Health Care Cost Reductions with Machine Learning-Directed Evaluations during Radiation Therapy - An Economic Analysis of a Randomized Controlled Study.

BACKGROUND: Machine learning (ML) may cost-effectively direct health care by identifying patients most likely to benefit from preventative interventions to avoid negative and expensive outcomes. System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT; NCT04277650) was a single-institution, randomized controlled study in which electronic health record-based ML accurately identified patients at high risk for acute care (emergency visit or hospitalization) during radiotherapy (RT) and targeted them for supplemental clinical evaluations. This ML-directed intervention resulted in decreased acute care utilization. Given the limited prospective data showing the ability of ML to direct interventions cost-efficiently, an economic analysis was performed. METHODS: A post hoc economic analysis was conducted of SHIELD-RT that included RT courses from January 7, 2019, to June 30, 2019. ML-identified high-risk courses (≥10% risk of acute care during RT) were randomized to receive standard of care weekly clinical evaluations with ad hoc supplemental evaluations per clinician discretion versus mandatory twice-weekly evaluations. The primary outcome was difference in mean total medical costs during and 15 days after RT. Acute care costs were obtained via institutional cost accounting. Physician and intervention costs were estimated via Medicare and Medicaid data. Negative binomial regression was used to estimate cost outcomes after adjustment for patient and disease factors. RESULTS: A total of 311 high-risk RT courses among 305 patients were randomized to the standard (n=157) or the intervention (n=154) group. Unadjusted mean intervention group supplemental visit costs were $155 per course (95% confidence interval, $142 to $168). The intervention group had fewer acute care visits per course (standard, 0.47; intervention, 0.31; P=0.04). Total mean adjusted costs were $3110 per course for the standard group and $1494 for the intervention group (difference in means, $1616 [95% confidence interval, $1450 to $1783]; P=0.03). CONCLUSIONS: In this economic analysis of a randomized controlled, health care ML study, mandatory supplemental evaluations for ML-identified high-risk patients were associated with both reduced total medical costs and improved clinical outcomes. Further study is needed to determine whether economic results are generalizable. (Funded in part by The Duke Endowment, The Conquer Cancer Foundation, the Duke Department of Radiation Oncology, and the National Cancer Institute of the National Institutes of Health [R01CA277782]; ClinicalTrials.gov number, NCT04277650.).

Healthcare provider evaluation of machine learning-directed care: reactions to deployment on a randomised controlled study.

OBJECTIVES: Clinical artificial intelligence and machine learning (ML) face barriers related to implementation and trust. There have been few prospective opportunities to evaluate these concerns. System for High Intensity EvaLuation During Radiotherapy (NCT03775265) was a randomised controlled study demonstrating that ML accurately directed clinical evaluations to reduce acute care during cancer radiotherapy. We characterised subsequent perceptions and barriers to implementation. METHODS: An anonymous 7-question Likert-type scale survey with optional free text was administered to multidisciplinary staff focused on workflow, agreement with ML and patient experience. RESULTS: 59/71 (83%) responded. 81% disagreed/strongly disagreed their workflow was disrupted. 67% agreed/strongly agreed patients undergoing intervention were high risk. 75% agreed/strongly agreed they would implement the ML approach routinely if the study was positive. Free-text feedback focused on patient education and ML predictions. CONCLUSIONS: Randomised data and firsthand experience support positive reception of clinical ML. Providers highlighted future priorities, including patient counselling and workflow optimisation.

U.S. Adult Perspectives on Facial Images, DNA, and Other Biometrics.

