Dataset Information

Customized reference ranges for laboratory values decrease false positive alerts in intensive care unit patients.

ABSTRACT:

Background

Traditional electronic medical record (EMR) interfaces mark laboratory tests as abnormal based on standard reference ranges derived from healthy, middle-aged adults. This yields many false positive alerts with subsequent alert-fatigue when applied to complex populations like hospitalized, critically ill patients. Novel EMR interfaces using adjusted reference ranges customized for specific patient populations may ameliorate this problem.

Objective

To compare accuracy of abnormal laboratory value indicators in a novel vs traditional EMR interface.

Methods

Laboratory data from intensive care unit (ICU) patients consecutively admitted during a two-day period were recorded. For each patient, available laboratory results and the problem list were sent to two mutually blinded critical care experts, who marked the values about which they would like to be alerted. All disagreements were resolved by an independent super-reviewer. Based on this gold standard, we calculated and compared the sensitivity, specificity, positive and negative predictive values (PPV, NPV) of customized vs traditional abnormal value indicators.

Results

Thirty seven patients with a total of 1341 laboratory results were included. Experts' agreement was fair (kappa = 0.39). Compared to the traditional EMR, custom abnormal laboratory value indicators had similar sensitivity (77% vs 85%, P = 0.22) and NPV (97.1% vs 98.6%, P = 0.06) but higher specificity (79% vs 61%, P < 0.001) and PPV (28% vs 11%, P < 0.001).

Conclusions

Reference ranges for laboratory values customized for an ICU population decrease false positive alerts. Disagreement among clinicians about which laboratory values should be indicated as abnormal limits the development of customized reference ranges.

SUBMITTER: Kilickaya O

PROVIDER: S-EPMC4169437 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Customized reference ranges for laboratory values decrease false positive alerts in intensive care unit patients.

Kilickaya Oguz O Schmickl Christopher C Ahmed Adil A Pulido Juan J Onigkeit James J Kashani Kianoush K Gajic Ognjen O Herasevich Vitaly V Pickering Brian B

PloS one 20140918 9

<h4>Background</h4>Traditional electronic medical record (EMR) interfaces mark laboratory tests as abnormal based on standard reference ranges derived from healthy, middle-aged adults. This yields many false positive alerts with subsequent alert-fatigue when applied to complex populations like hospitalized, critically ill patients. Novel EMR interfaces using adjusted reference ranges customized for specific patient populations may ameliorate this problem.<h4>Objective</h4>To compare accuracy of ...[more]

PMID: 25233485

Similar Datasets

Project description:ImportanceLaboratory data are frequently collected throughout the care of critically ill patients. Currently, these data are interpreted by comparison with values from healthy outpatient volunteers. Whether this is the most useful comparison has yet to be demonstrated.ObjectivesTo understand how the distribution of intensive care unit (ICU) laboratory values differs from the reference range, and how these distributions are related to patient outcomes.Design, setting, and participantsCross-sectional study of a large critical care database, the Medical Information Mart for Intensive Care database, from January 1, 2001, to October 31, 2012. The database is collected from ICU data from a large tertiary medical center in Boston, Massachusetts. The data are collected from medical, cardiac, neurologic, and surgical ICUs. All patients in the database from all ICUs for 2001 to 2012 were included. Common laboratory measurements over the time window of interest were sampled. The analysis was conducted from March to June 2017.Main outcomes and measuresThe overlapping coefficient and Cohen standardized mean difference between distributions were calculated, and kernel density estimate visualizations for the association between laboratory values and the probability of death or quartile of ICU length of stay were created.ResultsAmong 38?605 patients in the ICU (21?852 [56.6%] male; mean [SD] age, 74.5 [55.1] years), 8878 (23%) had the best outcome (ICU survival, shortest quartile length of stay) and 3090 (8%) had the worst outcome (ICU nonsurvival). Distribution curves based on ICU data differed significantly from the hospital standard range (mean [SD] overlapping coefficient, 0.51 [0.32-0.69]). All laboratory values for the best outcome group differed significantly from those in the worst outcome group. Both the best and worst outcome group curves revealed little overlap with and marked divergence from the reference range.Conclusions and relevanceThe standard reference ranges obtained from healthy volunteers differ from the analogous range generated from data from patients in intensive care. Laboratory data interpretation may benefit from greater consideration of clinically contextual and outcomes-related factors.

