Deep learning uncertainty quantification for clinical text classification.

INTRODUCTION: Machine learning algorithms are expected to work side-by-side with humans in decision-making pipelines. Thus, the ability of classifiers to make reliable decisions is of paramount importance. Deep neural networks (DNNs) represent the state-of-the-art models to address real-world classification. Although the strength of activation in DNNs is often correlated with the network's confidence, in-depth analyses are needed to establish whether they are well calibrated. METHOD: In this paper, we demonstrate the use of DNN-based classification tools to benefit cancer registries by automating information extraction of disease at diagnosis and at surgery from electronic text pathology reports from the US National Cancer Institute (NCI) Surveillance, Epidemiology, and End Results (SEER) population-based cancer registries. In particular, we introduce multiple methods for selective classification to achieve a target level of accuracy on multiple classification tasks while minimizing the rejection amount-that is, the number of electronic pathology reports for which the model's predictions are unreliable. We evaluate the proposed methods by comparing our approach with the current in-house deep learning-based abstaining classifier. RESULTS: Overall, all the proposed selective classification methods effectively allow for achieving the targeted level of accuracy or higher in a trade-off analysis aimed to minimize the rejection rate. On in-distribution validation and holdout test data, with all the proposed methods, we achieve on all tasks the required target level of accuracy with a lower rejection rate than the deep abstaining classifier (DAC). Interpreting the results for the out-of-distribution test data is more complex; nevertheless, in this case as well, the rejection rate from the best among the proposed methods achieving 97% accuracy or higher is lower than the rejection rate based on the DAC. CONCLUSIONS: We show that although both approaches can flag those samples that should be manually reviewed and labeled by human annotators, the newly proposed methods retain a larger fraction and do so without retraining-thus offering a reduced computational cost compared with the in-house deep learning-based abstaining classifier.

Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types.

In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.

Pharmacoepidemiology, Machine Learning, and COVID-19: An Intent-to-Treat Analysis of Hydroxychloroquine, With or Without Azithromycin, and COVID-19 Outcomes Among Hospitalized US Veterans.

Hydroxychloroquine (HCQ) was proposed as an early therapy for coronavirus disease 2019 (COVID-19) after in vitro studies indicated possible benefit. Previous in vivo observational studies have presented conflicting results, though recent randomized clinical trials have reported no benefit from HCQ among patients hospitalized with COVID-19. We examined the effects of HCQ alone and in combination with azithromycin in a hospitalized population of US veterans with COVID-19, using a propensity score-adjusted survival analysis with imputation of missing data. According to electronic health record data from the US Department of Veterans Affairs health care system, 64,055 US Veterans were tested for the virus that causes COVID-19 between March 1, 2020 and April 30, 2020. Of the 7,193 veterans who tested positive, 2,809 were hospitalized, and 657 individuals were prescribed HCQ within the first 48-hours of hospitalization for the treatment of COVID-19. There was no apparent benefit associated with HCQ receipt, alone or in combination with azithromycin, and there was an increased risk of intubation when HCQ was used in combination with azithromycin (hazard ratio = 1.55; 95% confidence interval: 1.07, 2.24). In conclusion, we assessed the effectiveness of HCQ with or without azithromycin in treatment of patients hospitalized with COVID-19, using a national sample of the US veteran population. Using rigorous study design and analytic methods to reduce confounding and bias, we found no evidence of a survival benefit from the administration of HCQ.

Acute Kidney Injury Incidence in Noncritically Ill Hospitalized Children, Adolescents, and Young Adults: A Retrospective Observational Study.

