Search

Objectives Scanned documents (SDs), while common in electronic health records and potentially rich in clinically relevant information, rarely fit well with clinician workflow. Here, we identify scanned imaging reports requiring follow-up with high recall and practically useful precision. Materials and methods We focused on identifying imaging findings for 3 common causes of malpractice claims: (1) potentially malignant breast (mammography) and (2) lung (chest computed tomography [CT]) lesions and (3) long-bone fracture (X-ray) reports. We train our ClinicalBERT-based pipeline on existing typed/dictated reports classified manually or using ICD-10 codes, evaluate using a test set of manually classified SDs, and compare against string-matching (baseline approach). Results A total of 393 mammograms, 305 chest CT, and 683 bone X-ray reports were manually reviewed. The string-matching approach had an F1 of 0.667. For mammograms, chest CTs, and bone X-rays, respectively: models trained on manually classified training data and optimized for F1 reached an F1 of 0.900, 0.905, and 0.817, while separate models optimized for recall achieved a recall of 1.000 with precisions of 0.727, 0.518, and 0.275. Models trained on ICD-10-labelled data and optimized for F1 achieved F1 scores of 0.647, 0.830, and 0.643, while those optimized for recall achieved a recall of 1.0 with precisions of 0.407, 0.683, and 0.358. Discussion Our pipeline can identify abnormal reports with potentially useful performance and so decrease the manual effort required to screen for abnormal findings that require follow-up. Conclusion It is possible to automatically identify clinically significant abnormalities in SDs with high recall and practically useful precision in a generalizable and minimally laborious way.

Terminology definitions as used by the Precision Oncology Decision Support (PODS) team at MD Anderson Cancer Center

Prominent commercial vendors providing decision support services (as of November 1, 2017)

With the increasing availability of genomics, routine analysis of advanced cancers is now feasible. Treatment selection is frequently guided by the molecular characteristics of a patient's tumor, and an increasing number of trials are genomically selected. Furthermore, multiple studies have demonstrated the benefit of therapies that are chosen based upon the molecular profile of a tumor. However, the rapid evolution of genomic testing platforms and emergence of new technologies make interpreting molecular testing reports more challenging. More sophisticated precision oncology decision support services are essential. This review outlines existing tools available for health care providers and precision oncology teams and highlights strategies for optimizing decision support. Specific attention is given to the assays currently available for molecular testing, as well as considerations for interpreting alteration information. This article also discusses strategies for identifying and matching patients to clinical trials, current challenges, and proposals for future development of precision oncology decision support. Clin Cancer Res; 24(12); 2719–31. ©2018 AACR.

Actionable gene list for the Precision Oncology Decision Support (PODS) team at MD Anderson Cancer Center (as of November 1, 2017)

ObjectiveSNOMED CT is the largest clinical terminology worldwide. Quality assurance of SNOMED CT is of utmost importance to ensure that it provides accurate domain knowledge to various SNOMED CT-based applications. In this work, we introduce a deep learning-based approach to uncover missing is-a relations in SNOMED CT.Materials and MethodsOur focus is to identify missing is-a relations between concept-pairs exhibiting a containment pattern (ie, the set of words of one concept being a proper subset of that of the other concept). We use hierarchically related containment concept-pairs as positive instances and hierarchically unrelated containment concept-pairs as negative instances to train a model predicting whether an is-a relation exists between 2 concepts with containment pattern. The model is a binary classifier leveraging concept name features, hierarchical features, enriched lexical attribute features, and logical definition features. We introduce a cross-validation inspired approach to identify missing is-a relations among all hierarchically unrelated containment concept-pairs.ResultsWe trained and applied our model on the Clinical finding subhierarchy of SNOMED CT (September 2019 US edition). Our model (based on the validation sets) achieved a precision of 0.8164, recall of 0.8397, and F1 score of 0.8279. Applying the model to predict actual missing is-a relations, we obtained a total of 1661 potential candidates. Domain experts performed evaluation on randomly selected 230 samples and verified that 192 (83.48%) are valid.ConclusionsThe results showed that our deep learning approach is effective in uncovering missing is-a relations between containment concept-pairs in SNOMED CT.

Objective Our objective was to evaluate tokens commonly used by clinical research consortia to aggregate clinical data across institutions. Methods This study compares tokens alone and token-based matching algorithms against manual annotation for 20,002 record pairs extracted from the University of Texas Houston's clinical data warehouse (CDW) in terms of entity resolution. Results The highest precision achieved was 99.9% with a token derived from the first name, last name, gender, and date-of-birth. The highest recall achieved was 95.5% with an algorithm involving tokens that reflected combinations of first name, last name, gender, date-of-birth, and social security number. Discussion To protect the privacy of patient data, information must be removed from a health care dataset to obscure the identity of individuals from which that data were derived. However, once identifying information is removed, records can no longer be linked to the same entity to enable analyses. Tokens are a mechanism to convert patient identifying information into Health Insurance Portability and Accountability Act-compliant deidentified elements that can be used to link clinical records, while preserving patient privacy. Conclusion Depending on the availability and accuracy of the underlying data, tokens are able to resolve and link entities at a high level of precision and recall for real-world data derived from a CDW.

Background We propose a new deep learning model to identify unnecessary hemoglobin (Hgb) tests for patients admitted to the hospital, which can help reduce health risks and healthcare costs. Methods We collected internal patient data from a teaching hospital in Houston and external patient data from the MIMIC III database. The study used a conservative definition of unnecessary laboratory tests, which was defined as stable (i.e., stability) and below the lower normal bound (i.e., normality). Considering that machine learning models may yield less reliable results when trained on noisy inputs containing low-quality information, we estimated prediction confidence to assess the reliability of predicted outcomes. We adopted a “select and predict” design philosophy to maximize prediction performance by selectively considering samples with high prediction confidence for recommendations. Our model accommodated irregularly sampled observational data to make full use of variable correlations (i.e., with other laboratory test values) and temporal dependencies (i.e., previous laboratory tests performed within the same encounter) in selecting candidates for training and prediction. Results The proposed model demonstrated remarkable Hgb prediction performance, achieving a normality AUC of 95.89% and a Hgb stability AUC of 95.94%, while recommending a reduction of 9.91% of Hgb tests that were deemed unnecessary. Additionally, the model could generalize well to external patients admitted to another hospital. Conclusions This study introduces a novel deep learning model with the potential to significantly reduce healthcare costs and improve patient outcomes by identifying unnecessary laboratory tests for hospitalized patients.

PURPOSE The Medicare Access and CHIP Reauthorization Act of 2015 (MACRA) requires eligible clinicians to report clinical quality measures (CQMs) in the Merit-Based Incentive Payment System (MIPS) to maximize reimbursement. To determine whether structured data in electronic health records (EHRs) were adequate to report MIPS CQMs, EHR data aggregated by ASCO's CancerLinQ platform were analyzed. MATERIALS AND METHODS Using the CancerLinQ health technology platform, 19 Oncology MIPS (oMIPS) CQMs were evaluated to determine the presence of data elements (DEs) necessary to satisfy each CQM and the DE percent population with patient data (fill rates). At the time of this analysis, the CancerLinQ network comprised 63 active practices, representing eight different EHR vendors and containing records for more than 1.63 million unique patients with one or more malignant neoplasms (1.73 million cancer cases). RESULTS Fill rates for the 63 oMIPS-associated DEs varied widely among the practices. The average site had at least one filled DE for 52% of the DEs. Only 35% of the DEs were populated for at least one patient record in 95% of the practices. However, the average DE fill rate of all practices was 23%. No data were found at any practice for 22% of the DEs. Since any oMIPS CQM with an unpopulated DE component resulted in an inability to compute the measure, only two (10.5%) of the 19 oMIPS CQMs were computable for more than 1% of the patients. CONCLUSION Although EHR systems had relatively high DE fill rates for some DEs, underfilling and inconsistency of DEs in EHRs render automated oncology MIPS CQM calculations impractical.

