Returning integrated genomic risk and clinical recommendations: The eMERGE study.

PURPOSE: Assessing the risk of common, complex diseases requires consideration of clinical risk factors as well as monogenic and polygenic risks, which in turn may be reflected in family history. Returning risks to individuals and providers may influence preventive care or use of prophylactic therapies for those individuals at high genetic risk. METHODS: To enable integrated genetic risk assessment, the eMERGE (electronic MEdical Records and GEnomics) network is enrolling 25,000 diverse individuals in a prospective cohort study across 10 sites. The network developed methods to return cross-ancestry polygenic risk scores, monogenic risks, family history, and clinical risk assessments via a genome-informed risk assessment (GIRA) report and will assess uptake of care recommendations after return of results. RESULTS: GIRAs include summary care recommendations for 11 conditions, education pages, and clinical laboratory reports. The return of high-risk GIRA to individuals and providers includes guidelines for care and lifestyle recommendations. Assembling the GIRA required infrastructure and workflows for ingesting and presenting content from multiple sources. Recruitment began in February 2022. CONCLUSION: Return of a novel report for communicating monogenic, polygenic, and family history-based risk factors will inform the benefits of integrated genetic risk assessment for routine health care.

Implementation of preemptive DNA sequence-based pharmacogenomics testing across a large academic medical center: The Mayo-Baylor RIGHT 10K Study.

PURPOSE: The Mayo-Baylor RIGHT 10K Study enabled preemptive, sequence-based pharmacogenomics (PGx)-driven drug prescribing practices in routine clinical care within a large cohort. We also generated the tools and resources necessary for clinical PGx implementation and identified challenges that need to be overcome. Furthermore, we measured the frequency of both common genetic variation for which clinical guidelines already exist and rare variation that could be detected by DNA sequencing, rather than genotyping. METHODS: Targeted oligonucleotide-capture sequencing of 77 pharmacogenes was performed using DNA from 10,077 consented Mayo Clinic Biobank volunteers. The resulting predicted drug response-related phenotypes for 13 genes, including CYP2D6 and HLA, affecting 21 drug-gene pairs, were deposited preemptively in the Mayo electronic health record. RESULTS: For the 13 pharmacogenes of interest, the genomes of 79% of participants carried clinically actionable variants in 3 or more genes, and DNA sequencing identified an average of 3.3 additional conservatively predicted deleterious variants that would not have been evident using genotyping. CONCLUSION: Implementation of preemptive rather than reactive and sequence-based rather than genotype-based PGx prescribing revealed nearly universal patient applicability and required integrated institution-wide resources to fully realize individualized drug therapy and to show more efficient use of health care resources.

Genomic considerations for FHIR®; eMERGE implementation lessons.

Structured representation of clinical genetic results is necessary for advancing precision medicine. The Electronic Medical Records and Genomics (eMERGE) Network's Phase III program initially used a commercially developed XML message format for standardized and structured representation of genetic results for electronic health record (EHR) integration. In a desire to move towards a standard representation, the network created a new standardized format based upon Health Level Seven Fast Healthcare Interoperability Resources (HL7® FHIR®), to represent clinical genomics results. These new standards improve the utility of HL7® FHIR® as an international healthcare interoperability standard for management of genetic data from patients. This work advances the establishment of standards that are being designed for broad adoption in the current health information technology landscape.

Predicting diabetes clinical outcomes using longitudinal risk factor trajectories.

