Towards global model generalizability: independent cross-site feature evaluation for patient-level risk prediction models using the OHDSI network.

BACKGROUND: Predictive models show promise in healthcare, but their successful deployment is challenging due to limited generalizability. Current external validation often focuses on model performance with restricted feature use from the original training data, lacking insights into their suitability at external sites. Our study introduces an innovative methodology for evaluating features during both the development phase and the validation, focusing on creating and validating predictive models for post-surgery patient outcomes with improved generalizability. METHODS: Electronic health records (EHRs) from 4 countries (United States, United Kingdom, Finland, and Korea) were mapped to the OMOP Common Data Model (CDM), 2008-2019. Machine learning (ML) models were developed to predict post-surgery prolonged opioid use (POU) risks using data collected 6 months before surgery. Both local and cross-site feature selection methods were applied in the development and external validation datasets. Models were developed using Observational Health Data Sciences and Informatics (OHDSI) tools and validated on separate patient cohorts. RESULTS: Model development included 41 929 patients, 14.6% with POU. The external validation included 31 932 (UK), 23 100 (US), 7295 (Korea), and 3934 (Finland) patients with POU of 44.2%, 22.0%, 15.8%, and 21.8%, respectively. The top-performing model, Lasso logistic regression, achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 during local validation and 0.69 (SD = 0.02) (averaged) in external validation. Models trained with cross-site feature selection significantly outperformed those using only features from the development site through external validation (P < .05). CONCLUSIONS: Using EHRs across four countries mapped to the OMOP CDM, we developed generalizable predictive models for POU. Our approach demonstrates the significant impact of cross-site feature selection in improving model performance, underscoring the importance of incorporating diverse feature sets from various clinical settings to enhance the generalizability and utility of predictive healthcare models.

Ranitidine Use and Incident Cancer in a Multinational Cohort.

Importance: Ranitidine, the most widely used histamine-2 receptor antagonist (H2RA), was withdrawn because of N-nitrosodimethylamine impurity in 2020. Given the worldwide exposure to this drug, the potential risk of cancer development associated with the intake of known carcinogens is an important epidemiological concern. Objective: To examine the comparative risk of cancer associated with the use of ranitidine vs other H2RAs. Design, Setting, and Participants: This new-user active comparator international network cohort study was conducted using 3 health claims and 9 electronic health record databases from the US, the United Kingdom, Germany, Spain, France, South Korea, and Taiwan. Large-scale propensity score (PS) matching was used to minimize confounding of the observed covariates with negative control outcomes. Empirical calibration was performed to account for unobserved confounding. All databases were mapped to a common data model. Database-specific estimates were combined using random-effects meta-analysis. Participants included individuals aged at least 20 years with no history of cancer who used H2RAs for more than 30 days from January 1986 to December 2020, with a 1-year washout period. Data were analyzed from April to September 2021. Exposure: The main exposure was use of ranitidine vs other H2RAs (famotidine, lafutidine, nizatidine, and roxatidine). Main Outcomes and Measures: The primary outcome was incidence of any cancer, except nonmelanoma skin cancer. Secondary outcomes included all cancer except thyroid cancer, 16 cancer subtypes, and all-cause mortality. Results: Among 1 183 999 individuals in 11 databases, 909 168 individuals (mean age, 56.1 years; 507 316 [55.8%] women) were identified as new users of ranitidine, and 274 831 individuals (mean age, 58.0 years; 145 935 [53.1%] women) were identified as new users of other H2RAs. Crude incidence rates of cancer were 14.30 events per 1000 person-years (PYs) in ranitidine users and 15.03 events per 1000 PYs among other H2RA users. After PS matching, cancer risk was similar in ranitidine compared with other H2RA users (incidence, 15.92 events per 1000 PYs vs 15.65 events per 1000 PYs; calibrated meta-analytic hazard ratio, 1.04; 95% CI, 0.97-1.12). No significant associations were found between ranitidine use and any secondary outcomes after calibration. Conclusions and Relevance: In this cohort study, ranitidine use was not associated with an increased risk of cancer compared with the use of other H2RAs. Further research is needed on the long-term association of ranitidine with cancer development.

