Medición de la mortalidad de pacientes internados por enfermedad cardiovascular mediante el desarrollo de un algoritmo de inteligencia artificial / Measurement of mortality during hospitalization due cardiovascular disease through the development of an artificial intelligence algorithm

Introducción: determinar la causa de muerte de los pacientes internados con enfermedad cardiovascular es de suma importancia para poder tomar medidas y así mejorar la calidad su atención y prevenir muertes evitables. Objetivos: determinar las principales causas de muerte durante la internación por enfermedades cardiovasculares. Desarrollar y validar un algoritmo para clasificar automáticamente a los pacientes fallecidos durante la internación con enfermedades cardiovasculares Diseño del estudio: estudio exploratorio retrospectivo. Desarrollo de un algoritmo de clasificación. Resultados: del total de 6161 pacientes, el 21,3% (1316) se internaron por causas cardiovasculares; las enfermedades cerebrovasculares representan el 30,7%, la insuficiencia cardíaca el 24,9% y las enfermedades cardíacas isquémicas el 14%. El algoritmo de clasificación según motivo de internación cardiovascular vs. no cardiovascular alcanzó una precisión de 0,9546 (IC 95%: 0,9351-0,9696). El algoritmo de clasificación de causa específica de internación cardiovascular alcanzó una precisión global de 0,9407 (IC 95%: 0,8866-0,9741). Conclusiones: la enfermedad cardiovascular representa el 21,3% de los motivos de internación de pacientes que fallecen durante su desarrollo. Los algoritmos presentaron en general buena performance, particularmente el de clasificación del motivo de internación cardiovascular y no cardiovascular y el clasificador según causa específica de internación cardiovascular. (AU)

Introduction: determining the cause of death of hospitalized patients with cardiovascular disease is of the utmost importance in order to take measures and thus improve the quality of care of these patients and prevent preventable deaths. Objectives: to determine the main causes of death during hospitalization due to cardiovascular diseases.To development and validate a natural language processing algorithm to automatically classify deceased patients according to their cause for hospitalization. Design: retrospective exploratory study. Development of a natural language processing classification algorithm. Results: of the total 6161 patients in our sample who died during hospitalization, 21.3% (1316) were hospitalized due to cardiovascular causes. The stroke represent 30.7%, heart failure 24.9%, and ischemic cardiac disease 14%. The classification algorithm for detecting cardiovascular vs. Non-cardiovascular admission diagnoses yielded an accuracy of 0.9546 (95% CI 0.9351, 0.9696), the algorithm for detecting specific cardiovascular cause of admission resulted in an overall accuracy of 0.9407 (95% CI 0.8866, 0.9741). Conclusions: cardiovascular disease represents 21.3% of the reasons for hospitalization of patients who die during hospital stays. The classification algorithms generally showed good performance, particularly the classification of cardiovascular vs non-cardiovascular cause for admission and the specific cardiovascular admission cause classifier. (AU)

Evaluación de la adherencia primaria a medicamentos en pacientes con enfermedades crónicas afiliados al Seguro de Salud del Hospital Italiano de Buenos Aires: estudio de cohorte retrospectiva / Evaluation of primary adherence to medications in patients with chronic conditions: A retrospective cohort study

Objetivos: Evaluar la proporción de afiliados al Seguro de Salud del Hospital Italiano de Buenos Aires con adherencia primaria a: 1) bifosfonatos para la prevención secundaria de fractura osteoporótica; 2) insulina y metformina para el tratamiento de diabetes tipo 2, y 3) tamoxifeno en el contexto del tratamiento del cáncer mamario. Diseño: Cohorte retrospectiva para determinar la proporción de la adherencia primaria durante los años 2012 y 2013. Emplazamiento: Hospital Italiano de Buenos Aires, Argentina. Participantes: Afiliados al Seguro de Salud del Hospital Italiano de Buenos Aires, a quienes en el periodo descrito anteriormente se les hubiera realizado una prescripción electrónica nueva de los fármacos descritos previamente. Fueron evaluadas 1.403 nuevas prescripciones electrónicas de los fármacos analizados, de las cuales se excluyeron 673 por no cumplir con los criterios de inclusión. Mediciones principales: Adherencia primaria: constatación de que se dispensó la nueva medicación durante los primeros 30 días de haber sido realizada la prescripción electrónica índice. El análisis primario evaluó la proporción de adherencia primaria de los diferentes medicamentos. Se realizó un análisis bivariado para comparar las características y los posibles predictores. Resultados: La proporción de adherencia primaria para los fármacos y las familias de los fármacos analizados fue: bifosfonatos, 93%; metformina, 88%; insulina, 96%; y tamoxifeno, 92%. Conclusiones: Este es el primer estudio que evaluó la adherencia primaria en Argentina y, según los resultados de nuestra búsqueda, el primero en el mundo para tamoxifeno. La adherencia primaria documentada en nuestra investigación fue algo mayor que la informada en la bibliografía (AU)

