Search AMIA.org

Research on pharmacovigilance from social media data has focused on mining adverse drug events (ADEs) using annotated datasets, with publications generally focusing on 1 of 3 tasks: ADE classification, named entity recognition for identifying the span of ADE mentions, and ADE mention normalization to standardized terminologies. While the common goal of such systems is to detect ADE signals that can be used to inform public policy, it has been impeded [...]

We propose an interpretable disease prediction model that efficiently fuses multiple types of patient records using a self-attentive fusion encoder. We assessed the model performance in predicting cardiovascular disease events, given the records of a general patient population.

As we enter an era of health care that incorporates telehealth for routine provision of care, we can build a system that consciously and proactively includes vulnerable patients, thereby avoiding further exacerbation of health disparities. A practical way to reach out to Latino patients is to use media they already widely use. Rather than expect patients to adapt to suboptimal systems of telehealth care, we can improve telehealth for Latinos [...]

The collection of patient reported outcomes (PROs) allows us to incorporate the patient's voice into their care in a quantifiable, validated manner. Large-scale collection of PROs is facilitated by the electronic health record and its portal, though, historically, patients have eschewed the portal and completed patient-reported outcome measures in the clinic via tablet. Furthermore, access and use of the portal is associated with known racial inequities. Our institution oversees the [...]

De-identification is a fundamental task in electronic health records to remove protected health information entities. Deep learning models have proven to be promising tools to automate de-identification processes. However, when the target domain (where the model is applied) is different from the source domain (where the model is trained), the model often suffers a significant performance drop, commonly referred to as domain adaptation issue. In de-identification, domain adaptation issues can [...]

The study sought to determine whether machine learning can predict initial inpatient total daily dose (TDD) of insulin from electronic health records more accurately than existing guideline-based dosing recommendations.

Using a risk stratification model to guide clinical practice often requires the choice of a cutoff-called the decision threshold-on the model's output to trigger a subsequent action such as an electronic alert. Choosing this cutoff is not always straightforward. We propose a flexible approach that leverages the collective information in treatment decisions made in real life to learn reference decision thresholds from physician practice. Using the example of prescribing a [...]