Estimating the effect of cesarean delivery on long-term childhood health across two countries.

Assessing the impact of cesarean delivery (CD) on long-term childhood outcomes is challenging as conducting a randomized controlled trial is rarely feasible and inferring it from observational data may be confounded. Utilizing data from electronic health records of 737,904 births, we defined and emulated a target trial to estimate the effect of CD on predefined long-term pediatric outcomes. Causal effects were estimated using pooled logistic regression and standardized survival curves, leveraging data breadth to account for potential confounders. Diverse sensitivity analyses were performed including replication of results in an external validation set from the UK including 625,044 births. Children born in CD had an increased risk to develop asthma (10-year risk differences (95% CI) 0.64% (0.31, 0.98)), an average treatment effect of 0.10 (0.07-0.12) on body mass index (BMI) z-scores at age 5 years old and 0.92 (0.68-1.14) on the number of respiratory infection events until 5 years of age. A positive 10-year risk difference was also observed for atopy (10-year risk differences (95% CI) 0.74% (-0.06, 1.52)) and allergy 0.47% (-0.32, 1.28)). Increased risk for these outcomes was also observed in the UK cohort. Our findings add to a growing body of evidence on the long-term effects of CD on pediatric morbidity, may assist in the decision to perform CD when not medically indicated and paves the way to future research on the mechanisms underlying these effects and intervention strategies targeting them.

Machine learning for improving high-dimensional proxy confounder adjustment in healthcare database studies: An overview of the current literature.

PURPOSE: Supplementing investigator-specified variables with large numbers of empirically identified features that collectively serve as 'proxies' for unspecified or unmeasured factors can often improve confounding control in studies utilizing administrative healthcare databases. Consequently, there has been a recent focus on the development of data-driven methods for high-dimensional proxy confounder adjustment in pharmacoepidemiologic research. In this paper, we survey current approaches and recent advancements for high-dimensional proxy confounder adjustment in healthcare database studies. METHODS: We discuss considerations underpinning three areas for high-dimensional proxy confounder adjustment: (1) feature generation-transforming raw data into covariates (or features) to be used for proxy adjustment; (2) covariate prioritization, selection, and adjustment; and (3) diagnostic assessment. We discuss challenges and avenues of future development within each area. RESULTS: There is a large literature on methods for high-dimensional confounder prioritization/selection, but relatively little has been written on best practices for feature generation and diagnostic assessment. Consequently, these areas have particular limitations and challenges. CONCLUSIONS: There is a growing body of evidence showing that machine-learning algorithms for high-dimensional proxy-confounder adjustment can supplement investigator-specified variables to improve confounding control compared to adjustment based on investigator-specified variables alone. However, more research is needed on best practices for feature generation and diagnostic assessment when applying methods for high-dimensional proxy confounder adjustment in pharmacoepidemiologic studies.

ISPE-Endorsed Guidance in Using Electronic Health Records for Comparative Effectiveness Research in COVID-19: Opportunities and Trade-Offs.

As the scientific research community along with healthcare professionals and decision makers around the world fight tirelessly against the coronavirus disease 2019 (COVID-19) pandemic, the need for comparative effectiveness research (CER) on preventive and therapeutic interventions for COVID-19 is immense. Randomized controlled trials markedly under-represent the frail and complex patients seen in routine care, and they do not typically have data on long-term treatment effects. The increasing availability of electronic health records (EHRs) for clinical research offers the opportunity to generate timely real-world evidence reflective of routine care for optimal management of COVID-19. However, there are many potential threats to the validity of CER based on EHR data that are not originally generated for research purposes. To ensure unbiased and robust results, we need high-quality healthcare databases, rigorous study designs, and proper implementation of appropriate statistical methods. We aimed to describe opportunities and challenges in EHR-based CER for COVID-19-related questions and to introduce best practices in pharmacoepidemiology to minimize potential biases. We structured our discussion into the following topics: (1) study population identification based on exposure status; (2) ascertainment of outcomes; (3) common biases and potential solutions; and (iv) data operational challenges specific to COVID-19 CER using EHRs. We provide structured guidance for the proper conduct and appraisal of drug and vaccine effectiveness and safety research using EHR data for the pandemic. This paper is endorsed by the International Society for Pharmacoepidemiology (ISPE).

