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.

Using clinical decision support as a means of implementing a universal postpartum depression screening program.

A major barrier to the diagnosis of postpartum depression (PPD) includes symptom detection. The lack of awareness and understanding of PPD among new mothers, the variability in clinical presentation, and the various diagnostic strategies can increase this further. The purpose of this study was to test the feasibility of adding clinical decision support (CDS) to the electronic health record (EHR) as a means of implementing a universal standardized PPD screening program within a large, at high risk, population. All women returning to the Mount Sinai Hospital OB/GYN Ambulatory Practice for postpartum care between 2010 and 2013 were presented with the Edinburgh Postnatal Depression Scale (EPDS) in response to a CDS "hard stop" built into the EHR. Of the 2102 women who presented for postpartum care, 2092 women (99.5 %) were screened for PPD in response to a CDS hard stop module. Screens were missing on ten records (0.5 %) secondary to refusal, language barrier, or lack of clarity in the EHR. Technology is becoming increasingly important in addressing the challenges faced by health care providers. While the identification of PPD has become the recent focus of public health concerns secondary to the significant social burden, numerous barriers to screening still exist within the clinical setting. The utility of adding CDS in the form of a hard stop, requiring clinicians to enter a standardized PPD mood assessment score to the patient EHR, offers a sufficient way to address a primary barrier to PPD symptom identification at the practitioner level.

Risk factors for wrong-patient medication orders in the emergency department.

Objectives: This paper investigates the risk factors for wrong-patient medication orders in an emergency department (ED) by studying intercepted ordering errors identified by the "retract-and-reorder" (RaR) metric (orders that were retracted and reordered for a different patient by the same provider within 10 min). Materials and Methods: Medication ordering data of an academic ED were analyzed to identify RaR events. The association of RaR events with similarity of patient names and birthdates, matching sex, age difference, the month, weekday, and hour of the RaR event, the elapsed hours since ED shift start, and the proximity of exam rooms in the electronic medical record (EMR) dashboard's layout was evaluated. Results: Over 5 years (2017-2021), 1031 RaR events were identified among a total of 561 099 medication orders leading to a proportional incidence of 184 per 100 000 ED orders (95% CI: 172; 195). RaR orders were less likely to be performed by nurses compared to physicians (OR 0.54 [0.47; 0.61], P < .001). Furthermore, RaR pairs were more likely to have the same sex (OR 1.26 [95% CI 1.10; 1.43], P = .001) and the proximity of the exam rooms was closer (-0.62 [95% CI -0.77; -0.47], P = .001) compared to control pairs. Patients' names, birthdates, age, and the other factors showed no significant association (P > .005). Discussion and Conclusion: This study found no significant influence from factors such as similarity of patient names, age, or birthdates. However, the proximity of exam rooms in the user interface of the EMR as well as patients' same sex emerged as risk factors.

Automatic knowledge extraction from Chinese electronic medical records and rheumatoid arthritis knowledge graph construction.

Background: Knowledge graphs are a powerful tool for organizing knowledge, processing information and integrating scattered information, effectively visualizing the relationships among entities and supporting further intelligent applications. One of the critical tasks in building knowledge graphs is knowledge extraction. The existing knowledge extraction models in the Chinese medical domain usually require high-quality and large-scale manually labeled corpora for model training. In this study, we investigate rheumatoid arthritis (RA)-related Chinese electronic medical records (CEMRs) and address the automatic knowledge extraction task with a small number of annotated samples from CEMRs, from which an authoritative RA knowledge graph is constructed. Methods: After constructing the domain ontology of RA and completing manual labeling, we propose the MC-bidirectional encoder representation from transformers-bidirectional long short-term memory-conditional random field (BERT-BiLSTM-CRF) model for the named entity recognition (NER) task and the MC-BERT + feedforward neural network (FFNN) model for the entity extraction task. The pretrained language model (MC-BERT) is trained with many unlabeled medical data and fine-tuned using other medical domain datasets. We apply the established model to automatically label the remaining CEMRs, and then an RA knowledge graph is constructed based on the entities and entity relations, a preliminary assessment is conducted, and an intelligent application is presented. Results: The proposed model achieved better performance than that of other widely used models in knowledge extraction tasks, with mean F1 scores of 92.96% in entity recognition and 95.29% in relation extraction. This study preliminarily confirmed that using a pretrained medical language model could solve the problem that knowledge extraction from CEMRs requires a large number of manual annotations. An RA knowledge graph based on the above identified entities and extracted relations from 1,986 CEMRs was constructed. Experts verified the effectiveness of the constructed RA knowledge graph. Conclusions: In this paper, an RA knowledge graph based on CEMRs was established, the processes of data annotation, automatic knowledge extraction, and knowledge graph construction were described, and a preliminary assessment and an application were presented. The study demonstrated the viability of a pretrained language model combined with a deep neural network for knowledge extraction tasks from CEMRs based on a small number of manually annotated samples.