Applications of biometrics in various societal contexts have been increasing in the United States, and policy debates about potential restrictions and expansions for specific biometrics (such as facial recognition and DNA identification) have been intensifying. Empirical data about public perspectives on different types of biometrics can inform these debates. We surveyed 4048 adults to explore perspectives regarding experience and comfort with six types of biometrics; comfort providing biometrics in distinct scenarios; trust in social actors to use two types of biometrics (facial images and DNA) responsibly; acceptability of facial images in eight scenarios; and perceived effectiveness of facial images for five tasks. Respondents were generally comfortable with biometrics. Trust in social actors to use biometrics responsibly appeared to be context specific rather than dependent on biometric type. Contrary to expectations given mounting attention to dataveillance concerns, we did not find sociodemographic factors to influence perspectives on biometrics in obvious ways. These findings underscore a need for qualitative approaches to understand the contextual factors that trigger strong opinions of comfort with and acceptability of biometrics in different settings, by different actors, and for different purposes and to identify the informational needs relevant to the development of appropriate policies and oversight.

Incorporation of near-real-time hospital occupancy data to improve hospitalization forecast accuracy during the COVID-19 pandemic.

Public health decision makers rely on hospitalization forecasts to inform COVID-19 pandemic planning and resource allocation. Hospitalization forecasts are most relevant when they are accurate, made available quickly, and updated frequently. We rapidly adapted an agent-based model (ABM) to provide weekly 30-day hospitalization forecasts (i.e., demand for intensive care unit [ICU] beds and non-ICU beds) by state and region in North Carolina for public health decision makers. The ABM was based on a synthetic population of North Carolina residents and included movement of agents (i.e., patients) among North Carolina hospitals, nursing homes, and the community. We assigned SARS-CoV-2 infection to agents using county-level compartmental models and determined agents' COVID-19 severity and probability of hospitalization using synthetic population characteristics (e.g., age, comorbidities). We generated weekly 30-day hospitalization forecasts during May-December 2020 and evaluated the impact of major model updates on statewide forecast accuracy under a SARS-CoV-2 effective reproduction number range of 1.0-1.2. Of the 21 forecasts included in the assessment, the average mean absolute percentage error (MAPE) was 7.8% for non-ICU beds and 23.6% for ICU beds. Among the major model updates, integration of near-real-time hospital occupancy data into the model had the largest impact on improving forecast accuracy, reducing the average MAPE for non-ICU beds from 6.6% to 3.9% and for ICU beds from 33.4% to 6.5%. Our results suggest that future pandemic hospitalization forecasting efforts should prioritize early inclusion of hospital occupancy data to maximize accuracy.

Association of mental health diagnosis with race and all-cause mortality after a cancer diagnosis: Large-scale analysis of electronic health record data.

BACKGROUND: Disparity in mental health care among cancer patients remains understudied. METHODS: A large, retrospective, single tertiary-care institution cohort study was conducted based on deidentified electronic health record data of 54,852 adult cancer patients without prior mental health diagnosis (MHD) diagnosed at the University of California, San Francisco between January 2012 and September 2019. The exposure of interest was early-onset MHD with or without psychotropic medication (PM) within 12 months of cancer diagnosis and primary outcome was all-cause mortality. RESULTS: There were 8.2% of patients who received a new MHD at a median of 197 days (interquartile range, 61-553) after incident cancer diagnosis; 31.0% received a PM prescription; and 3.7% a mental health-related visit (MHRV). There were 62.6% of patients who were non-Hispanic White (NHW), 10.8% were Asian, 9.8% were Hispanic, and 3.8% were Black. Compared with NHWs, minority cancer patients had reduced adjusted odds of MHDs, PM prescriptions, and MHRVs, particularly for generalized anxiety (Asian odds ratio [OR], 0.66, 95% CI, 0.55-0.78; Black OR, 0.60, 95% CI, 0.45-0.79; Hispanic OR, 0.72, 95% CI, 0.61-0.85) and selective serotonin-reuptake inhibitors (Asian OR, 0.43, 95% CI, 0.37-0.50; Black OR, 0.51, 95% CI, 0.40-0.61; Hispanic OR, 0.79, 95% CI, 0.70-0.89). New early MHD with PM was associated with elevated all-cause mortality (12-24 months: hazard ratio [HR], 1.43, 95% CI, 1.25-1.64) that waned by 24 to 36 months (HR, 1.18, 95% CI, 0.95-1.45). CONCLUSIONS: New mental health diagnosis with PM was a marker of early mortality among cancer patients. Minority cancer patients were less likely to receive documentation of MHDs or treatment, which may represent missed opportunities to identify and treat cancer-related mental health conditions.

