Issa J. Dahabreh

Learn More
Obtaining good probability estimates is imperative for many applications. The increased uncertainty and typically asymmetric costs surrounding rare events increase this need. Experts (and classification systems) often rely on probabilities to inform decisions. However, we demonstrate that class probability estimates obtained via supervised learning in(More)
Proposed molecular classifiers may be overfit to idiosyncrasies of noisy genomic and proteomic data. Cross-validation methods are often used to obtain estimates of classification accuracy, but both simulations and case studies suggest that, when inappropriate methods are used, bias may ensue. Bias can be bypassed and generalizability can be tested by(More)
Systematic reviews are being increasingly used to inform all levels of healthcare, from bedside decisions to policy-making. Since they are designed to minimize bias and subjectivity, they are a preferred option to assess the comparative effectiveness and safety of healthcare interventions. However, producing systematic reviews and keeping them up-to-date is(More)
OBJECTIVE To assess the association between risk of sudden cardiac death and stressful law enforcement duties compared with routine/non-emergency duties. DESIGN Case distribution study (case series with survey information on referent exposures). SETTING United States law enforcement. PARTICIPANTS Summaries of deaths of over 4500 US police officers(More)
We consider the task of grouping doctors with respect to communication patterns exhibited in outpatient visits. We propose a novel approach toward this end in which we model speech act transitions in conversations via a log-linear model incorporating physician specific components. We train this model over transcripts of outpatient visits annotated with(More)
BACKGROUND To improve quality of care and patient outcomes, health system decision-makers need to identify and implement effective interventions. An increasing number of systematic reviews document the effects of quality improvement programs to assist decision-makers in developing new initiatives. However, limitations in the reporting of primary studies and(More)
  • 1