In the context of competency-based medical education, poor student performance must be accurately documented to allow learners to improve and to protect the public. However, faculty may be reluctant to provide evaluations that could be perceived as negative, and clerkship directors report that some students pass who should have failed. Student perception of faculty may be considered in faculty promotion, teaching awards, and leadership positions. Therefore, faculty of lower academic rank may perceive themselves to be more vulnerable and, therefore, be less likely to document poor student performance. This study investigated faculty characteristics associated with low performance evaluations (LPEs).The authors analysed individual faculty evaluations of medical students who completed the third-year clerkships over 15 years using a generalised mixed regression model to assess the association of evaluator academic rank with likelihood of an LPE. Other available factors related to experience or academic vulnerability were incorporated including faculty age, race, ethnicity, and gender.The authors identified 50 120 evaluations by 585 faculty on 3447 students between January 2007 and April 2021. Faculty were more likely to give LPEs at the midpoint (4.9%), compared with the final (1.6%), evaluation (odds ratio [OR] = 4.004, 95% confidence interval [CI] [3.59, 4.53]; p 0.001). The likelihood of LPE decreased significantly during the 15-year study period (OR = 0.94 [0.90, 0.97]; p 0.01). Full professors were significantly more likely to give an LPE than assistant professors (OR = 1.62 [1.08, 2.43]; p = 0.02). Women were more likely to give LPEs than men (OR = 1.88 [1.37, 2.58]; p 0.01). Other faculty characteristics including race and experience were not associated with LPE.The number of LPEs decreased over time, and senior faculty were more likely to document poor medical student performance compared with assistant professors.

Unnecessary laboratory tests contribute to iatrogenic harm and are a major source of waste in the health care system. We previously developed a machine learning algorithm to help clinicians identify unnecessary laboratory tests, but it has not been externally validated. In this study, we externally validate our machine learning algorithm.To externally validate the machine learning algorithm that was originally trained on the Medical Information Mart for Intensive Care (MIMIC) III database, we tested the algorithm in a separate institution. We identified and abstracted data for all patients older than 18 years admitted to the intensive care unit at Memorial Hermann Hospital in Houston, Texas (MHH) from January 1, 2020 to November 13, 2020. Using the transfer learning style, we performed external validation of the machine learning algorithm.A total of 651 MHH patients were included. The model performed well in predicting abnormality (area under the curve [AUC] 0.98 for MIMIC III and 0.89 for MHH). The model performed similarly in predicting transitions from normal laboratory range to abnormal (AUC 0.71 for MIMIC III and 0.70 for MHH). The performance of the model in predicting the actual laboratory value was also similar in the MIMIC III (accuracy 0.41) and MHH data (0.45).We externally validated the machine learning model and showed that the model performed similarly, supporting the generalizability to other settings. While this model demonstrated good performance for predicting abnormal labs and transitions, it does not perform well enough for prediction of laboratory values in most clinical applications.

Objectives Electronic health records (EHRs) contain a large quantity of machine-readable data. However, institutions choose different EHR vendors, and the same product may be implemented differently at different sites. Our goal was to quantify the interoperability of real-world EHR implementations with respect to clinically relevant structured data. Materials and Methods We analyzed de-identified and aggregated data from 68 oncology sites that implemented 1 of 5 EHR vendor products. Using 6 medications and 6 laboratory tests for which well-accepted standards exist, we calculated inter- and intra-EHR vendor interoperability scores. Results The mean intra-EHR vendor interoperability score was 0.68 as compared to a mean of 0.22 for inter-system interoperability, when weighted by number of systems of each type, and 0.57 and 0.20 when not weighting by number of systems of each type. Discussion In contrast to data elements required for successful billing, clinically relevant data elements are rarely standardized, even though applicable standards exist. We chose a representative sample of laboratory tests and medications for oncology practices, but our set of data elements should be seen as an example, rather than a definitive list. Conclusions We defined and demonstrated a quantitative measure of interoperability between site EHR systems and within/between implemented vendor systems. Two sites that share the same vendor are, on average, more interoperable. However, even for implementation of the same EHR product, interoperability is not guaranteed. Our results can inform institutional EHR selection, analysis, and optimization for interoperability.

BackgroundIn the absence of genome sequencing, two positive molecular SARS-CoV-2 tests separated by negative tests, prolonged time, and symptom resolution remain the best surrogate measure of possible re-infection.MethodsUsing a large electronic health record database, we characterized clinical and testing data for 23 patients with repeatedly positive SARS-CoV-2 PCR test results ≥60 days apart, separated by ≥2 consecutive negative test results. Prevalence of chronic medical conditions, symptoms and severe outcomes related to COVID-19 illness were ascertained.ResultsMedian age was 64.5 years, 40% were Black, and 39% were female. 83% smoked within the prior year, 61% were overweight/obese, 83% had immune compromising conditions, and 96% had ≥2 comorbidities. Median interval between the two positive tests was 77 days. Among the 19 patients with 60-89 days between positive tests, 17 (89%) exhibited symptoms or clinical manifestations indicative of COVID-19 at the time of the second positive test and 14 (74%) were hospitalized at the second positive test. Of the four patients with ≥90 days between two positive tests, two had mild or no symptoms at the second positive test and one, an immune compromised patient, had a brief hospitalization at the first diagnosis, followed by ICU admission at the second diagnosis three months later.ConclusionsOur study demonstrated a high prevalence of immune compromise, comorbidities, obesity and smoking among patients with repeatedly positive SARS-CoV-2 tests. Despite limitations, including lack of semi-quantitative estimates of viral load, these data may help prioritize suspected cases of reinfection for investigation and continued surveillance.ImportanceComprehensive characterization of clinical and SARS-CoV-2 testing data for patients with repeatedly positive SARS-CoV-2 tests can help prioritize suspected cases of reinfection for investigation in the absence of sequencing data and for continued surveillance for potential long-term health consequences of SARS-CoV-2 infection.

Artificial intelligence (AI) is transforming many domains, including finance, agriculture, defense, and biomedicine. In this paper, we focus on the role of AI in clinical and translational research (CTR), including preclinical research (T1), clinical research (T2), clinical implementation (T3), and public (or population) health (T4). Given the rapid evolution of AI in CTR, we present three complementary perspectives: (1) scoping literature review, (2) survey, and (3) analysis of federally funded projects. For each CTR phase, we addressed challenges, successes, failures, and opportunities for AI. We surveyed Clinical and Translational Science Award (CTSA) hubs regarding AI projects at their institutions. Nineteen of 63 CTSA hubs (30%) responded to the survey. The most common funding source (48.5%) was the federal government. The most common translational phase was T2 (clinical research, 40.2%). Clinicians were the intended users in 44.6% of projects and researchers in 32.3% of projects. The most common computational approaches were supervised machine learning (38.6%) and deep learning (34.2%). The number of projects steadily increased from 2012 to 2020. Finally, we analyzed 2604 AI projects at CTSA hubs using the National Institutes of Health Research Portfolio Online Reporting Tools (RePORTER) database for 2011–2019. We mapped available abstracts to medical subject headings and found that nervous system (16.3%) and mental disorders (16.2) were the most common topics addressed. From a computational perspective, big data (32.3%) and deep learning (30.0%) were most common. This work represents a snapshot in time of the role of AI in the CTSA program.