A survey of U.S. public perspectives on facial recognition technology and facial imaging data practices in health and research contexts.

Facial imaging and facial recognition technologies, now common in our daily lives, also are increasingly incorporated into health care processes, enabling touch-free appointment check-in, matching patients accurately, and assisting with the diagnosis of certain medical conditions. The use, sharing, and storage of facial data is expected to expand in coming years, yet little is documented about the perspectives of patients and participants regarding these uses. We developed a pair of surveys to gather public perspectives on uses of facial images and facial recognition technologies in healthcare and in health-related research in the United States. We used Qualtrics Panels to collect responses from general public respondents using two complementary and overlapping survey instruments; one focused on six types of biometrics (including facial images and DNA) and their uses in a wide range of societal contexts (including healthcare and research) and the other focused on facial imaging, facial recognition technology, and related data practices in health and research contexts specifically. We collected responses from a diverse group of 4,048 adults in the United States (2,038 and 2,010, from each survey respectively). A majority of respondents (55.5%) indicated they were equally worried about the privacy of medical records, DNA, and facial images collected for precision health research. A vignette was used to gauge willingness to participate in a hypothetical precision health study, with respondents split as willing to (39.6%), unwilling to (30.1%), and unsure about (30.3%) participating. Nearly one-quarter of respondents (24.8%) reported they would prefer to opt out of the DNA component of a study, and 22.0% reported they would prefer to opt out of both the DNA and facial imaging component of the study. Few indicated willingness to pay a fee to opt-out of the collection of their research data. Finally, respondents were offered options for ideal governance design of their data, as "open science"; "gated science"; and "closed science." No option elicited a majority response. Our findings indicate that while a majority of research participants might be comfortable with facial images and facial recognition technologies in healthcare and health-related research, a significant fraction expressed concern for the privacy of their own face-based data, similar to the privacy concerns of DNA data and medical records. A nuanced approach to uses of face-based data in healthcare and health-related research is needed, taking into consideration storage protection plans and the contexts of use.

COVID-19 Vaccine Administration, by Race and Ethnicity - North Carolina, December 14, 2020-April 6, 2021.

COVID-19 has disproportionately affected non-Hispanic Black or African American (Black) and Hispanic persons in the United States (1,2). In North Carolina during January-September 2020, deaths from COVID-19 were 1.6 times higher among Black persons than among non-Hispanic White persons (3), and the rate of COVID-19 cases among Hispanic persons was 2.3 times higher than that among non-Hispanic persons (4). During December 14, 2020-April 6, 2021, the North Carolina Department of Health and Human Services (NCDHHS) monitored the proportion of Black and Hispanic persons* aged ≥16 years who received COVID-19 vaccinations, relative to the population proportions of these groups. On January 14, 2021, NCDHHS implemented a multipronged strategy to prioritize COVID-19 vaccinations among Black and Hispanic persons. This included mapping communities with larger population proportions of persons aged ≥65 years among these groups, increasing vaccine allocations to providers serving these communities, setting expectations that the share of vaccines administered to Black and Hispanic persons matched or exceeded population proportions, and facilitating community partnerships. From December 14, 2020-January 3, 2021 to March 29-April 6, 2021, the proportion of vaccines administered to Black persons increased from 9.2% to 18.7%, and the proportion administered to Hispanic persons increased from 3.9% to 9.9%, approaching the population proportion aged ≥16 years of these groups (22.3% and 8.0%, respectively). Vaccinating communities most affected by COVID-19 is a national priority (5). Public health officials could use U.S. Census tract-level mapping to guide vaccine allocation, promote shared accountability for equitable distribution of COVID-19 vaccines with vaccine providers through data sharing, and facilitate community partnerships to support vaccine access and promote equity in vaccine uptake.

