Drug therapy and vascular devices used by patients hospitalized for COVID-19: a descriptive study / Terapia medicamentosa e dispositivos vasculares utilizados por doentes hospitalizados para a COVID-19: um estudo descritivo

To describe drug therapy and types of vascular access adopted in the treatment of patients with COVID-19 and admitted to the clinical wards of a university hospital, a referential institution for COVID-19 in Rio de Janeiro, Brazil. Descriptive, retrospective documentary study with a quantitative approach. The sample consisted of 243 electronic medical records from hospitalized patients with a laboratory-confirmed diagnosis of COVID-19, between April and June 2020. The selection of participants took place by intentional non-probabilistic sampling. Peripheral venous access was the mostly applied in 83.5% of the patients. The mostly used classes of drugs were analgesics, (81.9%), followed by antiemetics (70.4%), and antihypertensives (51.9%). For medications directed to COVID-19, azithromycin, oseltamivir, ceftriaxone, and hydroxychloroquine stands out with 67.5%, 58.8%, 50.2% and 27.2%, respectively. Regarding the treatment directed to COVID-19, the medications mostly taken were azithromycin and hydroxychloroquine, justified to a large extent by being recommended by the Ministry of Health in the treatment, according to signs and symptoms (Brazil, 2020). Patients treated with the medications described had good recovery from the clinical condition. Thus, studies based on randomized clinical trials are suggested to prove the efficacy of drug therapies, including their combination.

Download Full-text

A Novel Deep Learning–Based System for Triage in the Emergency Department Using Electronic Medical Records: Retrospective Cohort Study

Journal of Medical Internet Research ◽

10.2196/27008 ◽

2021 ◽

Vol 23 (12) ◽

pp. e27008

Author(s):

Li-Hung Yao ◽

Ka-Chun Leung ◽

Chu-Lin Tsai ◽

Chien-Hua Huang ◽

Li-Chen Fu

Keyword(s):

Deep Learning ◽

Electronic Medical Records ◽

Medical Records ◽

Severity Index ◽

University Hospital ◽

Emergency Severity Index ◽

National Hospital ◽

Data Set ◽

Care Survey ◽

Ambulatory Medical Care

Background Emergency department (ED) crowding has resulted in delayed patient treatment and has become a universal health care problem. Although a triage system, such as the 5-level emergency severity index, somewhat improves the process of ED treatment, it still heavily relies on the nurse’s subjective judgment and triages too many patients to emergency severity index level 3 in current practice. Hence, a system that can help clinicians accurately triage a patient’s condition is imperative. Objective This study aims to develop a deep learning–based triage system using patients’ ED electronic medical records to predict clinical outcomes after ED treatments. Methods We conducted a retrospective study using data from an open data set from the National Hospital Ambulatory Medical Care Survey from 2012 to 2016 and data from a local data set from the National Taiwan University Hospital from 2009 to 2015. In this study, we transformed structured data into text form and used convolutional neural networks combined with recurrent neural networks and attention mechanisms to accomplish the classification task. We evaluated our performance using area under the receiver operating characteristic curve (AUROC). Results A total of 118,602 patients from the National Hospital Ambulatory Medical Care Survey were included in this study for predicting hospitalization, and the accuracy and AUROC were 0.83 and 0.87, respectively. On the other hand, an external experiment was to use our own data set from the National Taiwan University Hospital that included 745,441 patients, where the accuracy and AUROC were similar, that is, 0.83 and 0.88, respectively. Moreover, to effectively evaluate the prediction quality of our proposed system, we also applied the model to other clinical outcomes, including mortality and admission to the intensive care unit, and the results showed that our proposed method was approximately 3% to 5% higher in accuracy than other conventional methods. Conclusions Our proposed method achieved better performance than the traditional method, and its implementation is relatively easy, it includes commonly used variables, and it is better suited for real-world clinical settings. It is our future work to validate our novel deep learning–based triage algorithm with prospective clinical trials, and we hope to use it to guide resource allocation in a busy ED once the validation succeeds.

