Prediction of chronic kidney disease progression using recurrent neural network and electronic health records.

Chronic kidney disease (CKD) is a progressive loss in kidney function. Early detection of patients who will progress to late-stage CKD is of paramount importance for patient care. To address this, we develop a pipeline to process longitudinal electronic heath records (EHRs) and construct recurrent neural network (RNN) models to predict CKD progression from stages II/III to stages IV/V. The RNN model generates predictions based on time-series records of patients, including repeated lab tests and other clinical variables. Our investigation reveals that using a single variable, the recorded estimated glomerular filtration rate (eGFR) over time, the RNN model achieves an average area under the receiver operating characteristic curve (AUROC) of 0.957 for predicting future CKD progression. When additional clinical variables, such as demographics, vital information, lab test results, and health behaviors, are incorporated, the average AUROC increases to 0.967. In both scenarios, the standard deviation of the AUROC across cross-validation trials is less than 0.01, indicating a stable and high prediction accuracy. Our analysis results demonstrate the proposed RNN model outperforms existing standard approaches, including static and dynamic Cox proportional hazards models, random forest, and LightGBM. The utilization of the RNN model and the time-series data of previous eGFR measurements underscores its potential as a straightforward and effective tool for assessing the clinical risk of CKD patients concerning their disease progression.

BEATS: Bayesian hybrid design with flexible sample size adaptation for time-to-event endpoints.

As the roles of historical trials and real-world evidence in drug development have substantially increased, several approaches have been proposed to leverage external data and improve the design of clinical trials. While most of these approaches focus on methodology development for borrowing information during the analysis stage, there is a risk of inadequate or absent enrollment of concurrent control due to misspecification of heterogeneity from external data, which can result in unreliable estimates of treatment effect. In this study, we introduce a Bayesian hybrid design with flexible sample size adaptation (BEATS) that allows for adaptive borrowing of external data based on the level of heterogeneity to augment the control arm during both the design and interim analysis stages. Moreover, BEATS extends the Bayesian semiparametric meta-analytic predictive prior (BaSe-MAP) to incorporate time-to-event endpoints, enabling optimal borrowing performance. Initially, BEATS calibrates the expected sample size and initial randomization ratio based on heterogeneity among the external data. During the interim analysis, flexible sample size adaptation is performed to address conflicts between the concurrent and historical control, while also conducting futility analysis. At the final analysis, estimation is provided by incorporating the calibrated amount of external data. Therefore, our proposed design allows for an approximation of an ideal randomized controlled trial with an equal randomization ratio while controlling the size of the concurrent control to benefit patients and accelerate drug development. BEATS also offers optimal power and robust estimation through flexible sample size adaptation when conflicts arise between the concurrent control and external data.

Impact of socioeconomics and race on clinical follow-up and trial enrollment and adherence in cerebral cavernous malformation.

OBJECTIVES: Cerebral cavernous malformation (CCM) affects more than a million Americans but advanced care for symptomatic lesions and access to research studies is largely limited to referral academic centers MATERIALS AND METHODS: A cohort of CCM patients screened for research studies at an accredited center of excellence for CCM was analyzed. Demographics, lesion location, history of hemorrhage, insurance type and area of deprivation index (ADI) were collected. Primary outcomes were clinical follow-up within a year from initial evaluation, and enrollment and adherence in clinical trials among eligible subjects RESULTS: A majority (52.8%) of CCM patients evaluated had a high socioeconomic status (SES) (ADI 1-3), and only 11.5% were African American. Patients who had a symptomatic bleed were more likely to follow-up (p=0.01), and those with brainstem lesion were more likely to enroll/adhere in a clinical trial (p=0.02). Rates of clinical follow-up were similar across different ADI groups, insurance coverage and race. Patients who were uninsured/self-paying, and African Americans were more likely to decline/drop from clinical trials (OR 2.4, 95% CI 0.46-10.20 and OR 2.2, 95% CI 0.33-10.75, respectively), but differences were not statistically significant CONCLUSIONS: Access of disadvantaged patients to center of excellence care and research remains limited despite geographic proximity to their community. Patients with lower SES and African Americans are as likely to follow-up clinically, but there were trends of differences in enrollment/adherence in clinical trials. Mitigation efforts should target systemic causes of low access to specialized care among uninsured and African American patients.

Plasma metabolites with mechanistic and clinical links to the neurovascular disease cavernous angioma.

