Physician perceptions of clutter in electronic medical records

2017 ◽  
Vol 61 (1) ◽  
pp. 572-572
Author(s):  
Nadine Marie Moacdieh ◽  
Travis Ganje ◽  
Nadine Sarter
Keyword(s):  
Emergency Medicine ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Edge Density ◽  
Free Text ◽  
Visual Data ◽  
American Hospital ◽  
American Hospital Association ◽  
Amount Of Information ◽  
Wide Range

Electronic medical records (EMRs) are now used by more than 95% of US hospitals (American Hospital Association (AHA) Annual Survey Information Technology Supplement, 2013). EMR systems typically provide a wide range of functionalities, including computerized physician order entry and the storage and presentation of patient medical data. The expectation has always been that these EMR functions would contribute to increased efficiency and safety of operations in hospital environments (Blumenthal & Glaser, 2007). However, display clutter in EMRs can lead to negative performance effects that can compromise the efficiency and safety of medical environments (e.g., Moacdieh & Sarter, 2015; Murphy, Reis, Sittig, & Singh 2012). However, it is not clear to what extent physicians view clutter as an impediment to their work, and, if so, whether it is solely the amount of visual data that leads to their perception of “clutter”. To this end, the aims of this study were to determine 1) whether physicians believe the nature and amount of EMR visual data affect their use of EMRs, 2) whether physicians think improvements are needed, and 3) to what extent it is the amount of data that leads to clutter versus some other qualitative aspect of the data. An anonymous survey was conducted among emergency medicine residents at the University of Michigan Department of Emergency Medicine. The response rate was around 60%, with 31 residents responding (age range 21-40 years). Residents had to respond to 18 questions. The first five questions asked for demographic information and participants responded using a dropdown menu. The next eight questions asked participants for their opinions about their satisfaction with their current EMR and the effects of visual data load on their work; participants responded using a 5-point Likert scale (strongly disagree or not at all (1) to strongly agree or extremely important (5)). The next three questions were free text and allowed residents to suggest design improvements to their current EMRs. Finally, the last two questions asked residents to rate, on a 100-point scale, the amount of clutter and the amount of information on sample screenshots from their current EMRs. This data was then correlated with each of the clutter image processing algorithms of Rosenholtz, Li, & Nakano (2007): feature congestion, subband entropy, and edge density. In general, results showed that physicians place a lot of importance on the design of visual information. Of the residents who responded, 52% indicated that visual data representation was “extremely important” for safety and the same percentage also said it was “extremely important” for efficiency. Also, 41% of residents agreed or strongly agreed that problems with visual data presentation have led to medical errors in their experience. In the free text space, physicians described many improvements that could be made to their EMR displays, particularly the reduction of excess irrelevant data. In addition, the correlation coefficients between the algorithm values and the ratings of amount of information were lower than the coefficients for ratings of clutter. This suggests that it is not just the quantity of information that factors into physicians’ perception of clutter; other factors, such as color variation and organization, play a role as well. In conclusion, this study showed that there is more to EMR clutter than merely excess data, and physicians appear to be aware of the dangers of clutter in their EMR displays.

Health Information Technology and its Effects on Hospital Costs, Outcomes, and Patient Safety

2011 ◽  
Vol 48 (4) ◽  
pp. 288-303 ◽  
Author(s):  
William E. Encinosa ◽  
Jaeyong Bae
Keyword(s):  
Information Technology ◽  
Patient Safety ◽  
Electronic Medical Records ◽  
Affordable Care Act ◽  
Medical Records ◽  
Hospital Costs ◽  
American Hospital ◽  
American Hospital Association ◽  
Cost Offset ◽  
Patient Protection

Underlying many reforms in the Patient Protection and Affordable Care Act (ACA) is the use of electronic medical records (EMRs) to help contain costs. We use MarketScan® claims data and American Hospital Association information technology (IT) data to examine whether EMRs can contain costs in the ACA's reforms to reduce patient safety events. We find EMRs do not reduce the rate of patient safety events. However, once an event occurs, EMRs reduce death by 34%, readmissions by 39%, and spending by $4,850 (16%), a cost offset of $1.75 per $1 spent on IT capital. Thus, EMRs contain costs by better coordinating care to rescue patients from medical errors once they occur.