Download Full-text

Uncovering interpretable potential confounders in electronic medical records

10.1101/2021.02.03.21251034 ◽

2021 ◽

Author(s):

Jiaming Zeng ◽

Michael F. Gensheimer ◽

Daniel L. Rubin ◽

Susan Athey ◽

Ross D. Shachter

Keyword(s):

Electronic Medical Records ◽

Selection Bias ◽

Language Processing ◽

Medical Records ◽

Randomized Clinical Trials ◽

Research Database ◽

High Stake ◽

Medical Decisions ◽

Clinical Text ◽

Using Data

AbstractIn medicine, randomized clinical trials (RCT) are the gold standard for informing treatment decisions. Observational comparative effectiveness research (CER) is often plagued by selection bias, and expert-selected covariates may not be sufficient to adjust for confounding. We explore how the unstructured clinical text in electronic medical records (EMR) can be used to reduce selection bias and improve medical practice. We develop a method based on natural language processing to uncover interpretable potential confounders from the clinical text. We validate our method by comparing the hazard ratio (HR) from survival analysis with and without the confounders against the results from established RCTs. We apply our method to four study cohorts built from localized prostate and lung cancer datasets from the Stanford Cancer Institute Research Database and show that our method adjusts the HR estimate towards the RCT results. We further confirm that the uncovered terms can be interpreted by an oncologist as potential confounders. This research helps enable more credible causal inference using data from EMRs, offers a transparent way to improve the design of observational CER, and could inform high-stake medical decisions. Our method can also be applied to studies within and beyond medicine to extract important information from observational data to support decisions.

Download Full-text

Strategies for the Prevention of the Intra-Hospital Transmission of COVID-19: A Retrospective Cohort Study

Healthcare ◽

10.3390/healthcare8030195 ◽

2020 ◽

Vol 8 (3) ◽

pp. 195 ◽

Cited By ~ 1

Author(s):

Min Cheol Chang ◽

Jian Hur ◽

Donghwi Park

Keyword(s):

Cohort Study ◽

Electronic Medical Records ◽

Retrospective Cohort Study ◽

Medical Records ◽

Retrospective Cohort ◽

Hospital Staff ◽

University Hospital ◽

Actual Situation ◽

Recommended Guidelines ◽

Hospital Transmission

Coronavirus disease (COVID-19) has spread rapidly worldwide. We aimed to review the strategies used by our university hospital in Daegu (South Korea) to prevent the transmission of COVID-19 within our institution. We also investigated the actual situation at our hospital against the recommended guidelines. We conducted a survey among patients and staff in our hospital. Additionally, patients’ electronic medical records were reviewed along with closed-circuit television (CCTV) recordings. Various strategies and guidelines developed by our hospital have been implemented. A total of 303 hospital staff and patients had exposure to 29 confirmed COVID-19 patients. Of them, three tested positive for COVID-19 without further transmission. The intra-hospital infection of the disease occurred when the recommended strategies and guidelines such as wearing a mask and isolating for 2 weeks were not followed. In conclusion, the implementation of robust guidelines for preventing the intra-hospital transmission of COVID-19 is essential.

Download Full-text

Implementation of Electronic Medical Records at Seoul National University Hospital

Journal of Korean Society of Medical Informatics ◽

10.4258/jksmi.2006.12.3.213 ◽

2006 ◽

Vol 12 (3) ◽

pp. 213 ◽

Cited By ~ 3

Author(s):

Jeong Wook Seo ◽

Kyung Hwan Kim ◽

Jin Wook Choi ◽

Kyoo Seob Ha ◽

Ho Jun Chin ◽

...

Keyword(s):

Electronic Medical Records ◽

Medical Records ◽

University Hospital ◽

National University ◽

Seoul National University

Download Full-text

Targeting Glioblastoma Signaling and Metabolism with A Re-Purposed Brain-Penetrant Drug

10.1101/2021.03.16.435487 ◽

2021 ◽

Author(s):

Junfeng Bi ◽

Atif Khan ◽

Jun Tang ◽

Sihan Wu ◽

Wei Zhang ◽

...

Keyword(s):