Non-recovery of vancomycin-associated nephrotoxicity is related to worsening survival outcomes: Combined retrospective analyses of two real-world databases.

There has been growing concern in worsening survival and renal outcomes following vancomycin-associated nephrotoxicity (VAN) onset, but the factors associated with these phenomena remain unclear. To examine these factors, we performed a retrospective study combining the analysis of two real-world databases. Initially, the FDA Adverse Event Reporting System (FAERS) was used to evaluate the relationship between VAN and mortality using odds ratios (ORs) and 95% confidence intervals (CIs). Next, electronic medical records (EMRs) were examined in a more robust cohort for evaluation of the association between renal outcomes and worsening survival using Cox proportional hazards regression models. FAERS analysis revealed a significant correlation between VAN occurrence and increased mortality (OR: 1.30; 95% CI: 1.17-1.46). EMR analysis showed that non-recovery of VAN was associated with increased hospital mortality (hazard ratio [HR]: 4.05; 95% CI: 2.42-6.77) and 1-year mortality (HR: 3.03, 95% CI: 1.98-4.64). The HR for VAN recovery was lower for patients with acute kidney injury (AKI) stage ≥2 (HR: 0.09; 95% CI: 0.02-0.40). Thus, worsening survival outcomes were associated with non-recovery of VAN, whereby AKI stage ≥2 was a significant risk factor. Progression to severe VAN should be prevented for better survival outcomes.

Inferencing Bulk Tumor and Single-Cell Multi-Omics Regulatory Networks for Discovery of Biomarkers and Therapeutic Targets.

There are insufficient accurate biomarkers and effective therapeutic targets in current cancer treatment. Multi-omics regulatory networks in patient bulk tumors and single cells can shed light on molecular disease mechanisms. Integration of multi-omics data with large-scale patient electronic medical records (EMRs) can lead to the discovery of biomarkers and therapeutic targets. In this review, multi-omics data harmonization methods were introduced, and common approaches to molecular network inference were summarized. Our Prediction Logic Boolean Implication Networks (PLBINs) have advantages over other methods in constructing genome-scale multi-omics networks in bulk tumors and single cells in terms of computational efficiency, scalability, and accuracy. Based on the constructed multi-modal regulatory networks, graph theory network centrality metrics can be used in the prioritization of candidates for discovering biomarkers and therapeutic targets. Our approach to integrating multi-omics profiles in a patient cohort with large-scale patient EMRs such as the SEER-Medicare cancer registry combined with extensive external validation can identify potential biomarkers applicable in large patient populations. These methodologies form a conceptually innovative framework to analyze various available information from research laboratories and healthcare systems, accelerating the discovery of biomarkers and therapeutic targets to ultimately improve cancer patient survival outcomes.

Text-mining in electronic healthcare records can be used as efficient tool for screening and data collection in cardiovascular trials: a multicenter validation study.

OBJECTIVE: This study aimed to validate trial patient eligibility screening and baseline data collection using text-mining in electronic healthcare records (EHRs), comparing the results to those of an international trial. STUDY DESIGN AND SETTING: In three medical centers with different EHR vendors, EHR-based text-mining was used to automatically screen patients for trial eligibility and extract baseline data on nineteen characteristics. First, the yield of screening with automated EHR text-mining search was compared with manual screening by research personnel. Second, the accuracy of extracted baseline data by EHR text mining was compared to manual data entry by research personnel. RESULTS: Of the 92,466 patients visiting the out-patient cardiology departments, 568 (0.6%) were enrolled in the trial during its recruitment period using manual screening methods. Automated EHR data screening of all patients showed that the number of patients needed to screen could be reduced by 73,863 (79.9%). The remaining 18,603 (20.1%) contained 458 of the actual participants (82.4% of participants). In trial participants, automated EHR text-mining missed a median of 2.8% (Interquartile range [IQR] across all variables 0.4-8.5%) of all data points compared to manually collected data. The overall accuracy of automatically extracted data was 88.0% (IQR 84.7-92.8%). CONCLUSION: Automatically extracting data from EHRs using text-mining can be used to identify trial participants and to collect baseline information.

Education and Training on Electronic Medical Records (EMRs) for health care professionals and students: A Scoping Review.