BACKGROUND: The ubiquity of electronic health records (EHR) offers an opportunity to observe trajectories of laboratory results and vital signs over long periods of time. This study assessed the value of risk factor trajectories available in the electronic health record to predict incident type 2 diabetes. STUDY DESIGN AND METHODS: Analysis was based on a large 13-year retrospective cohort of 71,545 adult, non-diabetic patients with baseline in 2005 and median follow-up time of 8 years. The trajectories of fasting plasma glucose, lipids, BMI and blood pressure were computed over three time frames (2000-2001, 2002-2003, 2004) before baseline. A novel method, Cumulative Exposure (CE), was developed and evaluated using Cox proportional hazards regression to assess risk of incident type 2 diabetes. We used the Framingham Diabetes Risk Scoring (FDRS) Model as control. RESULTS: The new model outperformed the FDRS Model (.802 vs .660; p-values <2e-16). Cumulative exposure measured over different periods showed that even short episodes of hyperglycemia increase the risk of developing diabetes. Returning to normoglycemia moderates the risk, but does not fully eliminate it. The longer an individual maintains glycemic control after a hyperglycemic episode, the lower the subsequent risk of diabetes. CONCLUSION: Incorporating risk factor trajectories substantially increases the ability of clinical decision support risk models to predict onset of type 2 diabetes and provides information about how risk changes over time.

CLINICAL RECOGNITION AND MANAGEMENT OF PATIENTS WITH PREDIABETES.

Objective: Early identification and management of prediabetes is critical to prevent progression to diabetes. We aimed to assess whether prediabetes is appropriately recognized and managed among patients with impaired fasting glucose (IFG). Methods: We carried out an observational study of Olmsted County residents evaluated at the Mayo Clinic between 1999-2017. We randomly selected 108 subjects with biochemical criteria of IFG and 105 normoglycemic subjects. We reviewed their health records at baseline (1999-2004) and during follow up (2005-2017) collecting demographic and clinical data including vitals, diagnoses, laboratory, and medications associated with cardiovascular comorbidities. The main outcome was documentation of any recognition of prediabetes and management recommendations (lifestyle changes and/or medications). Results: At baseline (1999-2004), 26.85% (29/108) of subjects with IFG were recognized as having prediabetes, and of these 75.86% (22/29) received management recommendations with 6.9% (2/29) getting metformin. During follow-up (2005-2017), 26.67% (28/105) of initial cohort of normoglycemic subjects developed incident IFG and of these, 85.71% (24/28) were recognized as having prediabetes, and 58.33% (14/24) received management recommendations. During the entire study period, 62.50% (85/136) were recognized as having prediabetes of which 75.29% (64/85) had documented management recommendations. High body mass index (BMI) (≥35) was associated with increased recognition (odds ratio [OR] 3.66; confidence interval [CI] 1.065, 12.500; P = .0395), and normal BMI (<25) was associated with a lack of recognition (OR 0.146; CI 0.189, 0.966; P = .0413). Conclusion: Despite evidence supporting the efficacy of lifestyle changes and medications in managing prediabetes, this condition is not fully recognized in routine clinical practice. Increased awareness of diagnostic criteria and appropriate management are essential to enhance diabetes prevention. Abbreviations: BMI = body mass index; CI = confidence interval; EHR = electronic health records; FBG = fasting blood glucose; IFG = impaired fasting glucose; IGT = impaired glucose tolerance; OR = odds ratio.

Towards more Accessible Precision Medicine: Building a more Transferable Machine Learning Model to Support Prognostic Decisions for Micro- and Macrovascular Complications of Type 2 Diabetes Mellitus.

Although machine learning models are increasingly being developed for clinical decision support for patients with type 2 diabetes, the adoption of these models into clinical practice remains limited. Currently, machine learning (ML) models are being constructed on local healthcare systems and are validated internally with no expectation that they would validate externally and thus, are rarely transferrable to a different healthcare system. In this work, we aim to demonstrate that (1) even a complex ML model built on a national cohort can be transferred to two local healthcare systems, (2) while a model constructed on a local healthcare system's cohort is difficult to transfer; (3) we examine the impact of training cohort size on the transferability; and (4) we discuss criteria for external validity. We built a model using our previously published Multi-Task Learning-based methodology on a national cohort extracted from OptumLabs® Data Warehouse and transferred the model to two local healthcare systems (i.e., University of Minnesota Medical Center and Mayo Clinic) for external evaluation. The model remained valid when applied to the local patient populations and performed as well as locally constructed models (concordance: .73-.92), demonstrating transferability. The performance of the locally constructed models reduced substantially when applied to each other's healthcare system (concordance: .62-.90). We believe that our modeling approach, in which a model is learned from a national cohort and is externally validated, produces a transferable model, allowing patients at smaller healthcare systems to benefit from precision medicine.

