scholarly journals Automatic phenotyping of electronical health record: PheVis algorithm

2020 ◽  
Author(s):  
Thomas Ferté ◽  
Sébastien Cossin ◽  
Thierry Schaeverbeke ◽  
Thomas Barnetche ◽  
Vianney Jouhet ◽  
...  
Keyword(s):  
Language Processing ◽  
Medical Condition ◽  
Past History ◽  
University Hospital ◽  
Medical Conditions ◽  
Diagnosis Codes ◽  
Acute Condition ◽  
The University ◽  
Automatic Phenotyping ◽  
Medical Concepts

ABSTRACTElectronic Health Records (EHRs) often lack reliable annotation of patient medical conditions. Yu et al. recently proposed PheNorm, an automated unsupervised algorithm to identify patient medical conditions from EHR data. PheVis extends PheNorm at the visit resolution. PheVis combines diagnosis codes together with medical concepts extracted from medical notes, incorporating past history in a machine learning approach to provide an interpretable “white box” predictor of the occurrence probability for a given medical condition at each visit. PheVis is applied to two real-world use-cases using the datawarehouse of the University Hospital of Bordeaux: i) rheumatoid arthritis, a chronic condition; ii) tuberculosis, an acute condition (cross-validated AUROC were respectively 0.948 [0.945 ; 0.950] and 0.987 [0.983 ; 0.990]). PheVis performs well for chronic conditions, though absence of exclusion of past medical history by natural language processing tools limits its performance in French for acute conditions.

scholarly journals First Steps to Evaluate an NLP Tool’s Medication Extraction Accuracy from Discharge Letters

2021 ◽  
Author(s):  
Deniz Caliskan ◽  
Jakob Zierk ◽  
Detlef Kraska ◽  
Stefan Schulz ◽  
Philipp Daumke ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Data Warehouse ◽  
Language Processing ◽  
Gold Standard ◽  
Evaluation System ◽  
University Hospital ◽  
Industry Partner ◽  
Standard Medication ◽  
The University ◽  
F Measure

Introduction: The aim of this study is to evaluate the use of a natural language processing (NLP) software to extract medication statements from unstructured medical discharge letters. Methods: Ten randomly selected discharge letters were extracted from the data warehouse of the University Hospital Erlangen (UHE) and manually annotated to create a gold standard. The AHD NLP tool, provided by MIRACUM’s industry partner was used to annotate these discharge letters. Annotations by the NLP tool where then compared to the gold standard on two levels: phrase precision (whether or not the whole medication statement has been identified correctly) and token precision (whether or not the medication name has been identified correctly within correctly discovered medication phrases). Results: The NLP tool detected medication related phrases with an overall F-measure of 0.852. The medication name has been identified correctly with an overall F-measure of 0.936. Discussion: This proof-of-concept study is a first step towards an automated scalable evaluation system for MIRACUM’s industry partner’s NLP tool by using a gold standard. Medication phrases and names have been correctly identified in most cases by the NLP system. Future effort needs to be put into extending and validating the gold standard.

scholarly journals Beyond History: A Legacy and a Vision

2015 ◽  
Vol 49 (1) ◽  
Author(s):  
Leonor I. Cabral-Lim ◽  
Martesio C. Perez
Keyword(s):  
Past History ◽  
Health Sciences ◽  
The Philippines ◽  
University Hospital ◽  
Professor Emeritus ◽  
The Past ◽  
The Future ◽  
University History ◽  
National University ◽  
The University

Introduction This work is a tribute to all those who have shaped the Department of Neurosciences of the National University Hospital and the University of the Philippines Health Sciences Center. I am deeply honored to have collaborated with my highly esteemed mentor and colleague, Dr. Martesio Perez, Professor Emeritus of the University. History is more than a chronology of the past. There is much more beyond the names and events of the past. History has not only made us what we are today, but will also guide us to where we want to be in the future. As the historian David McCullough stated, "History is an unending dialogue between the past and the present." This written history starts at the present, goes back in time, and moves forward toward our envisioned future.

Contraceptive Practices in Women With Medical Conditions in the Clinics at the University Hospital of the West Indies [3G]

2018 ◽  
Vol 131 ◽  
pp. 75S
Author(s):  
Tiffany Hunter-Greaves ◽  
Nastassia Tate ◽  
Natalie Medley-Singh ◽  
Donnette Simms-Stewart
Keyword(s):  
West Indies ◽  
University Hospital ◽  
Medical Conditions ◽  
The West ◽  
The University

scholarly journals Medical Informatics Training and Research at Rennes University School of Medicine

1998 ◽  
Vol 07 (01) ◽  
pp. 71-77
Author(s):  
P. Beux ◽  
A. Burgun ◽  
P. Jarno ◽  
P. Siregar
Keyword(s):  
Medical Informatics ◽  
Language Processing ◽  
Local Area Network ◽  
Local Area ◽  
University Hospital ◽  
Research Network ◽  
Area Network ◽  
School Of Medicine ◽  
Informatics Training ◽  
The University

