RESUMO
OBJECTIVES: Our main objective is to design a method of, and supporting software for, interactive correction and semantic annotation of narrative clinical reports, which would allow for their easier and less erroneous processing outside their original context: first, by physicians unfamiliar with the original language (and possibly also the source specialty), and second, by tools requiring structured information, such as decision-support systems. Our additional goal is to gain insights into the process of narrative report creation, including the errors and ambiguities arising therein, and also into the process of report annotation by clinical terms. Finally, we also aim to provide a dataset of ground-truth transformations (specific for Czech as the source language), set up by expert physicians, which can be reused in the future for subsequent analytical studies and for training automated transformation procedures. METHODS: A three-phase preprocessing method has been developed to support secondary use of narrative clinical reports in electronic health record. Narrative clinical reports are narrative texts of healthcare documentation often stored in electronic health records. In the first phase a narrative clinical report is tokenized. In the second phase the tokenized clinical report is normalized. The normalized clinical report is easily readable for health professionals with the knowledge of the language used in the narrative clinical report. In the third phase the normalized clinical report is enriched with extracted structured information. The final result of the third phase is a semi-structured normalized clinical report where the extracted clinical terms are matched to codebook terms. Software tools for interactive correction, expansion and semantic annotation of narrative clinical reports has been developed and the three-phase preprocessing method validated in the cardiology area. RESULTS: The three-phase preprocessing method was validated on 49 anonymous Czech narrative clinical reports in the field of cardiology. Descriptive statistics from the database of accomplished transformations has been calculated. Two cardiologists participated in the annotation phase. The first cardiologist annotated 1500 clinical terms found in 49 narrative clinical reports to codebook terms using the classification systems ICD 10, SNOMED CT, LOINC and LEKY. The second cardiologist validated annotations of the first cardiologist. The correct clinical terms and the codebook terms have been stored in a database. CONCLUSIONS: We extracted structured information from Czech narrative clinical reports by the proposed three-phase preprocessing method and linked it to electronic health records. The software tool, although generic, is tailored for Czech as the specific language of electronic health record pool under study. This will provide a potential etalon for porting this approach to dozens of other less-spoken languages. Structured information can support medical decision making, quality assurance tasks and further medical research.
Assuntos
Registros Eletrônicos de Saúde/normas , Aprendizado de Máquina , Processamento de Linguagem Natural , Semântica , Vocabulário Controlado , Processamento de Texto/normas , Redação/normas , Confiabilidade dos Dados , Guias como Assunto , Classificação Internacional de Doenças , Uso Significativo/normas , Software , Interface Usuário-ComputadorRESUMO
Body surface potential mapping (BSPM) enables to obtain more information about local changes of the heart electrical field then classical electrocardiography makes it possible. We performed this non-invasive diagnostic method in the group of 108 men in the frame of the primary preventive study of the risk factors of atherosclerosis. The findings of BSPM were compared to the selective coronary angiography. The study was started in the years 1976-1979 in the district Prague 2. Out of 2370 invited middle-aged men, 1419 took part in the study. 937 men (66.0%) were affected by one or more risk factors of atherosclerosis. No statistical significance was found in regard to the number and the level of risk factors of atherosclerosis between the groups of patients with different findings on the coronary angiography. Nevertheless, the method of BSPM is a very useful in epidemiological studies of atherosclerosis, namely with coronary localization, in clinical practice, and in the biomedical research too.
Assuntos
Arteriosclerose/diagnóstico , Mapeamento Potencial de Superfície Corporal , Arteriosclerose/epidemiologia , República Tcheca/epidemiologia , Estudos Epidemiológicos , Humanos , Masculino , Fatores de RiscoRESUMO
An electronic form of 1999 ISH/WHO Guidelines for Management of Hypertension was developed. It concentrates on two main problems--assessment of a patient's cardiovascular risk and selecting drug treatment. Moreover, it can remind the risk of unfilled items both for a cardiovascular risk calculation and drug contraindications. It can be stored for comparison with other records from follow-up both in an electronic and paper form.
Assuntos
Sistemas de Apoio a Decisões Clínicas , Hipertensão , Guias de Prática Clínica como Assunto , Anti-Hipertensivos/uso terapêutico , Humanos , Hipertensão/tratamento farmacológico , Fatores de RiscoRESUMO
Up to 20% to 30% of patients with angina and abnormal stress test have normal coronary arteries at angiography or syndrome X (Sy X). We tested whether body surface potential mapping (BSPM) with intravenous dipyridamole could differentiate patients with Sy X from patients with coronary artery disease (CAD). We compared the effects of intravenous dipyridamole (0.28 mg/kg over 4 min) on BSPM in 17 healthy volunteers (controls) and in 2 groups of patients with angina and abnormal ergometric tests who were referred for angiography: 27 patients with obstructive disease (> or =70% diameter stenosis) in the CAD group, and 17 patients with Sy X. Control subjects were easily differentiated from patients with CAD or Sy X by markedly smaller baseline BSPM DeltaST-T < or = LSD departure areas (P <.001), but the Sy X and CAD groups had similar ST-T departure areas. The average potential integral difference after dipyridamole (APID) differentiated Sy X and CAD patients: the mean APID increased in patients with Sy X and trended negative in the CAD group. The APID(20%-40%) (integrated over 20% to 40% of the ST-T interval) mean value was 0.59 +/- 0.67 microVs in the Sy X group and -0.18 +/- 0.59 microVs in the CAD group (P <.01). At a threshold APID(20%-40%) > 0.17 microVs, the sensitivity and specificity for Sy X was 71% and 78%, respectively; the area under the receiver operating characteristic curve was 0.79 (95% CI 0.64, 0.93). Dipyridamole BSPM is a promising noninvasive diagnostic modality to differentiate patients with Sy X from those with CAD.