Project description:BackgroundIn recent years, the volume of medical knowledge and health data has increased rapidly. For example, the increased availability of electronic health records (EHRs) provides accurate, up-to-date, and complete information about patients at the point of care and enables medical staff to have quick access to patient records for more coordinated and efficient care. With this increase in knowledge, the complexity of accurate, evidence-based medicine tends to grow all the time. Health care workers must deal with an increasing amount of data and documentation. Meanwhile, relevant patient data are frequently overshadowed by a layer of less relevant data, causing medical staff to often miss important values or abnormal trends and their importance to the progression of the patient's case.ObjectiveThe goal of this work is to analyze the current laboratory results for patients in the intensive care unit (ICU) and classify which of these lab values could be abnormal the next time the test is done. Detecting near-future abnormalities can be useful to support clinicians in their decision-making process in the ICU by drawing their attention to the important values and focus on future lab testing, saving them both time and money. Additionally, it will give doctors more time to spend with patients, rather than skimming through a long list of lab values.MethodsWe used Structured Query Language to extract 25 lab values for mechanically ventilated patients in the ICU from the MIMIC-III and eICU data sets. Additionally, we applied time-windowed sampling and holding, and a support vector machine to fill in the missing values in the sparse time series, as well as the Tukey range to detect and delete anomalies. Then, we used the data to train 4 deep learning models for time series classification, as well as a gradient boosting-based algorithm and compared their performance on both data sets.ResultsThe models tested in this work (deep neural networks and gradient boosting), combined with the preprocessing pipeline, achieved an accuracy of at least 80% on the multilabel classification task. Moreover, the model based on the multiple convolutional neural network outperformed the other algorithms on both data sets, with the accuracy exceeding 89%.ConclusionsIn this work, we show that using machine learning and deep neural networks to predict near-future abnormalities in lab values can achieve satisfactory results. Our system was trained, validated, and tested on 2 well-known data sets to ensure that our system bridged the reality gap as much as possible. Finally, the model can be used in combination with our preprocessing pipeline on real-life EHRs to improve patients' diagnosis and treatment.

Project description:BackgroundIn metabarcoding analyses, the taxonomic assignment is crucial to place sequencing data in biological and ecological contexts. This fundamental step depends on a reference database, which should have a good taxonomic coverage to avoid unassigned sequences. However, this goal is rarely achieved in many geographic regions and for several taxonomic groups. On the other hand, more is not necessarily better, as sequences in reference databases belonging to taxonomic groups out of the studied region/environment context might lead to false assignments.MethodsWe investigated the effect of using several subsets of a cytochrome c oxidase subunit I (COI) reference database on taxonomic assignment. Published metabarcoding sequences from the Mediterranean Sea were assigned to taxa using COInr, which is a comprehensive, non-redundant and recent database of COI sequences obtained both from BOLD and NCBI, and two of its subsets: (i) all sequences except insects (COInr-WO-Insecta), which represent the overwhelming majority of COInr database, but are irrelevant for marine samples, and (ii) all sequences from taxonomic families present in the Mediterranean Sea (COInr-Med). Four different algorithms for taxonomic assignment were employed in parallel to evaluate differences in their output and data consistency.ResultsThe reduction of the database to more specific custom subsets increased the number of unassigned sequences. Nevertheless, since most of them were incorrectly assigned by the less specific databases, this is a positive outcome. Moreover, the taxonomic resolution (the lowest taxonomic level to which a sequence is attributed) of several sequences tended to increase when using customized databases. These findings clearly indicated the need for customized databases adapted to each study. However, the very high proportion of unassigned sequences points to the need to enrich the local database with new barcodes specifically obtained from the studied region and/or taxonomic group. Including novel local barcodes to the COI database proved to be very profitable: by adding only 116 new barcodes sequenced in our laboratory, thus increasing the reference database by only 0.04%, we were able to improve the resolution for ca. 0.6-1% of the Amplicon Sequence Variants (ASVs).

Project description:Healthcare expenses are increasing, as is the utilization of laboratory resources. Despite this, between 20% and 40% of requested tests are deemed inappropriate. Improper use of laboratory resources leads to unwanted consequences such as hospital-acquired anemia, infections, increased costs, staff workload and patient stress and discomfort. The most unfavorable consequences result from unnecessary follow-up tests and treatments (overuse) and missed or delayed diagnoses (underuse). In this context, several interventions have been carried out to improve the appropriateness of laboratory testing. To date, there have been few published assessments of interventions specific to the intensive care unit. We reviewed the literature for interventions implemented in the ICU to improve the appropriateness of laboratory testing. We searched literature from 2008 to 2023 in PubMed, Embase, Scopus, and Google Scholar databases between April and June 2023. Five intervention categories were identified: education and guidance (E&G), audit and feedback, gatekeeping, computerized physician order entry (including reshaping of ordering panels), and multifaceted interventions (MFI). We included a sixth category exploring the potential role of artificial intelligence and machine learning (AI/ML)-based assisting tools in such interventions. E&G-based interventions and MFI are the most frequently used approaches. MFI is the most effective type of intervention, and shows the strongest persistence of effect over time. AI/ML-based tools may offer valuable assistance to the improvement of appropriate laboratory testing in the near future. Patient safety outcomes are not impaired by interventions to reduce inappropriate testing. The literature focuses mainly on reducing overuse of laboratory tests, with only one intervention mentioning underuse. We highlight an overall poor quality of methodological design and reporting and argue for standardization of intervention methods. Collaboration between clinicians and laboratory staff is key to improve appropriate laboratory utilization. This article offers practical guidance for optimizing the effectiveness of an intervention protocol designed to limit inappropriate use of laboratory resources.

Dataset Information

Customized reference ranges for laboratory values decrease false positive alerts in intensive care unit patients.

Background

Objective

Methods

Results

Conclusions

Publications

Customized reference ranges for laboratory values decrease false positive alerts in intensive care unit patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets