MedTextSeg: A Deep Dual Sequential Model for Section Segmentation in Medical Reports

2021 ◽  
Author(s):  
Shaika Chowdhury ◽  
Halid Yerebakan ◽  
Yoshihisa Shinagawa ◽  
Philip S. Yu
Keyword(s):  
Sequential Model ◽  
Medical Reports

Structured Reporting of Medical Findings: Evaluation of a System in Gastroenterology

1992 ◽  
Vol 31 (04) ◽  
pp. 268-274 ◽  
Author(s):  
W. Gaus ◽  
J. G. Wechsler ◽  
P. Janowitz ◽  
J. Tudyka ◽  
W. Kratzer ◽  
...  
Keyword(s):  
Structured Data ◽  
Structured Reporting ◽  
Free Text ◽  
Clinical Documentation ◽  
Abdominal Sonography ◽  
Technical Examination ◽  
Medical Reports ◽  
Time Required ◽  
Upper Abdominal ◽  
Structured Approach

Abstract:A system using structured reporting of findings was developed for the preparation of medical reports and for clinical documentation purposes in upper abdominal sonography, and evaluated in the course of routine use. The evaluation focussed on the following parameters: completeness and correctness of the entered data, the proportion of free text, the validity and objectivity of the documentation, user acceptance, and time required. The completeness in the case of two clinically relevant parameters could be compared with an already existing database containing freely dictated reports. The results confirmed the hypothesis that, for the description of results of a technical examination, structured data reporting is a viable alternative to free-text dictation. For the application evaluated, there is even evidence of the superiority of a structured approach. The system can be put to use in related areas of application.

Traditional aspects to sciatic pain and allied therapies from Persian medical reports

2020 ◽  
Vol 17 ◽  
Author(s):  
Ramin Ansari ◽  
Amirhossein Dadbakhsh ◽  
Fatemeh Hasani ◽  
Fatemeh Hosseinzadeh ◽  
Zohreh Abolhassanzadeh ◽  
...  
Keyword(s):  
Medicinal Plants ◽  
Zingiber Officinale ◽  
Therapeutic Effects ◽  
School Of Medicine ◽  
Sciatic Pain ◽  
Novel Drugs ◽  
Zingiber Officinale Roscoe ◽  
Medical Reports ◽  
Traditional Persian Medicine ◽  
Increasing Demand

: Sciatica is a common back pain caused by irritation of the sciatic nerve. Current pharmacologic therapies have proven inadequate for many patients with sciatic pain. On the other hand, there is a global increasing demand toward the use and administration of natural medicaments for this disorder. Traditional Persian Medicine (TPM) is a school of medicine and a medicinal plant based resource for clinical studies put forward by Persian scholars. The aim of the present study is to gather and study the effectiveness of all medicinal plants from five main Persian pharmacopeias. Furthermore, different data bases such as PubMed and Scopus have been checked to derive relevant activities for these plants. In all, 99 medicinal plants related to 42 families have been authenticated. Asteraceae and Apiaceae were the most frequent families and Roots and Seeds were the most reported botanical parts. The employed routs of administration were oral (54%), topical (33%) and rectal (13%). Anti-inflammatory, analgesic activity and anti-nociceptive properties of medicines are known as some main mechanisms to manage sciatic pain. These functions are possessed by 30%, 15%, and 15% of the studied plants, respectively. Medicaments that can be introduced as lead agents for further investigation are Zingiber officinale Roscoe, Olea europaea L., Strychnos nux-vomica L and Artemisia vulgaris L which showed all of these properties in previous studies. Hence, conducting adducible clinical trials using these lead agents may lead to novel drugs with lesser undesirable and much more therapeutic effects on controlling sciatic pain.

Survival With Respect to Morphology in Pulmonary Atresia and Intact Ventricular Septum in Sweden

2021 ◽  
Vol 12 (1) ◽  
pp. 27-34
Author(s):  
Stina Manhem ◽  
Katarina Hanséus ◽  
Håkan Berggren ◽  
Britt-Marie Ekman-Joelsson
Keyword(s):  
Pulmonary Atresia ◽  
Early Time ◽  
Ventricular Septum ◽  
Intact Ventricular Septum ◽  
Early Group ◽  
Time Period ◽  
Medical Reports ◽  
One Year ◽  
Survival Risk ◽  
Late Group