BACKGROUND: Cavernous angiomas (CAs) affect 0.5% of the population, predisposing to serious neurologic sequelae from brain bleeding. A leaky gut epithelium associated with a permissive gut microbiome, was identified in patients who develop CAs, favoring lipid polysaccharide producing bacterial species. Micro-ribonucleic acids along with plasma levels of proteins reflecting angiogenesis and inflammation were also previously correlated with CA and CA with symptomatic hemorrhage. METHODS: The plasma metabolome of CA patients and CA patients with symptomatic hemorrhage was assessed using liquid-chromatography mass spectrometry. Differential metabolites were identified using partial least squares-discriminant analysis (p < 0.05, FDR corrected). Interactions between these metabolites and the previously established CA transcriptome, microbiome, and differential proteins were queried for mechanistic relevance. Differential metabolites in CA patients with symptomatic hemorrhage were then validated in an independent, propensity matched cohort. A machine learning-implemented, Bayesian approach was used to integrate proteins, micro-RNAs and metabolites to develop a diagnostic model for CA patients with symptomatic hemorrhage. RESULTS: Here we identify plasma metabolites, including cholic acid and hypoxanthine distinguishing CA patients, while arachidonic and linoleic acids distinguish those with symptomatic hemorrhage. Plasma metabolites are linked to the permissive microbiome genes, and to previously implicated disease mechanisms. The metabolites distinguishing CA with symptomatic hemorrhage are validated in an independent propensity-matched cohort, and their integration, along with levels of circulating miRNAs, enhance the performance of plasma protein biomarkers (up to 85% sensitivity and 80% specificity). CONCLUSIONS: Plasma metabolites reflect CAs and their hemorrhagic activity. A model of their multiomic integration is applicable to other pathologies.

Cavernous angiomas (CAs) are clusters of abnormal blood vessels found in the brain or spinal cord. A blood test that could identify people with CAs that have recently bled would help determine who need surgery or closer medical monitoring. We looked at the blood of people with CAs to compare the levels of metabolites, a type of small molecule produced within the body, in those who had recently bled and those who had not. We found that some metabolites may contribute to CA and have an impact on CA symptoms. Monitoring the levels of these metabolites can determine whether there had been a recent bleed. In the future, drugs or other therapies could be developed that would block or change the levels of these molecules and possibly be used to treat CA disease.

Circulating Plasma miRNA Homologs in Mice and Humans Reflect Familial Cerebral Cavernous Malformation Disease.

Patients with familial cerebral cavernous malformation (CCM) inherit germline loss of function mutations and are susceptible to progressive development of brain lesions and neurological sequelae during their lifetime. To date, no homologous circulating molecules have been identified that can reflect the presence of germ line pathogenetic CCM mutations, either in animal models or patients. We hypothesize that homologous differentially expressed (DE) plasma miRNAs can reflect the CCM germline mutation in preclinical murine models and patients. Herein, homologous DE plasma miRNAs with mechanistic putative gene targets within the transcriptome of preclinical and human CCM lesions were identified. Several of these gene targets were additionally found to be associated with CCM-enriched pathways identified using the Kyoto Encyclopedia of Genes and Genomes. DE miRNAs were also identified in familial-CCM patients who developed new brain lesions within the year following blood sample collection. The miRNome results were then validated in an independent cohort of human subjects with real-time-qPCR quantification, a technique facilitating plasma assays. Finally, a Bayesian-informed machine learning approach showed that a combination of plasma levels of miRNAs and circulating proteins improves the association with familial-CCM disease in human subjects to 95% accuracy. These findings act as an important proof of concept for the future development of translatable circulating biomarkers to be tested in preclinical studies and human trials aimed at monitoring and restoring gene function in CCM and other diseases.

Bayesian Sample Size Planning Tool for Phase I Dose-Finding Trials.

PURPOSE: Through Bayesian inference, we propose a method called BayeSize as a reference tool for investigators to assess the sample size and its associated scientific property for phase I clinical trials. METHODS: BayeSize applies the concept of effect size in dose finding, assuming that the maximum tolerated dose can be identified on the basis of an interval surrounding its true value because of statistical uncertainty. Leveraging a decision framework that involves composite hypotheses, BayeSize uses two types of priors, the fitting prior (for model fitting) and sampling prior (for data generation), to conduct sample size calculation under the constraints of statistical power and type I error. RESULTS: Simulation results showed that BayeSize can provide reliable sample size estimation under the constraints of type I/II error rates. CONCLUSION: BayeSize could facilitate phase I trial planning by providing appropriate sample size estimation. Look-up tables and R Shiny app are provided for practical applications.