BACKGROUND: Acute kidney injury (AKI) has been characterized in high-risk pediatric hospital inpatients, in whom AKI is frequent and associated with increased mortality, morbidity, and length of stay. The incidence of AKI among patients not requiring intensive care is unknown. STUDY DESIGN: Retrospective cohort study. SETTING & PARTICIPANTS: 13,914 noncritical admissions during 2011 and 2012 at our tertiary referral pediatric hospital were evaluated. Patients younger than 28 days or older than 21 years of age or with chronic kidney disease (CKD) were excluded. Admissions with 2 or more serum creatinine measurements were evaluated. FACTORS: Demographic features, laboratory measurements, medication exposures, and length of stay. OUTCOME: AKI defined as increased serum creatinine level in accordance with KDIGO (Kidney Disease: Improving Global Outcomes) criteria. Based on time of admission, time interval requirements were met in 97% of cases, but KDIGO time window criteria were not strictly enforced to allow implementation using clinically obtained data. RESULTS: 2 or more creatinine measurements (one baseline before or during admission and a second during admission) in 2,374 of 13,914 (17%) patients allowed for AKI evaluation. A serum creatinine difference ≥0.3mg/dL or ≥1.5 times baseline was seen in 722 of 2,374 (30%) patients. A minimum of 5% of all noncritical inpatients without CKD in pediatric wards have an episode of AKI during routine hospital admission. LIMITATIONS: Urine output, glomerular filtration rate, and time interval criteria for AKI were not applied secondary to study design and available data. The evaluated cohort was restricted to patients with 2 or more clinically obtained serum creatinine measurements, and baseline creatinine level may have been measured after the AKI episode. CONCLUSIONS: AKI occurs in at least 5% of all noncritically ill hospitalized children, adolescents, and young adults without known CKD. Physicians should increase their awareness of AKI and improve surveillance strategies with serum creatinine measurements in this population so that exacerbating factors such as nephrotoxic medication exposures may be modified as indicated.

Secondary use of clinical data: the Vanderbilt approach.

The last decade has seen an exponential growth in the quantity of clinical data collected nationwide, triggering an increase in opportunities to reuse the data for biomedical research. The Vanderbilt research data warehouse framework consists of identified and de-identified clinical data repositories, fee-for-service custom services, and tools built atop the data layer to assist researchers across the enterprise. Providing resources dedicated to research initiatives benefits not only the research community, but also clinicians, patients and institutional leadership. This work provides a summary of our approach in the secondary use of clinical data for research domain, including a description of key components and a list of lessons learned, designed to assist others assembling similar services and infrastructure.

Question-answering system extracts information on injection drug use from clinical notes.

BACKGROUND: Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients' electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. METHODS: To address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model's ability to extract IDU-related information from temporally out-of-distribution data. RESULTS: Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. CONCLUSIONS: Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.

There are many health risks associated with injection drug use (IDU). Identifying people who inject drugs early can reduce the likelihood of these issues arising. However, extracting information about any possible IDU from a person's electronic health records can be difficult because the information is often in text-based general clinical notes rather than provided in a particular section of the record or as numerical data. Manually extracting information from these notes is time-consuming and inefficient. We used a computational method to train computer software to be able to extract IDU details. Potentially, this approach could be used by healthcare providers to more efficiently and accurately identify people who inject drugs, and therefore provide better advice and medical care.

Adaption and National Validation of a Tool for Predicting Mortality from Other Causes Among Men with Nonmetastatic Prostate Cancer.

BACKGROUND: An electronic health record-based tool could improve accuracy and eliminate bias in provider estimation of the risk of death from other causes among men with nonmetastatic cancer. OBJECTIVE: To recalibrate and validate the Veterans Aging Cohort Study Charlson Comorbidity Index (VACS-CCI) to predict non-prostate cancer mortality (non-PCM) and to compare it with a tool predicting prostate cancer mortality (PCM). DESIGN, SETTING, AND PARTICIPANTS: An observational cohort of men with biopsy-confirmed nonmetastatic prostate cancer, enrolled from 2001 to 2018 in the national US Veterans Health Administration (VA), was divided by the year of diagnosis into the development (2001-2006 and 2008-2018) and validation (2007) sets. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Mortality (all cause, non-PCM, and PCM) was evaluated. Accuracy was assessed using calibration curves and C statistic in the development, validation, and combined sets; overall; and by age (<65 and 65+ yr), race (White and Black), Hispanic ethnicity, and treatment groups. RESULTS AND LIMITATIONS: Among 107 370 individuals, we observed 24 977 deaths (86% non-PCM). The median age was 65 yr, 4947 were Black, and 5010 were Hispanic. Compared with CCI and age alone (C statistic 0.67, 95% confidence interval [CI] 0.67-0.68), VACS-CCI demonstrated improved validated discrimination (C statistic 0.75, 95% CI 0.74-0.75 for non-PCM). The prostate cancer mortality tool also discriminated well in validation (C statistic 0.81, 95% CI 0.78-0.83). Both were well calibrated overall and within subgroups. Owing to missing data, 18 009/125 379 (14%) were excluded, and VACS-CCI should be validated outside the VA prior to outside application. CONCLUSIONS: VACS-CCI is ready for implementation within the VA. Electronic health record-assisted calculation is feasible, improves accuracy over age and CCI alone, and could mitigate inaccuracy and bias in provider estimation. PATIENT SUMMARY: Veterans Aging Cohort Study Charlson Comorbidity Index is ready for application within the Veterans Health Administration. Electronic health record-assisted calculation is feasible, improves accuracy over age and Charlson Comorbidity Index alone, and might help mitigate inaccuracy and bias in provider estimation of the risk of non-prostate cancer mortality.