Prevalence and Outcome of High-Risk QT Prolongation Recorded in the Emergency Department from an Institution-Wide QT Alert System.

BACKGROUND: QT prolongation is an independent risk factor for sudden death, stroke, and all-cause mortality. However, additional studies have shown that in certain settings, QT prolongation may be transient and a result of external factors. OBJECTIVE: In this study, we evaluated the clinical characteristics and outcomes of patients seen in the emergency department (ED) with QT prolongation. METHODS: Between November 2010 and June 2011, 7522 patients had an electrocardiogram (ECG) obtained during their evaluation in the ED. Clinical, laboratory, and therapeutic information was collected for all patients with QT prolongation (i.e., ≥ 500 ms and QRS < 120 ms). Potential QT-inciting factors (drugs, electrolyte disturbances, and comorbidities) were synthesized into a pro-QT score. RESULTS: Among the 7522 patients with an ECG obtained in the ED, a QT alert was activated in 93 (1.2%; mean QTc 521 ± 34 ms). The majority of ED patients (64%) had more than one underlying condition associated with QT prolongation, with electrolyte disturbances in 51%, a QT prolonging condition in 56%, and QT-prolonging drugs in 77%. Thirty-day mortality was 13% for patients with QT prolongation noted in the ED. CONCLUSIONS: One percent of patients evaluated with an ECG in the ED activated our prolonged QTc warning system, with most demonstrating > 1 QT-prolonging condition. Thirty-day mortality was significant, but it requires further investigation to determine whether the QTc simply provided a non-invasive indicator of increased risk or heralded the presence of a vulnerable host at risk of a QT-mediated sudden dysrhythmic death.

Participant-perceived understanding and perspectives on pharmacogenomics: the Mayo Clinic RIGHT protocol (Right Drug, Right Dose, Right Time).

PURPOSE: To examine predictors of understanding preemptive CYP2D6 pharmacogenomics test results and to identify key features required to improve future educational efforts of preemptive pharmacogenomics testing. METHODS: One thousand ten participants were surveyed after receiving preemptive CYP2D6 pharmacogenomics test results. RESULTS: Eighty-six percent (n = 869) of patients responded. Of the responders, 98% were white and 55% were female; 57% had 4 years or more of post-secondary education and an average age of 58.9 ± 5.5 years. Twenty-six percent said that they only somewhat understood their results and 7% reported they did not understand them at all. Only education predicted understanding. The most common suggestion for improvement was the use of layperson's terms when reporting results. In addition, responders suggested that results should be personalized by referring to medications that they were currently using. Of those reporting imperfect drug adherence, most (91%) reported they would be more likely to use medication as prescribed if pharmacogenomic information was used to help select the drug or dose. CONCLUSION: Despite great efforts to simplify pharmacogenomic results (or because of them), approximately one-third of responders did not understand their results. Future efforts need to provide more examples and tailor results to the individual. Incorporation of pharmacogenomics is likely to improve medication adherence.Genet Med advance online publication 05 January 2017.

Multidisciplinary model to implement pharmacogenomics at the point of care.