Objectives: To assess the proportion of members of a private health insurance at the Hospital Italiano de Buenos Aires with primary adherence to, 1) bisphosphonates for secondary prevention of osteoporotic fractures, 2) insulin and metformin in type 2 diabetes, and 3) tamoxifen in the context of treatment of breast cancer. Design: Retrospective cohort study to determine the proportion of primary treatment adherence during 2012 and 2013. Site: Hospital Italiano de Buenos Aires, Argentina. Participants: Members of the Hospital Italiano de Buenos Aires private health insurance, who had received a new electronic prescription (alendronate or ibandronate for secondary prevention of fractures following an osteoporotic fracture; insulin and/or metformin for type 2 diabetes; or tamoxifen as a treatment for breast cancer) during the years 2012 and 2013. An analysis was performed on 1,403 new electronic prescriptions, of which 673 were excluded for not meeting the inclusion criteria. Main measurements: Primary adherence has been defined as the execution of a first-time treatment after it was agreed with the health care provider. The primary analysis assessed the proportion of primary adherence for the three medications. A bivariate analysis was performed to compare the characteristics and potential predictors of primary adherence. Results: Primary adherence for each drug group was, 93% Bisphosphonates, 88% Metformin, 96% Insulin, and 92% Tamoxifen. Conclusions: To the best of our knowledge, this is the first study that has evaluated primary adherence in Argentina, and the first for Tamoxifen world wide. The primary adherence documented in our study was somewhat higher than that reported in the literature (AU)

[Evaluation of primary adherence to medications in patients with chronic conditions: A retrospective cohort study]. / Evaluación de la adherencia primaria a medicamentos en pacientes con enfermedades crónicas afiliados al Seguro de Salud del Hospital Italiano de Buenos Aires: estudio de cohorte retrospectiva.

OBJECTIVES: To assess the proportion of members of a private health insurance at the Hospital Italiano de Buenos Aires with primary adherence to, 1) bisphosphonates for secondary prevention of osteoporotic fractures, 2) insulin and metformin in type 2 diabetes, and 3) tamoxifen in the context of treatment of breast cancer. DESIGN: Retrospective cohort study to determine the proportion of primary treatment adherence during 2012 and 2013. SITE: Hospital Italiano de Buenos Aires, Argentina. PARTICIPANTS: Members of the Hospital Italiano de Buenos Aires private health insurance, who had received a new electronic prescription (alendronate or ibandronate for secondary prevention of fractures following an osteoporotic fracture; insulin and/or metformin for type 2 diabetes; or tamoxifen as a treatment for breast cancer) during the years 2012 and 2013. An analysis was performed on 1,403 new electronic prescriptions, of which 673 were excluded for not meeting the inclusion criteria. MAIN MEASUREMENTS: Primary adherence has been defined as the execution of a first-time treatment after it was agreed with the health care provider. The primary analysis assessed the proportion of primary adherence for the three medications. A bivariate analysis was performed to compare the characteristics and potential predictors of primary adherence. RESULTS: Primary adherence for each drug group was, 93% Bisphosphonates, 88% Metformin, 96% Insulin, and 92% Tamoxifen. CONCLUSIONS: To the best of our knowledge, this is the first study that has evaluated primary adherence in Argentina, and the first for Tamoxifen world wide. The primary adherence documented in our study was somewhat higher than that reported in the literature.

Mortalidad y causas de muerte de pacientes internados por enfermedad coronaria aguda o accidente vascular cerebral / Mortality and causes of death of patients hospitalized for acute coronary disease or cerebrovascular accident