Effect of image resolution on automated classification of chest X-rays.

Purpose: Deep learning (DL) models have received much attention lately for their ability to achieve expert-level performance on the accurate automated analysis of chest X-rays (CXRs). Recently available public CXR datasets include high resolution images, but state-of-the-art models are trained on reduced size images due to limitations on graphics processing unit memory and training time. As computing hardware continues to advance, it has become feasible to train deep convolutional neural networks on high-resolution images without sacrificing detail by downscaling. This study examines the effect of increased resolution on CXR classification performance. Approach: We used the publicly available MIMIC-CXR-JPG dataset, comprising 377,110 high resolution CXR images for this study. We applied image downscaling from native resolution to 2048×2048 pixels, 1024×1024 pixels, 512×512 pixels, and 256×256 pixels and then we used the DenseNet121 and EfficientNet-B4 DL models to evaluate clinical task performance using these four downscaled image resolutions. Results: We find that while some clinical findings are more reliably labeled using high resolutions, many other findings are actually labeled better using downscaled inputs. We qualitatively verify that tasks requiring a large receptive field are better suited to downscaled low resolution input images, by inspecting effective receptive fields and class activation maps of trained models. Finally, we show that stacking an ensemble across resolutions outperforms each individual learner at all input resolutions while providing interpretable scale weights, indicating that diverse information is extracted across resolutions. Conclusions: This study suggests that instead of focusing solely on the finest image resolutions, multi-scale features should be emphasized for information extraction from high-resolution CXRs.

Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients.

Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients' length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.

Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks.

BACKGROUND: Genome-wide Association Studies (GWAS) aims to uncover the link between genomic variation and phenotype. They have been actively applied in cancer biology to investigate associations between variations and cancer phenotypes, such as susceptibility to certain types of cancer and predisposed responsiveness to specific treatments. Since GWAS primarily focuses on finding associations between individual genomic variations and cancer phenotypes, there are limitations in understanding the mechanisms by which cancer phenotypes are cooperatively affected by more than one genomic variation. RESULTS: This paper proposes a network representation learning approach to learn associations among genomic variations using a prostate cancer cohort. The learned associations are encoded into representations that can be used to identify functional modules of genomic variations within genes associated with early- and late-onset prostate cancer. The proposed method was applied to a prostate cancer cohort provided by the Veterans Administration's Million Veteran Program to identify candidates for functional modules associated with early-onset prostate cancer. The cohort included 33,159 prostate cancer patients, 3181 early-onset patients, and 29,978 late-onset patients. The reproducibility of the proposed approach clearly showed that the proposed approach can improve the model performance in terms of robustness. CONCLUSIONS: To our knowledge, this is the first attempt to use a network representation learning approach to learn associations among genomic variations within genes. Associations learned in this way can lead to an understanding of the underlying mechanisms of how genomic variations cooperatively affect each cancer phenotype. This method can reveal unknown knowledge in the field of cancer biology and can be utilized to design more advanced cancer-targeted therapies.

In with the old, in with the new: machine learning for time to event biomedical research.