Background: Patients born with pulmonary atresia and intact ventricular septum represent a challenge to pediatric cardiologists. Our objective was to study changes in survival with respect to morphology in all children born with pulmonary atresia and intact ventricular septum in Sweden during 36 years. Methods: A retrospective, descriptive study based on medical reports and echocardiographic examinations consisting of those born between 1980 and 1998 (early group) and those born between 1999 and 2016 (late group). Results: The cohort consists of 171 patients (early group, n = 86 and late group, n = 85) yielding an incidence of 4.35 and 4.46 per 100,000 live births, respectively. One-year survival in the early group was 76% compared to 92% in the late group ( P = .0004). For patients with membranous atresia, one-year survival increased from 78% to 98%, and for muscular pulmonary atresia, from 68% to 85%. In patients with muscular pulmonary atresia and ventriculocoronary arterial communications, there was no significant increase in survival. Risk factors for death were being born in the early time period hazard ratio (HR), 6; 95% CI (2.33-14.28) P = .0002, low birth weight HR, 1.26; 95% CI (1.14-1.4) P < .0001 and having muscular pulmonary atresia HR, 3.74; 95% CI (1.71-8.19) P = .0010. Conclusion: The incidence of pulmonary atresia and intact ventricular septum remained unchanged during the study period. Survival has improved, especially for patients with membranous pulmonary atresia, while being born with muscular pulmonary atresia is still a risk factor for death. To further improve survival, greater focus on patients with muscular pulmonary atresia and ventriculocoronary arterial communications is required.

scholarly journals Dementia epidemiology in Hungary based on data from neurological and psychiatric specialty services

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nóra Balázs ◽  
András Ajtay ◽  
Ferenc Oberfrank ◽  
Dániel Bereczki ◽  
Tibor Kovács
Keyword(s):  
Psychiatric Services ◽  
Psychiatric Diagnoses ◽  
Prevalence Rates ◽  
Health Insurance System ◽  
Crude Incidence ◽  
Specialist Services ◽  
Single Payer ◽  
Icd 10 ◽  
Medical Reports ◽  
The Mean

AbstractHungary has a single-payer health insurance system covering 10 million inhabitants. All medical reports of the in- and outpatient specialist services were collected in the NEUROHUN database. We used ICD-10 codes of Alzheimer’s disease (AD), vascular dementia (VaD), miscellaneous dementia group and mild cognitive impairment (MCI) for the inclusion of the patients. Incidence, prevalence and survival of different dementias and MCI were calculated and analyzed depending on the diagnoses given by neurological or psychiatric services or both. Between 2011 and 2016, the mean crude incidence of all dementias was 242/100,000/year, whereas the age standardized incidence was 287/100,000/year. Crude and age standardized mean prevalence rates were 570/100,000 and 649/100,000, respectively. There were significantly more VaD diagnoses than AD, the VaD:AD ratio was 2.54:1, being the highest in patients with psychiatric diagnoses only (4.85:1) and the lowest in patients with only neurological diagnoses (1.32:1). The median survival after the first diagnosis was 3.01 years regarding all dementia cases. Compared to international estimates, the prevalence of dementia and MCI is considerably lower in Hungary and the VaD:AD ratio is reversed.

scholarly journals Improving early diagnosis of rare diseases using Natural Language Processing in unstructured medical records: an illustration from Dravet syndrome

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Tommaso Lo Barco ◽  
Mathieu Kuchenbuch ◽  
Nicolas Garcelon ◽  
Antoine Neuraz ◽  
Rima Nabbout
Keyword(s):  
Natural Language Processing ◽  
Early Diagnosis ◽  
Natural Language ◽  
Language Processing ◽  
Rare Diseases ◽  
Febrile Seizures ◽  
Epileptic Encephalopathy ◽  
Dravet Syndrome ◽  
Written Information ◽  
Medical Reports

Abstract Background The growing use of Electronic Health Records (EHRs) is promoting the application of data mining in health-care. A promising use of big data in this field is to develop models to support early diagnosis and to establish natural history. Dravet Syndrome (DS) is a rare developmental and epileptic encephalopathy that commonly initiates in the first year of life with febrile seizures (FS). Age at diagnosis is often delayed after 2 years, as it is difficult to differentiate DS at onset from FS. We aimed to explore if some clinical terms (concepts) are significantly more used in the electronic narrative medical reports of individuals with DS before the age of 2 years compared to those of individuals with FS. These concepts would allow an earlier detection of patients with DS resulting in an earlier orientation toward expert centers that can provide early diagnosis and care. Methods Data were collected from the Necker Enfants Malades Hospital using a document-based data warehouse, Dr Warehouse, which employs Natural Language Processing, a computer technology consisting in processing written information. Using Unified Medical Language System Meta-thesaurus, phenotype concepts can be recognized in medical reports. We selected individuals with DS (DS Cohort) and individuals with FS (FS Cohort) with confirmed diagnosis after the age of 4 years. A phenome-wide analysis was performed evaluating the statistical associations between the phenotypes of DS and FS, based on concepts found in the reports produced before 2 years and using a series of logistic regressions. Results We found significative higher representation of concepts related to seizures’ phenotypes distinguishing DS from FS in the first phases, namely the major recurrence of complex febrile convulsions (long-lasting and/or with focal signs) and other seizure-types. Some typical early onset non-seizure concepts also emerged, in relation to neurodevelopment and gait disorders. Conclusions Narrative medical reports of individuals younger than 2 years with FS contain specific concepts linked to DS diagnosis, which can be automatically detected by software exploiting NLP. This approach could represent an innovative and sustainable methodology to decrease time of diagnosis of DS and could be transposed to other rare diseases.

Sign in / Sign up

Export Citation Format

Share Document