MetaRNN . The stand-alone program is also available at https://github.com/Chang-Li2019/MetaRNN .

PK-RNN-V E: A deep learning model approach to vancomycin therapeutic drug monitoring using electronic health record data.

Vancomycin is a commonly used antimicrobial in hospitals, and therapeutic drug monitoring (TDM) is required to optimize its efficacy and avoid toxicities. Bayesian models are currently recommended to predict the antibiotic levels. These models, however, although using carefully designed lab observations, were often developed in limited patient populations. The increasing availability of electronic health record (EHR) data offers an opportunity to develop TDM models for real-world patient populations. Here, we present a deep learning-based pharmacokinetic prediction model for vancomycin (PK-RNN-V E) using a large EHR dataset of 5,483 patients with 55,336 vancomycin administrations. PK-RNN-V E takes the patient's real-time sparse and irregular observations and offers dynamic predictions. Our results show that RNN-PK-V E offers a root mean squared error (RMSE) of 5.39 and outperforms the traditional Bayesian model (VTDM model) with an RMSE of 6.29. We believe that PK-RNN-V E can provide a pharmacokinetic model for vancomycin and other antimicrobials that require TDM.

Toward a standard formal semantic representation of the model card report.

BACKGROUND: Model card reports aim to provide informative and transparent description of machine learning models to stakeholders. This report document is of interest to the National Institutes of Health's Bridge2AI initiative to address the FAIR challenges with artificial intelligence-based machine learning models for biomedical research. We present our early undertaking in developing an ontology for capturing the conceptual-level information embedded in model card reports. RESULTS: Sourcing from existing ontologies and developing the core framework, we generated the Model Card Report Ontology. Our development efforts yielded an OWL2-based artifact that represents and formalizes model card report information. The current release of this ontology utilizes standard concepts and properties from OBO Foundry ontologies. Also, the software reasoner indicated no logical inconsistencies with the ontology. With sample model cards of machine learning models for bioinformatics research (HIV social networks and adverse outcome prediction for stent implantation), we showed the coverage and usefulness of our model in transforming static model card reports to a computable format for machine-based processing. CONCLUSIONS: The benefit of our work is that it utilizes expansive and standard terminologies and scientific rigor promoted by biomedical ontologists, as well as, generating an avenue to make model cards machine-readable using semantic web technology. Our future goal is to assess the veracity of our model and later expand the model to include additional concepts to address terminological gaps. We discuss tools and software that will utilize our ontology for potential application services.

P-smoother: efficient PBWT smoothing of large haplotype panels.

Motivation: As large haplotype panels become increasingly available, efficient string matching algorithms such as positional Burrows-Wheeler transformation (PBWT) are promising for identifying shared haplotypes. However, recent mutations and genotyping errors create occasional mismatches, presenting challenges for exact haplotype matching. Previous solutions are based on probabilistic models or seed-and-extension algorithms that passively tolerate mismatches. Results: Here, we propose a PBWT-based smoothing algorithm, P-smoother, to actively 'correct' these mismatches and thus 'smooth' the panel. P-smoother runs a bidirectional PBWT-based panel scanning that flips mismatching alleles based on the overall haplotype matching context, which we call the IBD (identical-by-descent) prior. In a simulated panel with 4000 haplotypes and a 0.2% error rate, we show it can reliably correct 85% of errors. As a result, PBWT algorithms running over the smoothed panel can identify more pairwise IBD segments than that over the unsmoothed panel. Most strikingly, a PBWT-cluster algorithm running over the smoothed panel, which we call PS-cluster, achieves state-of-the-art performance for identifying multiway IBD segments, a challenging problem in the computational community for years. We also showed that PS-cluster is adequately efficient for UK Biobank data. Therefore, P-smoother opens up new possibilities for efficient error-tolerating algorithms for biobank-scale haplotype panels. Availability and implementation: Source code is available at github.com/ZhiGroup/P-smoother.

Recurrent neural network models (CovRNN) for predicting outcomes of patients with COVID-19 on admission to hospital: model development and validation using electronic health record data.