Results of an early second PCR test performed on SARS-CoV-2 positive patients may support risk assessment for severe COVID-19.

Identifying patients at increased risk for severe COVID-19 is of high priority during the pandemic as it could affect clinical management and shape public health guidelines. In this study we assessed whether a second PCR test conducted 2-7 days after a SARS-CoV-2 positive test could identify patients at risk for severe illness. Analysis of a nationwide electronic health records data of 1683 SARS-CoV-2 positive individuals indicated that a second negative PCR test result was associated with lower risk for severe illness compared to a positive result. This association was seen across different age groups and clinical settings. More importantly, it was not limited to recovering patients but also observed in patients who still had evidence of COVID-19 as determined by a subsequent positive PCR test. Our study suggests that an early second PCR test may be used as a supportive risk-assessment tool to improve disease management and patient care.

Personalized approach to childhood obesity: Lessons from gut microbiota and omics studies. Narrative review and insights from the 29th European childhood obesity congress.

The traditional approach to childhood obesity prevention and treatment should fit most patients, but misdiagnosis and treatment failure could be observed in some cases that lie away from average as part of individual variation or misclassification. Here, we reflect on the contributions that high-throughput technologies such as next-generation sequencing, mass spectrometry-based metabolomics and microbiome analysis make towards a personalized medicine approach to childhood obesity. We hypothesize that diagnosing a child as someone with obesity captures only part of the phenotype; and that metabolomics, genomics, transcriptomics and analyses of the gut microbiome, could add precision to the term "obese," providing novel corresponding biomarkers. Identifying a cluster -omic signature in a given child can thus facilitate the development of personalized prognostic, diagnostic, and therapeutic approaches. It can also be applied to the monitoring of symptoms/signs evolution, treatment choices and efficacy, predisposition to drug-related side effects and potential relapse. This article is a narrative review of the literature and summary of the main observations, conclusions and perspectives raised during the annual meeting of the European Childhood Obesity Group. Authors discuss some recent advances and future perspectives on utilizing a systems approach to understanding and managing childhood obesity in the context of the existing omics data.

Emulated Clinical Trials from Longitudinal Real-World Data Efficiently Identify Candidates for Neurological Disease Modification: Examples from Parkinson's Disease.

Real-world healthcare data hold the potential to identify therapeutic solutions for progressive diseases by efficiently pinpointing safe and efficacious repurposing drug candidates. This approach circumvents key early clinical development challenges, particularly relevant for neurological diseases, concordant with the vision of the 21st Century Cures Act. However, to-date, these data have been utilized mainly for confirmatory purposes rather than as drug discovery engines. Here, we demonstrate the usefulness of real-world data in identifying drug repurposing candidates for disease-modifying effects, specifically candidate marketed drugs that exhibit beneficial effects on Parkinson's disease (PD) progression. We performed an observational study in cohorts of ascertained PD patients extracted from two large medical databases, Explorys SuperMart (N = 88,867) and IBM MarketScan Research Databases (N = 106,395); and applied two conceptually different, well-established causal inference methods to estimate the effect of hundreds of drugs on delaying dementia onset as a proxy for slowing PD progression. Using this approach, we identified two drugs that manifested significant beneficial effects on PD progression in both datasets: rasagiline, narrowly indicated for PD motor symptoms; and zolpidem, a psycholeptic. Each confers its effects through distinct mechanisms, which we explored via a comparison of estimated effects within the drug classification ontology. We conclude that analysis of observational healthcare data, emulating otherwise costly, large, and lengthy clinical trials, can highlight promising repurposing candidates, to be validated in prospective registration trials, beneficial against common, late-onset progressive diseases for which disease-modifying therapeutic solutions are scarce.

What Factors Increase the Risk of Complications in SARS-CoV-2-Infected Patients? A Cohort Study in a Nationwide Israeli Health Organization.