Hospital Care in the United States, Commission on Hospital Care, New York, The Commonwealth Fund

PEDIATRICS ◽  
1950 ◽  
Vol 6 (1) ◽  
pp. 172-172
Keyword(s):  
New York ◽  
Hospital Care ◽  
The United States ◽  
Hospital Services ◽  
Source Book ◽  
American Hospital ◽  
American Hospital Association ◽  
Commonwealth Fund ◽  
Wide Range ◽  
Present Pattern

Many individuals and organizations have had a part in the making of this book. They have described influences and forces whose interaction has resulted in the present pattern of our hospital services, and documented their interpretations. The result is a source book of basic information which should be valuable for all students of hospital problems. The Commission was appointed by the American Hospital Association, and chosen to represent a wide range of those providing hospital, health and welfare services, as well as the consuming public.

Medical Records-Based Genetic Studies of the Complement System

2021 ◽  
pp. ASN.2020091371
Author(s):  
Atlas Khan ◽  
Ning Shang ◽  
Lynn Petukhova ◽  
Jun Zhang ◽  
Yufeng Shen ◽  
...  
Keyword(s):  
Electronic Medical Records ◽  
Complement Activation ◽  
Genetic Variants ◽  
Medical Records ◽  
Kidney Diseases ◽  
Association Studies ◽  
Structural Genomic ◽  
Genome Wide ◽  
A Genome ◽  
Wide Range

BackgroundGenetic variants in complement genes have been associated with a wide range of human disease states, but well-powered genetic association studies of complement activation have not been performed in large multiethnic cohorts.MethodsWe performed medical records–based genome-wide and phenome-wide association studies for plasma C3 and C4 levels among participants of the Electronic Medical Records and Genomics (eMERGE) network.ResultsIn a GWAS for C3 levels in 3949 individuals, we detected two genome-wide significant loci: chr.1q31.3 (CFH locus; rs3753396-A; β=0.20; 95% CI, 0.14 to 0.25; P=1.52x10-11) and chr.19p13.3 (C3 locus; rs11569470-G; β=0.19; 95% CI, 0.13 to 0.24; P=1.29x10-8). These two loci explained approximately 2% of variance in C3 levels. GWAS for C4 levels involved 3998 individuals and revealed a genome-wide significant locus at chr.6p21.32 (C4 locus; rs3135353-C; β=0.40; 95% CI, 0.34 to 0.45; P=4.58x10-35). This locus explained approximately 13% of variance in C4 levels. The multiallelic copy number variant analysis defined two structural genomic C4 variants with large effect on blood C4 levels: C4-BS (β=−0.36; 95% CI, −0.42 to −0.30; P=2.98x10-22) and C4-AL-BS (β=0.25; 95% CI, 0.21 to 0.29; P=8.11x10-23). Overall, C4 levels were strongly correlated with copy numbers of C4A and C4B genes. In comprehensive phenome-wide association studies involving 102,138 eMERGE participants, we cataloged a full spectrum of autoimmune, cardiometabolic, and kidney diseases genetically related to systemic complement activation.ConclusionsWe discovered genetic determinants of plasma C3 and C4 levels using eMERGE genomic data linked to electronic medical records. Genetic variants regulating C3 and C4 levels have large effects and multiple clinical correlations across the spectrum of complement-related diseases in humans.

scholarly journals iPSYcare: the development of a linked electronic medical records database to study and optimize psychiatric care in Antwerp

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Eva Rens ◽  
Joris Michielsen ◽  
Geert Dom ◽  
Roy Remmen ◽  
Kris Van den Broeck
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Psychiatric Care ◽  
Ethical Issues ◽  
Psychiatric Patients ◽  
Unique Identifier ◽  
Explicit Consent ◽  
Wide Range ◽  
Psychiatric Units ◽  
The University