BACKGROUND AND OBJECTIVES: The ability of health care providers and students to use EMRs efficiently can lead to achieving improved clinical outcomes. Training policies and strategies play a major role in successful technology implementation and ongoing use of the EMR systems. To provide evidence-based guidance for developing and implementing educational interventions and training, we reviewed and summarized the current literature on EMR training targeting both healthcare professionals (HCP) and students. METHODS: We used the Joanna Briggs Institute (JBI) approach for scoping reviews and the PRISMA extension of scoping reviews (PRISMA-ScR) checklist for reporting our review. 46 full-text articles that met the eligibility criteria were selected for the review. Narrative synthesis was performed to summarize the evidence using numerical and descriptive analysis. We used inductive content analysis for categorizing the training methods. Also, the modified version of the Kirkpatrick's levels model was used for abstracting the training outcome. RESULTS: Five types of training methods were identified: one-on-one training, peer-coach training, classroom training (CRT), computer-based training (CBT), and blended training. A variety of CBT platforms were used, including a prototype academic electronic medical record system (AEMR), AEMR/simulated EMR (Sim-EMR), mobile based AEMR, eLearning, and electronic educational materials. Each training intervention could have resulted in several outcomes. Most outcomes were related to levels 1-3 of the Kirkpatrick model that involves learners (n = 108), followed by level 4a that involves organizations (n = 7), and lastly level 4b that involves patients (n = 1). The outcomes related to participants' knowledge (level 2b) was the most often measured training outcome (n = 44). CONCLUSIONS: This review presents a comprehensive synthesis of the evidence on EMR training. A variety of training methods, participants, locations, strategies, and outcomes were described in the studies. Training should be aligned with the particular training needs, training objectives, EMR system utilized, and organizational environment. A training plan should include an overall goal and SMART (Specific, Measurable, Achievable, Realistic, Tangible) training objectives, that would allow a more rigorous evaluation of the training outcomes.

Exploring and validating the clinical risk factors for pancreatic cancer in chronic pancreatitis patients using electronic medical records datasets: three cohorts comprising 2,960 patients.

BACKGROUND: Patients with chronic pancreatitis (CP) have an increased risk of developing pancreatic cancer (PC). The purpose of this study was to identify predictors of PC in CP patients. METHODS: Electronic medical records (EMRs) of CP patients from two cohorts were collected, and a logistic regression analysis was performed to investigate the risk factors for PC. Subsequently, we validated the value of the risk prediction model with the EMRs of a third cohort. RESULTS: The derivation cohort consisted of 2,545 CP patients, and among them, 14 patients developed PC 7 years after CP diagnosis. Cyst of the pancreas [COP; odds ratio (OR): 4.37, 95% confidence interval (CI): 1.11 to 18.40, P=0.033], loss of weight (LW; OR: 3.21, 95% CI: 0.76 to 12.91, P=0.096) and high platelet (PLT) count (OR: 1.01 per 1 increment, 95% CI: 1.00 to 1.01, P=0.042) were independent risk factors for PC among CP patients. A risk prediction equation was constructed as follows: ln[p/(1-p)] = -6.68 + 1.55COP + 1.23LW + 0.0046PLT. The areas under the receiver operating characteristic (ROC) curve of our risk score were 0.83 and 0.72 in the derivation and validation cohorts, respectively. A score >0.0128 and >0.0122 had the best balance between sensitivity and specificity in the derivation and validation cohorts, respectively. CONCLUSIONS: In CP patients, LW, COP and high PLT count were identified as novel predictors of PC. A risk prediction model based on these factors exhibited moderate predictive value for CP patients.

Electronic tumor board presentations as the basis for the development of a head and neck cancer database.

BACKGROUND: Multidisciplinary team meetings or tumor boards (TBs) form a pivotal component of oncology practice. The crux of a TB revolves around making treatment decisions based on succinct head and neck cancer (HNC) patient data presentations, which can be challenging and complex. Apart from meticulous TB presentations, discussions and treatment plan documentation is equally important. The aim of this study was to structure an electronic synoptic TB data presentation to address all these areas. The overarching benefits of systematic TB data collection include facilitating audits and research. METHODS: We utilized a secure web-based tool that was used for common scientific research purposes but customized to store HNC patient data. The data points were tabulated across eight TB pages: (a) TB scheduling, (b) patient biodata, (c) diagnosis details, (d) index presentation, (e) images, (f) management and histopathology, (g) TB presentation, and (h) TB discussion and decisions. Each data point leads to additional fields by branching logic to permit further relevant data entry. This was integrated within the patient electronic medical records allowing for a direct internal trajectory to recall TB data. RESULTS: From October 2015 to October 2018, we recorded over 2000 presentations for 1279 individual patients. This is a quality improvement initiative, and hence, the results are more of a broad analysis of our TB presentation process. The most common cancers were squamous cell (523, 41%), thyroid (207, 16%), and nasopharyngeal (139, 11%) carcinomas. Importantly, this system has formed the basis for a number of clinical and translational research projects and audit outcomes. CONCLUSION: Despite TBs being vital to oncologic practice, little attempt has been made to report TB data management. In this study, we present an efficient system that permits the integration of dual functions: TB data presentation and oncologic data collection for research, recall, and audit purposes.