INTRODUCCIÓN Determinar la causa de muerte de los pacientes internados con enfermedad cardiovascular es de suma importancia para poder tomar medidas y así mejorar la calidad de atención de estos pacientes y prevenir muertes evitables. En la bibliografía existe muy poca información sobre la causas de muerte de estos pacientes. OBJETIVOS Determinar las principales causas de muerte durante la internación por Enfermedades cardíacas isquémicas o Enfermedades cerebrovasculares de pacientes del Hospital Italiano de Bs As durante el periodo 1 de enero 2005 al 31 de diciembre 2016. Desarrollar y validar un algoritmo para clasificar automáticamente a los pacientes fallecidos durante la internación con Enfermedades cardíacas isquémicas o Enfermedades cerebrovasculares y dentro de estos pacientes identificar la causa final de muerte documentada en la epicrisis e información de texto libre en la Historia Clínica Electrónica. Diseño del estudio Estudio exploratorio retrospectivo en el Hospital Italiano de Bs As. Desarrollo de un algoritmo de clasificación. RESULTADOS Del total de 6161 pacientes que fallecieron durante la internación, el 21,3% (1316) se internaron por causas cardiovasculares. Los siguientes motivos componen >80% de los motivos de internación; Enf cerebrovasculares 30.7%, Insuficiencia cardiaca 24,9%, Enf cardíacas isq 14%, Edema Agudo de pulmón 4,9%. Las principales causas finales de muerte de los pacientes que se internaron por causas cardiovasculares estuvieron entre Shock cardiogénico/hipovolémico 23.9%, Enf Cerebrovasculares 18,4%, Shock Séptico 14%, Neumonía 10,9%, e Insuficiencia cardiaca 8%. Algoritmo de clasificación según motivo de internación cardiovascular vs. no cardiovascular. La performance sobre el test set resultó en una precisión de 0.9546 (IC 95% 0.9351, 0.9696). Algoritmo de clasificación por tipo de motivo de internación cardiovascular. La performance sobre el test set resultó en una precisión global de 0.9407 (IC 95% 0.8866, 0.9741). Algoritmo de clasificación según causa final de muerte; La performance sobre el test set resultó en una precisión global de 0.78 (IC 95% 0.73, 0.844). DISCUSIÓN La enfermedad cardiovascular representa el 21,3% de los motivos de internación de pacientes que fallecen durante la misma. En estos casos, la falla cardíaca, la enfermedad cerebrovascular y las infecciones son las principales causas de muerte final. Los algoritmos presentaron en general buena performance, particularmente el de clasificación de MI CV vs MI no CV y el clasificador según MI CV. El de causa final de muerte sufrió principalmente limitaciones en su performance por el tamaño del set de datos validados, teniendo en cuenta que hay un mayor número de categorías de clasificación

Development and validation of various phenotyping algorithms for Diabetes Mellitus using data from electronic health records.

BACKGROUND AND OBJECTIVE: Recent progression towards precision medicine has encouraged the use of electronic health records (EHRs) as a source for large amounts of data, which is required for studying the effect of treatments or risk factors in more specific subpopulations. Phenotyping algorithms allow to automatically classify patients according to their particular electronic phenotype thus facilitating the setup of retrospective cohorts. Our objective is to compare the performance of different classification strategies (only using standardized problems, rule-based algorithms, statistical learning algorithms (six learners) and stacked generalization (five versions)), for the categorization of patients according to their diabetic status (diabetics, not diabetics and inconclusive; Diabetes of any type) using information extracted from EHRs. METHODS: Patient information was extracted from the EHR at Hospital Italiano de Buenos Aires, Buenos Aires, Argentina. For the derivation and validation datasets, two probabilistic samples of patients from different years (2005: n = 1663; 2015: n = 800) were extracted. The only inclusion criterion was age (≥40 & <80 years). Four researchers manually reviewed all records and classified patients according to their diabetic status (diabetic: diabetes registered as a health problem or fulfilling the ADA criteria; non-diabetic: not fulfilling the ADA criteria and having at least one fasting glycemia below 126 mg/dL; inconclusive: no data regarding their diabetic status or only one abnormal value). The best performing algorithms within each strategy were tested on the validation set. RESULTS: The standardized codes algorithm achieved a Kappa coefficient value of 0.59 (95% CI 0.49, 0.59) in the validation set. The Boolean logic algorithm reached 0.82 (95% CI 0.76, 0.88). A slightly higher value was achieved by the Feedforward Neural Network (0.9, 95% CI 0.85, 0.94). The best performing learner was the stacked generalization meta-learner that reached a Kappa coefficient value of 0.95 (95% CI 0.91, 0.98). CONCLUSIONS: The stacked generalization strategy and the feedforward neural network showed the best classification metrics in the validation set. The implementation of these algorithms enables the exploitation of the data of thousands of patients accurately.

Development and Validation of Various Phenotyping Algorithms for Diabetes Mellitus Using Data from Electronic Health Records.

Precision medicine requires extremely large samples. Electronic health records (EHR) are thought to be a cost-effective source of data for that purpose. Phenotyping algorithms help reduce classification errors, making EHR a more reliable source of information for research. Four algorithm development strategies for classifying patients according to their diabetes status (diabetics; non-diabetics; inconclusive) were tested (one codes-only algorithm; one boolean algorithm, four statistical learning algorithms and six stacked generalization meta-learners). The best performing algorithms within each strategy were tested on the validation set. The stacked generalization algorithm yielded the highest Kappa coefficient value in the validation set (0.95 95% CI 0.91, 0.98). The implementation of these algorithms allows for the exploitation of data from thousands of patients accurately, greatly reducing the costs of constructing retrospective cohorts for research.

Pubertad precoz y temprana: evaluación y tratamiento / Early puberty: evaluation and treatment

El autor de este artículo repasa las características clínicas de la pubertad precoz y la pubertad temprana, las pruebas diagnósticas indicadas en la evaluación de los pacientes que la presentan y las recomendaciones actuales de tratamiento. (AU)

The author of this article reviews the clinical features of early puberty, the diagnostic tests for the patients ́ evaluation andthe current treatment recommendations. (AU)