Utilizing timestamps of longitudinal electronic health record data to classify clinical deterioration events

ObjectiveTo propose an algorithm that utilizes only timestamps of longitudinal electronic health record data to classify clinical deterioration events.Materials and methodsThis retrospective study explores the efficacy of machine learning algorithms in classifying clinical deterioration events among patients in intensive care units using sequences of timestamps of vital sign measurements, flowsheets comments, order entries, and nursing notes. We design a data pipeline to partition events into discrete, regular time bins that we refer to as timesteps. Logistic regressions, random forest classifiers, and recurrent neural networks are trained on datasets of different length of timesteps, respectively, against a composite outcome of death, cardiac arrest, and Rapid Response Team calls. Then these models are validated on a holdout dataset.ResultsA total of 6720 intensive care unit encounters meet the criteria and the final dataset includes 830 578 timestamps. The gated recurrent unit model utilizes timestamps of vital signs, order entries, flowsheet comments, and nursing notes to achieve the best performance on the time-to-outcome dataset, with an area under the precision-recall curve of 0.101 (0.06, 0.137), a sensitivity of 0.443, and a positive predictive value of 0. 092 at the threshold of 0.6.Discussion and ConclusionThis study demonstrates that our recurrent neural network models using only timestamps of longitudinal electronic health record data that reflect healthcare processes achieve well-performing discriminative power.     

Inaccuracies in electronic health records smoking data and a potential approach to address resulting underestimation in determining lung cancer screening eligibility

ObjectiveThe US Preventive Services Task Force (USPSTF) requires the estimation of lifetime pack-years to determine lung cancer screening eligibility. Leading electronic health record (EHR) vendors calculate pack-years using only the most recently recorded smoking data. The objective was to characterize EHR smoking data issues and to propose an approach to addressing these issues using longitudinal smoking data.Materials and MethodsIn this cross-sectional study, we evaluated 16 874 current or former smokers who met USPSTF age criteria for screening (50–80 years old), had no prior lung cancer diagnosis, and were seen in 2020 at an academic health system using the Epic^® EHR. We described and quantified issues in the smoking data. We then estimated how many additional potentially eligible patients could be identified using longitudinal data. The approach was verified through manual review of records from 100 subjects.ResultsOver 80% of evaluated records had inaccuracies, including missing packs-per-day or years-smoked (42.7%), outdated data (25.1%), missing years-quit (17.4%), and a recent change in packs-per-day resulting in inaccurate lifetime pack-years estimation (16.9%). Addressing these issues by using longitudinal data enabled the identification of 49.4% more patients potentially eligible for lung cancer screening (P < .001).DiscussionMissing, outdated, and inaccurate smoking data in the EHR are important barriers to effective lung cancer screening. Data collection and analysis strategies that reflect changes in smoking habits over time could improve the identification of patients eligible for screening.ConclusionThe use of longitudinal EHR smoking data could improve lung cancer screening.     

患者共享个人健康档案数据意愿实证研究

目的：通过调查影响个人健康档案数据共享的因素,调动患者共享个人健康档案数据的积极性。方法：以隐私计算理论为基础,构建患者个人健康档案数据共享意愿模型,收集了400份社区居民数据调查问卷,利用SPSS和AMOS进行因子分析和路径分析,检验所提出的假设。结果：感知隐私风险、信任和利他主义是患者个人健康档案数据共享意愿的影响因素,其中利他主义的影响最强烈。结论：要提高患者的共享个人健康档案数据意愿,最重要的是处理好其共享公益特性和共享风险担忧之间的关系。患者的共享个人健康档案数据意愿不受感知利益的影响是样本代表性问题还是因为相关变量在个人健康档案领域出现了特殊结果,还需要更多类似研究加以证明。     

Factors associated with nurse well-being in relation to electronic health record use: A systematic review