The predictive modeling literature for biomedical applications is dominated by biostatistical methods for survival analysis, and more recently some out of the box machine learning approaches. In this article, we show a presentation of a machine learning method appropriate for time-to-event modeling in the area of prostate cancer long-term disease progression. Using XGBoost adapted to long-term disease progression, we developed a predictive model for 118 788 patients with localized prostate cancer at diagnosis from the Department of Veterans Affairs (VA). Our model accounted for patient censoring. Harrell's c-index for our model using only features available at the time of diagnosis was 0.757 95% confidence interval [0.756, 0.757]. Our results show that machine learning methods like XGBoost can be adapted to use accelerated failure time (AFT) with censoring to model long-term risk of disease progression. The long median survival justifies and requires censoring. Overall, we show that an existing machine learning approach can be used for AFT outcome modeling in prostate cancer, and more generally for other chronic diseases with long observation times.

Adopting real-time surveillance dashboards as a component of an enterprisewide medication safety strategy.

BACKGROUND: High-alert medications are frequently responsible for adverse drug events and present significant hazards to inpatients, despite technical improvements in the way they are ordered, dispensed, and administered. METHODS: A real-time surveillance application was designed and implemented to enable pharmacy review of high-alert medication orders to complement existing computerized provider order entry and integrated clinical decision support systems in a tertiary care hospital. The surveillance tool integrated real-time data from multiple clinical systems and applied logical criteria to highlight potentially high-risk scenarios. Use of the surveillance system for adult inpatients was analyzed for warfarin, heparin and enoxaparin, and aminoglycoside antibiotics. RESULTS: Among 28,929 hospitalizations during the study period, patients eligible to appear on a dashboard included 2224 exposed to warfarin, 8383 to heparin or enoxaparin, and 893 to aminoglycosides. Clinical pharmacists reviewed the warfarin and aminoglycoside dashboards during 100% of the days in the study period-and the heparinlenoxaparin dashboard during 71% of the days. Displayed alert conditions ranged from common events, such as 55% of patients receiving aminoglycosides were missing a baseline creatinine, to rare events, such as 0.1% of patients exposed to heparin were given a bolus greater than 10,000 units. On the basis of interpharmacist communication and electronic medical record notes recorded within the dashboards, interventions to prevent further patient harm were frequent. CONCLUSIONS: Even in an environment with sophisticated computerized provider order entry and clinical decision support systems, real-time pharmacy surveillance of high-alert medications provides an important platform for intercepting medication errors and optimizing therapy.

A computerized provider order entry intervention for medication safety during acute kidney injury: a quality improvement report.

BACKGROUND: Frequently, prescribers fail to account for changing kidney function when prescribing medications. We evaluated the use of a computerized provider order entry intervention to improve medication management during acute kidney injury. STUDY DESIGN: Quality improvement report with time series analyses. SETTING & PARTICIPANTS: 1,598 adult inpatients with a minimum 0.5-mg/dL increase in serum creatinine level over 48 hours after an order for at least one of 122 nephrotoxic or renally cleared medications. QUALITY IMPROVEMENT PLAN: Passive noninteractive warnings about increasing serum creatinine level appeared within the computerized provider order entry interface and on printed rounding reports. For contraindicated or high-toxicity medications that should be avoided or adjusted, an interruptive alert within the system asked providers to modify or discontinue the targeted orders, mark the current dosing as correct and to remain unchanged, or defer the alert to reappear in the next session. OUTCOMES & MEASUREMENTS: Intervention effect on drug modification or discontinuation, time to modification or discontinuation, and provider interactions with alerts. RESULTS: The modification or discontinuation rate per 100 events for medications included in the interruptive alert within 24 hours of increasing creatinine level improved from 35.2 preintervention to 52.6 postintervention (P < 0.001); orders were modified or discontinued more quickly (P < 0.001). During the postintervention period, providers initially deferred 78.1% of interruptive alerts, although 54% of these eventually were modified or discontinued before patient death, discharge, or transfer. The response to passive alerts about medications requiring review did not significantly change compared with baseline. LIMITATIONS: Single tertiary-care academic medical center; provider actions were not independently adjudicated for appropriateness. CONCLUSIONS: A computerized provider order entry-based alerting system to support medication management after acute kidney injury significantly increased the rate and timeliness of modification or discontinuation of targeted medications.