AbstractThe University of Rennes Medical School has offered Medical informatics training since 1988; at the same time, research in medical informatics was started. This paper describes the teaching programs at both the undergraduate level and at the graduate level. Research topics comprise fundamental research on biomedical models, ontologies for medical knowledge representations, natural language processing, and research for diagnosis and therapeutic aids. We have developed a local area network which communicates between the School of Medicine and the University Hospital, both internally (Intranet) and externally by access to the National Research network (RENA TER) in France, which is connected to the internet.

scholarly journals Missed Registration of Disease Codes for Pediatric Anaphylaxis at the Emergency Department

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Byungho Choi ◽  
Sun Hyu Kim ◽  
Hyeji Lee
Keyword(s):  
Emergency Department ◽  
Pediatric Patients ◽  
Past History ◽  
Gastrointestinal Symptoms ◽  
University Hospital ◽  
Future Research ◽  
Hospital Emergency ◽  
Steroid Use ◽  
History Of ◽  
The University

Background. It is important to register anaphylaxis codes correctly to study the exact prevalence of anaphylaxis. The purpose of this study was to analyze the clinical characteristics and disease codes of inaccurately registered groups in pediatric anaphylaxis patients. Methods. This study reviewed the medical records of all pediatric patients who presented to the university hospital emergency department over a 5-year period. Study subjects were divided into 2 groups: the accurate group, including those registered under anaphylaxis codes, and the inaccurate coding group, including those registered under other codes. Results. From a total of 79,676 pediatric patients, 184 (0.23%) had anaphylaxis. Of these, 23 (12.5%) and 161 (87.5%) patients were classified to the accurate and inaccurate coding groups, respectively. Average age, time from symptom onset to emergency department presentation, past history of allergy, and penicillin and cephalosporin as causes of anaphylaxis differed between the 2 groups. Cardiovascular (39.1% vs. 5.6%, p=0.001) and respiratory symptoms (65.2% vs. 42.2%, p=0.038) manifested more frequently in the accurate group, while gastrointestinal symptoms (68.3% vs. 26.1%, p=0.001) were more frequently observed in the inaccurate coding group. Fluid administration (82.6% vs. 28.0%, p=0.001), steroid use (60.9% vs. 23.0%, p=0.001), and epinephrine use (65.2% vs. 13.0% p=0.001) were more common treatments for anaphylaxis in the emergency department in the accurate group. Anaphylaxis patients with cardiovascular symptoms, steroid use, and epinephrine use were more likely to be accurately registered with anaphylaxis disease codes. Conclusions. In the case of pediatric anaphylaxis, more patients were registered inaccurately under other allergy-related codes and simple symptom codes, rather than under anaphylaxis codes. Therefore, future research on anaphylaxis should consider inaccurately registered anaphylactic patients, as shown in this study.

Eosinophilia and Agammaglobulinemia

PEDIATRICS ◽  
1965 ◽  
Vol 36 (3) ◽  
pp. 425-428
Author(s):  
CAROLYN C. HUNTLEY ◽  
MARGARITA C. COSTAS
Keyword(s):  
Past History ◽  
University Hospital ◽  
Larva Migrans ◽  
Helminth Infections ◽  
Child's Play ◽  
Immune Globulins ◽  
Group A ◽  
The University ◽  
Tissue Phase ◽  
Visceral Larva Migrans Syndrome

While studying a group of children with the visceral larva migrans syndrome we encountered in the patient group a child with agammaglobulinemia. This child, in spite of an almost complete absence of immune globulins, exhibited the massive eosinophilia characteristic of the tissue phase of helminth infections. Case Report L.C.S., a 16-month-old Puerto Rican boy, was admitted to the University Hospital in San Juan on February 19, 1963, because of fever, wheezing and cough of 3 weeks' duration. His past history revealed chronic diarrhea and episodes of purulent conjunctivitis, otitis, and pneumonia. Pica had been noted for 5 months, and dogs, cats, pigs, and cows were present near the child's play area.

scholarly journals Measures of Risk for Sepsis and Mortality in Severe Burned Patients with Stress Induced Hyperglycemia.

2021 ◽  
Vol 5 (2) ◽  
pp. 830-833
Author(s):  
Albana Aleksi ◽  
Monika Belba
Keyword(s):  
Medical Condition ◽  
University Hospital ◽  
Burn Shock ◽  
Burn Treatment ◽  
Risk Of Mortality ◽  
Close Relationship ◽  
Life Threatening ◽  
Burn Disease ◽  
The University ◽  
The Impact