PURPOSE Many targeted therapies are currently available only via clinical trials. Therefore, routine precision oncology using biomarker-based assignment to drug depends on matching patients to clinical trials. A comprehensive and up-to-date trial database is necessary for optimal patient-trial matching. METHODS We describe processes for establishing and maintaining a clinical trial database, focusing on genomically informed trials. Furthermore, we present OCTANE (Oncology Clinical Trial Annotation Engine), an informatics framework supporting these processes in a scalable fashion. To illustrate how the framework can be applied at an institution, we describe how we implemented an instance of OCTANE at a large cancer center. OCTANE consists of three modules. The data aggregation module automates retrieval, aggregation, and update of trial information. The annotation module establishes the database schema, implements data integration necessary for automation, and provides an annotation interface. The update module monitors trial change logs, identifies critical change events, and alerts the annotators when manual intervention may be needed. RESULTS Using OCTANE, we annotated 5,439 oncology clinical trials (4,438 genomically informed trials) that collectively were associated with 1,453 drugs, 779 genes, and 252 cancer types. To date, we have used the database to screen 4,220 patients for trial eligibility. We compared the update module with expert review, and the module achieved 98.5% accuracy, 0% false-negative rate, and 2.3% false-positive rate. CONCLUSION OCTANE is a general informatics framework that can be helpful for establishing and maintaining a comprehensive database necessary for automating patient-trial matching, which facilitates the successful delivery of personalized cancer care on a routine basis. Several OCTANE components are publically available and may be useful to other precision oncology programs.

Objective The study sought to design, pilot, and evaluate a federated data completeness tracking system (CTX) for assessing completeness in research data extracted from electronic health record data across the Accessible Research Commons for Health (ARCH) Clinical Data Research Network. Materials and Methods The CTX applies a systems-based approach to design workflow and technology for assessing completeness across distributed electronic health record data repositories participating in a queryable, federated network. The CTX invokes 2 positive feedback loops that utilize open source tools (DQe-c and Vue) to integrate technology and human actors in a system geared for increasing capacity and taking action. A pilot implementation of the system involved 6 ARCH partner sites between January 2017 and May 2018. Results The ARCH CTX has enabled the network to monitor and, if needed, adjust its data management processes to maintain complete datasets for secondary use. The system allows the network and its partner sites to profile data completeness both at the network and partner site levels. Interactive visualizations presenting the current state of completeness in the context of the entire network as well as changes in completeness across time were valued among the CTX user base. Discussion Distributed clinical data networks are complex systems. Top-down approaches that solely rely on technology to report data completeness may be necessary but not sufficient for improving completeness (and quality) of data in large-scale clinical data networks. Improving and maintaining complete (high-quality) data in such complex environments entails sociotechnical systems that exploit technology and empower human actors to engage in the process of high-quality data curating. Conclusions The CTX has increased the network’s capacity to rapidly identify data completeness issues and empowered ARCH partner sites to get involved in improving the completeness of respective data in their repositories.

Jane E Hamilton,1 Eduardo Blanco,2 Salih Selek,1 Kelly L Wirfel,3 Elmer V Bernstam,3,4 Dawn Velligan,5 Meghana Gudala,4 Kirk Roberts4 1The University of Texas Health Science Center at Houston, McGovern Medical School, Louis Faillace Department of Psychiatry and Behavioral Sciences, Houston, TX, USA; 2Arizona State University, School of Computing and Augmented Intelligence, Tempe, AZ, USA; 3The University of Texas Health Science Center at Houston, McGovern Medical School, Department of Internal Medicine, Houston, TX, USA; 4The University of Texas Health Science Center at Houston, School of Biomedical Informatics, Houston, TX, USA; 5The University of Texas Health Science Center at San Antonio, Long School of Medicine, Department of Psychiatry, San Antonio, TX, USACorrespondence: Jane E Hamilton, The University of Texas Health Science Center at Houston, McGovern Medical School, Louis A. Faillace, MD, Department of Psychiatry and Behavioral Sciences, 1941 East Road, BBSB 1204, Houston, TX, 77054, USA, Tel +1 713-486-2858, Email Jane.E.Hamilton@uth.tmc.eduBackground: Diabetes and depression affect a significant percentage of the world’s total population, and the management of these conditions is critical for reducing the global burden of disease. Medication adherence is crucial for improving diabetes and depression outcomes, and research is needed to elucidate barriers to medication adherence, including the intentionality of non-adherence, to intervene effectively. The purpose of this study was to explore the perspectives of patients and health care providers on intentional and unintentional medication adherence among patients with depression and diabetes through a series of focus groups conducted across clinical settings in a large urban area.Methods: This qualitative study utilized a grounded theory approach to thematically analyze qualitative data using the framework method. Four focus groups in total were conducted, two with patients and two with providers, over a one-year period using a semi-structured facilitation instrument containing open-ended questions about experiences, perceptions and beliefs about medication adherence.Results: Across the focus groups, communication difficulties between patients and providers resulting in medication non-adherence was a primary theme that emerged. Concerns about medication side effects and beliefs about medication effectiveness were identified as perceptual barriers related to intentional medication non-adherence. Practical barriers to medication adherence, including medication costs, forgetting to take medications and polypharmacy, emerged as themes related to unintentional medication non-adherence.Conclusion: The study findings contribute to a growing body of research suggesting health system changes are needed to improve provider education and implement multicomponent interventions to improve medication adherence among patients with depression and/or diabetes, both chronic illnesses accounting for significant disease burden globally.Keywords: medication adherence, patient and provider preferences, intentional versus unintentional nonadherence

Background and Aims Endoscopic ultrasound (EUS), magnetic resonance cholangiopancreatography (MRCP), and intraoperative cholangiogram (IOC) are the recommended diagnostic modalities for patients with intermediate probability for choledocholithiasis (IPC). The relative cost-effectiveness of these modalities in patients with cholelithiasis and IPC is understudied. Methods We developed a decision tree for diagnosing IPC (base case probability: 50%; range 10%-70%); patients with a positive test were modeled to undergo therapeutic ERCP. The strategies tested include (1) Laparoscopic cholecystectomy with IOC (LC-IOC), (2) MRCP, (3) single-session EUS + ERCP, and (4) separate session EUS + ERCP. Costs and probabilities were extracted from the published literature. Effectiveness was assessed by (1) assigning utility scores to health states, (2) the average proportion of true positive diagnosis of IPC, and (3) the mean length of stay (LOS) per strategy. Cost-effectiveness was assessed by extrapolating a net-monetary benefit (NMB), and average cost per true positive diagnosis. Results LC-IOC was the most cost-effective strategy to diagnose IPC (base-case probability of 50%) among patients with cholelithiasis in health state-based effectiveness analysis (NMB of $34,612), diagnostic test accuracy-based effectiveness analysis (average cost of $13,260 per true positive diagnosis), and LOS-based effectiveness analysis (mean LOS of 4.13) compared with strategy 2 (MRCP), 3 (single-session EUS+ERCP), and 4 (separate-session EUS+ERCP). These findings were robust on deterministic and probabilistic sensitivity analyses. Conclusion For patients with cholelithiasis with IPC, LC-IOC is a cost-effective approach that should limit preoperative testing and may shorten length of hospital stay. Our findings may be used to design institutional and organizational management protocols.