PURPOSE: Despite potential clinical benefits, implementation of pharmacogenomics (PGx) faces many technical and clinical challenges. These challenges can be overcome with a comprehensive and systematic implementation model. METHODS: The development and implementation of PGx were organized into eight interdependent components addressing resources, governance, clinical practice, education, testing, knowledge translation, clinical decision support (CDS), and maintenance. Several aspects of implementation were assessed, including adherence to the model, production of PGx-CDS interventions, and access to educational resources. RESULTS: Between August 2012 and June 2015, 21 specific drug-gene interactions were reviewed and 18 of them were implemented in the electronic medical record as PGx-CDS interventions. There was complete adherence to the model with variable production time (98-392 days) and delay time (0-148 days). The implementation impacted approximately 1,247 unique providers and 3,788 unique patients. A total of 11 educational resources complementary to the drug-gene interactions and 5 modules specific for pharmacists were developed and implemented. CONCLUSION: A comprehensive operational model can support PGx implementation in routine prescribing. Institutions can use this model as a roadmap to support similar efforts. However, we also identified challenges that will require major multidisciplinary and multi-institutional efforts to make PGx a universal reality.Genet Med 19 4, 421-429.

Automated T-wave analysis can differentiate acquired QT prolongation from congenital long QT syndrome.

BACKGROUND: Prolongation of the QT on the surface electrocardiogram can be due to either genetic or acquired causes. Distinguishing congenital long QT syndrome (LQTS) from acquired QT prolongation has important prognostic and management implications. We aimed to investigate if quantitative T-wave analysis could provide a tool for the physician to differentiate between congenital and acquired QT prolongation. METHODS: Patients were identified through an institution-wide computer-based QT screening system which alerts the physician if the QTc ≥ 500 ms. ECGs were retrospectively analyzed with an automated T-wave analysis program. Congenital LQTS was compared in a 1:3 ratio to those with an identified acquired etiology for QT prolongation (electrolyte abnormality and/or prescription of known QT prolongation medications). Linear discriminant analysis was performed using 10-fold cross-validation to statistically test the selected features. RESULTS: The 12-lead ECG of 38 patients with congenital LQTS and 114 patients with drug-induced and/or electrolyte-mediated QT prolongation were analyzed. In lead V5 , patients with acquired QT prolongation had a shallower T wave right slope (-2,322 vs. -3,593 mV/s), greater T-peak-Tend interval (109 vs. 92 ms), and smaller T wave center of gravity on the x axis (290 ms vs. 310 ms; p < .001). These features could distinguish congenital from acquired causes in 77% of cases (sensitivity 90%, specificity 58%). CONCLUSION: T-wave morphological analysis on lead V5 of the surface ECG could successfully differentiate congenital from acquired causes of QT prolongation.

Providers' Response to Clinical Decision Support for QT Prolonging Drugs.

Commonly used drugs in hospital setting can cause QT prolongation and trigger life-threatening arrhythmias. We evaluate changes in prescribing behavior after the implementation of a clinical decision support system to prevent the use of QT prolonging medications in the hospital setting. We conducted a quasi-experimental study, before and after the implementation of a clinical decision support system integrated in the electronic medical record (QT-alert system). This system detects patients at risk of significant QT prolongation (QTc>500ms) and alerts providers ordering QT prolonging drugs. We reviewed the electronic health record to assess the provider's responses which were classified as "action taken" (QT drug avoided, QT drug changed, other QT drug(s) avoided, ECG monitoring, electrolytes monitoring, QT issue acknowledged, other actions) or "no action taken". Approximately, 15.5% (95/612) of the alerts were followed by a provider's action in the pre-intervention phase compared with 21% (228/1085) in the post-intervention phase (p=0.006). The most common type of actions taken during pre-intervention phase compared to post-intervention phase were ECG monitoring (8% vs. 13%, p=0.002) and QT issue acknowledgment (2.1% vs. 4.1%, p=0.03). Notably, there was no significant difference for other actions including QT drug avoided (p=0.8), QT drug changed (p=0.06) and other QT drug(s) avoided (p=0.3). Our study demonstrated that the QT alert system prompted a higher proportion of providers to take action on patients at risk of complications. However, the overall impact was modest underscoring the need for educating providers and optimizing clinical decision support to further reduce drug-induced QT prolongation.

