scholarly journals Development of prediction model for trauma assessment using electronic medical records

2020 ◽  
Author(s):  
Kentaro Ogura ◽  
Tadahiro Goto ◽  
Toru Shirakawa ◽  
Tomohiro Sonoo ◽  
Hidehiko Nakano ◽  
...  
Keyword(s):  
Prediction Model ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Injury Severity ◽  
Care Center ◽  
Predictive Performance ◽  
Mortality Prediction ◽  
Hospital Death ◽  
Trauma Patients ◽  
Clinical Diagnoses

Abbreviated Injury Score (AIS) and Injury Severity Score (ISS) scores are used to measure the severity of trauma patients in the emergency department, but they have several problems such as a calculation complexity. In this study, we developed a mortality prediction model of trauma patients using the data from electronic medical records and compared it with a model using AIS/ISS scores. This is a prognostic study using the data of patients who were admitted to Hitachi General Hospital Emergency and Critical Care Center from April 2018 to March 2019. The features were age, sex, vital signs, and clinical diagnoses, and the outcome was in-hospital death. Of 337 eligible patients, 11 died during the hospitalization. The predictive performance of our model was comparable to that of the AIS/ISS scores model (AUC 0.912 vs 0.961). Clinical diagnoses were important in predicting the mortality rate. Our study suggests that a trauma severity index calculated by the predicting model using information from electronic medical records might replace AIS/ISS score.

scholarly journals Genetic Modifiers of Hereditary Neuromuscular Disorders and Cardiomyopathy

Cells ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 349
Author(s):  
Sholeh Bazrafshan ◽  
Hani Kushlaf ◽  
Mashhood Kakroo ◽  
John Quinlan ◽  
Richard C. Becker ◽  
...  
Keyword(s):  
Muscular Dystrophy ◽  
Electronic Medical Records ◽  
Cardiac Disease ◽  
Medical Records ◽  
Care Center ◽  
Neuromuscular Disorders ◽  
Next Generation Sequencing Data ◽  
Comparative Genomic ◽  
Genetic Modifiers ◽  
Cardiac Phenotype

Novel genetic variants exist in patients with hereditary neuromuscular disorders (NMD), including muscular dystrophy. These patients also develop cardiac manifestations. However, the association between these gene variants and cardiac abnormalities is understudied. To determine genetic modifiers and features of cardiac disease in NMD patients, we have reviewed electronic medical records of 651 patients referred to the Muscular Dystrophy Association Care Center at the University of Cincinnati and characterized the clinical phenotype of 14 patients correlating with their next-generation sequencing data. The data were retrieved from the electronic medical records of the 14 patients included in the current study and comprised neurologic and cardiac phenotype and genetic reports which included comparative genomic hybridization array and NGS. Novel associations were uncovered in the following eight patients diagnosed with Limb-girdle Muscular Dystrophy, Bethlem Myopathy, Necrotizing Myopathy, Charcot-Marie-Tooth Disease, Peripheral Polyneuropathy, and Valosin-containing Protein-related Myopathy. Mutations in COL6A1, COL6A3, SGCA, SYNE1, FKTN, PLEKHG5, ANO5, and SMCHD1 genes were the most common, and the associated cardiac features included bundle branch blocks, ventricular chamber dilation, septal thickening, and increased outflow track gradients. Our observations suggest that features of cardiac disease and modifying gene mutations in patients with NMD require further investigation to better characterize genotype–phenotype relationships.

Non-Selective Thoracic Computed Tomography in Trauma Patients Results in Injury Severity Score Inflation

2021 ◽  
pp. 000313482110249
Author(s):  
Leonardo Alaniz ◽  
Omaer Muttalib ◽  
Juan Hoyos ◽  
Cesar Figueroa ◽  
Cristobal Barrios
Keyword(s):  
Computed Tomography ◽  
Injury Severity Score ◽  
Severity Score ◽  
Injury Severity ◽  
Treatment Plan ◽  
Mortality Prediction ◽  
Trauma Patients ◽  
Mortality Benefit ◽  
Severity Scores ◽  
Score Inflation

Introduction Extensive research relying on Injury Severity Scores (ISS) reports a mortality benefit from routine non-selective thoracic CTs (an integral part of pan-computed tomography (pan-CT)s). Recent research suggests this mortality benefit may be artifact. We hypothesized that the use of pan-CTs inflates ISS categorization in patients, artificially affecting admission rates and apparent mortality benefit. Methods Eight hundred and eleven patients were identified with an ISS >15 with significant findings in the chest area. Patient charts were reviewed and scores were adjusted to exclude only occult injuries that did not affect treatment plan. Pearson chi-square tests and multivariable logistic regression were used to compare adjusted cases vs non-adjusted cases. Results After adjusting for inflation, 388 (47.8%) patients remained in the same ISS category, 378 (46.6%) were reclassified into 1 lower ISS category, and 45 (5.6%) patients were reclassified into 2 lower ISS categories. Patients reclassified by 1 category had a lower rate of mortality ( P < 0.001), lower median total hospital LOS ( P < .001), ICU days ( P < .001), and ventilator days ( P = 0.008), compared to those that remained in the same ISS category. Conclusion Injury Severity Score inflation artificially increases survival rate, perpetuating the increased use of pan-CTs. This artifact has been propagated by outdated mortality prediction calculation methods. Thus, prospective evaluations of algorithms for more selective CT scanning are warranted.