IntroductionConfounding bias threatens the reliability of observational studies and poses a significant scientific challenge. This paper introduces a framework for identifying confounding factors by exploiting literature-derived computable knowledge. In previous work, we have shown that semantic constraint search over computable knowledge extracted from the literature can be useful for reducing confounding bias in statistical models of EHR-derived observational clinical data. We hypothesize that adjustment sets of literature-derived confounders could also improve causal inference.MethodsWe introduce two methods (semantic vectors and string-based confounder search) that query the literature for potential confounders and use this information to build models from EHR-derived data to more accurately estimate causal effects. These methods search SemMedDB for indications TREATED BY the drug that is also known to CAUSE the adverse event. For evaluation, we attempt to rediscover associations in a publicly available reference dataset containing expected pairwise relationships between drugs and adverse events from empirical data derived from a corpus of 2.2M EHR-derived clinical notes. For our knowledge-base, we use SemMedDB, a database of computable knowledge mined from the biomedical literature. Using standard adjustment and causal inference procedures on dichotomous drug exposures, confounders, and adverse event outcomes, varying numbers of literature-derived confounders are combined with EHR data to predict and estimate causal effects in light of the literature-derived confounders. We then compare the performance of the new methods with naive (χ2, reporting odds ratio) measures of association.Results and ConclusionsLogistic regression with ten vector space-derived confounders achieved the most improvement with AUROC of 0.628 (95% CI: [0.556,0.720]), compared with baseline χ20.507 (95% CI: [0.431,0.583]). Bias reduction was improved more often in modeling methods using more rather than less information, and using semantic vector rather than string-based search. We found computable knowledge useful for improving automated causal inference, and identified opportunities for further improvement, including a role for adjudicating literature-derived confounders by subject matter experts.Graphical AbstractHighlightsAccess to causal background knowledge is required for causal learning to scale to large datasets.We introduce a framework for identifying confounders to enhance causal inference from EHR.We search computable knowledge for indications TREATED BY the drug that CAUSE the outcome.Literature-derived confounders reduce confounding bias in EHR data.Structured knowledge helps interpret and explain data captured in clinical narratives.

The American Society for Gastrointestinal Endoscopy (ASGE) 2010 guidelines for suspected choledocholithiasis were recently updated by proposing more specific criteria for selection of high-risk patients to undergo direct ERCP while advocating the use of additional imaging studies for intermediate- and low-risk individuals. We aim to compare the performance and diagnostic accuracy of 2019 versus 2010 ASGE criteria for suspected choledocholithiasis.We performed a retrospective chart review of a prospectively maintained database (2013-2019) of over 10,000 ERCPs performed by 70 gastroenterologists in our 14-hospital system. We randomly selected 744 ERCPs in which the primary indication was suspected choledocholithiasis. Patients with a history of cholecystectomy or prior sphincterotomy were excluded. The same patient cohort was assigned as low, intermediate, or high risk according to the 2010 and 2019 guideline criteria. Overall accuracy of both guidelines was compared against the presence of stones and/or sludge on ERCP.Of 744 patients who underwent ERCP, 544 patients (73.1%) had definite stones during ERCP and 696 patients (93.5%) had stones and/or sludge during ERCP. When classified according to the 2019 guidelines, fewer patients were high risk (274/744, 36.8%) compared with 2010 guidelines (449/744, 60.4%; P .001). Within the high-risk group per both guidelines, definitive stone was found during ERCP more frequently in the 2019 guideline cohort (226/274, 82.5%) compared with the 2010 guideline cohort (342/449, 76.2%; P .001). In our patient cohort, overall specificity of the 2010 guideline was 46.5%, which improved to 76.0% as per 2019 guideline criteria (P .001). However, no significant change was noted for either positive predictive value or negative predictive value between 2019 and 2010 guidelines.The 2019 ASGE guidelines are more specific for detection of choledocholithiasis during ERCP when compared with the 2010 guidelines. However, a large number of patients are categorized as intermediate risk per 2019 guidelines and will require an additional confirmatory imaging study.

Defining patient-to-patient similarity is essential for the development of precision medicine in clinical care and research. Conceptually, the identification of similar patient cohorts appears straightforward; however, universally accepted definitions remain elusive. Simultaneously, an explosion of vendors and published algorithms have emerged and all provide varied levels of functionality in identifying patient similarity categories. To provide clarity and a common framework for patient similarity, a workshop at the American Medical Informatics Association 2019 Annual Meeting was convened. This workshop included invited discussants from academics, the biotechnology industry, the FDA, and private practice oncology groups. Drawing from a broad range of backgrounds, workshop participants were able to coalesce around 4 major patient similarity classes: (1) feature, (2) outcome, (3) exposure, and (4) mixed-class. This perspective expands into these 4 subtypes more critically and offers the medical informatics community a means of communicating their work on this important topic.

Purpose Genomic analysis of individual patients is now affordable, and therapies targeting specific molecular aberrations are being tested in clinical trials. Genomically-informed therapy is relevant to many clinical domains, but is particularly applicable to cancer treatment. However, even specialized clinicians need help to interpret genomic data, to navigate the complicated space of clinical trials, and to keep up with the rapidly expanding biomedical literature. To quantitate the cognitive load on treating clinicians, we attempt to quantitate the rate of change in potential treatment options for patients considering genomically-relevant and genomically-selected therapy for cancer. Materials and methods To this end, we analyzed patient-specific reports generated by a precision oncology decision support team (PODS) at a large academic cancer center. Two types of potential treatment options were analyzed: FDA-approved genomically-relevant and genomically-selected therapies and therapies available via clinical trials. We focused on two clinically-actionable alterations: ERBB2 (Her2/neu; amplified vs. non-amplified) and BRAF mutation (V600 vs. non-V600). To determine changes in available treatment options, we grouped patients into similar groups by disease site (ERBB2: breast, gastric and “other”; BRAF: melanoma, non-melanoma). Results A total of 2927 reports for 2366 unique patients were generated 8/2016-12/2018. Reports included 9902 gene variants and 150 disease classifications. BRAF mutation and ERBB2 amplification were annotated with therapeutic options in 270 reports (225 unique patients). The median survival time of a therapeutic option was nine months. Conclusion When compared to “traditional” clinical practice guideline recommendations, treatment options for personalized cancer therapy change seven times more rapidly; partly due to change in knowledge and partly due to logistics such as clinical trial availability.

Objective To build a machine-learning model that predicts laboratory test results and provides a promising lab test reduction strategy, using spatial-temporal correlations. Materials and methods We developed a global prediction model to treat laboratory testing as a series of decisions by considering contextual information over time and across modalities. We validated our method using a critical care database (MIMIC III), which includes 4,570,709 observations of 12 standard laboratory tests, among 38,773 critical care patients. Our deep-learning model made real-time laboratory reduction recommendations and predicted the properties of lab tests, including values, normal/abnormal (whether labs were within the normal range) and transition (normal to abnormal or abnormal to normal from the latest lab test). We reported area under the receiver operating characteristic curve (AUC) for predicting normal/abnormal, evaluated accuracy and absolute bias on prediction vs. observation against lab test reduction proportion. We compared our model against baseline models and analyzed the impact of variations on the recommended reduction strategy. Results Our best model offered a 20.26 % reduction in the number of laboratory tests. By applying the recommended reduction policy on the hold-out dataset (7755 patients), our model predicted normality/abnormality of laboratory tests with a 98.27 % accuracy (AUC, 0.9885; sensitivity, 97.84 %; specificity, 98.80 %; PPV, 99.01 %; NPV, 97.39 %) on 20.26 % reduced lab tests, and recommended 98.10 % of transitions to be checked. Our model performed better than the greedy models, and the recommended reduction strategy was robust. Discussion Strong spatial and temporal correlations between laboratory tests can be used to optimize policies for reducing laboratory tests throughout the hospital course. Our method allows for iterative predictions and provides a superior solution for the dynamic decision-making laboratory reduction problem. Conclusion This work demonstrates a machine-learning model that assists physicians in determining which laboratory tests may be omitted.