Abstract Objective The study of care trajectories of psychiatric patients across hospitals was previously not possible in Belgium as each hospital stores its data autonomously, and government-related registrations do not contain a unique identifier or are incomplete. A new longitudinal database called iPSYcare (Improved Psychiatric Care and Research) was therefore constructed in 2021, and links the electronic medical records of patients in psychiatric units of eight hospitals in the Antwerp Province, Belgium. The database provides a wide range of information on patients, care trajectories and delivered care in the region. In a first phase, the database will only contain information about adult patients who were admitted to a hospital or treated by an outreach team and who gave explicit consent. In the future, the database may be expanded to other regions and additional data on outpatient care may be added. Results IPSYcare is a close collaboration between the University of Antwerp and hospitals in the province of Antwerp. This paper describes the development of the database, how privacy and ethical issues will be handled, and how the governance of the database will be organized.

scholarly journals Emergency Medicine Residents on Electronic Medical Records: Perspectives and Advice

Cureus ◽  
2019 ◽  
Author(s):  
Maxwell A Hockstein ◽  
Sara N Pope ◽  
Kayla Donnawell ◽  
Summer A Chavez ◽  
Lipika Bhat
Keyword(s):  
Emergency Medicine ◽  
Electronic Medical Records ◽  
Medical Records

scholarly journals A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0247404
Author(s):  
Akshaya V. Annapragada ◽  
Marcella M. Donaruma-Kwoh ◽  
Ananth V. Annapragada ◽  
Zbigniew A. Starosolski
Keyword(s):  
Child Abuse ◽  
Natural Language Processing ◽  
Natural Language ◽  
Physical Abuse ◽  
Electronic Medical Records ◽  
Language Processing ◽  
Child Protection ◽  
Medical Records ◽  
Free Text ◽  
Average Accuracy

Child physical abuse is a leading cause of traumatic injury and death in children. In 2017, child abuse was responsible for 1688 fatalities in the United States, of 3.5 million children referred to Child Protection Services and 674,000 substantiated victims. While large referral hospitals maintain teams trained in Child Abuse Pediatrics, smaller community hospitals often do not have such dedicated resources to evaluate patients for potential abuse. Moreover, identification of abuse has a low margin of error, as false positive identifications lead to unwarranted separations, while false negatives allow dangerous situations to continue. This context makes the consistent detection of and response to abuse difficult, particularly given subtle signs in young, non-verbal patients. Here, we describe the development of artificial intelligence algorithms that use unstructured free-text in the electronic medical record—including notes from physicians, nurses, and social workers—to identify children who are suspected victims of physical abuse. Importantly, only the notes from time of first encounter (e.g.: birth, routine visit, sickness) to the last record before child protection team involvement were used. This allowed us to develop an algorithm using only information available prior to referral to the specialized child protection team. The study was performed in a multi-center referral pediatric hospital on patients screened for abuse within five different locations between 2015 and 2019. Of 1123 patients, 867 records were available after data cleaning and processing, and 55% were abuse-positive as determined by a multi-disciplinary team of clinical professionals. These electronic medical records were encoded with three natural language processing (NLP) algorithms—Bag of Words (BOW), Word Embeddings (WE), and Rules-Based (RB)—and used to train multiple neural network architectures. The BOW and WE encodings utilize the full free-text, while RB selects crucial phrases as identified by physicians. The best architecture was selected by average classification accuracy for the best performing model from each train-test split of a cross-validation experiment. Natural language processing coupled with neural networks detected cases of likely child abuse using only information available to clinicians prior to child protection team referral with average accuracy of 0.90±0.02 and average area under the receiver operator characteristic curve (ROC-AUC) 0.93±0.02 for the best performing Bag of Words models. The best performing rules-based models achieved average accuracy of 0.77±0.04 and average ROC-AUC 0.81±0.05, while a Word Embeddings strategy was severely limited by lack of representative embeddings. Importantly, the best performing model had a false positive rate of 8%, as compared to rates of 20% or higher in previously reported studies. This artificial intelligence approach can help screen patients for whom an abuse concern exists and streamline the identification of patients who may benefit from referral to a child protection team. Furthermore, this approach could be applied to develop computer-aided-diagnosis platforms for the challenging and often intractable problem of reliably identifying pediatric patients suffering from physical abuse.