Standardized Architecture for a Mega-Biobank Phenomic Library: The Million Veteran Program (MVP).

Electronic health records (EHRs) provide a wealth of data for phenotype development in population health studies, and researchers invest considerable time to curate data elements and validate disease definitions. The ability to reproduce well-defined phenotypes increases data quality, comparability of results and expedites research. In this paper, we present a standardized approach to organize and capture phenotype definitions, resulting in the creation of an open, online repository of phenotypes. This resource captures phenotype development, provenance and process from the Million Veteran Program, a national mega-biobank embedded in the Veterans Health Administration (VHA). To ensure that the repository is searchable, extendable, and sustainable, it is necessary to develop both a proper digital catalog architecture and underlying metadata infrastructure to enable effective management of the data fields required to define each phenotype. Our methods provide a resource for VHA investigators and a roadmap for researchers interested in standardizing their phenotype definitions to increase portability.

JSONize: A Scalable Machine Learning Pipeline to Model Medical Notes as Semi-structured Documents.

The Department of Veteran's Affairs (VA) archives one of the largest corpora of clinical notes in their corporate data warehouse as unstructured text data. Unstructured text easily supports keyword searches and regular expressions. Often these simple searches do not adequately support the complex searches that need to be performed on notes. For example, a researcher may want all notes with a Duke Treadmill Score of less than five or people that smoke more than one pack per day. Range queries like this and more can be supported by modelling text as semi-structured documents. In this paper, we implement a scalable machine learning pipeline that models plain medical text as useful semi-structured documents. We improve on existing models and achieve an F1-score of 0.912 and scale our methods to the entire VA corpus.

Use of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical Records.

Current models for correlating electronic medical records with -omics data largely ignore clinical text, which is an important source of phenotype information for patients with cancer. This data convergence has the potential to reveal new insights about cancer initiation, progression, metastasis, and response to treatment. Insights from this real-world data will catalyze clinical care, research, and regulatory activities. Natural language processing (NLP) methods are needed to extract these rich cancer phenotypes from clinical text. Here, we review the advances of NLP and information extraction methods relevant to oncology based on publications from PubMed as well as NLP and machine learning conference proceedings in the last 3 years. Given the interdisciplinary nature of the fields of oncology and information extraction, this analysis serves as a critical trail marker on the path to higher fidelity oncology phenotypes from real-world data.

Managing and Communicating Operational Workflow: Designing and Implementing an Electronic Outpatient Whiteboard.

BACKGROUND: Healthcare team members in emergency department contexts have used electronic whiteboard solutions to help manage operational workflow for many years. Ambulatory clinic settings have highly complex operational workflow, but are still limited in electronic assistance to communicate and coordinate work activities. OBJECTIVE: To describe and discuss the design, implementation, use, and ongoing evolution of a coordination and collaboration tool supporting ambulatory clinic operational workflow at Vanderbilt University Medical Center (VUMC). METHODS: The outpatient whiteboard tool was initially designed to support healthcare work related to an electronic chemotherapy order-entry application. After a highly successful initial implementation in an oncology context, a high demand emerged across the organization for the outpatient whiteboard implementation. Over the past 10 years, developers have followed an iterative user-centered design process to evolve the tool. RESULTS: The electronic outpatient whiteboard system supports 194 separate whiteboards and is accessed by over 2800 distinct users on a typical day. Clinics can configure their whiteboards to support unique workflow elements. Since initial release, features such as immunization clinical decision support have been integrated into the system, based on requests from end users. CONCLUSIONS: The success of the electronic outpatient whiteboard demonstrates the usefulness of an operational workflow tool within the ambulatory clinic setting. Operational workflow tools can play a significant role in supporting coordination, collaboration, and teamwork in ambulatory healthcare settings.

A prognostic model based on readily available clinical data enriched a pre-emptive pharmacogenetic testing program.

