Bayesian joint ordinal and survival modeling for breast cancer risk assessment.

We propose a joint model to analyze the structure and intensity of the association between longitudinal measurements of an ordinal marker and time to a relevant event. The longitudinal process is defined in terms of a proportional-odds cumulative logit model. Time-to-event is modeled through a left-truncated proportional-hazards model, which incorporates information of the longitudinal marker as well as baseline covariates. Both longitudinal and survival processes are connected by means of a common vector of random effects. General inferences are discussed under the Bayesian approach and include the posterior distribution of the probabilities associated to each longitudinal category and the assessment of the impact of the baseline covariates and the longitudinal marker on the hazard function. The flexibility provided by the joint model makes possible to dynamically estimate individual event-free probabilities and predict future longitudinal marker values. The model is applied to the assessment of breast cancer risk in women attending a population-based screening program. The longitudinal ordinal marker is mammographic breast density measured with the Breast Imaging Reporting and Data System (BI-RADS) scale in biennial screening exams. © 2016 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

A cost-utility analysis of increasing percutaneous coronary intervention use in elderly patients with acute coronary syndromes in six European countries.

AIMS: Percutaneous coronary intervention reduces mortality in acute coronary syndrome patients but the cost-utility of increasing its use in elderly acute coronary syndrome patients is unknown. METHODS: We assessed the efficiency of increased percutaneous coronary intervention use compared to current practice in patients aged ≥75 years admitted for acute coronary syndrome in France, Germany, Greece, Italy, Portugal and Spain with a semi-Markov state transition model. In-hospital mortality reduction estimates by percutaneous coronary intervention use and costs were derived from the EUROpean Treatment & Reduction of Acute Coronary Syndromes cost analysis EU project (n = 28,600). Risk of recurrence and out-of-hospital all-cause mortality were obtained from the Information System for the Development of Research in Primary Care (SIDIAP) database from North-Eastern Spain (n = 55,564). In-hospital mortality was modelled using stratified propensity score analysis. The 8-year acute coronary syndrome recurrence risk and out-of-hospital mortality were estimated with a multistate survival model. The scenarios analysed were to increase percutaneous coronary intervention use among patients with the highest, moderate and lowest probability of receiving percutaneous coronary intervention based on the propensity score analysis. RESULTS: France, Greece and Portugal showed similar total costs/1000 individuals (7.29-11.05 m €); while in Germany, Italy and Spain, costs were higher (13.53-22.57 m €). Incremental cost-utility ratios of providing percutaneous coronary intervention to all patients ranged from 2262.8 €/quality adjusted life year gained for German males to 6324.3 €/quality adjusted life year gained for Italian females. Increasing percutaneous coronary intervention use was cost-effective at a willingness-to-pay threshold of 10,000 €/quality adjusted life year gained for all scenarios in the six countries, in males and females. CONCLUSION: Compared to current clinical practice, broadening percutaneous coronary intervention use in elderly acute coronary syndrome patients would be cost-effective across different healthcare systems in Europe, regardless of the selected strategy.

Costs of outpatient parenteral antimicrobial therapy (OPAT) administered by Hospital at Home units in Spain.

The aim of this study was to assess the direct healthcare costs of outpatient parenteral antimicrobial therapy (OPAT) administered by Hospital at Home (HaH) units in Spain. An observational, multicentre, economic evaluation of retrospective cohorts was conducted. Patients were treated at home by the HaH units of three Spanish hospitals between January 2012 and December 2013. From the cost accounting of HaH OPAT (staff, pharmacy, transportation, diagnostic tests and structural), the cost of each outpatient course was obtained following a top-down strategy based on the use of resources. Costs associated with inpatient stay, if any, were estimated based on length of stay and ICD-9-CM diagnosis. There were 1324 HaH episodes in 1190 patients (median age 70 years). The median (interquartile range) stay at home was 10 days (7-15 days). Of the OPAT episodes, 91.5% resulted in cure or improvement on completion of intravenous therapy. The mean total cost of each infectious episode was €6707 [95% confidence interval (CI) €6189-7406]. The mean cost per OPAT episode was €1356 (95% CI €1247-1560), mainly distributed between healthcare staff costs (46%) and pharmacy costs (39%). The mean cost of inpatient hospitalisation of an infectious episode was €4357 (95% CI €3947-4977). The cost per day of inpatient hospitalisation was €519, whilst the cost per day of OPAT was €98, meaning a saving of 81%. This study shows that OPAT administered by HaH units resulted in lower costs compared with inpatient care in Spain.