Natural Language Processing to Identify Cancer Treatments With Electronic Medical Records

2021 ◽  
pp. 379-393
Author(s):  
Jiaming Zeng ◽  
Imon Banerjee ◽  
A. Solomon Henry ◽  
Douglas J. Wood ◽  
Ross D. Shachter ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Electronic Medical Records ◽  
Language Processing ◽  
Medical Records ◽  
Structured Data ◽  
Free Text ◽  
Esophagus Cancer ◽  
Clinical Notes ◽  
Patients With Cancer

PURPOSE Knowing the treatments administered to patients with cancer is important for treatment planning and correlating treatment patterns with outcomes for personalized medicine study. However, existing methods to identify treatments are often lacking. We develop a natural language processing approach with structured electronic medical records and unstructured clinical notes to identify the initial treatment administered to patients with cancer. METHODS We used a total number of 4,412 patients with 483,782 clinical notes from the Stanford Cancer Institute Research Database containing patients with nonmetastatic prostate, oropharynx, and esophagus cancer. We trained treatment identification models for each cancer type separately and compared performance of using only structured, only unstructured ( bag-of-words, doc2vec, fasttext), and combinations of both ( structured + bow, structured + doc2vec, structured + fasttext). We optimized the identification model among five machine learning methods (logistic regression, multilayer perceptrons, random forest, support vector machines, and stochastic gradient boosting). The treatment information recorded in the cancer registry is the gold standard and compares our methods to an identification baseline with billing codes. RESULTS For prostate cancer, we achieved an f1-score of 0.99 (95% CI, 0.97 to 1.00) for radiation and 1.00 (95% CI, 0.99 to 1.00) for surgery using structured + doc2vec. For oropharynx cancer, we achieved an f1-score of 0.78 (95% CI, 0.58 to 0.93) for chemoradiation and 0.83 (95% CI, 0.69 to 0.95) for surgery using doc2vec. For esophagus cancer, we achieved an f1-score of 1.0 (95% CI, 1.0 to 1.0) for both chemoradiation and surgery using all combinations of structured and unstructured data. We found that employing the free-text clinical notes outperforms using the billing codes or only structured data for all three cancer types. CONCLUSION Our results show that treatment identification using free-text clinical notes greatly improves upon the performance using billing codes and simple structured data. The approach can be used for treatment cohort identification and adapted for longitudinal cancer treatment identification.

A Medical Decision Support Tool Using Text-mining Techniques with Electronic Medical Records

2018 ◽  
Author(s):  
Michael Judd
Keyword(s):  
Back Pain ◽  
Text Mining ◽  
Electronic Medical Records ◽  
Lower Back Pain ◽  
Medical Records ◽  
Medical Condition ◽  
Medical Decision ◽  
Free Text ◽  
Clinical Notes ◽  
Lower Back

Free-text clinical notes represent a vast amount of information which in the past has been un-analyzed data. In this paper we apply text-mining methods on the free-text in electronic medical records (EMRs) to define treatment options for patients with lower back pain. The goal of the project is to develop a generalized text-mining framework that can be used not only in the treatment of lower back pain, but any medical condition. The framework takes advantage of open-source algorithms for anonymization and the clinical NLP tool Apache Clinical Text Analysis and Knowledge Extraction System (cTAKES) to form structured data from clinical notes. The machine learning algorithm uses seven years of extracted clinical notes from the primary care physician to classify 20 patients’ pattern of back pain. With the small dataset provided, the algorithm managed to achieve diagnosis accuracy of up to 100%. The twenty-patient dataset was simply too homogenous and small to make statistical claims for sensitivity and specificity. However, the system shows indicators of satisfactory performance, and we are trying to extract more data of patients who do not have back pain to be able to validate our system better.

Sign in / Sign up

Export Citation Format

Share Document