Strategies for handling missing clinical data for automated surgical site infection detection from the electronic health record.
Ontology highlight
ABSTRACT:
SUBMITTER: Hu Z
PROVIDER: S-EPMC5474942 | biostudies-literature | 2017 Apr
REPOSITORIES: biostudies-literature
Publications
Strategies for handling missing clinical data for automated surgical site infection detection from the electronic health record.
Hu Zhen Z Melton Genevieve B GB Arsoniadis Elliot G EG Wang Yan Y Kwaan Mary R MR Simon Gyorgy J GJ
Journal of biomedical informatics 20170316
Proper handling of missing data is important for many secondary uses of electronic health record (EHR) data. Data imputation methods can be used to handle missing data, but their use for analyzing EHR data is limited and specific efficacy for postoperative complication detection is unclear. Several data imputation methods were used to develop data models for automated detection of three types (i.e., superficial, deep, and organ space) of surgical site infection (SSI) and overall SSI using Americ ...[more]
Similar Datasets
Project description:Background. While often first treated in the emergency department (ED), identification of sepsis is difficult. Electronic medical record (EMR) clinical decision tools offer a novel strategy for identifying patients with sepsis. The objective of this study was to test the accuracy of an EMR-based, automated sepsis identification system. Methods. We tested an EMR-based sepsis identification tool at a major academic, urban ED with 64,000 annual visits. The EMR system collected vital sign and laboratory test information on all ED patients, triggering a "sepsis alert" for those with ?2 SIRS (systemic inflammatory response syndrome) criteria (fever, tachycardia, tachypnea, leukocytosis) plus ?1 major organ dysfunction (SBP ? 90 mm Hg, lactic acid ?2.0 mg/dL). We confirmed the presence of sepsis through manual review of physician, nursing, and laboratory records. We also reviewed a random selection of ED cases that did not trigger a sepsis alert. We evaluated the diagnostic accuracy of the sepsis identification tool. Results. From January 1 through March 31, 2012, there were 795 automated sepsis alerts. We randomly selected 300 cases without a sepsis alert from the same period. The true prevalence of sepsis was 355/795 (44.7%) among alerts and 0/300 (0%) among non-alerts. The positive predictive value of the sepsis alert was 44.7% (95% CI [41.2-48.2%]). Pneumonia and respiratory infections (38%) and urinary tract infection (32.7%) were the most common infections among the 355 patients with true sepsis (true positives). Among false-positive sepsis alerts, the most common medical conditions were gastrointestinal (26.1%), traumatic (25.7%), and cardiovascular (20.0%) conditions. Rates of hospital admission were: true-positive sepsis alert 91.0%, false-positive alert 83.0%, no sepsis alert 5.7%. Conclusions. This ED EMR-based automated sepsis identification system was able to detect cases with sepsis. Automated EMR-based detection may provide a viable strategy for identifying sepsis in the ED.
| S-EPMC3994640 | biostudies-literature
Project description:BACKGROUND:Untargeted mass spectrometry (MS)-based metabolomics data often contain missing values that reduce statistical power and can introduce bias in biomedical studies. However, a systematic assessment of the various sources of missing values and strategies to handle these data has received little attention. Missing data can occur systematically, e.g. from run day-dependent effects due to limits of detection (LOD); or it can be random as, for instance, a consequence of sample preparation. METHODS:We investigated patterns of missing data in an MS-based metabolomics experiment of serum samples from the German KORA F4 cohort (n = 1750). We then evaluated 31 imputation methods in a simulation framework and biologically validated the results by applying all imputation approaches to real metabolomics data. We examined the ability of each method to reconstruct biochemical pathways from data-driven correlation networks, and the ability of the method to increase statistical power while preserving the strength of established metabolic quantitative trait loci. RESULTS:Run day-dependent LOD-based missing data accounts for most missing values in the metabolomics dataset. Although multiple imputation by chained equations performed well in many scenarios, it is computationally and statistically challenging. K-nearest neighbors (KNN) imputation on observations with variable pre-selection showed robust performance across all evaluation schemes and is computationally more tractable. CONCLUSION:Missing data in untargeted MS-based metabolomics data occur for various reasons. Based on our results, we recommend that KNN-based imputation is performed on observations with variable pre-selection since it showed robust results in all evaluation schemes.