BACKGROUND: Predicting outcomes of patients with COVID-19 at an early stage is crucial for optimised clinical care and resource management, especially during a pandemic. Although multiple machine learning models have been proposed to address this issue, because of their requirements for extensive data preprocessing and feature engineering, they have not been validated or implemented outside of their original study site. Therefore, we aimed to develop accurate and transferrable predictive models of outcomes on hospital admission for patients with COVID-19. METHODS: In this study, we developed recurrent neural network-based models (CovRNN) to predict the outcomes of patients with COVID-19 by use of available electronic health record data on admission to hospital, without the need for specific feature selection or missing data imputation. CovRNN was designed to predict three outcomes: in-hospital mortality, need for mechanical ventilation, and prolonged hospital stay (>7 days). For in-hospital mortality and mechanical ventilation, CovRNN produced time-to-event risk scores (survival prediction; evaluated by the concordance index) and all-time risk scores (binary prediction; area under the receiver operating characteristic curve [AUROC] was the main metric); we only trained a binary classification model for prolonged hospital stay. For binary classification tasks, we compared CovRNN against traditional machine learning algorithms: logistic regression and light gradient boost machine. Our models were trained and validated on the heterogeneous, deidentified data of 247 960 patients with COVID-19 from 87 US health-care systems derived from the Cerner Real-World COVID-19 Q3 Dataset up to September 2020. We held out the data of 4175 patients from two hospitals for external validation. The remaining 243 785 patients from the 85 health systems were grouped into training (n=170 626), validation (n=24 378), and multi-hospital test (n=48 781) sets. Model performance was evaluated in the multi-hospital test set. The transferability of CovRNN was externally validated by use of deidentified data from 36 140 patients derived from the US-based Optum deidentified COVID-19 electronic health record dataset (version 1015; from January, 2007, to Oct 15, 2020). Exact dates of data extraction were masked by the databases to ensure patient data safety. FINDINGS: CovRNN binary models achieved AUROCs of 93·0% (95% CI 92·6-93·4) for the prediction of in-hospital mortality, 92·9% (92·6-93·2) for the prediction of mechanical ventilation, and 86·5% (86·2-86·9) for the prediction of a prolonged hospital stay, outperforming light gradient boost machine and logistic regression algorithms. External validation confirmed AUROCs in similar ranges (91·3-97·0% for in-hospital mortality prediction, 91·5-96·0% for the prediction of mechanical ventilation, and 81·0-88·3% for the prediction of prolonged hospital stay). For survival prediction, CovRNN achieved a concordance index of 86·0% (95% CI 85·1-86·9) for in-hospital mortality and 92·6% (92·2-93·0) for mechanical ventilation. INTERPRETATION: Trained on a large, heterogeneous, real-world dataset, our CovRNN models showed high prediction accuracy and transferability through consistently good performances on multiple external datasets. Our results show the feasibility of a COVID-19 predictive model that delivers high accuracy without the need for complex feature engineering. FUNDING: Cancer Prevention and Research Institute of Texas.

Real World Long-term Assessment of The Efficacy of Tocilizumab in Patients with COVID-19: Results From A Large De-identified Multicenter Electronic Health Record Dataset in the United States.

BACKGROUND: Studies have shown conflicting results on the efficacy of tocilizumab (TCZ) for patients with COVID-19, with many confounders of clinical status and limited duration of the observation. Here, we evaluate the real-world long-term efficacy of TCZ in COVID-19 patients. METHODS: We conducted a retrospective study of hospitalized adult patients with COVID-19 using a large US-based multicenter COVID-19 database (Cerner Real-World Data; updated in September, 2020). The TCZ group was defined as patients who received at least one dose of the drug. Matching weight (MW) and a propensity score weighting method were used to balance confounding factors. RESULTS: A total of 20,399 patients were identified. 1,510 and 18,899 were in the TCZ and control groups, respectively. After MW adjustment, no statistically significant differences in all-cause mortality were found for the TCZ vs. control group (Hazard Ratio [HR]:0.76, p=0.06). Survival curves suggested a better trend in short-term observation, driven from a subgroup of patients requiring oxygen masks, BIPAP or CPAP. CONCLUSION: We observed a temporal (early) benefit of TCZ, especially in patients on non-invasive high-flow supplemental oxygen. However, the benefit effects faded with longer observation. The long-term benefits and risks of TCZ should be carefully evaluated with follow-up studies.