BACKGROUND: Reliably identifying patients at increased risk for coronavirus disease (COVID-19) complications could guide clinical decisions, public health policies, and preparedness efforts. Multiple studies have attempted to characterize at-risk patients, using various data sources and methodologies. Most of these studies, however, explored condition-specific patient cohorts (eg, hospitalized patients) or had limited access to patients' medical history, thus, investigating related questions and, potentially, obtaining biased results. OBJECTIVE: This study aimed to identify factors associated with COVID-19 complications from the complete medical records of a nationally representative cohort of patients, with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. METHODS: We studied a cohort of all SARS-CoV-2-positive individuals, confirmed by polymerase chain reaction testing of either nasopharyngeal or saliva samples, in a nationwide health organization (covering 2.3 million individuals) and identified those who suffered from serious complications (ie, experienced moderate or severe symptoms of COVID-19, admitted to the intensive care unit, or died). We then compared the prevalence of pre-existing conditions, extracted from electronic health records, between complicated and noncomplicated COVID-19 patient cohorts to identify the conditions that significantly increase the risk of disease complications, in various age and sex strata. RESULTS: Of the 4353 SARS-CoV-2-positive individuals, 173 (4%) patients suffered from COVID-19 complications (all age ≥18 years). Our analysis suggests that cardiovascular and kidney diseases, obesity, and hypertension are significant risk factors for COVID-19 complications. It also indicates that depression (eg, males ≥65 years: odds ratio [OR] 2.94, 95% CI 1.55-5.58; P=.01) as well as cognitive and neurological disorders (eg, individuals ≥65 years old: OR 2.65, 95% CI 1.69-4.17; P<.001) are significant risk factors. Smoking and presence of respiratory diseases do not significantly increase the risk of complications. CONCLUSIONS: Our analysis agrees with previous studies on multiple risk factors, including hypertension and obesity. It also finds depression as well as cognitive and neurological disorders, but not smoking and respiratory diseases, to be significantly associated with COVID-19 complications. Adjusting existing risk definitions following these observations may improve their accuracy and impact the global pandemic containment and recovery efforts.

Framework for identifying drug repurposing candidates from observational healthcare data.

OBJECTIVE: Observational medical databases, such as electronic health records and insurance claims, track the healthcare trajectory of millions of individuals. These databases provide real-world longitudinal information on large cohorts of patients and their medication prescription history. We present an easy-to-customize framework that systematically analyzes such databases to identify new indications for on-market prescription drugs. MATERIALS AND METHODS: Our framework provides an interface for defining study design parameters and extracting patient cohorts, disease-related outcomes, and potential confounders in observational databases. It then applies causal inference methodology to emulate hundreds of randomized controlled trials (RCTs) for prescribed drugs, while adjusting for confounding and selection biases. After correcting for multiple testing, it outputs the estimated effects and their statistical significance in each database. RESULTS: We demonstrate the utility of the framework in a case study of Parkinson's disease (PD) and evaluate the effect of 259 drugs on various PD progression measures in two observational medical databases, covering more than 150 million patients. The results of these emulated trials reveal remarkable agreement between the two databases for the most promising candidates. DISCUSSION: Estimating drug effects from observational data is challenging due to data biases and noise. To tackle this challenge, we integrate causal inference methodology with domain knowledge and compare the estimated effects in two separate databases. CONCLUSION: Our framework enables systematic search for drug repurposing candidates by emulating RCTs using observational data. The high level of agreement between separate databases strongly supports the identified effects.

Inferring new relations between medical entities using literature curated term co-occurrences.

OBJECTIVES: Identifying new relations between medical entities, such as drugs, diseases, and side effects, is typically a resource-intensive task, involving experimentation and clinical trials. The increased availability of related data and curated knowledge enables a computational approach to this task, notably by training models to predict likely relations. Such models rely on meaningful representations of the medical entities being studied. We propose a generic features vector representation that leverages co-occurrences of medical terms, linked with PubMed citations. MATERIALS AND METHODS: We demonstrate the usefulness of the proposed representation by inferring two types of relations: a drug causes a side effect and a drug treats an indication. To predict these relations and assess their effectiveness, we applied 2 modeling approaches: multi-task modeling using neural networks and single-task modeling based on gradient boosting machines and logistic regression. RESULTS: These trained models, which predict either side effects or indications, obtained significantly better results than baseline models that use a single direct co-occurrence feature. The results demonstrate the advantage of a comprehensive representation. DISCUSSION: Selecting the appropriate representation has an immense impact on the predictive performance of machine learning models. Our proposed representation is powerful, as it spans multiple medical domains and can be used to predict a wide range of relation types. CONCLUSION: The discovery of new relations between various medical entities can be translated into meaningful insights, for example, related to drug development or disease understanding. Our representation of medical entities can be used to train models that predict such relations, thus accelerating healthcare-related discoveries.