Background; Hyperglycemia as a medical condition due to diabetes or other underlying conditions like Stress-Induced Hyperglycemia and sepsis as a life-threatening medical condition are two of the challenges faced during burn treatment. The purpose of this study was to evaluate the risk for sepsis and mortality for the patients with critical hyperglycemic values during the disease. Material and Methods; This is an observational retrospective cohort study conducted in the Service of Burns of the University Hospital Centre “Mother Teresa” in Tirana (UHCT), Albania from 1st January 2010 to 31st December 2014. Patients were categorized as having euglycemia (mean BG values ranging from 80-120 mg/dl), moderate hyper Sepsis was defined according to the ABA Consensus Panel Publication for Infection and Sepsis glycemia (mean BG values <180 mg/dl) or critical hyperglycemia (mean BG values ≥180 mg/dl). to evaluate the impact of the presence of critical hyperglycemia during the disease in sepsis and mortality, we performed Relative risk, Odds ratio Results; Those who had overall hyperglycemia (Moderate and Critical) had 2.6 times the risk for sepsis compared to those who were in the euglycemia group. Analyzing the risk of mortality in patients with overall hyperglycemia during the disease, we observed that the chance of a bad outcome was 2.7 times more likely to occur if the patient had hyperglycemia (RR=2.7). Conclusions: Glucose values on admission, as one of the derangement features of burn shock, are prognostic factors in critical hyperglycemia during burn disease and have a close relationship with other outcomes (sepsis and mortality).

Symptomatic vascular complications after vascular closure device use following diagnostic and interventional catheterisation

VASA ◽  
2004 ◽  
Vol 33 (2) ◽  
pp. 78-81 ◽  
Author(s):  
Thalhammer ◽  
Aschwanden ◽  
Jeanneret ◽  
Labs ◽  
Jäger
Keyword(s):  
Current Literature ◽  
Vascular Complications ◽  
University Hospital ◽  
Closure Device ◽  
Ultrasound Guided ◽  
Vascular Closure Device ◽  
Device Use ◽  
Arterial Stenoses ◽  
The University ◽  
Stenotic Lesions

Background: Haemostatic puncture closure devices for rapid and effective hemostasis after arterial catheterisation are a comfortable alternative to manual compression. Implanting a collagen plug against the vessel wall may become responsible for other kind of vascular injuries i.e. thrombotic or stenotic lesions and peripheral embolisation. The aim of this paper is to report our clinically relevant vascular complications after Angio-Seal® and to discuss the results in the light of the current literature. Patients and methods: We report the symptomatic vascular complications in 17 of 7376 patients undergoing diagnostic or therapeutic catheterisation between May 2000 and March 2003 at the University Hospital Basel. Results: Most patients presented with ischaemic symptoms, arterial stenoses or occlusions and thrombotic lesions (n = 14), whereas pseudoaneurysms were extremely rare (n = 3). Most patients with ischaemic lesions underwent vascular surgery and all patients with a pseudoaneurysm were successfully treated by ultrasound-guided compression. Conclusions: Severe vascular complications after Angio-Seal® are rare, consistent with the current literature. There may be a shift from pseudoaneurysms to ischaemic lesions.

User Evaluation of an Integrated Medical Workstation for Clinical Data Analysis

1993 ◽  
Vol 32 (05) ◽  
pp. 365-372 ◽  
Author(s):  
T. Timmeis ◽  
J. H. van Bemmel ◽  
E. M. van Mulligen
Keyword(s):  
Data Analysis ◽  
Clinical Research ◽  
Clinical Data ◽  
University Hospital ◽  
User Evaluation ◽  
Scientific Staff ◽  
Medical Institutions ◽  
Clinical Data Analysis ◽  
Research Problems ◽  
The University

AbstractResults are presented of the user evaluation of an integrated medical workstation for support of clinical research. Twenty-seven users were recruited from medical and scientific staff of the University Hospital Dijkzigt, the Faculty of Medicine of the Erasmus University Rotterdam, and from other Dutch medical institutions; and all were given a written, self-contained tutorial. Subsequently, an experiment was done in which six clinical data analysis problems had to be solved and an evaluation form was filled out. The aim of this user evaluation was to obtain insight in the benefits of integration for support of clinical data analysis for clinicians and biomedical researchers. The problems were divided into two sets, with gradually more complex problems. In the first set users were guided in a stepwise fashion to solve the problems. In the second set each stepwise problem had an open counterpart. During the evaluation, the workstation continuously recorded the user’s actions. From these results significant differences became apparent between clinicians and non-clinicians for the correctness (means 54% and 81%, respectively, p = 0.04), completeness (means 64% and 88%, respectively, p = 0.01), and number of problems solved (means 67% and 90%, respectively, p = 0.02). These differences were absent for the stepwise problems. Physicians tend to skip more problems than biomedical researchers. No statistically significant differences were found between users with and without clinical data analysis experience, for correctness (means 74% and 72%, respectively, p = 0.95), and completeness (means 82% and 79%, respectively, p = 0.40). It appeared that various clinical research problems can be solved easily with support of the workstation; the results of this experiment can be used as guidance for the development of the successor of this prototype workstation and serve as a reference for the assessment of next versions.

Sign in / Sign up

Export Citation Format

Share Document