| S-EPMC6153696 | biostudies-literature
Project description:Electronic health records (EHRs) have become a vital source of patient outcome data but the widespread prevalence of missing data presents a major challenge. Different causes of missing data in the EHR data may introduce unintentional bias. Here, we compare the effectiveness of popular multiple imputation strategies with a deeply learned autoencoder using the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT). To evaluate performance, we examined imputation accuracy for known values simulated to be either missing completely at random or missing not at random. We also compared ALS disease progression prediction across different imputation models. Autoencoders showed strong performance for imputation accuracy and contributed to the strongest disease progression predictor. Finally, we show that despite clinical heterogeneity, ALS disease progression appears homogenous with time from onset being the most important predictor.
| S-EPMC5144587 | biostudies-literature
Project description:BackgroundDespite extensive efforts to monitor and prevent surgical site infections (SSIs), real-time surveillance of clinical practice has been sparse and expensive or nonexistent. However, natural language processing (NLP) and machine learning (i.e., Bayesian network analysis) may provide the methodology necessary to approach this issue in a new way. We investigated the ability to identify SSIs after colorectal surgery (CRS) through an automated detection system using a Bayesian network.Materials and methodsPatients who underwent CRS from 2010 to 2012 and were captured in our institutional American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) comprised our cohort. A Bayesian network was applied to detect SSIs using risk factors from ACS-NSQIP data and keywords extracted from clinical notes by NLP. Two surgeons provided expertise informing the Bayesian network to identify clinically meaningful SSIs (CM-SSIs) occurring within 30 d after surgery.ResultsWe used data from 751 CRS cases experiencing 67 (8.9%) SSIs and 78 (10.4%) CM-SSIs. Our Bayesian network detected ACS-NSQIP-captured SSIs with a receiver operating characteristic area under the curve of 0.827, but this value increased to 0.892 when using surgeon-identified CM-SSIs.ConclusionsA Bayesian network coupled with NLP has the potential to be used in real-time SSI surveillance. Moreover, surgeons identified CM-SSI not captured under current NSQIP definitions. Future efforts to expand CM-SSI identification may lead to improved and potentially automated approaches to survey for postoperative SSI in clinical practice.
| S-EPMC5391146 | biostudies-literature
Project description:BackgroundWell-designed randomized trials provide high-quality clinical evidence but are not always feasible or ethical. In their absence, the electronic medical record (EMR) presents a platform to conduct comparative effectiveness research, central to the emerging academic learning health system (aLHS) model. A barrier to realizing this vision is the lack of a process to efficiently generate a reference comparison group for each patient.ObjectiveTo test a multi-step process for the selection of comparators in the EMR.Materials and methodsWe conducted a mixed-methods study within a large aLHS in North Carolina. We (1) created a list of 35 candidate variables; (2) surveyed 270 researchers to assess the importance of candidate variables; and (3) built consensus rankings around survey-identified variables (ie, importance scores >7) across two panels of 7-8 clinical research experts. Prioritized algorithm inputs were collected from the EMR and applied using a greedy matching technique. Feasibility was measured as the percentage of patients with 100 matched comparators and performance was measured via computational time and Euclidean distance.ResultsNine variables were selected: age, sex, race, ethnicity, body mass index, insurance status, smoking status, Charlson Comorbidity Index, and neighborhood percentage in poverty. The final process successfully generated 100 matched comparators for each of 1.8 million candidate patients, executed in less than 100 min for the majority of strata, and had average Euclidean distance 0.043.ConclusionEMR-derived matching is feasible to implement across a diverse patient population and can provide a reproducible, efficient source of comparator data for observational studies, with additional testing in clinical research applications needed.