Changes in vaginal community state types reflect major shifts in the microbiome.

Background: Recent studies of various human microbiome habitats have revealed thousands of bacterial species and the existence of large variation in communities of microorganisms in the same habitats across individual human subjects. Previous efforts to summarize this diversity, notably in the human gut and vagina, have categorized microbiome profiles by clustering them into community state types (CSTs). The functional relevance of specific CSTs has not been established. Objective: We investigate whether CSTs can be used to assess dynamics in the microbiome. Design: We conduct a re-analysis of five sequencing-based microbiome surveys derived from vaginal samples with repeated measures. Results: We observe that detection of a CST transition is largely insensitive to choices in methods for normalization or clustering. We find that healthy subjects persist in a CST for two to three weeks or more on average, while those with evidence of dysbiosis tend to change more often. Changes in CST can be gradual or occur over less than one day. Upcoming CST changes and switches to high-risk CSTs can be predicted with high accuracy in certain scenarios. Finally, we observe that presence of Gardnerella vaginalis is a strong predictor of an upcoming CST change. Conclusion: Overall, our results show that the CST concept is useful for studying microbiome dynamics.

Fast and Efficient Feature Engineering for Multi-Cohort Analysis of EHR Data.

We present a framework for feature engineering, tailored for longitudinal structured data, such as electronic health records (EHRs). To fast-track feature engineering and extraction, the framework combines general-use plug-in extractors, a multi-cohort management mechanism, and modular memoization. Using this framework, we rapidly extracted thousands of features from diverse and large healthcare data sources in multiple projects.

Integrated multisystem analysis in a mental health and criminal justice ecosystem.

BACKGROUND: Patients with a serious mental illness often receive care that is fragmented due to reduced availability of or access to resources, and inadequate, discontinuous, and uncoordinated care across health, social services, and criminal justice organizations. This article describes the creation of a multisystem analysis that derives insights from an integrated dataset including patient access to case management services, medical services, and interactions with the criminal justice system. METHODS: Data were combined from electronic systems within a US mental health ecosystem that included mental health and substance abuse services, as well as data from the criminal justice system. Cox models were applied to test the associations between delivery of services and re-incarceration. Additionally, machine learning was used to train and validate a predictive model to examine effects of non-modifiable risk factors (age, past arrests, mental health diagnosis) and modifiable risk factors (outpatient, medical and case management services, and use of a jail diversion program) on re-arrest outcome. RESULTS: An association was found between past arrests and admission to crisis stabilization services in this population (N = 10,307). Delivery of case management or medical services provided after release from jail was associated with a reduced risk for re-arrest. Predictive models linked non-modifiable and modifiable risk factors and outcomes and predicted the probability of re-arrests with fair accuracy (area under the receiver operating characteristic curve of 0.67). CONCLUSIONS: By modeling the complex interactions between risk factors, service delivery, and outcomes, systems of care might be better enabled to meet patient needs and improve outcomes.

Estimating the effects of second-line therapy for type 2 diabetes mellitus: retrospective cohort study.