There are an ever-increasing number of reports and commentaries that describe the challenges and opportunities associated with the use of big data and data science (DS) in the context of biomedical education, research, and practice. These publications argue that there are substantial benefits resulting from the use of data-centric approaches to solve complex biomedical problems, including an acceleration in the rate of scientific discovery, improved clinical decision making, and the ability to promote healthy behaviors at a population level. In addition, there is an aligned and emerging body of literature that describes the ethical, legal, and social issues that must be addressed to responsibly use big data in such contexts. At the same time, there has been growing recognition that the challenges and opportunities being attributed to the expansion in DS often parallel those experienced by the biomedical informatics community. Indeed, many informaticians would consider some of these issues relevant to the core theories and methods incumbent to the field of biomedical informatics science and practice. In response to this topic area, during the 2016 American College of Medical Informatics Winter Symposium, a series of presentations and focus group discussions intended to define the current state and identify future directions for interaction and collaboration between people who identify themselves as working on big data, DS, and biomedical informatics were conducted. We provide a perspective concerning these discussions and the outcomes of that meeting, and also present a set of recommendations that we have generated in response to a thematic analysis of those same outcomes. Ultimately, this report is intended to: (1) summarize the key issues currently being discussed by the biomedical informatics community as it seeks to better understand how to constructively interact with the emerging biomedical big data and DS fields; and (2) propose a framework and agenda that can serve to advance this type of constructive interaction, with mutual benefit accruing to both fields.

BACKGROUND Genomic testing is increasingly performed in oncology, but concerns remain regarding the clinician's ability to interpret results. In the current study, the authors sought to determine the agreement between physicians and genomic annotators from the Precision Oncology Decision Support (PODS) team at The University of Texas MD Anderson Cancer Center in Houston regarding actionability and the clinical use of test results. METHODS On a prospective protocol, patients underwent clinical genomic testing for hotspot mutations in 46 or 50 genes. Six months after sequencing, physicians received questionnaires for patients who demonstrated a variant in an actionable gene, investigating their perceptions regarding the actionability of alterations and clinical use of these findings. Genomic annotators independently classified these variants as actionable, potentially actionable, unknown, or not actionable. RESULTS Physicians completed 250 of 288 questionnaires (87% response rate). Physicians considered 168 of 250 patients (67%) as having an actionable alteration; of these, 165 patients (98%) were considered to have an actionable alteration by the PODS team and 3 were of unknown significance. Physicians were aware of genotype-matched therapy available for 119 patients (71%) and 48 of these 119 patients (40%) received matched therapy. Approximately 46% of patients in whom physicians regarded alterations as not actionable (36 of 79 patients) were classified as having an actionable/potentially actionable mutation by the PODS team. However, many of these were only theoretically actionable due to limited trials and/or therapies (eg, KRAS). CONCLUSIONS Physicians are aware of recurrent mutations in actionable genes on “hotspot” panels. As larger genomic panels are used, there may be a growing need for annotation of actionability. Decision support to increase awareness of genomically relevant trials and novel treatment options for recurrent mutations (eg, KRAS) also are needed. Cancer 2017. © 2017 American Cancer Society.

High-throughput genomic and molecular profiling of tumors is emerging as an important clinical approach. Molecular profiling is increasingly being used to guide cancer patient care, especially in advanced and incurable cancers. However, navigating the scientific literature to make evidence-based clinical decisions based on molecular profiling results is overwhelming for many oncology clinicians and researchers. The Personalized Cancer Therapy website (www.personalizedcancertherapy.org) was created to provide an online resource for clinicians and researchers to facilitate navigation of available data. Specifically, this resource can be used to help identify potential therapy options for patients harboring oncogenic genomic alterations. Herein, we describe how content on www.personalizedcancertherapy.org is generated and maintained. We end with case scenarios to illustrate the clinical utility of the website. The goal of this publicly available resource is to provide easily accessible information to a broad oncology audience, as this may help ease the information retrieval burden facing participants in the precision oncology field. Cancer Res; 77(21); e123–6. ©2017 AACR.

At the ASCO Data Standards and Interoperability Summit held in May 2016, it was unanimously decided that four areas of current oncology clinical practice have serious, unmet health information technology needs. The following areas of need were identified: 1) omics and precision oncology, 2) advancing interoperability, 3) patient engagement, and 4) value-based oncology. To begin to address these issues, ASCO convened two complementary workshops: the Omics and Precision Oncology Workshop in October 2016 and the Advancing Interoperability Workshop in December 2016. A common goal was to address the complexity, enormity, and rapidly changing nature of genomic information, which existing electronic health records are ill equipped to manage. The subject matter experts invited to the Omics and Precision Oncology Workgroup were tasked with the responsibility of determining a specific, limited need that could be addressed by a software application (app) in the short-term future, using currently available genomic knowledge bases. Hence, the scope of this workshop was to determine the basic functionality of one app that could serve as a test case for app development. The goal of the second workshop, described separately, was to identify the specifications for such an app. This approach was chosen both to facilitate the development of a useful app and to help ASCO and oncologists better understand the mechanics, difficulties, and gaps in genomic clinical decision support tool development. In this article, we discuss the key challenges and recommendations identified by the workshop participants. Our hope is to narrow the gap between the practicing oncologist and ongoing national efforts to provide precision oncology and value-based care to cancer patients.

Objective One promise of nationwide adoption of electronic health records (EHRs) is the availability of data for large-scale clinical research studies. However, because the same patient could be treated at multiple health care institutions, data from only a single site might not contain the complete medical history for that patient, meaning that critical events could be missing. In this study, we evaluate how simple heuristic checks for data “completeness” affect the number of patients in the resulting cohort and introduce potential biases. Materials and Methods We began with a set of 16 filters that check for the presence of demographics, laboratory tests, and other types of data, and then systematically applied all 216 possible combinations of these filters to the EHR data for 12 million patients at 7 health care systems and a separate payor claims database of 7 million members. Results EHR data showed considerable variability in data completeness across sites and high correlation between data types. For example, the fraction of patients with diagnoses increased from 35.0% in all patients to 90.9% in those with at least 1 medication. An unrelated claims dataset independently showed that most filters select members who are older and more likely female and can eliminate large portions of the population whose data are actually complete. Discussion and Conclusion As investigators design studies, they need to balance their confidence in the completeness of the data with the effects of placing requirements on the data on the resulting patient cohort.

In the information age, we expect data systems to make us more effective and efficient—not to make our lives more difficult! In this article, we discuss how we are using data systems, such as electronic health records (EHRs), to improve care delivery. We illustrate how US Oncology is beginning to use real-world evidence to facilitate trial accrual by automatic identification of eligible patients and how big data and predictive analytics will transform the field of oncology. Some information systems are already being used at the point of care and are already empowering clinicians to improve the care of their patients in real time. Telehealth platforms are being used to bridge gaps that currently exist in expertise, geography, and technical capability. Optimizing virtual collaboration, such as through virtual tumor boards, is empowering communities that are geographically disparate to coordinate care. Informatics methods can provide solutions to the challenging problems of how to manage the vast amounts of data confronting the practicing oncologist, including information about treatment regimens, side effects, and the influence of genomics on the practice of oncology. We also discuss some of the challenges of clinical documentation in the modern era, and review emerging efforts to engage patients as digital donors of their EHR data.