Gender representation in U.S. biomedical informatics leadership and recognition.

OBJECTIVE: This study sought to describe gender representation in leadership and recognition within the U.S. biomedical informatics community. MATERIALS AND METHODS: Data were collected from public websites or provided by American Medical Informatics Association (AMIA) personnel from 2017 to 2019, including gender of membership, directors of academic informatics programs, clinical informatics subspecialty fellowships, AMIA leadership (2014-2019), and AMIA awardees (1993-2019). Differences in gender proportions were calculated using chi-square tests. RESULTS: Men were more often in leadership positions and award recipients (P < .01). Men led 74.7% (n = 71 of 95) of academic informatics programs and 83.3% (n = 35 of 42) of clinical informatics fellowships. Within AMIA, men held 56.8% (n = 1086 of 1913) of leadership roles and received 64.1% (n = 59 of 92) of awards. DISCUSSION: As in other STEM fields, leadership and recognition in biomedical informatics is lower for women. CONCLUSIONS: Quantifying gender inequity should inform data-driven strategies to foster diversity and inclusion. Standardized collection and surveillance of demographic data within biomedical informatics is necessary.

Use of electronic health records to support a public health response to the COVID-19 pandemic in the United States: a perspective from 15 academic medical centers.

Our goal is to summarize the collective experience of 15 organizations in dealing with uncoordinated efforts that result in unnecessary delays in understanding, predicting, preparing for, containing, and mitigating the COVID-19 pandemic in the US. Response efforts involve the collection and analysis of data corresponding to healthcare organizations, public health departments, socioeconomic indicators, as well as additional signals collected directly from individuals and communities. We focused on electronic health record (EHR) data, since EHRs can be leveraged and scaled to improve clinical care, research, and to inform public health decision-making. We outline the current challenges in the data ecosystem and the technology infrastructure that are relevant to COVID-19, as witnessed in our 15 institutions. The infrastructure includes registries and clinical data networks to support population-level analyses. We propose a specific set of strategic next steps to increase interoperability, overall organization, and efficiencies.

System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT): A Prospective Randomized Study of Machine Learning-Directed Clinical Evaluations During Radiation and Chemoradiation.

PURPOSE: Patients undergoing outpatient radiotherapy (RT) or chemoradiation (CRT) frequently require acute care (emergency department evaluation or hospitalization). Machine learning (ML) may guide interventions to reduce this risk. There are limited prospective studies investigating the clinical impact of ML in health care. The objective of this study was to determine whether ML can identify high-risk patients and direct mandatory twice-weekly clinical evaluation to reduce acute care visits during treatment. PATIENTS AND METHODS: During this single-institution randomized quality improvement study (ClinicalTrials.gov identifier: NCT04277650), 963 outpatient adult courses of RT and CRT started from January 7 to June 30, 2019, were evaluated by an ML algorithm. Among these, 311 courses identified by ML as high risk (> 10% risk of acute care during treatment) were randomized to standard once-weekly clinical evaluation (n = 157) or mandatory twice-weekly evaluation (n = 154). Both arms allowed additional evaluations on the basis of clinician discretion. The primary end point was the rate of acute care visits during RT. Model performance was evaluated using receiver operating characteristic area under the curve (AUC) and decile calibration plots. RESULTS: Twice-weekly evaluation reduced rates of acute care during treatment from 22.3% to 12.3% (difference, -10.0%; 95% CI, -18.3 to -1.6; relative risk, 0.556; 95% CI, 0.332 to 0.924; P = .02). Low-risk patients had a 2.7% acute care rate. Model discrimination was good in high- and low-risk patients undergoing standard once-weekly evaluation (AUC, 0.851). CONCLUSION: In this prospective randomized study, ML accurately triaged patients undergoing RT and CRT, directing clinical management with reduced acute care rates versus standard of care. This prospective study demonstrates the potential benefit of ML in health care and offers opportunities to enhance care quality and reduce health care costs.