Statin Use, Diabetes Incidence and Overall Mortality in Normoglycemic and Impaired Fasting Glucose Patients.

BACKGROUND: The association between the use of statins and the risk of diabetes and increased mortality within the same population has been a source of controversy, and may underestimate the value of statins for patients at risk. OBJECTIVE: We aimed to assess whether statin use increases the risk of developing diabetes or affects overall mortality among normoglycemic patients and patients with impaired fasting glucose (IFG). DESIGN AND PARTICIPANTS: Observational cohort study of 13,508 normoglycemic patients (n = 4460; 33% taking statins) and 4563 IFG patients (n = 1865; 41% taking statin) among residents of Olmsted County, Minnesota, with clinical data in the Mayo Clinic electronic medical record and at least one outpatient fasting glucose test between 1999 and 2004. Demographics, vital signs, tobacco use, laboratory results, medications and comorbidities were obtained by electronic search for the period 1999-2004. Results were analyzed by Cox proportional hazards models, and the risk of incident diabetes and mortality were analyzed by survival curves using the Kaplan-Meier method. MAIN MEASURES: The main endpoints were new clinical diagnosis of diabetes mellitus and total mortality. KEY RESULTS: After a mean of 6 years of follow-up, statin use was found to be associated with an increased risk of incident diabetes in the normoglycemic (HR 1.19; 95% CI, 1.05 to 1.35; p = 0.007) and IFG groups (HR 1.24; 95%CI, 1.11 to 1.38; p = 0.0001). At the same time, overall mortality decreased in both normoglycemic (HR 0.70; 95% CI, 0.66 to 0.80; p < 0.0001) and IFG patients (HR 0.77, 95% CI, 0.64 to 0.91; p = 0.0029) with statin use. CONCLUSION: In general, recommendations for statin use should not be affected by concerns over an increased risk of developing diabetes, since the benefit of reduced mortality clearly outweighs this small (19-24%) risk.

Phenotype of Children with QT Prolongation Identified Using an Institution-Wide QT Alert System.

QT prolongation is an independent risk factor for cardiovascular mortality in adults. However, there is little information available on pediatric patients with QT prolongation and their outcomes. Herein, we evaluated the prevalence of QT prolongation in pediatric patients identified by an institution-wide QT alert system, and the spectrum of their phenotype. Patients with documented QT prolongation on an ECG obtained between November 2010 and June 2011 were included. There were 1303 pediatric ECGs, and 68 children had electrographically isolated QT prolongation. Comprehensive review of medical records was performed with particular attention to QT-prolonging clinical, laboratory, and medication data, which were summarized into a pro-QTc score. Overall, 68 (5 %) pediatric patients had isolated QT prolongation. The mean age of this pediatric cohort was 9 ± 6 years, and the average QTc was 494 ± 42 ms. All children had 1 or more QT-prolonging risk factor(s), most commonly QT-prolonging medications. One patient was identified with congenital long QT syndrome (LQTS), which was not previously diagnosed. In one-year follow-up, only one pediatric death (non-cardiac) occurred (1.5 %). Potentially QT-offending/pro-arrhythmic medications were changed in 80 % of pediatric patients after the physician received the QT alert. Children with QT prolongation had very low mortality and minimal polypharmacy. Still, medications and other modifiable conditions were the most common causes of QT prolongation. Children with a prolonged QTc should be evaluated for modifiable QT-prolonging factors. However, if no risk factors are present or the QTc does not attenuate after risk factor modification/removal, the child should be evaluated for congenital LQTS.

Contrastive Transfer Learning for Prediction of Adverse Events in Hospitalized Patients.