OBJECTIVES: We describe the development, implementation, and evaluation of a model to pre-emptively select patients for genotyping based on medication exposure risk. STUDY DESIGN AND SETTING: Using deidentified electronic health records, we derived a prognostic model for the prescription of statins, warfarin, or clopidogrel. The model was implemented into a clinical decision support (CDS) tool to recommend pre-emptive genotyping for patients exceeding a prescription risk threshold. We evaluated the rule on an independent validation cohort and on an implementation cohort, representing the population in which the CDS tool was deployed. RESULTS: The model exhibited moderate discrimination with area under the receiver operator characteristic curves ranging from 0.68 to 0.75 at 1 and 2 years after index dates. Risk estimates tended to underestimate true risk. The cumulative incidences of medication prescriptions at 1 and 2 years were 0.35 and 0.48, respectively, among 1,673 patients flagged by the model. The cumulative incidences in the same number of randomly sampled subjects were 0.12 and 0.19, and in patients over 50 years with the highest body mass indices, they were 0.22 and 0.34. CONCLUSION: We demonstrate that prognostic algorithms can guide pre-emptive pharmacogenetic testing toward those likely to benefit from it.

Electronic surveillance and pharmacist intervention for vulnerable older inpatients on high-risk medication regimens.

OBJECTIVES: To develop and evaluate an electronic tool to assist clinical pharmacists with reviewing potentially inappropriate medications (PIMs) in hospitalized elderly adults. DESIGN: Pilot intervention. SETTING: Academic tertiary care hospital. PARTICIPANTS: Hospitalized adults aged 65 and older admitted to the general medicine, orthopedics, and urology services during a 3-week period in 2011 who were administered at least one medication from a list of 240 PIMs. INTERVENTION: A computerized PIMS dashboard flagged individuals with at least one administered PIM or a high calculated anticholinergic score. The dashboard also displayed 48-hour cumulative narcotic and benzodiazepine administration. Participants were ranked to reflect the estimated risk of an adverse event using logical combinations of data (e.g., use of multiple sedatives in a nonmonitored location). In a pilot implementation, a clinical pharmacist reviewed the flagged records and delivered an immediate point-of-care intervention for the treating physician. MEASUREMENTS: Clinician response to pharmacist intervention. RESULTS: The PIMS dashboard flagged 179 of 797 individuals (22%) admitted over a 3-week period and 485 participant-medication pairs for review by the clinical pharmacist. Seventy-one participant records with 139 participant-medication pairs required additional manual review of the electronic medical record. Twenty-two participants receiving 40 inappropriate medication orders were judged to warrant an intervention, which was delivered by personal communication over the telephone or text message. Clinicians enacted 31 of 40 (78%) pharmacist recommendations. CONCLUSION: An electronic PIM dashboard provided an efficient mechanism for clinical pharmacists to rapidly screen the medication regimens of hospitalized elderly adults and deliver a timely point-of-care intervention when indicated.

Adverse drug events during AKI and its recovery.

BACKGROUND AND OBJECTIVES: The impact of AKI on adverse drug events and therapeutic failures and the medication errors leading to these events have not been well described. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: A single-center observational study of 396 hospitalized patients with a minimum 0.5 mg/dl change in serum creatinine who were prescribed a nephrotoxic or renally eliminated medication was conducted. The population was stratified into two groups by the direction of their initial serum creatinine change: AKI and AKI recovery. Adverse drug events, potential adverse drug events, therapeutic failures, and potential therapeutic failures for 148 drugs and 46 outcomes were retrospectively measured. Events were classified for preventability and severity by expert adjudication. Multivariable analysis identified medication classes predisposing AKI patients to adverse drug events. RESULTS: Forty-three percent of patients experienced a potential adverse drug event, adverse drug event, therapeutic failure, or potential therapeutic failure; 66% of study events were preventable. Failure to adjust for kidney function (63%) and use of nephrotoxic medications during AKI (28%) were the most common potential adverse drug events. Worsening AKI and hypotension were the most common preventable adverse drug events. Most adverse drug events were considered serious (63%) or life-threatening (31%), with one fatal adverse drug event. Among AKI patients, administration of angiotensin-converting enzyme inhibitors/angiotensin receptor blockers, antibiotics, and antithrombotics was most strongly associated with the development of an adverse drug event or potential adverse drug event. CONCLUSIONS: Adverse drug events and potential therapeutic failures are common and frequently severe in patients with AKI exposed to nephrotoxic or renally eliminated medications.