A comparison of the Injury Severity Score and the Trauma Mortality Prediction Model

2014 ◽  
Vol 76 (1) ◽  
pp. 47-53 ◽  
Author(s):  
Alan Cook ◽  
Jo Weddle ◽  
Susan Baker ◽  
David Hosmer ◽  
Laurent Glance ◽  
...  
Keyword(s):  
Injury Severity Score ◽  
Prediction Model ◽  
Severity Score ◽  
Injury Severity ◽  
Mortality Prediction ◽  
Mortality Prediction Model ◽  
Trauma Mortality

Abstract 17956: External Validation of a Prediction Model for the Development of Atrial Fibrillation in a Repository of Electronic Medical Records

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Matthew J Kolek ◽  
Amy J Graves ◽  
Aihua Bian ◽  
Pedro L Teixeira ◽  
Moore B Shoemaker ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Prediction Model ◽  
Electronic Medical Records ◽  
Risk Prediction ◽  
Medical Records ◽  
Risk Model ◽  
External Validation ◽  
Left Ventricular ◽  
Cox Proportional Hazards Model ◽  
Ambulatory Setting

Background: Atrial fibrillation (AF) contributes to substantial morbidity, mortality, and healthcare costs. Accurate prediction of incident AF might enhance patient care and improve outcomes. We aimed to externally validate the AF risk model developed by the CHARGE-AF investigators utilizing a large repository of electronic medical records (EMR). Methods: Using a database of de-identified EMRs, we conducted a retrospective cohort study of subjects serially followed in internal medicine clinics at our institution (minimum 3 visits in a 24 month window). Subjects were followed for incident AF from 2005 until 2010. We applied the published CHARGE-AF Cox proportional hazards model beta coefficients to our cohort. Predictors included age, race, height, weight, systolic and diastolic blood pressure, treatment for hypertension, smoking status, diabetes, heart failure, history of myocardial infarction, left ventricular hypertrophy, and PR interval. Calibration and discrimination were assessed by generating calibration plots and calculating C-statistics. Results: The study included 33,494 subjects with median age 57 years (25th to 75th percentile: 49 - 67), 57% women, 86% whites, and 14% African Americans. During the mean follow-up period of 4.8 ± 0.85 years, 2455 (7.3%) subjects developed AF. After correcting for baseline hazard, the CHARGE-AF model over-predicted AF at the highest risk deciles but was otherwise well-calibrated (Figure) and showed good discrimination, with a C-statistic of 0.746 (95% confidence interval: 0.738 to 0.754). Conclusion: From clinical factors readily accessible in a large de-identified EMR repository, we externally validated the CHARGE-AF risk prediction model to identify individuals at risk for developing AF in an ambulatory setting. These data not only provide strong validation for the CHARGE-AF risk prediction tool, but also indicate that the tool, and thus primary prevention strategies, can be implemented in an EMR context.

scholarly journals Night admission is an independent risk factor for mortality in trauma patients - a systemic error approach

2015 ◽  
Vol 42 (4) ◽  
pp. 209-214 ◽  
Author(s):  
LEONARDO DE SOUZA BARBOSA ◽  
GEIBEL SANTOS REIS DOS JÚNIOR ◽  
RICARDO ZANTIEFF TOPOLSKI CHAVES ◽  
DAVI JORGE FONTOURA SOLLA ◽  
LEONARDO FERNANDES CANEDO ◽  
...  
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Night Shift ◽  
Risk Classification ◽  
Trauma Patients ◽  
Degree Of Contamination ◽  
Systemic Error ◽  
Observational Cohort ◽  
The Impact ◽  
Retrospective Observational Cohort Study

ABSTRACTObjective:to assess the impact of the shift inlet trauma patients, who underwent surgery, in-hospital mortality.Methods:a retrospective observational cohort study from November 2011 to March 2012, with data collected through electronic medical records. The following variables were statistically analyzed: age, gender, city of origin, marital status, admission to the risk classification (based on the Manchester Protocol), degree of contamination, time / admission round, admission day and hospital outcome.Results:during the study period, 563 patients injured victims underwent surgery, with a mean age of 35.5 years (± 20.7), 422 (75%) were male, with 276 (49.9%) received in the night shift and 205 (36.4%) on weekends. Patients admitted at night and on weekends had higher mortality [19 (6.9%) vs. 6 (2.2%), p=0.014, and 11 (5.4%) vs. 14 (3.9%), p=0.014, respectively]. In the multivariate analysis, independent predictors of mortality were the night admission (OR 3.15), the red risk classification (OR 4.87), and age (OR 1.17).Conclusion:the admission of night shift and weekend patients was associated with more severe and presented higher mortality rate. Admission to the night shift was an independent factor of surgical mortality in trauma patients, along with the red risk classification and age.