ObjectiveAlthough nurses comprise the largest group of health professionals and electronic health record (EHR) user base, it is unclear how EHR use has affected nurse well-being. This systematic review assesses the multivariable (ie, organizational, nurse, and health information technology [IT]) factors associated with EHR-related nurse well-being and identifies potential improvements recommended by frontline nurses.Materials and MethodsWe searched MEDLINE, Embase, CINAHL, PsycINFO, ProQuest, and Web of Science for literature reporting on EHR use, nurses, and well-being. A quality appraisal was conducted using a previously developed tool.ResultsOf 4583 articles, 12 met inclusion criteria. Two-thirds of the studies were deemed to have a moderate or low risk of bias. Overall, the studies primarily focused on nurse- and IT-level factors, with 1 study examining organizational characteristics. That study found worse nurse well-being was associated with EHRs compared with paper charts. Studies on nurse-level factors suggest that personal digital literacy is one modifiable factor to improving well-being. Additionally, EHRs with integrated displays were associated with improved well-being. Recommendations for improving EHRs suggested IT-, organization-, and policy-level solutions to address the complex nature of EHR-related nurse well-being.ConclusionsThe overarching finding from this synthesis reveals a critical need for multifaceted interventions that better organize, manage, and display information for clinicians to facilitate decision making. Our study also suggests that nurses have valuable insight into ways to reduce EHR-related burden. Future research is needed to test multicomponent interventions that address these complex factors and use participatory approaches to engage nurses in intervention development.     

A study in transfer learning: leveraging data from multiple hospitals to enhance hospital-specific predictions

Background

Data-driven risk stratification models built using data from a single hospital often have a paucity of training data. However, leveraging data from other hospitals can be challenging owing to institutional differences with patients and with data coding and capture.

Objective

To investigate three approaches to learning hospital-specific predictions about the risk of hospital-associated infection with Clostridium difficile, and perform a comparative analysis of the value of different ways of using external data to enhance hospital-specific predictions.

Materials and methods

We evaluated each approach on 132 853 admissions from three hospitals, varying in size and location. The first approach was a single-task approach, in which only training data from the target hospital (ie, the hospital for which the model was intended) were used. The second used only data from the other two hospitals. The third approach jointly incorporated data from all hospitals while seeking a solution in the target space.

Results

The relative performance of the three different approaches was found to be sensitive to the hospital selected as the target. However, incorporating data from all hospitals consistently had the highest performance.

Discussion

The results characterize the challenges and opportunities that come with (1) using data or models from collections of hospitals without adapting them to the site at which the model will be used, and (2) using only local data to build models for small institutions or rare events.

Conclusions

We show how external data from other hospitals can be successfully and efficiently incorporated into hospital-specific models.     

Informative presence and observation in routine health data: A review of methodology for clinical risk prediction

ObjectiveInformative presence (IP) is the phenomenon whereby the presence or absence of patient data is potentially informative with respect to their health condition, with informative observation (IO) being the longitudinal equivalent. These phenomena predominantly exist within routinely collected healthcare data, in which data collection is driven by the clinical requirements of patients and clinicians. The extent to which IP and IO are considered when using such data to develop clinical prediction models (CPMs) is unknown, as is the existing methodology aiming at handling these issues. This review aims to synthesize such existing methodology, thereby helping identify an agenda for future methodological work.Materials and MethodsA systematic literature search was conducted by 2 independent reviewers using prespecified keywords.ResultsThirty-six articles were included. We categorized the methods presented within as derived predictors (including some representation of the measurement process as a predictor in the model), modeling under IP, and latent structures. Including missing indicators or summary measures as predictors is the most commonly presented approach amongst the included studies (24 of 36 articles).DiscussionThis is the first review to collate the literature in this area under a prediction framework. A considerable body relevant of literature exists, and we present ways in which the described methods could be developed further. Guidance is required for specifying the conditions under which each method should be used to enable applied prediction modelers to use these methods.ConclusionsA growing recognition of IP and IO exists within the literature, and methodology is increasingly becoming available to leverage these phenomena for prediction purposes. IP and IO should be approached differently in a prediction context than when the primary goal is explanation. The work included in this review has demonstrated theoretical and empirical benefits of incorporating IP and IO, and therefore we recommend that applied health researchers consider incorporating these methods in their work.     