Circulating ethanolamine plasmalogen indices in Alzheimer's disease: Relation to diagnosis, cognition, and CSF tau.

INTRODUCTION: Altered lipid metabolism is implicated in Alzheimer's disease (AD), but the mechanisms remain obscure. Aging-related declines in circulating plasmalogens containing omega-3 fatty acids may increase AD risk by reducing plasmalogen availability. METHODS: We measured four ethanolamine plasmalogens (PlsEtns) and four closely related phosphatidylethanolamines (PtdEtns) from the Alzheimer's Disease Neuroimaging Initiative (ADNI; n = 1547 serum) and University of Pennsylvania (UPenn; n = 112 plasma) cohorts, and derived indices reflecting PlsEtn and PtdEtn metabolism: PL-PX (PlsEtns), PL/PE (PlsEtn/PtdEtn ratios), and PBV (plasmalogen biosynthesis value; a composite index). We tested associations with baseline diagnosis, cognition, and cerebrospinal fluid (CSF) AD biomarkers. RESULTS: Results revealed statistically significant negative relationships in ADNI between AD versus CN with PL-PX (P = 0.007) and PBV (P = 0.005), late mild cognitive impairment (LMCI) versus cognitively normal (CN) with PL-PX (P = 2.89 × 10-5 ) and PBV (P = 1.99 × 10-4 ), and AD versus LMCI with PL/PE (P = 1.85 × 10-4 ). In the UPenn cohort, AD versus CN diagnosis associated negatively with PL/PE (P = 0.0191) and PBV (P = 0.0296). In ADNI, cognition was negatively associated with plasmalogen indices, including Alzheimer's Disease Assessment Scale 13-item cognitive subscale (ADAS-Cog13; PL-PX: P = 3.24 × 10-6 ; PBV: P = 6.92 × 10-5 ) and Mini-Mental State Examination (MMSE; PL-PX: P = 1.28 × 10-9 ; PBV: P = 6.50 × 10-9 ). In the UPenn cohort, there was a trend toward a similar relationship of MMSE with PL/PE (P = 0.0949). In ADNI, CSF total-tau was negatively associated with PL-PX (P = 5.55 × 10-6 ) and PBV (P = 7.77 × 10-6 ). Additionally, CSF t-tau/Aß1-42 ratio was negatively associated with these same indices (PL-PX, P = 2.73 × 10-6 ; PBV, P = 4.39 × 10-6 ). In the UPenn cohort, PL/PE was negatively associated with CSF total-tau (P = 0.031) and t-tau/Aß1-42 (P = 0.021). CSF Aß1-42 was not significantly associated with any of these indices in either cohort. DISCUSSION: These data extend previous studies by showing an association of decreased plasmalogen indices with AD, mild cognitive impairment (MCI), cognition, and CSF tau. Future studies are needed to better define mechanistic relationships, and to test the effects of interventions designed to replete serum plasmalogens.

Interrater Reliability in Toxicity Identification: Limitations of Current Standards.

PURPOSE: The National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE) v5.0 is the standard for oncology toxicity encoding and grading, despite limited validation. We assessed interrater reliability (IRR) in multireviewer toxicity identification. METHODS AND MATERIALS: Two reviewers independently reviewed 100 randomly selected notes for weekly on-treatment visits during radiation therapy from the electronic health record. Discrepancies were adjudicated by a third reviewer for consensus. Term harmonization was performed to account for overlapping symptoms in CTCAE. IRR was assessed based on unweighted and weighted Cohen's kappa coefficients. RESULTS: Between reviewers, the unweighted kappa was 0.68 (95% confidence interval, 0.65-0.71) and the weighted kappa was 0.59 (0.22-1.00). IRR was consistent between symptoms noted as present or absent with a kappa of 0.6 (0.66-0.71) and 0.6 (0.65-0.69), respectively. CONCLUSIONS: Significant discordance suggests toxicity identification, particularly retrospectively, is a complex and error-prone task. Strategies to minimize IRR, including training and simplification of the CTCAE criteria, should be considered in trial design and future terminologies.