| S-EPMC10797581 | biostudies-literature
Project description:ObjectiveTo demonstrate that electronic health record (EHR) data can be used in an automated approach to evaluate cataract surgery outcomes.DesignRetrospective analysis.SubjectsResident and faculty surgeons.MethodsElectronic health record data were collected from cataract surgeries performed at the Johns Hopkins Wilmer Eye Institute, and cases were categorized into resident or attending as primary surgeon. Preoperative and postoperative visual acuity (VA) and unplanned return to operating room were extracted from the EHR.Main outcome measuresPostoperative VA and reoperation rate within 90 days.ResultsThis study analyzed 14 537 cataract surgery cases over 32 months. Data were extracted from the EHR using an automated approach to assess surgical outcomes for resident and attending surgeons. Of 337 resident surgeries with both preoperative and postoperative VA data, 248 cases (74%) had better postoperative VA, and 170 cases (51%) had more than 2 lines improvement. There was no statistical difference in the proportion of cases with better postoperative VA or more than 2 lines improvement between resident and attending cases. Attending surgeons had a statistically greater proportion of cases with postoperative VA better than 20/40, but this finding has to be considered in the context that, on average, resident cases started out with poorer baseline VA.A multivariable regression model of VA outcomes vs. resident/attending status that controlled for preoperative VA, patient age, American Society of Anesthesiologists (ASA) score, and estimated income found that resident status, preoperative VA, patient age, ASA score, and estimated income were all significant predictors of VA. The rate of unplanned return to the operating room within 90 days of cataract surgery was not statistically different between resident (1.8%) and attending (1.2%) surgeons.ConclusionsThis study demonstrates that EHR data can be used to evaluate and monitor surgical outcomes in an ongoing way. Analysis of EHR-extracted cataract outcome data showed that preoperative VA, ASA classification, and attending/resident status were important in predicting postoperative VA outcomes. These findings suggest that the utilization of EHR data could enable continuous assessment of surgical outcomes and inform interventions to improve resident training. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.
| S-EPMC9852949 | biostudies-literature
Project description:BackgroundThe guidelines for the prevention, detection, and management of gastroenterological surgical site infections (SSIs) were published in Japanese by the Japan Society for Surgical Infection in 2018. This is a summary of these guidelines for medical professionals worldwide.MethodsWe conducted a systematic review and comprehensive evaluation of the evidence for diagnosis and treatment of gastroenterological SSIs, based on the concepts of the Grading of Recommendations Assessment, Development and Evaluation (GRADE) system. The strength of recommendations was graded and voted using the Delphi method and the nominal group technique. Modifications were made to the guidelines in response to feedback from the general public and relevant medical societies.ResultsThere were 44 questions prepared in seven subject areas, for which 51 recommendations were made. The seven subject areas were: definition and etiology, diagnosis, preoperative management, prophylactic antibiotics, intraoperative management, perioperative management, and wound management. According to the GRADE system, we evaluated the body of evidence for each clinical question. Based on the results of the meta-analysis, recommendations were graded using the Delphi method to generate useful information. The final version of the recommendations was published in 2018, in Japanese.ConclusionsThe Japanese Guidelines for the prevention, detection, and management of gastroenterological SSI were published in 2018 to provide useful information for clinicians and improve the clinical outcome of patients.
| S-EPMC7788056 | biostudies-literature
Project description:ObjectiveA major bottleneck hindering utilization of electronic health record data for translational research is the lack of precise phenotype labels. Chart review as well as rule-based and supervised phenotyping approaches require laborious expert input, hampering applicability to studies that require many phenotypes to be defined and labeled de novo. Though International Classification of Diseases codes are often used as surrogates for true labels in this setting, these sometimes suffer from poor specificity. We propose a fully automated topic modeling algorithm to simultaneously annotate multiple phenotypes.Materials and methodsSurrogate-guided ensemble latent Dirichlet allocation (sureLDA) is a label-free multidimensional phenotyping method. It first uses the PheNorm algorithm to initialize probabilities based on 2 surrogate features for each target phenotype, and then leverages these probabilities to constrain the LDA topic model to generate phenotype-specific topics. Finally, it combines phenotype-feature counts with surrogates via clustering ensemble to yield final phenotype probabilities.ResultssureLDA achieves reliably high accuracy and precision across a range of simulated and real-world phenotypes. Its performance is robust to phenotype prevalence and relative informativeness of surogate vs nonsurrogate features. It also exhibits powerful feature selection properties.DiscussionsureLDA combines attractive properties of PheNorm and LDA to achieve high accuracy and precision robust to diverse phenotype characteristics. It offers particular improvement for phenotypes insufficiently captured by a few surrogate features. Moreover, sureLDA's feature selection ability enables it to handle high feature dimensions and produce interpretable computational phenotypes.ConclusionssureLDA is well suited toward large-scale electronic health record phenotyping for highly multiphenotype applications such as phenome-wide association studies .