The effect of an electronic health record system on nursing staff time in a nursing home: a longitudinal cohort study

Background

Nursing homes are increasingly introducing electronic health record (EHR) systems into nursing practice; however, there is limited evidence about the effect of these systems on nursing staff time.

Aims

To investigate the effect of introducing an EHR system on time spent on activities by nursing staff in a nursing home.

Method

An observational work sampling study was undertaken with nursing staff between 2009 and 2011 at two months before, and at 3, 6, 12, and 23 months after implementation of an EHR system at an Australian nursing home. An observer used pre-determined tasks to record activities of the nursing staff at nine-minute intervals.

Results

There was no significant change in registered nurses and endorsed enrolled nurses’ time on most activities after implementation. Personal carers’ time on oral-communication reduced, and time on documentation increased at most measurement periods in the first 12 months after implementation. At 23 months, time on these activities had returned to pre-implementation levels. Nursing staff time on direct care remained stable after implementation. No considerable change was observed in time spent on other activities after implementation.

Conclusion

Findings suggest that successful introduction of an EHR system in a nursing home may not interfere with nursing staff time on direct care duties. However, there is scope for improving the support provided by EHR systems through incorporation of functions to support collaborative nursing care.     

Demonstrating an approach for evaluating synthetic geospatial and temporal epidemiologic data utility: results from analyzing >1.8 million SARS-CoV-2 tests in the United States National COVID Cohort Collaborative (N3C)

ObjectiveThis study sought to evaluate whether synthetic data derived from a national coronavirus disease 2019 (COVID-19) dataset could be used for geospatial and temporal epidemic analyses.Materials and MethodsUsing an original dataset (n = 1 854 968 severe acute respiratory syndrome coronavirus 2 tests) and its synthetic derivative, we compared key indicators of COVID-19 community spread through analysis of aggregate and zip code-level epidemic curves, patient characteristics and outcomes, distribution of tests by zip code, and indicator counts stratified by month and zip code. Similarity between the data was statistically and qualitatively evaluated.ResultsIn general, synthetic data closely matched original data for epidemic curves, patient characteristics, and outcomes. Synthetic data suppressed labels of zip codes with few total tests (mean = 2.9 ± 2.4; max = 16 tests; 66% reduction of unique zip codes). Epidemic curves and monthly indicator counts were similar between synthetic and original data in a random sample of the most tested (top 1%; n = 171) and for all unsuppressed zip codes (n = 5819), respectively. In small sample sizes, synthetic data utility was notably decreased.DiscussionAnalyses on the population-level and of densely tested zip codes (which contained most of the data) were similar between original and synthetically derived datasets. Analyses of sparsely tested populations were less similar and had more data suppression.ConclusionIn general, synthetic data were successfully used to analyze geospatial and temporal trends. Analyses using small sample sizes or populations were limited, in part due to purposeful data label suppression—an attribute disclosure countermeasure. Users should consider data fitness for use in these cases.     

Real-time clinical note monitoring to detect conditions for rapid follow-up: A case study of clinical trial enrollment in drug-induced torsades de pointes and Stevens-Johnson syndrome

Identifying acute events as they occur is challenging in large hospital systems. Here, we describe an automated method to detect 2 rare adverse drug events (ADEs), drug-induced torsades de pointes and Stevens-Johnson syndrome and toxic epidermal necrolysis, in near real time for participant recruitment into prospective clinical studies. A text processing system searched clinical notes from the electronic health record (EHR) for relevant keywords and alerted study personnel via email of potential patients for chart review or in-person evaluation. Between 2016 and 2018, the automated recruitment system resulted in capture of 138 true cases of drug-induced rare events, improving recall from 43% to 93%. Our focused electronic alert system maintained 2-year enrollment, including across an EHR migration from a bespoke system to Epic. Real-time monitoring of EHR notes may accelerate research for certain conditions less amenable to conventional study recruitment paradigms.