Sex and APOE ε4 genotype modify the Alzheimer's disease serum metabolome.

Late-onset Alzheimer's disease (AD) can, in part, be considered a metabolic disease. Besides age, female sex and APOE ε4 genotype represent strong risk factors for AD that also give rise to large metabolic differences. We systematically investigated group-specific metabolic alterations by conducting stratified association analyses of 139 serum metabolites in 1,517 individuals from the AD Neuroimaging Initiative with AD biomarkers. We observed substantial sex differences in effects of 15 metabolites with partially overlapping differences for APOE ε4 status groups. Several group-specific metabolic alterations were not observed in unstratified analyses using sex and APOE ε4 as covariates. Combined stratification revealed further subgroup-specific metabolic effects limited to APOE ε4+ females. The observed metabolic alterations suggest that females experience greater impairment of mitochondrial energy production than males. Dissecting metabolic heterogeneity in AD pathogenesis can therefore enable grading the biomedical relevance for specific pathways within specific subgroups, guiding the way to personalized medicine.

Design and analytic considerations for using patient-reported health data in pragmatic clinical trials: report from an NIH Collaboratory roundtable.

Pragmatic clinical trials often entail the use of electronic health record (EHR) and claims data, but bias and quality issues associated with these data can limit their fitness for research purposes particularly for study end points. Patient-reported health (PRH) data can be used to confirm or supplement EHR and claims data in pragmatic trials, but these data can bring their own biases. Moreover, PRH data can complicate analyses if they are discordant with other sources. Using experience in the design and conduct of multi-site pragmatic trials, we itemize the strengths and limitations of PRH data and identify situational criteria for determining when PRH data are appropriate or ideal to fill gaps in the evidence collected from EHRs. To provide guidance for the scientific rationale and appropriate use of patient-reported data in pragmatic clinical trials, we describe approaches for ascertaining and classifying study end points and addressing issues of incomplete data, data alignment, and concordance. We conclude by identifying areas that require more research.

Natural language processing for abstraction of cancer treatment toxicities: accuracy versus human experts.

OBJECTIVES: Expert abstraction of acute toxicities is critical in oncology research but is labor-intensive and variable. We assessed the accuracy of a natural language processing (NLP) pipeline to extract symptoms from clinical notes compared to physicians. MATERIALS AND METHODS: Two independent reviewers identified present and negated National Cancer Institute Common Terminology Criteria for Adverse Events (CTCAE) v5.0 symptoms from 100 randomly selected notes for on-treatment visits during radiation therapy with adjudication by a third reviewer. A NLP pipeline based on Apache clinical Text Analysis Knowledge Extraction System was developed and used to extract CTCAE terms. Accuracy was assessed by precision, recall, and F1. RESULTS: The NLP pipeline demonstrated high accuracy for common physician-abstracted symptoms, such as radiation dermatitis (F1 0.88), fatigue (0.85), and nausea (0.88). NLP had poor sensitivity for negated symptoms. CONCLUSION: NLP accurately detects a subset of documented present CTCAE symptoms, though is limited for negated symptoms. It may facilitate strategies to more consistently identify toxicities during cancer therapy.

Bile acids targeted metabolomics and medication classification data in the ADNI1 and ADNIGO/2 cohorts.