Automating the Renal Cell Carcinoma Registry in Singapore: A Case Study on the Integration of the Research Electronic Data Capture System with the Enterprise Data Warehouse.

The renal cell carcinoma registry (RCCR) at the Singapore General Hospital was established in the 1980s. In 2012, the registry transited to a partially automated system using Research Electronic Data Capture (REDCap) and Oracle Business Intelligence Enterprise Edition (OBIEE), which is a platform for retrieval of electronic data from the Electronic Health Intelligence System (eHIntS). A committee was formed of experts from the department of urology and the health services research center, as well as an information technology (IT) team to evaluate the efficacy of the partially automated system. In the 5 years after the new system was implemented, 1,751 cases were recorded in the RCCR. The casefinding completeness increased by 1.9%, the data accuracy rate was 97%, and the efficiency increased by 12%. Strengths of the new system after partial automation were: (1) secure access to the registry via the hospital Web, (2) direct access to REDCap via the electronic medical records system, (3) automated and timely data extraction, and (4) visual presentation of data. On the other hand, we also encountered several challenges in the process of automating the registry, including limited IT support, limited expertise in matching data variables from RCCR and eHIntS, and limited availability and accessibility of eHIntS information for import into REDCap. In summary, despite these challenges, partial automation was achieved with the REDCap/OBIEE system, enhancing efficiency, data security, and data quality.

Attitudes of Jewish and Bedouin responders toward family physicians' use of electronic medical records during the medical encounter.

OBJECTIVE: Culture is known to impact expectations from medical treatments. The effects of cultural differences on attitudes toward Electronic Medical Records (EMR) have not been investigated. We compared the attitudes of Jewish and Bedouin responders toward EMR's use by family physicians during the medical encounter, and examined the contribution of background variables to these attitudes. METHODS: 86 Jewish and 89 Bedouin visitors of patients in a regional Israeli University Medical Center responded to a self-reporting questionnaire with Hebrew and Arabic versions. RESULTS: T-tests and a linear regression analysis found that culture did not predict attitudes. Respondents' self-reported health status, Internet and e-mail use, and estimates of their physician's typing speed explained a total of 18.6% of the variance in attitudes (p<0.001). CONCLUSION: Bedouins respondents' attitudes toward EMR use were better than expected and similar to those of their Jewish counterparts. The most significant factor influencing respondents' attitudes was the physician's typing speed. PRACTICE IMPLICATIONS: (1) Further studies should consider the possible impact of cultural differences between the family physician and the healthcare client on attitudes. (2) Interventions to improve physicians' skill in operating EMRs and typing will potentially have a positive impact on patients' satisfaction with physicians' EMR use.

Translating genome wide association study results to associations among common diseases: in silico study with an electronic medical record.

OBJECTIVE: To develop a map of disease associations exclusively using two publicly available genetic sources: the catalog of single nucleotide polymorphisms (SNPs) from the HapMap, and the catalog of Genome Wide Association Studies (GWAS) from the NHGRI, and to evaluate it with a large, long-standing electronic medical record (EMR). METHODS: A computational model, In Silico Bayesian Integration of GWAS (IsBIG), was developed to learn associations among diseases using a Bayesian network (BN) framework, using only genetic data. The IsBIG model (I-Model) was re-trained using data from our EMR (M-Model). Separately, another clinical model (C-Model) was learned from this training dataset. The I-Model was compared with both the M-Model and the C-Model for power to discriminate a disease given other diseases using a test dataset from our EMR. Area under receiver operator characteristics curve was used as a performance measure. Direct associations between diseases in the I-Model were also searched in the PubMed database and in classes of the Human Disease Network (HDN). RESULTS: On the basis of genetic information alone, the I-Model linked a third of diseases from our EMR. When compared to the M-Model, the I-Model predicted diseases given other diseases with 94% specificity, 33% sensitivity, and 80% positive predictive value. The I-Model contained 117 direct associations between diseases. Of those associations, 20 (17%) were absent from the searches of the PubMed database; one of these was present in the C-Model. Of the direct associations in the I-Model, 7 (35%) were absent from disease classes of HDN. CONCLUSION: Using only publicly available genetic sources we have mapped associations in GWAS to a human disease map using an in silico approach. Furthermore, we have validated this disease map using phenotypic data from our EMR. Models predicting disease associations on the basis of known genetic associations alone are specific but not sensitive. Genetic data, as it currently exists, can only explain a fraction of the risk of a disease. Our approach makes a quantitative statement about disease variation that can be explained in an EMR on the basis of genetic associations described in the GWAS.