Perfusion and Permeability MRI Predicts Future Cavernous Angioma Hemorrhage and Growth.

BACKGROUND: Cerebral cavernous angioma (CA) is a capillary vasculopathy affecting more than a million Americans with a small fraction of cases demonstrating lesional bleed or growth with major clinical sequelae. Perfusion and permeability are fundamental features of CA pathophysiology, but their role as prognostic biomarkers is unclear. PURPOSE: To investigate whether perfusion or permeability lesional descriptors derived from dynamic contrast-enhanced quantitative perfusion (DCEQP) magnetic resonance imaging (MRI) can predict subsequent lesional bleed/growth in the year following imaging. STUDY TYPE: Single-site case-controlled study. SUBJECTS: Two hundred and five consecutively enrolled patients (63.4% female). FIELD STRENGTH/SEQUENCE: Three-Tesla/T1 -mapping with contrast-enhanced dynamic two-dimensional (2D) spoiled gradient recalled acquisition (SPGR) sequences. ASSESSMENT: Prognostic associations with bleed/growth (present or absent) in the following year were assessed in 745 CA lesions evaluated by DCEQP in the 205 patients in relation to lesional descriptors calculated from permeability and perfusion maps. A subgroup of 30 cases also underwent peripheral blood collection at the time of DCEQP scans and assays of plasma levels of soluble CD14, IL-1ß, VEGF, and soluble ROBO4 proteins, whose weighted combination had been previously reported in association with future CA bleeding. STATISTICAL TESTS: Mann-Whitney U-test for univariate analyses. Logistic regression models minimizing the Bayesian information criterion (BIC), testing sensitivity and specificity (receiver operating characteristic curves) of weighted combinations of parameters. RESULTS: The best prognostic biomarker for lesional bleed or growth included brainstem lesion location, mean lesional permeability, and low-value perfusion cluster mean (BIC = 201.5, sensitivity = 77%, specificity = 72%, P < 0.05). Adding a previously published prognostic plasma protein biomarker improved the performance of the imaging model (sensitivity = 100%, specificity = 88%, P < 0.05). DATA CONCLUSION: A combination of MRI-based descriptors reflecting higher lesional permeability and lower perfusion cluster may potentially predict future bleed/growth in CAs. The sensitivity and specificity of the prognostic imaging biomarker can be enhanced when combined with brainstem lesion location and a plasma protein biomarker of CA hemorrhage. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 5.

Perfusion and permeability as diagnostic biomarkers of cavernous angioma with symptomatic hemorrhage.

Cavernous angiomas with symptomatic hemorrhage (CASH) have a high risk of rebleeding, and hence an accurate diagnosis is needed. With blood flow and vascular leak as established mechanisms, we analyzed perfusion and permeability derivations of dynamic contrast-enhanced quantitative perfusion (DCEQP) MRI in 745 lesions of 205 consecutive patients. Thirteen respective derivations of lesional perfusion and permeability were compared between lesions that bled within a year prior to imaging (N = 86), versus non-CASH (N = 659) using machine learning and univariate analyses. Based on logistic regression and minimizing the Bayesian information criterion (BIC), the best diagnostic biomarker of CASH within the prior year included brainstem lesion location, sporadic genotype, perfusion skewness, and high-perfusion cluster area (BIC = 414.9, sensitivity = 74%, specificity = 87%). Adding a diagnostic plasma protein biomarker enhanced sensitivity to 100% and specificity to 85%. A slightly modified derivation achieved similar accuracy (BIC = 321.6, sensitivity = 80%, specificity = 82%) in the cohort where CASH occurred 3-12 months prior to imaging after signs of hemorrhage would have disappeared on conventional MRI sequences. Adding the same plasma biomarker enhanced sensitivity to 100% and specificity to 87%. Lesional blood flow on DCEQP may distinguish CASH after hemorrhagic signs on conventional MRI have disappeared and are enhanced in combination with a plasma biomarker.

Contact reductions from live poultry market closures limit the epidemic of human infections with H7N9 influenza.