OBJECTIVE: Metformin is the recommended initial drug treatment in type 2 diabetes mellitus, but there is no clearly preferred choice for an additional drug when indicated. We compare the counterfactual drug effectiveness in lowering glycated hemoglobin (HbA1c) levels and effect on body mass index (BMI) of four diabetes second-line drug classes using electronic health records. STUDY DESIGN AND SETTING: Retrospective analysis of electronic health records of US-based patients in the Explorys database using causal inference methodology to adjust for patient censoring and confounders. PARTICIPANTS AND EXPOSURES: Our cohort consisted of more than 40 000 patients with type 2 diabetes, prescribed metformin along with a drug out of four second-line drug classes-sulfonylureas, thiazolidinediones, dipeptidyl peptidase 4 (DPP-4) inhibitors and glucagon-like peptide-1 agonists-during the years 2000-2015. Roughly, 17 000 of these patients were followed for 12 months after being prescribed a second-line drug. MAIN OUTCOME MEASURES: HbA1c and BMI of these patients after 6 and 12 months following treatment. RESULTS: We demonstrate that all four drug classes reduce HbA1c levels, but the effect of sulfonylureas after 6 and 12 months of treatment is less pronounced compared with other classes. We also estimate that DPP-4 inhibitors decrease body weight significantly more than sulfonylureas and thiazolidinediones. CONCLUSION: Our results are in line with current knowledge on second-line drug effectiveness and effect on BMI. They demonstrate that causal inference from electronic health records is an effective way for conducting multitreatment causal inference studies.

Paradoxical Hypersusceptibility of Drug-resistant Mycobacteriumtuberculosis to ß-lactam Antibiotics.

Mycobacterium tuberculosis (M. tuberculosis) is considered innately resistant to ß-lactam antibiotics. However, there is evidence that susceptibility to ß-lactam antibiotics in combination with ß-lactamase inhibitors is variable among clinical isolates, and these may present therapeutic options for drug-resistant cases. Here we report our investigation of susceptibility to ß-lactam/ß-lactamase inhibitor combinations among clinical isolates of M. tuberculosis, and the use of comparative genomics to understand the observed heterogeneity in susceptibility. Eighty-nine South African clinical isolates of varying first and second-line drug susceptibility patterns and two reference strains of M. tuberculosis underwent minimum inhibitory concentration (MIC) determination to two ß-lactams: amoxicillin and meropenem, both alone and in combination with clavulanate, a ß-lactamase inhibitor. 41/91 (45%) of tested isolates were found to be hypersusceptible to amoxicillin/clavulanate relative to reference strains, including 14/24 (58%) of multiple drug-resistant (MDR) and 22/38 (58%) of extensively drug-resistant (XDR) isolates. Genome-wide polymorphisms identified using whole-genome sequencing were used in a phylogenetically-aware linear mixed model to identify polymorphisms associated with amoxicillin/clavulanate susceptibility. Susceptibility to amoxicillin/clavulanate was over-represented among isolates within a specific clade (LAM4), in particular among XDR strains. Twelve sets of polymorphisms were identified as putative markers of amoxicillin/clavulanate susceptibility, five of which were confined solely to LAM4. Within the LAM4 clade, 'paradoxical hypersusceptibility' to amoxicillin/clavulanate has evolved in parallel to first and second-line drug resistance. Given the high prevalence of LAM4 among XDR TB in South Africa, our data support an expanded role for ß-lactam/ß-lactamase inhibitor combinations for treatment of drug-resistant M. tuberculosis.

The intron-22-inverted F8 locus permits factor VIII synthesis: explanation for low inhibitor risk and a role for pharmacogenomics.

Intron-22-inversion patients express the entire Factor VIII (FVIII)-amino-acid sequence intracellularly as 2 non-secreted polypeptides and have a positive "intracellular (I)-FVIII-CRM" status. Mutations conferring a positive I-FVIII-CRM status are associated with low inhibitor risk and are pharmacogenetically relevant because inhibitor risk may be affected by the nature of the therapeutic FVIII-protein (tFVIII), the affinity of any tFVIII-derived foreign peptide (tFVIII-fp) for any HLA class-II isomer (HLA-II) comprising individual major histocompatibility complex (MHC) repertoires, and the stability of any tFVIII-fp/HLA-II complex. We hypothesize that mutations conferring a completely or substantially negative I-FVIII-CRM status are pharmacogenetically irrelevant because inhibitor risk is high with any tFVIII and individual MHC repertoire.

Redundancy-weighting for better inference of protein structural features.