// Natalia Paez Arango 1 , Lauren Brusco 2 , Kenna R. Mills Shaw 2 , Ken Chen 3 , Agda Karina Eterovic 4 , Vijaykumar Holla 2 , Amber Johnson 2 , Beate Litzenburger 2 , Yekaterina B. Khotskaya 2 , Nora Sanchez 2 , Ann Bailey 2 , Xiaofeng Zheng 3 , Chacha Horombe 2 , Scott Kopetz 5 , Carol J. Farhangfar 6 , Mark Routbort 7 , Russell Broaddus 8 , Elmer V. Bernstam 9,10 , John Mendelsohn 2,11 , Gordon B. Mills 2,4 and Funda Meric-Bernstam 1,2,12 1 Department of Surgical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 2 Sheikh Khalifa Bin Zayed Al Nahyan Institute for Personalized Cancer Therapy, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 3 Department of Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 4 Department of Systems Biology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 5 Gastrointestinal Medical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 6 Levine Cancer Institute, Carolinas Healthcare System, Charlotte, NC, USA 7 Department of Hematopathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 8 Department of Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 9 School of Biomedical Informatics, The University of Texas Health Science Center at Houston, TX, USA 10 Division of General Internal Medicine, Medical School, The University of Texas Health Science Center at Houston, TX, USA 11 Department of Genomic Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA 12 Department of Investigational Cancer Therapeutics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA Correspondence to: Funda Meric-Bernstam, email: // Keywords : precision medicine, genomics, somatic mutation, CLIA, clinical trial Received : November 09, 2016 Accepted : February 27, 2017 Published : March 08, 2017 Abstract Purpose: Molecular profiling performed in the research setting usually does not benefit the patients that donate their tissues. Through a prospective protocol, we sought to determine the feasibility and utility of performing broad genomic testing in the research laboratory for discovery, and the utility of giving treating physicians access to research data, with the option of validating actionable alterations in the CLIA environment. Experimental design: 1200 patients with advanced cancer underwent characterization of their tumors with high depth hybrid capture sequencing of 201 genes in the research setting. Tumors were also tested in the CLIA laboratory, with a standardized hotspot mutation analysis on an 11, 46 or 50 gene platform. Results: 527 patients (44%) had at least one likely somatic mutation detected in an actionable gene using hotspot testing. With the 201 gene panel, 945 patients (79%) had at least one alteration in a potentially actionable gene that was undetected with the more limited CLIA panel testing. Sixty-four genomic alterations identified on the research panel were subsequently tested using an orthogonal CLIA assay. Of 16 mutations tested in the CLIA environment, 12 (75%) were confirmed. Twenty-five (52%) of 48 copy number alterations were confirmed. Nine (26.5%) of 34 patients with confirmed results received genotype-matched therapy. Seven of these patients were enrolled onto genotype-matched targeted therapy trials. Conclusion: Expanded cancer gene sequencing identifies more actionable genomic alterations. The option of CLIA validating research results can provide alternative targets for personalized cancer therapy.

Objective: There is a lot of information about cancer in Electronic Health Record (EHR) notes that can be useful for biomedical research provided natural language processing (NLP) methods are available to extract and structure this information. In this paper, we present a scoping review of existing clinical NLP literature for cancer. Methods: We identified studies describing an NLP method to extract specific cancer-related information from EHR sources from PubMed, Google Scholar, ACL Anthology, and existing reviews. Two exclusion criteria were used in this study. We excluded articles where the extraction techniques used were too broad to be represented as frames and also where very low-level extraction methods were used. 79 articles were included in the final review. We organized this information according to frame semantic principles to help identify common areas of overlap and potential gaps. Results: Frames were created from the reviewed articles pertaining to cancer information such as cancer diagnosis, tumor description, cancer procedure, breast cancer diagnosis, prostate cancer diagnosis and pain in prostate cancer patients. These frames included both a definition as well as specific frame elements (i.e. extractable attributes). We found that cancer diagnosis was the most common frame among the reviewed papers (36 out of 79), with recent work focusing on extracting information related to treatment and breast cancer diagnosis. Conclusion: The list of common frames described in this paper identifies important cancer-related information extracted by existing NLP techniques and serves as a useful resource for future researchers requiring cancer information extracted from EHR notes. We also argue, due to the heavy duplication of cancer NLP systems, that a general purpose resource of annotated cancer frames and corresponding NLP tools would be valuable., Comment: 2 figures, 4 tables

The paradigm of representation learning through transfer learning has the potential to greatly enhance clinical natural language processing. In this work, we propose a multi-task pre-training and fine-tuning approach for learning generalized and transferable patient representations from medical language. The model is first pre-trained with different but related high-prevalence phenotypes and further fine-tuned on downstream target tasks. Our main contribution focuses on the impact this technique can have on low-prevalence phenotypes, a challenging task due to the dearth of data. We validate the representation from pre-training, and fine-tune the multi-task pre-trained models on low-prevalence phenotypes including 38 circulatory diseases, 23 respiratory diseases, and 17 genitourinary diseases. We find multi-task pre-training increases learning efficiency and achieves consistently high performance across the majority of phenotypes. Most important, the multi-task pre-training is almost always either the best-performing model or performs tolerably close to the best-performing model, a property we refer to as robust. All these results lead us to conclude that this multi-task transfer learning architecture is a robust approach for developing generalized and transferable patient language representations for numerous phenotypes., Comment: Journal of Biomedical Informatics (in press)

Introduction Genomic profiling information is frequently available to oncologists, enabling targeted cancer therapy. Because clinically relevant information is rapidly emerging in the literature and elsewhere, there is a need for informatics technologies to support targeted therapies. To this end, we have developed a system for Automated Identification of Molecular Effects of Drugs, to help biomedical scientists curate this literature to facilitate decision support. Objectives To create an automated system to identify assertions in the literature concerning drugs targeting genes with therapeutic implications and characterize the challenges inherent in automating this process in rapidly evolving domains. Methods We used subject-predicate-object triples (semantic predications) and co-occurrence relations generated by applying the SemRep Natural Language Processing system to MEDLINE abstracts and ClinicalTrials.gov descriptions. We applied customized semantic queries to find drugs targeting genes of interest. The results were manually reviewed by a team of experts. Results Compared to a manually curated set of relationships, recall, precision, and F2 were 0.39, 0.21, and 0.33, respectively, which represents a 3- to 4-fold improvement over a publically available set of predications (SemMedDB) alone. Upon review of ostensibly false positive results, 26% were considered relevant additions to the reference set, and an additional 61% were considered to be relevant for review. Adding co-occurrence data improved results for drugs in early development, but not their better-established counterparts. Conclusions Precision medicine poses unique challenges for biomedical informatics systems that help domain experts find answers to their research questions. Further research is required to improve the performance of such systems, particularly for drugs in development.

Background Understanding patients' knowledge and prior information-seeking regarding personalized cancer therapy (PCT) may inform future patient information systems, consent for molecular testing and PCT protocols. We evaluated breast cancer patients' knowledge and information-seeking behaviors regarding PCT. Methods Newly registered female breast cancer patients ( n =100) at a comprehensive cancer center completed a self-administered questionnaire prior to their first clinic visit. Results Knowledge regarding cancer genetics and PCT was moderate (mean 8.7±3.8 questions correct out of 16). A minority of patients (27%) indicated that they had sought information regarding PCT. Higher education ( p =0.009) and income levels ( p =0.04) were associated with higher knowledge scores and with seeking PCT information ( p =0.04). Knowledge was not associated with willingness to participate in PCT research. Conclusion Educational background and financial status impact patient knowledge as well as information-seeking behavior. For most patients, clinicians are likely to be patients' initial source of information about PCT. Understanding patients' knowledge deficits at presentation may help inform patient education efforts.