Assuntos
Mapeamento Potencial de Superfície Corporal/efeitos dos fármacos , Doença das Coronárias/diagnóstico , Dipiridamol/farmacologia , Angina Microvascular/diagnóstico , Angiografia Coronária , Diagnóstico Diferencial , Dipiridamol/administração & dosagem , Teste de Esforço , Feminino , Humanos , Injeções Intravenosas , Masculino , Pessoa de Meia-Idade , Sensibilidade e EspecificidadeRESUMO
En un estudio de prevención primaria de la enfermedad coronaria (EC), 164 varones con factores de riesgo (FR) al inicio del ensayo (1975 a 1979) se evaluaron durante el período comprendido entre 1996 y 2002 mediante un mapeo de superficie corporal (MSC). Los resultados se dividieron en dos grupos, uno con 71 varones (43.3%) con buen pronóstico (MSC normal y síndrome X) y el otro grupo con 93 sujetos (56.7%) con pronóstico desfavorable (MSC avanzado con EC moderada). Esta división hizo posible el análisis estadístico, ya que de otro modo los grupos hubieran resultado pequeños. En el análisis univariado, entre los fumadores se observó un efecto significativo del patrón de MSC sobre la EC, en comparación con los no fumadores (p = 0.002). La hipertensión sistólica (HTS) y el colesterol total no influyeron significativamente sobre el MSC. En el análisis multivariado, la probabilidad de que los fumadores presentaran un patrón de EC en el MSC fue 2.6 veces mayor en comparación con los no fumadores (p = 0.007). Los resultados del MSC se relacionaron parcialmente con la HTS (p = 0.074). Las probabilidades fueron 1.9 veces mayores en los varones con HTS > 140 mm Hg en comparación con los sujetos con presión arterial sistólica normal. No se encontraron diferencias estadísticamente significativas para el colesterol total. Los motivos de estos resultados se discuten en relación con los datos del estudio a largo plazo. Se comparan los resultados del MSC con los obtenidos en 2 pequeños ensayos sobre angina de pecho (AP) en los cuales se utilizaron electrocardiogramas.(AU)
Assuntos
Humanos , Masculino , Adulto , Doença das Coronárias/diagnóstico , Doença das Coronárias/prevenção & controle , Mapeamento Potencial de Superfície Corporal/instrumentação , Mapeamento Potencial de Superfície Corporal/métodos , Mapeamento Potencial de Superfície Corporal/estatística & dados numéricos , Prevenção Primária/métodos , Prevenção Primária/instrumentaçãoRESUMO
En un estudio de prevención primaria de la enfermedad coronaria (EC), 164 varones con factores de riesgo (FR) al inicio del ensayo (1975 a 1979) se evaluaron durante el período comprendido entre 1996 y 2002 mediante un mapeo de superficie corporal (MSC). Los resultados se dividieron en dos grupos, uno con 71 varones (43.3%) con buen pronóstico (MSC normal y síndrome X) y el otro grupo con 93 sujetos (56.7%) con pronóstico desfavorable (MSC avanzado con EC moderada). Esta división hizo posible el análisis estadístico, ya que de otro modo los grupos hubieran resultado pequeños. En el análisis univariado, entre los fumadores se observó un efecto significativo del patrón de MSC sobre la EC, en comparación con los no fumadores (p = 0.002). La hipertensión sistólica (HTS) y el colesterol total no influyeron significativamente sobre el MSC. En el análisis multivariado, la probabilidad de que los fumadores presentaran un patrón de EC en el MSC fue 2.6 veces mayor en comparación con los no fumadores (p = 0.007). Los resultados del MSC se relacionaron parcialmente con la HTS (p = 0.074). Las probabilidades fueron 1.9 veces mayores en los varones con HTS > 140 mm Hg en comparación con los sujetos con presión arterial sistólica normal. No se encontraron diferencias estadísticamente significativas para el colesterol total. Los motivos de estos resultados se discuten en relación con los datos del estudio a largo plazo. Se comparan los resultados del MSC con los obtenidos en 2 pequeños ensayos sobre angina de pecho (AP) en los cuales se utilizaron electrocardiogramas.