[Use of multiple regression models in observational studies (1970-2013) and requirements of the STROBE guidelines in Spanish scientific journals]. / Utilización de los modelos de regresión múltiple en estudios observacionales (1970-2013) y requerimiento de la guía STROBE en revistas científicas españolas.

BACKGROUND: In medicine and biomedical research, statistical techniques like logistic, linear, Cox and Poisson regression are widely known. The main objective is to describe the evolution of multivariate techniques used in observational studies indexed in PubMed (1970-2013), and to check the requirements of the STROBE guidelines in the author guidelines in Spanish journals indexed in PubMed. METHODS: A targeted PubMed search was performed to identify papers that used logistic linear Cox and Poisson models. Furthermore, a review was also made of the author guidelines of journals published in Spain and indexed in PubMed and Web of Science. RESULTS: Only 6.1% of the indexed manuscripts included a term related to multivariate analysis, increasing from 0.14% in 1980 to 12.3% in 2013. In 2013, 6.7, 2.5, 3.5, and 0.31% of the manuscripts contained terms related to logistic, linear, Cox and Poisson regression, respectively. On the other hand, 12.8% of journals author guidelines explicitly recommend to follow the STROBE guidelines, and 35.9% recommend the CONSORT guideline. CONCLUSIONS: A low percentage of Spanish scientific journals indexed in PubMed include the STROBE statement requirement in the author guidelines. Multivariate regression models in published observational studies such as logistic regression, linear, Cox and Poisson are increasingly used both at international level, as well as in journals published in Spanish.

Utilización de los modelos de regresión múltiple en estudios observacionales (1970-2013) y requerimiento de la guía STROBE en revistas científicas españolas / Use of multiple regression models in observational studies (1970-2013) and requirements of the STROBE guidelines in Spanish scientific journals

Fundamentos. En el ámbito de la investigación médica los modelos de regresión logística, lineal, Cox y Poisson son técnicas estadísticas ampliamente conocidas. El objetivo de este trabajo es describir la evolución de estas técnicas de regresión en los artículos observacionales indexados en PubMed (1970-2013) y revisar los requerimientos de las normas de autor de revistas españolas para conocer si requieren el cumplimiento de la guía STROBE. Métodos. Se realizó una búsqueda dirigida en PubMed para identificar los artículos que utilizaron modelos de regresión logística, lineal, Cox y Poisson. Además, se revisaron las normas de autor de las revistas editadas en España indexadas en PubMed e incluidas en Web Of Science. Resultados. El 6,1% de los artículos de estudios observacionales contenían algún término relativo a los modelos seleccionados, pasando del 0,14% en 1980 hasta un 12,3% en 2013. Este último año, un 6,7% de los artículos contenían algún término referido a regresión logística, un 2,5% a lineal, un 3,5% a Cox y un 0,31% a Poisson. Por otro lado, el 12,8% de las normas de autor de las revistas revisadas recomendaban explícitamente seguir la guía STROBE, y el 35,9%, la guía CONSORT. Conclusiones. Los modelos de regresión multivariantes en estudios observacionales publicados, tales como la regresión logística, lineal, Cox y Poisson, son cada vez más utilizados tanto a nivel global como en revistas publicadas en lengua española. Además, un porcentaje bajo de las revistas científicas españolas indexadas en PubMed incluyen en las normas de autoría el requerimiento de la guía STROBE (AU)

Background. In medicine and biomedical research, statistical techniques like logistic, linear, Cox and Poisson regression are widely known. The main objective is to describe the evolution of multivariate techniques used in observational studies indexed in PubMed (1970-2013), and to check the requirements of the STROBE guidelines in the author guidelines in Spanish journals indexed in PubMed. Methods. A targeted PubMed search was performed to identify papers that used logistic linear Cox and Poisson models. Furthermore, a review was also made of the author guidelines of journals published in Spain and indexed in PubMed and Web of Science. Results. Only 6.1% of the indexed manuscripts included a term related to multivariate analysis, increasing from 0.14% in 1980 to 12.3% in 2013. In 2013, 6.7, 2.5, 3.5, and 0.31% of the manuscripts contained terms related to logistic, linear, Cox and Poisson regression, respectively. On the other hand, 12.8% of journals author guidelines explicitly recommend to follow the STROBE guidelines, and 35.9% recommend the CONSORT guideline. Conclusions. A low percentage of Spanish scientific journals indexed in PubMed include the STROBE statement requirement in the author guidelines. Multivariate regression models in published observational studies such as logistic regression, linear, Cox and Poisson are increasingly used both at international level, as well as in journals published in Spanish (AU)