An early steep increase in the number of humans infected with avian influenza A(H7N9) virus was observed in China, raising great public concern domestically and internationally. Little is known about the dynamics of the transmission contacts between poultry and human populations, although such understanding is essential for developing effective strategies to control this zoonosis. In this study, we evaluated the effects of contact reductions from live poultry markets (LPMs) closures on the transmission of H7N9 virus during epidemics in Guangdong Province, China. A mathematical model of the poultry-to-person transmission dynamics of H7N9 virus was constructed. The parameters in the model were estimated from publicly available data on confirmed cases of human infection and information on LPMs closure during 2013-2017. By fitting the model, we measured the time-dependent contact quantity of the susceptible population to LPMs. The results showed that periodic intervention strategies can greatly reduce the magnitude of outbreaks, and the earlier interventions for policy are implemented, the smaller is the outbreak. The control efforts for LPMs to decrease the contact quantity are critical in preventing epidemics in the long term. This model should provide important insights for the development of a national intervention strategy for the long-term control of avian influenza virus epidemics.

An Integrative Analysis Reveals a Central Role of P53 Activation via MDM2 in Zika Virus Infection Induced Cell Death.

Zika virus (ZIKV) infection is an emerging global threat that is suspected to be associated with fetal microcephaly. However, the molecular mechanisms underlying ZIKV disease pathogenesis in humans remain elusive. Here, we investigated the human protein interaction network associated with ZIKV infection using a systemic virology approach, and reconstructed the transcriptional regulatory network to analyze the mechanisms underlying ZIKV-elicited microcephaly pathogenesis. The bioinformatics findings in this study show that P53 is the hub of the genetic regulatory network for ZIKV-related and microcephaly-associated proteins. Importantly, these results imply that the ZIKV capsid protein interacts with mouse double-minute-2 homolog (MDM2), which is involved in the P53-mediated apoptosis pathway, activating the death of infected neural cells. We also found that synthetic mimics of the ZIKV capsid protein induced cell death in vitro and in vivo. This study provides important insight into the relationship between ZIKV infection and brain diseases.

Model-informed risk assessment for Zika virus outbreaks in the Asia-Pacific regions.

Recently, Zika virus (ZIKV) has been recognized as a significant threat to global public health. The disease was present in large parts of the Americas, the Caribbean, and also the western Pacific area with southern Asia during 2015 and 2016. However, little is known about the factors affecting the transmission of ZIKV. We used Gradient Boosted Regression Tree models to investigate the effects of various potential explanatory variables on the spread of ZIKV, and used current with historical information from a range of sources to assess the risks of future ZIKV outbreaks. Our results indicated that the probability of ZIKV outbreaks increases with vapor pressure, the occurrence of Dengue virus, and population density but decreases as health expenditure, GDP, and numbers of travelers. The predictive results revealed the potential risk countries of ZIKV infection in the Asia-Pacific regions between October 2016 and January 2017. We believe that the high-risk conditions would continue in South Asia and Australia over this period. By integrating information on eco-environmental, social-economical, and ZIKV-related niche factors, this study estimated the probability for locally acquired mosquito-borne ZIKV infections in the Asia-Pacific region and improves the ability to forecast, and possibly even prevent, future outbreaks of ZIKV.

Dynamic Forecasting of Zika Epidemics Using Google Trends.

We developed a dynamic forecasting model for Zika virus (ZIKV), based on real-time online search data from Google Trends (GTs). It was designed to provide Zika virus disease (ZVD) surveillance and detection for Health Departments, and predictive numbers of infection cases, which would allow them sufficient time to implement interventions. In this study, we found a strong correlation between Zika-related GTs and the cumulative numbers of reported cases (confirmed, suspected and total cases; p<0.001). Then, we used the correlation data from Zika-related online search in GTs and ZIKV epidemics between 12 February and 20 October 2016 to construct an autoregressive integrated moving average (ARIMA) model (0, 1, 3) for the dynamic estimation of ZIKV outbreaks. The forecasting results indicated that the predicted data by ARIMA model, which used the online search data as the external regressor to enhance the forecasting model and assist the historical epidemic data in improving the quality of the predictions, are quite similar to the actual data during ZIKV epidemic early November 2016. Integer-valued autoregression provides a useful base predictive model for ZVD cases. This is enhanced by the incorporation of GTs data, confirming the prognostic utility of search query based surveillance. This accessible and flexible dynamic forecast model could be used in the monitoring of ZVD to provide advanced warning of future ZIKV outbreaks.