Electronic Medical Records ◽

Medical Records ◽

Drug Target ◽

Randomized Clinical Trials ◽

Tumor Regression ◽

Standard Of Care ◽

Egfr Signaling ◽

Real World Evidence ◽

Daunting Challenge

The highly lethal brain cancer glioblastoma (GBM) poses a daunting challenge because the blood-brain barrier renders potentially druggable amplified or mutated oncoproteins relatively inaccessible. Here, we identify SMPD1, an enzyme that regulates the conversion of sphingomyelin to ceramide and a critical regulator of plasma membrane structure and organization, as an actionable drug target in glioblastoma. We show that the safe and highly brain-penetrant antidepressant fluoxetine, potently inhibits SMPD1 activity, killing GBMs, in vitro and in patient-derived xenografts, through inhibition of EGFR signaling and via activation of lysosomal stress. Combining fluoxetine with the chemotherapeutic agent temozolomide, a standard of care for GBM patients, causes massive increases in GBM cell death, and complete and long-lived tumor regression in mice. Incorporation of real-world evidence from electronic medical records from insurance databases, reveals significantly increased survival in glioblastoma patients treated with fluoxetine, which was not seen in patients treated with other SSRI anti-depressants. These results nominate the repurposing of fluoxetine as a potentially safe and promising therapy for GBM patients and suggest prospective randomized clinical trials.

Download Full-text

A Strategy for Prioritizing Electronic Medical Records Using Structured Analysis and Natural Language Processing

Ingenieria y Universidad ◽

10.11144/javeriana.iyu22-1.spem ◽

2017 ◽

Vol 22 (1) ◽

pp. 7-31 ◽

Cited By ~ 2

Author(s):

Alexandra Pomares Quimbaya ◽

Rafael A. Gonzalez ◽

Oscar Muñoz ◽

Olga Milena García ◽

Wilson Ricardo Bohorquez

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Electronic Medical Records ◽

Language Processing ◽

Medical Records ◽

Information Needs ◽

Software Tool ◽

High Sensitivity ◽

University Hospital ◽

Structured Analysis

Objective: Electronic medical records (EMR) typically contain both structured attributes as well as narrative text. The usefulness of EMR for research and administration is hampered by the difficulty in automatically analyzing their narrative portions. Accordingly, this paper proposes SPIRE, a strategy for prioritizing EMR, using natural language processing in combination with analysis of structured data, in order to identify and rank EMR that match specific queries from clinical researchers and health administrators. Materials and Methods: The resulting software tool was evaluated technically and validated with three cases (heart failure, pulmonary hypertension and diabetes mellitus) compared against expert obtained results. Results and Discussion: Our preliminary results show high sensitivity (70%, 82% and 87% respectively) and specificity (85%, 73.7% and 87.5%) in the resulting set of records. The AUC was between 0.84 and 0.9. Conclusions: SPIRE was successfully implemented and used in the context of a university hospital information system, enabling clinical researchers to obtain prioritized EMR to solve their information needs through collaborative search templates with faster and more accurate results than other existing methods.

Download Full-text

Prevalence of APOL1 Risk Variants in Afro-Descendant Patients with Chronic Kidney Disease in a Latin American Country

International Journal of Nephrology ◽

10.1155/2019/7076326 ◽

2019 ◽

Vol 2019 ◽

pp. 1-5

Author(s):

Carlos E. Duran ◽

Alejandro Ramírez ◽

Juan G. Posada ◽

Johanna Schweineberg ◽

Liliana Mesa ◽

...

Keyword(s):

Chronic Kidney Disease ◽

Kidney Disease ◽

Electronic Medical Records ◽

Latin American ◽

Medical Records ◽

Cross Sectional Study ◽

University Hospital ◽

Cross Sectional ◽

Risk Variants ◽

Different Levels

Introduction. In Colombia, the genetic background of the populations was shaped by different levels of admixture between Natives, European, and Africans. Approximately 35.363 patients have diagnosed chronic kidney disease and according to population studies, 10.4% of these patients are Afro-descendant. We aim to assess the frequency of APOL1 variants G1 and G2 in Afro-descendant patients with ESRD treated at la Fundacion Valle del Lili University Hospital in Cali, Colombia. Methods. This is an observational cross-sectional study. Afro-descendant patients with ESRD in waitlist or recipients of kidney transplant were evaluated. Clinical data were collected from the electronic medical records. Genotyping was carried out by amplification of the exon 7 of the APOL1 gene. For the identification of risk genotypes, the bioinformatics tool BLAST was used. Results. We enrolled 102 participants. The frequency of APOL1 risk variants was 67.2%, in which 24.5% (n = 25) were G1 heterozygous and 5.8% (n = 6) were G2 heterozygous and 37% of the patients had high-risk status with two alleles in homozygous (G1/G1 = 21 and G2/G2 = 3) or compound heterozygote (G1/G2 = 14) form.