MOTIVATION: Structural knowledge, extracted from the Protein Data Bank (PDB), underlies numerous potential functions and prediction methods. The PDB, however, is highly biased: many proteins have more than one entry, while entire protein families are represented by a single structure, or even not at all. The standard solution to this problem is to limit the studies to non-redundant subsets of the PDB. While alleviating biases, this solution hides the many-to-many relations between sequences and structures. That is, non-redundant datasets conceal the diversity of sequences that share the same fold and the existence of multiple conformations for the same protein. A particularly disturbing aspect of non-redundant subsets is that they hardly benefit from the rapid pace of protein structure determination, as most newly solved structures fall within existing families. RESULTS: In this study we explore the concept of redundancy-weighted datasets, originally suggested by Miyazawa and Jernigan. Redundancy-weighted datasets include all available structures and associate them (or features thereof) with weights that are inversely proportional to the number of their homologs. Here, we provide the first systematic comparison of redundancy-weighted datasets with non-redundant ones. We test three weighting schemes and show that the distributions of structural features that they produce are smoother (having higher entropy) compared with the distributions inferred from non-redundant datasets. We further show that these smoothed distributions are both more robust and more correct than their non-redundant counterparts. We suggest that the better distributions, inferred using redundancy-weighting, may improve the accuracy of knowledge-based potentials and increase the power of protein structure prediction methods. Consequently, they may enhance model-driven molecular biology.

Integrated multisystem analysis in a mental health and criminal justice ecosystem.

Patients with a serious mental illness often receive care that is fragmented due to reduced availability of or access to resources, and inadequate, discontinuous, and uncoordinated care across health, social services, and criminal justice organizations. These gaps in care may lead to increased mental health disease burden and relapse, as well as repeated incarcerations. Further, the complex health, social service, and criminal justice ecosystem within which the patient may be embedded makes it difficult to examine the role of modifiable risk factors and delivered services on patient outcomes, particularly given that agencies often maintain isolated sets of relevant data. Here we describe an approach to creating a multisystem analysis that derives insights from an integrated data set including patient access to case management services, medical services, and interactions with the criminal justice system. We combined data from electronic systems within a US mental health ecosystem that included mental health and substance abuse services, as well as data from the criminal justice system. We applied Cox models to test the associations between delivery of services and re-incarceration. Using this approach, we found an association between arrests and crisis stabilization services in this population. We also found that delivery of case management or medical services provided after release from jail was associated with a reduced risk for re-arrest. Additionally, we used machine learning to train and validate a predictive model linking non-modifiable and modifiable risk factors and outcomes. A predictive model, constructed using elastic net regularized logistic regression, and considering age, past arrests, mental health diagnosis, as well as use of a jail diversion program, outpatient, medical and case management services predicted the probability of re-arrests with fair accuracy (AUC=.67). By modeling the complex interactions between risk factors, service delivery and outcomes, we may better enable systems of care to meet patient needs and improve outcomes.

Endogenous factor VIII synthesis from the intron 22-inverted F8 locus may modulate the immunogenicity of replacement therapy for hemophilia A.

Neutralizing antibodies (inhibitors) to replacement factor VIII (FVIII, either plasma derived or recombinant) impair the effective management of hemophilia A. Individuals with hemophilia A due to major deletions of the FVIII gene (F8) lack antigenically cross-reactive material in their plasma ("CRM-negative"), and the prevalence of inhibitors in these individuals may be as high as 90%. Conversely, individuals with hemophilia A caused by F8 missense mutations are CRM-positive, and their overall prevalence of inhibitors is <10% (ref. 2). Individuals with the F8 intron 22 inversion (found in ∼50% of individuals with severe hemophilia A) have been grouped with the former on the basis of their genetic defect and CRM-negative status. However, only ∼20% of these individuals develop inhibitors. Here we demonstrate that the levels of F8 mRNA and intracellular FVIII protein in B lymphoblastoid cells and liver biopsies from individuals with the intron 22 inversion are comparable to those in healthy controls. These results support the hypothesis that most individuals with the intron 22 inversion are tolerized to FVIII and thus do not develop inhibitors. Furthermore, we developed a new pharmacogenetic algorithm that permits the stratification of inhibitor risk for individuals and subpopulations by predicting the immunogenicity of replacement FVIII using, as input, the number of putative T cell epitopes in the infused protein and the competence of major histocompatibility complex class II molecules to present such epitopes. This algorithm showed statistically significant accuracy in predicting the presence of inhibitors in 25 unrelated individuals with the intron 22 inversion.