OBJECTIVE: Deterioration index (DI) is a computer-generated score at a specific frequency that represents the overall condition of hospitalized patients using a variety of clinical, laboratory and physiologic data. In this paper, a contrastive transfer learning method is proposed and validated for early prediction of adverse events in hospitalized patients using DI scores. METHODS AND PROCEDURES: An unsupervised contrastive learning (CL) model with a classifier is proposed to predict adverse outcome using a single temporal variable (DI scores). The model is pretrained on an unsupervised fashion with large-scale time series data and fine-tuned with retrospective DI score data. RESULTS: The performance of this model is compared with supervised deep learning models for time series classification. Results show that unsupervised contrastive transfer learning with a classifier outperforms supervised deep learning solutions. Pretraining of the proposed CL model with large-scale time series data and fine-tuning that with DI scores can enhance prediction accuracy. CONCLUSION: A relationship exists between longitudinal DI scores of a patient and the corresponding outcome. DI scores and contrastive transfer learning can be used to predict and prevent adverse outcomes in hospitalized patients. CLINICAL IMPACT: This paper successfully developed an unsupervised contrastive transfer learning algorithm for prediction of adverse events in hospitalized patients. The proposed model can be deployed in hospitals as an early warning system for preemptive intervention in hospitalized patients, which can mitigate the likelihood of adverse outcomes.

Clinical Implementation of an AI Early Warning System Algorithm: Lessons Learned.

The Deterioration Index (DI) is an automatic early warning system that utilizes a machine learning algorithm integrated into the electronic health record and was implemented to improve risk stratification of inpatients. Our pilot implementation showed superior diagnostic accuracy than standard care. A score >60 had a specificity of 88.5% and a sensitivity of 59.8% (PPV 0.1758, NPP 0.9817). However, acceptance in the clinical workflow was divided; nurses preferred standard care, while providers found it helpful.

Decision Support System Detecting Patients at Risk of Prolonged QT and Associated Mortality.

Prolonged QT interval is an independent risk factor for all-cause mortality. However, evaluation of mortality associated to the implementation of a clinical decision support system to increase awareness and provide management recommendations has been challenging. Here we present our attempt to develop a model using only electronic data and different control groups.

Effect of clinical decision support for severe hypercholesterolemia on low-density lipoprotein cholesterol levels.

Severe hypercholesterolemia/possible familial hypercholesterolemia (FH) is relatively common but underdiagnosed and undertreated. We investigated whether implementing clinical decision support (CDS) was associated with lower low-density lipoprotein cholesterol (LDL-C) in patients with severe hypercholesterolemia/possible FH (LDL-C ≥ 190 mg/dL). As part of a pre-post implementation study, a CDS alert was deployed in the electronic health record (EHR) in a large health system comprising 3 main sites, 16 hospitals and 53 clinics. Data were collected for 3 months before ('silent mode') and after ('active mode') its implementation. Clinicians were only able to view the alert in the EHR during active mode. We matched individuals 1:1 in both modes, based on age, sex, and baseline lipid lowering therapy (LLT). The primary outcome was difference in LDL-C between the two groups and the secondary outcome was initiation/intensification of LLT after alert trigger. We identified 800 matched patients in each mode (mean ± SD age 56.1 ± 11.8 y vs. 55.9 ± 11.8 y; 36.0% male in both groups; mean ± SD initial LDL-C 211.3 ± 27.4 mg/dL vs. 209.8 ± 23.9 mg/dL; 11.2% on LLT at baseline in each group). LDL-C levels were 6.6 mg/dL lower (95% CI, -10.7 to -2.5; P = 0.002) in active vs. silent mode. The odds of high-intensity statin use (OR, 1.78; 95% CI, 1.41-2.23; P < 0.001) and LLT initiation/intensification (OR, 1.30, 95% CI, 1.06-1.58, P = 0.01) were higher in active vs. silent mode. Implementation of a CDS was associated with lowering of LDL-C levels in patients with severe hypercholesterolemia/possible FH, likely due to higher rates of clinician led LLT initiation/intensification.

Clinician Perspectives on Clinical Decision Support for Familial Hypercholesterolemia.