Download Full-text

Peripheral venous puncture: local complications in patients assisted in a university hospital

Revista de Enfermagem UFPE on line ◽

10.5205/reuol.1197-10480-1-le.0501201108 ◽

2010 ◽

Vol 5 (1) ◽

pp. 61 ◽

Cited By ~ 1

Author(s):

Paulene Bezerra Xavier ◽

Regina Célia de Oliveira ◽

Renata De Souza Araújo

Keyword(s):

Medical Records ◽

Signs And Symptoms ◽

Cross Sectional Study ◽

University Hospital ◽

Cross Sectional ◽

Local Complications ◽

Venous Puncture ◽

Preventive Actions ◽

Grade 3 ◽

Quantitative Descriptive

ABSTRACTObjective: to identify the most frequent local complications resulting from peripheral venipuncture in patients assisted at a university hospital in Recife city, Pernambuco state, aiming at proposing preventive actions in nursing care. Method: this is about a quantitative, descriptive, cross sectional study, approved by the Committee of Research Ethics under registration CAAE 0038.0.102.000-07. The population consisted of 328 patients and sample included 131 patients. Data was collected through a survey, using questionnaires and by reviewing medical records. We used the Epi-Info software for tabulation. Results: the most frequent local complications found were: phlebitis (64.9%), infiltration (40.5%) and hematoma (18.3%). We were able to identify the prevalence of signs and symptoms, as well as the degrees of phlebitis, which were grade 1 (40%) and grade 3 (38.8%), and the degree of infiltration, which was grade 2 (49.1%). Results related to nursing action amounted to 89.3% (117 reports) of positive evaluation, where the only type nursing action reported by patients was the withdrawal of the device. Conclusion: considering the risks inherent in intravenous therapy, the nurse plays an important role in preventing and reducing local complications. Descriptors: blood vessel; phlebitis; nursing care.RESUMOObjetivo: identificar as complicações locais mais frequentes da punção venosa periférica em pacientes assistidos em um hospital universitário do Recife/PE, visando propor ações preventivas na Assistência de Enfermagem. Método: estudo quantitativo, descritivo, de corte transversal aprovado pelo Comitê de Ética em Pesquisa sob o registro CAAE 0038.0.102.000-07. A população foi composta por 328 pacientes e a amostra comportou 131. A coleta de dados foi obtida com aplicação de formulário e com análise de prontuários. Utilizou-se para a tabulação o Software Epi-Info. Resultados: encontraram-se como complicações locais mais frequentes: flebite com 64,9 %, infiltração com 40,5% e hematoma com 18,3%. A predominância dos seus sinais e sintomas foi identificada, assim como os graus da Flebite, cujos graus encontrados foram, grau 1 (40%) e grau 3 (38,8) e o da Infiltração, grau 2 (49,1%). Os resultados referentes à ação de enfermagem totalizaram 89,3% (117 relatos) de positividade, sendo a única relatada pelos pacientes, a retirada do dispositivo. Conclusão: face aos riscos inerentes à terapia intravenosa, o enfermeiro desempenha papel primordial na prevenção e na redução dessas complicações. Descritores: vasos sanguíneos; flebite; assistência de enfermagem.RESUMEN Objetivo: identificar las complicaciones locales más frecuentes de la punción venosa en pacientes atendidos en un hospital universitario de Recife/PE, para proponer acciones preventivas en el cuidado de enfermería. Método: estudio descriptivo, cuantitativo, de corte transversal aprobado por el Comité de Ética en Investigación, registro CAAE 00.38.0.102.000-07. La población estuvo constituida por 328 pacientes y la muestra fue de 131. Los datos se obtuvieron con la ayuda de un formulário y con la ayuda de los registros médicos. Fue utilizado para tabular la información el programa Epi info. Resultados: las complicaciones más frecuentes encontradas fueron flebitis (64,9%), infiltración (40,5%) y hematoma (18,3%). Además del predominio, estos signos y síntomas fueron clasificados por grados, conforme se observa a seguir: flebitis - grado 1 (40%), grado 3 (38,8%) e infiltración - grado 2 (49,1%). Los resultados de la acción de enfermería ascendió a 89,3% (117 informes) de positividad y la única informada por el paciente fue la retirada del dispositivo. Conclusión: teniendo en cuenta los riesgos asociados con la terapia intravenosa, la enfermera juega un papel importante en la prevención y la reducción de estas complicaciones. Descriptores: vasos sanguíneos, flebitis, asistencia de enfermería.

Download Full-text