Alzheimer's disease (AD) is the most common cause of dementia. The mechanism of disease development and progression is not well understood, but increasing evidence suggests multifactorial etiology, with a number of genetic, environmental, and aging-related factors. There is a growing body of evidence that metabolic defects may contribute to this complex disease. To interrogate the relationship between system level metabolites and disease susceptibility and progression, the AD Metabolomics Consortium (ADMC) in partnership with AD Neuroimaging Initiative (ADNI) is creating a comprehensive biochemical database for patients in the ADNI1 cohort. We used the Biocrates Bile Acids platform to evaluate the association of metabolic levels with disease risk and progression. We detail the quantitative metabolomics data generated on the baseline samples from ADNI1 and ADNIGO/2 (370 cognitively normal, 887 mild cognitive impairment, and 305 AD). Similar to our previous reports on ADNI1, we present the tools for data quality control and initial analysis. This data descriptor represents the third in a series of comprehensive metabolomics datasets from the ADMC on the ADNI.

Symptom-based patient stratification in mental illness using clinical notes.

Mental illnesses are highly heterogeneous with diagnoses based on symptoms that are generally qualitative, subjective, and documented in free text clinical notes rather than as structured data. Moreover, there exists significant variation in symptoms within diagnostic categories as well as substantial overlap in symptoms between diagnostic categories. These factors pose extra challenges for phenotyping patients with mental illness, a task that has proven challenging even for seemingly well characterized diseases. The ability to identify more homogeneous patient groups could both increase our ability to apply a precision medicine approach to psychiatric disorders and enable elucidation of underlying biological mechanism of pathology. We describe a novel approach to deep phenotyping in mental illness in which contextual term extraction is used to identify constellations of symptoms in a cohort of patients diagnosed with schizophrenia and related disorders. We applied topic modeling and dimensionality reduction to identify similar groups of patients and evaluate the resulting clusters through visualization and interrogation of clinically interpretable weighted features. Our findings show that patients diagnosed with schizophrenia may be meaningfully stratified using symptom-based clustering.

Translational bioinformatics in mental health: open access data sources and computational biomarker discovery.

Mental illness is increasingly recognized as both a significant cost to society and a significant area of opportunity for biological breakthrough. As -omics and imaging technologies enable researchers to probe molecular and physiological underpinnings of multiple diseases, opportunities arise to explore the biological basis for behavioral health and disease. From individual investigators to large international consortia, researchers have generated rich data sets in the area of mental health, including genomic, transcriptomic, metabolomic, proteomic, clinical and imaging resources. General data repositories such as the Gene Expression Omnibus (GEO) and Database of Genotypes and Phenotypes (dbGaP) and mental health (MH)-specific initiatives, such as the Psychiatric Genomics Consortium, MH Research Network and PsychENCODE represent a wealth of information yet to be gleaned. At the same time, novel approaches to integrate and analyze data sets are enabling important discoveries in the area of mental and behavioral health. This review will discuss and catalog into an organizing framework the increasingly diverse set of MH data resources available, using schizophrenia as a focus area, and will describe novel and integrative approaches to molecular biomarker discovery that make use of mental health data.

Reimagining the research-practice relationship: policy recommendations for informatics-enabled evidence-generation across the US health system.

The widespread adoption and use of electronic health records and their use to enable learning health systems (LHS) holds great promise to accelerate both evidence-generating medicine (EGM) and evidence-based medicine (EBM), thereby enabling a LHS. In 2016, AMIA convened its 10th annual Policy Invitational to discuss issues key to facilitating the EGM-EBM paradigm at points-of-care (nodes), across organizations (networks), and to ensure viability of this model at scale (sustainability). In this article, we synthesize discussions from the conference and supplements those deliberations with relevant context to inform ongoing policy development. Specifically, we explore and suggest public policies needed to facilitate EGM-EBM activities on a national scale, particularly those policies that can enable and improve clinical and health services research at the point-of-care, accelerate biomedical discovery, and facilitate translation of findings to improve the health of individuals and populations.