Biopsy forceps disruption paired with bougie dilation of esophageal strictures lengthens time to repeat intervention

2020 ◽  
Author(s):  
Tricia Hengehold ◽  
Benjamin D Rogers ◽  
Farhan Quader ◽  
C Prakash Gyawali
Keyword(s):  
Electronic Medical Records ◽  
Medical Records ◽  
Care Center ◽  
Tertiary Care ◽  
Balloon Dilation ◽  
Biopsy Forceps ◽  
Kaplan Meier ◽  
Esophageal Strictures ◽  
Foregut Surgery

Summary Esophageal strictures commonly cause dysphagia and require treatment with endoscopic dilation using balloons or bougies. We aimed to determine whether biopsy forceps disruption of strictures at time of dilation increases time to repeat intervention or duration of intervention-free follow-up. We performed a retrospective analysis of 289 adults (age 61.0 ± 0.8 years, 66.4% female) who underwent dilation of an esophageal stricture at our tertiary care center between 2014 and 2016. Exclusions consisted of endoscopic intervention within the preceding 6 months, prior foregut neoplasia, achalasia, radiofrequency ablation, endoscopic mucosal resection, endoscopic submucosal dissection, or foregut surgery. Demographics, clinical presentation, dilation technique, and follow-up were abstracted from electronic medical records. We compared time to repeat dilation and duration of intervention-free follow-up between treatment subgroups. Balloon dilation was performed more often than bougie dilation (76.8 vs. 17.6%); biopsy forceps disruption was performed in 23.2%. Over a median follow-up of 52.9 months, 135 patients (46.7%) underwent repeat dilation. Age, body mass index, gender, and use of antisecretory medications did not influence need for repeat dilation (P = ns for each). Bougie dilation with biopsy forceps disruption prolonged time to repeat dilation in all patients (P ≤ 0.02), particularly in those with gastroesophageal reflux disease (P ≤ 0.03), compared with bougie dilation alone and balloon dilation with or without disruption. On Kaplan–Meier analysis, bougie dilation with biopsy forceps resulted in longer intervention-free follow-up compared with dilation alone (P = 0.03). We conclude that stricture disruption with biopsy forceps increases time to repeat intervention with bougie but not balloon dilation.

scholarly journals Multimodal temporal-clinical note network for mortality prediction

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Haiyang Yang ◽  
Li Kuang ◽  
FengQiang Xia
Keyword(s):  
Chronic Illness ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Medical Information ◽  
Short Term Memory ◽  
Mortality Prediction ◽  
Clinical Note ◽  
Clinical Notes ◽  
Smart Healthcare ◽  
Temporal Events

Abstract Background Mortality prediction is an important task to achieve smart healthcare, especially for the management of intensive care unit. It can provide a reference for doctors to quickly predict the course of disease and customize early intervention programs for the patients in need. With the development of the electronic medical records, deep learning methods are introduced to deal with the prediction task. In the electronic medical records, clinical notes always contain rich and diverse medical information, including the clinical histories and reports during admission. Mortality prediction methods mostly rely on the temporal events such as medical examinations and ignore the related reports and history information in the clinical notes. We hope that we can utilize both temporal events and clinical notes information to get better mortality prediction results. Results We propose a multimodal temporal-clinical note network to model both temporal and clinical notes. Specifically, the clinical text are further processed for differentiating the chronic illness patients in the historical information of clinical notes from non-chronic illness patients. In order to further mine the information related to the mortality in the text, we learn the time series embedding with Long Short Term Memory networks and the clinical notes embedding with a label aware convolutional neural network. We also propose a scoring function to measure the importance of clinical note sections. Our approach achieved a better AUCPR and AUCROC than competing methods and visual explanations for word importance showed the interpretability improvement of the model. Conclusions We have tested our methodology on the MIMIC-III dataset. Contributions of different clinical note sections were uncovered by visualization methods. Our work demonstrates that the introduction of the medical history related information can improve the performance of the mortality prediction. Using label aware convolutional neural networks can further improve the results.

scholarly journals Predictors of Mortality and Prehospital Monitoring Limitations in Blunt Trauma Patients