Serial laboratory testing is common, especially in Intensive Care Units (ICU). Such repeated testing is expensive and may even harm patients. However, identifying specific tests that can be omitted is challenging. The search space of different lab tests is large and the optimal reduction is hard to determine without modeling the time trajectory of decisions, which is a nontrivial optimization problem. In this paper, we propose a novel deep-learning method with a very concise architecture to jointly predict future lab test events to be omitted and the values of the omitted events based on observed testing values. Using our method, we were able to omit 15% of lab tests with

Importance Suicide is a leading cause of mortality, with suicide-related deaths increasing in recent years. Automated methods for individualized risk prediction have great potential to address this growing public health threat. To facilitate their adoption, they must first be validated across diverse health care settings. Objective To evaluate the generalizability and cross-site performance of a risk prediction method using readily available structured data from electronic health records in predicting incident suicide attempts across multiple, independent, US health care systems. Design, Setting, and Participants For this prognostic study, data were extracted from longitudinal electronic health record data comprisingInternational Classification of Diseases, Ninth Revisiondiagnoses, laboratory test results, procedures codes, and medications for more than 3.7 million patients from 5 independent health care systems participating in the Accessible Research Commons for Health network. Across sites, 6 to 17 years’ worth of data were available, up to 2018. Outcomes were defined byInternational Classification of Diseases, Ninth Revisioncodes reflecting incident suicide attempts (with positive predictive value >0.70 according to expert clinician medical record review). Models were trained using naive Bayes classifiers in each of the 5 systems. Models were cross-validated in independent data sets at each site, and performance metrics were calculated. Data analysis was performed from November 2017 to August 2019. Main Outcomes and Measures The primary outcome was suicide attempt as defined by a previously validated case definition usingInternational Classification of Diseases, Ninth Revisioncodes. The accuracy and timeliness of the prediction were measured at each site. Results Across the 5 health care systems, of the 3 714 105 patients (2 130 454 female [57.2%]) included in the analysis, 39 162 cases (1.1%) were identified. Predictive features varied by site but, as expected, the most common predictors reflected mental health conditions (eg, borderline personality disorder, with odds ratios of 8.1-12.9, and bipolar disorder, with odds ratios of 0.9-9.1) and substance use disorders (eg, drug withdrawal syndrome, with odds ratios of 7.0-12.9). Despite variation in geographical location, demographic characteristics, and population health characteristics, model performance was similar across sites, with areas under the curve ranging from 0.71 (95% CI, 0.70-0.72) to 0.76 (95% CI, 0.75-0.77). Across sites, at a specificity of 90%, the models detected a mean of 38% of cases a mean of 2.1 years in advance. Conclusions and Relevance Across 5 diverse health care systems, a computationally efficient approach leveraging the full spectrum of structured electronic health record data was able to detect the risk of suicidal behavior in unselected patients. This approach could facilitate the development of clinical decision support tools that inform risk reduction interventions.

Causal discovery methods provide a means to ascertain causal attribution from observational data. Causal modeling at scale requires a method to populate models with relevant domain knowledge. We propose to use the biomedical literature to perform feature selection for drug/adverse drug event (ADE) models with clinical observational data derived from electronic health records (EHR) as our primary input data source. We reason that spurious (non-causal) drug-ADE associations from co-occurrence-based analyses should diminish conditional on sets of validated confounders identified in the literature. To evaluate this hypothesis, we used a publicly available reference data set to test the proposed methodology with 4 ADEs and 399 drug-ADE pairs. We calculated baseline scores using the rank order regression coefficients each drug-ADE pair. We then identified confounding variable candidates for each drug-ADE pair using relationship constraints based on normalized predicates to search knowledge extracted from the literature in the publicly available SemMedDB repository. To determine eligibility for inclusion, we checked whether or not there were directed edges pointing to both the drug and the ADE. Finally, we tested whether associations from co-occurrence in the clinical data are diminished conditional on sets of permutations of confounders identified in the literature. Confounder yield rate was ~ 90%, indicating that our method successfully identified confounders in the observational data. Causal models attained aggregate performance improvements of ~ 0.07 area under the curve and reduced the False Discovery Rate from 0.50 to 0.38 over purely statistical models using unadjusted logistic regression.

Background: The role of cancer-related internet use on the patient-physician relationship has not been adequately explored among patients who are cancer-related internet users (CIUs) in early-phase clinical trial clinics. Objective: We examined the association between cancer-related internet use and the patient-physician relationship and decision making among CIUs in an early drug development clinic. Methods: Of 291 Phase I clinic patients who completed a questionnaire on internet use, 179 were CIUs. Generations were defined by the year of patient’s birth: “millennials” (after 1990) and “Generation X/Y” (1965-1990) grouped as “Millennials or Generation X/Y”; “Baby Boomers” (1946-1964); and “Greatest or Silent Generation” (1945 and earlier). Statistical analyses included the Wilcoxon matched-pairs signed-rank test and the Mann-Whitney U test. Results: CIUs were 52% (94/179) female, 44% (78/179) were older than 60 years, and 60% (108/179) had household incomes exceeding US $60,000. The sources of information on cancer and clinical trials included physicians (171/179, 96%), the internet (159/179, 89%), and other clinical trial personnel (121/179, 68%). For the overall sample and each generation, the median values for trust in referring and Phase I clinical trial physicians among early drug development clinic CIUs were 5 on a 0-5 scale, with 5 indicating “complete trust.” CIUs’ trust in their referring (5) and phase 1 (5) physicians was higher than CIUs’ trust in Web-based cancer-related information (3; P

BACKGROUND The role of cancer-related internet use on the patient-physician relationship has not been adequately explored among patients who are cancer-related internet users (CIUs) in early-phase clinical trial clinics. OBJECTIVE We examined the association between cancer-related internet use and the patient-physician relationship and decision making among CIUs in an early drug development clinic. METHODS Of 291 Phase I clinic patients who completed a questionnaire on internet use, 179 were CIUs. Generations were defined by the year of patient’s birth: “millennials” (after 1990) and “Generation X/Y” (1965-1990) grouped as “Millennials or Generation X/Y”; “Baby Boomers” (1946-1964); and “Greatest or Silent Generation” (1945 and earlier). Statistical analyses included the Wilcoxon matched-pairs signed-rank test and the Mann-Whitney U test. RESULTS CIUs were 52% (94/179) female, 44% (78/179) were older than 60 years, and 60% (108/179) had household incomes exceeding US $60,000. The sources of information on cancer and clinical trials included physicians (171/179, 96%), the internet (159/179, 89%), and other clinical trial personnel (121/179, 68%). For the overall sample and each generation, the median values for trust in referring and Phase I clinical trial physicians among early drug development clinic CIUs were 5 on a 0-5 scale, with 5 indicating “complete trust.” CIUs’ trust in their referring (5) and phase 1 (5) physicians was higher than CIUs’ trust in Web-based cancer-related information (3; P CONCLUSIONS Despite the plethora of websites related to cancer and cancer clinical trials, patients in early-phase clinical trial settings trust their physicians more than Web-based information. Cancer-related organizations should provide regularly updated links to trustworthy websites with cancer and clinical trial information for patients and providers and educate providers on reliable cancer websites so that they can better direct their patients to appropriate internet content.