Familial Hypercholesterolemia (FH) is underdiagnosed in the United States. Clinical decision support (CDS) could increase FH detection once implemented in clinical workflows. We deployed CDS for FH at an academic medical center and sought clinician insights using an implementation survey. In November 2020, the FH CDS was deployed in the electronic health record at all Mayo Clinic sites in two formats: a best practice advisory (BPA) and an in-basket alert. Over three months, 104 clinicians participated in the survey (response rate 11.1%). Most clinicians (81%) agreed that CDS implementation was a good option for identifying FH patients; 78% recognized the importance of implementing the tool in practice, and 72% agreed it would improve early diagnosis of FH. In comparing the two alert formats, clinicians found the in-basket alert more acceptable (p = 0.036) and more feasible (p = 0.042) than the BPA. Overall, clinicians favored implementing the FH CDS in clinical practice and provided feedback that led to iterative refinement of the tool. Such a tool can potentially increase FH detection and optimize patient management.

Novel machine learning model to improve performance of an early warning system in hospitalized patients: a retrospective multisite cross-validation study.

Background: Threshold-based early warning systems (EWS) are used to predict adverse events (Aes). Machine learning (ML) algorithms that incorporate all EWS scores prior to an event may perform better in hospitalized patients. Methods: The deterioration index (DI) is a proprietary EWS. A threshold of DI >60 is used to predict a composite AE: all-cause mortality, cardiac arrest, transfer to intensive care, and evaluation by the rapid response team in practice. The DI scores were collected for adult patients (≥18 y-o) hospitalized on medical or surgical services during 8-23-2021 to 3-31-2022 from four different Mayo Clinic sites in the United States. A novel ML model was developed and trained on a retrospective cohort of hospital encounters. DI scores were represented in a high-dimensional space using random convolution kernels to facilitate training of a classifier and the area under the receiver operator characteristics curve (AUC) was calculated. Multiple time intervals prior to an AE were analyzed. A leave-one-out cross-validation protocol was used to evaluate performance across separate clinic sites. Findings: Three different classifiers were trained on 59,617 encounter-derived DI scores in high-dimensional feature space and the AUCs were compared to two threshold models. All three tested classifiers improved the AUC over the threshold approaches from 0.56 and 0.57 to 0.76, 0.85 and 0.94. Time interval analysis of the top performing classifier showed best accuracy in the hour before an event occurred (AUC 0.91), but prediction held up even in the 12 h before an AE (AUC 0.80 at minus 12 h, 0.81 at minus 9 h, 0.85 at minus 6 h, and 0.88 at minus 3 h before an AE). Multisite cross-validation using leave-one-out approach on data from four different clinical sites showed broad generalization performance of the top performing ML model with AUC of 0.91, 0.91, 0.95, and 0.91. Interpretation: A novel ML model that incorporates all the longitudinal DI scores prior to an AE in a hospitalized patient performs better at outcome prediction than the currently used threshold model. The use of clinical data, a generalized ML technique, and successful multisite cross-validation demonstrate the feasibility of our model in clinical implementation. Funding: No funding to report.

Pharmacogenomics education and perceptions: is there a gap between internal medicine resident and attending physicians?

Aim: To determine if differences in self-reported pharmacogenomics knowledge, skills and perceptions exist between internal medicine residents and attending physicians. Materials & methods: Forty-six internal medicine residents and 54 attending physicians completed surveys. Thirteen participated in focus groups to explore themes emerging from the surveys. Results: Resident physicians reported a greater amount of pharmacogenomics training compared with attending physicians (48 vs 13%, p < 0.00012). No differences were found in self-reported knowledge, skills and perceptions. Conclusion: Both groups expressed pharmacogenomics was relevant to their current clinical practice; they should be able to provide information to patients and use to guide prescribing, but lacked sufficient education to be able to do so effectively. Practical approaches are needed to teach pharmacogenomics concepts and address point of care gaps.