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Matej Strnad ◽  
Vesna Borovnik Lesjak ◽  
Vitka Vujanović ◽  
Tine Pelcl ◽  
Miljenko Križmarić
Keyword(s):  
Hospital Mortality ◽  
Regression Model ◽  
Blunt Trauma ◽  
Injury Severity ◽  
Vital Signs ◽  
Study Groups ◽  
Multivariate Logistic Regression Model ◽  
Hospital Death ◽  
Trauma Patients ◽  
Arterial Blood

This study aimed at determining predictors of in-hospital mortality and prehospital monitoring limitations in severely injured intubated blunt trauma patients. We retrospectively reviewed patients’ charts. Prehospital vital signs, Injury Severity Score (ISS), initial Glasgow Coma Scale (GCS), Revised Trauma Score (RTS), arterial blood gases, and lactate were compared in two study groups: survivors (n=40) and nonsurvivors (n=30). There were no significant differences in prehospital vital signs between compared groups. Nonsurvivors were older (P=0.006), with lower initial GCS (P<0.001) and higher ISS (P<0.001), along with higher lactate (P<0.001) and larger base deficit (BD;P=0.006), whereas RTS (P=0.001) was lower in nonsurvivors. For predicting mortality, area under the curve (AUC) was calculated: for lactate 0.82 (P<0.001), for ISS 0.82 (P<0.001), and for BD 0.69 (P=0.006). Lactate level of 3.4 mmol/L or more was 82% sensitive and 75% specific for predicting in-hospital death. In a multivariate logistic regression model, ISS (P=0.037), GCS (P=0.033), and age (P=0.002) were found to be independent predictors of in-hospital mortality. The AUC for regression model was 0.93 (P<0.001). Increased levels of lactate and BD on admission indicate more severe occult hypoperfusion in nonsurvivors whereas vital signs did not differ between the groups.

Using Electronic Medical Records of Nursing Care to Characterize Constipation in Patients with Intracerebral Hemorrhage

2021 ◽  
pp. 1-8
Author(s):  
Wei Chen ◽  
Jieyi Zhao ◽  
Xiangkui Li ◽  
Xiaoyu Wang ◽  
Jing Chen ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Risk Factors ◽  
Intracerebral Hemorrhage ◽  
Hospital Mortality ◽  
Electronic Medical Records ◽  
Nursing Care ◽  
Medical Records ◽  
Care Center ◽  
Tertiary Care

<b><i>Introduction:</i></b> Constipation is one of the common poststroke complications that directly affect the patients’ quality of life in patients with intracerebral hemorrhage (ICH), which has not been paid enough attention. <b><i>Objective:</i></b> This study investigates constipation’s clinical characteristics and its risk factors in ICH patients driven by the electronic medical records of nursing care. <b><i>Methods:</i></b> This retrospective chart review investigated patients with acute spontaneous ICH admitted at a tertiary care center from October 2010 to December 2018. Poststroke constipation was defined as a first stool passage occurring after 3 days postadmission and the use of enemas or laxatives after ICH. The associations between constipation present and potential factors were evaluated. <b><i>Results:</i></b> Of 1,748 patients, 408 (70.3% men, mean age 58 ± 14 years) patients with poststroke constipation were identified. After adjusting for potential confounding variables, the risk factors independently associated with poststroke constipation are admission Glasgow Coma Scale score (odds ratio [OR] 0.62, 95% confidence interval [CI] 0.44–0.88; <i>p</i> = 0.007), use of mechanical ventilation (OR 3.74, 95% CI 2.37–5.89, <i>p</i> &#x3c; 0.001), enteral nutrition (OR 2.82, 95% CI 1.85–4.30, <i>p</i> &#x3c; 0.001), hematoma evacuation (OR 2.10, 95% CI 1.40–3.16; <i>p</i> &#x3c; 0.001), opioid analgesics (OR 1.86, 95% CI 1.32–2.62; <i>p</i> &#x3c; 0.001), sedation (OR 1.83, 95% CI 1.20–2.77; <i>p</i> = 0.005), and vasopressors (OR 1.81, 95% CI 1.26–2.61; <i>p</i> = 0.001) in order. Similar associations were observed in the prespecified length of the stay subgroup. Patients with constipation were associated with a longer hospital stay length (2.24 days, 95% CI 1.43–3.05, <i>p</i> &#x3c; 0.001) but not with in-hospital mortality (OR 1.05, 95% CI 0.58–1.90, <i>p</i> = 0.871). <b><i>Conclusions:</i></b> Our findings suggested that risk factors influence the absence of constipation after ICH with the synergy of different weights. The occurrence of constipation likely affects a longer length of stay, but not in-hospital mortality. Future prospective investigations are warranted to validate our findings and identify the optimal management of constipation that may improve the quality of life in patients with ICH.

Sign in / Sign up

Export Citation Format

Share Document