| S-EPMC7481024 | biostudies-literature
Project description:BackgroundHigh-quality outcomes data is crucial for continued surgical quality improvement. Outcomes are generally captured through structured administrative data or through manual curation of unstructured electronic health record (EHR) data. The aim of this study was to apply natural language processing (NLP) to chart notes in the EHR to accurately capture postoperative superficial surgical site infections (SSSIs).MethodsDeep Learning (DL) NLP models were trained on data from 389,865 surgical cases across all 11 hospitals in the Capital Region of Denmark. Surgical cases in the training dataset were performed between January 01st, 2017, and October 30th, 2021. We trained a forward reading and a backward reading universal language model on unlabeled postoperative chart notes recorded within 30 days of a surgical procedure. The two language models were subsequently finetuned on labeled data for the classification of SSSIs. Validation and testing were performed on surgical cases performed during the month of November 2021. We propose two different use cases: a stand-alone machine learning (SAM) pipeline and a human-in-the-loop (HITL) pipeline. Performances of both pipelines were compared to administrative data and to manual curation.ResultsThe models were trained on 3,983,864 unlabeled chart notes and finetuned on 1,231,656 labeled notes. Models had a test area under the receiver operating characteristic curves (ROC AUC) of 0.989 on individual chart notes and 0.980 on an aggregated case level. The SAM pipeline had a sensitivity of 0.604, a specificity of 0.996, a positive predictive value (PPV) of 0.763, and a negative predictive value (NPV) of 0.991. Prior to human review, the HITL pipeline had a sensitivity of 0.854, a specificity of 0.987, a PPV of 0.603, and a NPV of 0.997.ConclusionThe performance of the SAM pipeline was superior to administrative data, and significantly outperformed previously published results. The performance of the HITL pipeline approached that of manual curation.
| S-EPMC10801170 | biostudies-literature
Project description:ObjectivesRecent sepsis studies have defined patients as "infected" using a combination of culture and antibiotic orders rather than billing data. However, the accuracy of these definitions is unclear. We aimed to compare the accuracy of different established criteria for identifying infected patients using detailed chart review.DesignRetrospective observational study.SettingSix hospitals from three health systems in Illinois.PatientsAdult admissions with blood culture or antibiotic orders, or Angus International Classification of Diseases infection codes and death were eligible for study inclusion as potentially infected patients. Nine-hundred to 1,000 of these admissions were randomly selected from each health system for chart review, and a proportional number of patients who did not meet chart review eligibility criteria were also included and deemed not infected.InterventionsNone.Measurements and main resultsThe accuracy of published billing code criteria by Angus et al and electronic health record criteria by Rhee et al and Seymour et al (Sepsis-3) was determined using the manual chart review results as the gold standard. A total of 5,215 patients were included, with 2,874 encounters analyzed via chart review and a proportional 2,341 added who did not meet chart review eligibility criteria. In the study cohort, 27.5% of admissions had at least one infection. This was most similar to the percentage of admissions with blood culture orders (26.8%), Angus infection criteria (28.7%), and the Sepsis-3 criteria (30.4%). Sepsis-3 criteria was the most sensitive (81%), followed by Angus (77%) and Rhee (52%), while Rhee (97%) and Angus (90%) were more specific than the Sepsis-3 criteria (89%). Results were similar for patients with organ dysfunction during their admission.ConclusionsPublished criteria have a wide range of accuracy for identifying infected patients, with the Sepsis-3 criteria being the most sensitive and Rhee criteria being the most specific. These findings have important implications for studies investigating the burden of sepsis on a local and national level.
| S-EPMC8217098 | biostudies-literature