INTRODUCTION: Breast cancer patients and providers are increasingly interested in personalized cancer therapy. Information-seeking behaviors and knowledge about personalized cancer therapy, cancer genetics, and molecular testing may influence patients’ participation in clinical trials and decision making regarding their care. We evaluated breast cancer patients’ knowledge and information seeking behaviors regarding personalized cancer therapy (PCT). METHODS: The study population included newly registered female breast cancer patients at The University of Texas MD Anderson Cancer Center prior to their first clinical visit. Of 308 consecutive patients who were invited to participate, 100 (32%) completed a self-administered questionnaire assessing their knowledge and information seeking preferences regarding PCT. Knowledge regarding cancer genetics and PCT research was assessed using 16 true/false questions (Cronbach’s α=0.88). A knowledge score was computed from the total number of correct responses. RESULTS: Respondents were predominantly white (70%), older (median age 55 years; SD=12.9; range 26-84), educated (78% with college degree or higher) and higher incomes (54% >$50,000/year); 71% had been diagnosed with breast cancer for at most one year at time of participation. Knowledge regarding cancer genetics and PCT was moderate (M=8.68, SD=3.8). Although most participants (85%) could correctly identify the definition of PCT, many (59%) did not know that somatic mutations are not hereditary. Many (75%) knew that molecular testing can reveal risk for other hereditary cancers. Less than half (46.5%) knew about the availability of PCT in clinical trials. A minority (27%) indicated that they had sought information regarding PCT. They sought for information related to specific treatment options. Higher education (p CONCLUSION: Study participants could define PCT, but had limited knowledge of its availability and underlying treatment principles. This may be due, in part, to the fact that few participants had sought information about PCT. Understanding patients’ knowledge and prior information seeking regarding PCT may inform clinicians, who are likely to be patients’ initial source of information about PCT. Citation Format: Deevakar Rogith, Rafeek A Yusuf, Shelley R Hovick, Bryan M Fellman, Susan K Peterson, Allison Burton-Chase, Yisheng Li, Elmer V Bernstam, Funda Meric-Bernstam. Knowledge and Information seeking about personalized breast cancer therapy [abstract]. In: Proceedings of the Thirty-Seventh Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2014 Dec 9-13; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2015;75(9 Suppl):Abstract nr P2-12-13.

With the increasing availability of genomics, routine analysis of advanced cancers is now feasible. Treatment selection is frequently guided by the molecular characteristics of a patient's tumor, and an increasing number of trials are genomically selected. Furthermore, multiple studies have demonstrated the benefit of therapies that are chosen based upon the molecular profile of a tumor. However, the rapid evolution of genomic testing platforms and emergence of new technologies make interpreting molecular testing reports more challenging. More sophisticated precision oncology decision support services are essential. This review outlines existing tools available for health care providers and precision oncology teams and highlights strategies for optimizing decision support. Specific attention is given to the assays currently available for molecular testing, as well as considerations for interpreting alteration information. This article also discusses strategies for identifying and matching patients to clinical trials, current challenges, and proposals for future development of precision oncology decision support. Clin Cancer Res; 24(12); 2719–31. ©2018 AACR.

Genomic testing is increasingly performed in oncology, but concerns remain regarding the clinician's ability to interpret results. In the current study, the authors sought to determine the agreement between physicians and genomic annotators from the Precision Oncology Decision Support (PODS) team at The University of Texas MD Anderson Cancer Center in Houston regarding actionability and the clinical use of test results.On a prospective protocol, patients underwent clinical genomic testing for hotspot mutations in 46 or 50 genes. Six months after sequencing, physicians received questionnaires for patients who demonstrated a variant in an actionable gene, investigating their perceptions regarding the actionability of alterations and clinical use of these findings. Genomic annotators independently classified these variants as actionable, potentially actionable, unknown, or not actionable.Physicians completed 250 of 288 questionnaires (87% response rate). Physicians considered 168 of 250 patients (67%) as having an actionable alteration; of these, 165 patients (98%) were considered to have an actionable alteration by the PODS team and 3 were of unknown significance. Physicians were aware of genotype-matched therapy available for 119 patients (71%) and 48 of these 119 patients (40%) received matched therapy. Approximately 46% of patients in whom physicians regarded alterations as not actionable (36 of 79 patients) were classified as having an actionable/potentially actionable mutation by the PODS team. However, many of these were only theoretically actionable due to limited trials and/or therapies (eg, KRAS).Physicians are aware of recurrent mutations in actionable genes on "hotspot" panels. As larger genomic panels are used, there may be a growing need for annotation of actionability. Decision support to increase awareness of genomically relevant trials and novel treatment options for recurrent mutations (eg, KRAS) also are needed. Cancer 2018;124:966-72. © 2017 American Cancer Society.

SummaryBackground: Patient matching is a key barrier to achieving interoperability. Patient demographic elements must be consistently collected over time and region to be valuable elements for patient matching.Objectives: We sought to determine what patient demographic attributes are collected at multiple institutions in the United States and see how their availability changes over time and across clinical sites.Methods: We compiled a list of 36 demographic elements that stakeholders previously identified as essential patient demographic attributes that should be collected for the purpose of linking patient records. We studied a convenience sample of 9 health care systems from geographically distinct sites around the country. We identified changes in the availability of individual patient demographic attributes over time and across clinical sites.Results: Several attributes were consistently available over the study period (2005–2014) including last name (99.96%), first name (99.95%), date of birth (98.82%), gender/sex (99.73%), postal code (94.71%), and full street address (94.65%). Other attributes changed significantly from 2005–2014: Social security number (SSN) availability declined from 83.3% to 50.44% (pConclusions: Overall, first name, last name, date of birth, gender/sex and address were widely collected across institutional sites and over time. Availability of emerging attributes such as email and phone numbers are increasing while SSN use is declining. Understanding the relative availability of patient attributes can inform strategies for optimal matching in healthcare.Citation: Culbertson A, Goel S, Madden MB, Jackson KL, Carton T, Waitman R, Liu M, Krishnamurthy A, Hall L, Cappella N, Visweswaran S, Safaeinili N, Becich MJ, Applegate R, Bernstam E, Rothman R, Matheny M, Lipori G, Bian J, Hogan W, Bell D, Martin A, Grannis S, Klann J, Sutphen R, O’Hara AB, Kho A. The building blocks of interoperability: A multisite analysis of patient demographic attributes available for matching. Appl Clin Inform 2017; 8: 322–336 https://doi.org/10.4338/ACI-2016-11-RA-0196

Observational data recorded in the Electronic Health Record (EHR) can help us better understand the effects of therapeutic agents in routine clinical practice. As such data were not collected for research purposes, their reuse for research must compensate for additional information that may bias analyses and lead to faulty conclusions. Confounding is present when factors aside from the given predictor(s) affect the response of interest. However, these additional factors may not be known at the outset. In this paper, we present a scalable literature-based confounding variable discovery method for biomedical research applications with pharmacovigilance as our use case. We hypothesized that statistical models, adjusted with literature-derived confounders, will more accurately identify causative drug-adverse drug event (ADE) relationships. We evaluated our method with a curated reference standard, and found a pattern of improved performance ~ 5% in two out of three models for gastrointestinal bleeding (pre-adjusted Area Under Curve ≥ 0.6).

Background We assessed attitudes of breast cancer patients regarding molecular testing for personalized therapy and research.