Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes

Neural Information Processing Systems

Predicated on the increasing abundance of electronic health records, we investigate the problem of inferring individualized treatment effects using observational data. Stemming from the potential outcomes model, we propose a novel multi-task learning framework in which factual and counterfactual outcomes are modeled as the outputs of a function in a vector-valued reproducing kernel Hilbert space (vvRKHS). We develop a nonparametric Bayesian method for learning the treatment effects using a multi-task Gaussian process (GP) with a linear coregionalization kernel as a prior over the vvRKHS. The Bayesian approach allows us to compute individualized measures of confidence in our estimates via pointwise credible intervals, which are crucial for realizing the full potential of precision medicine. The impact of selection bias is alleviated via a risk-based empirical Bayes method for adapting the multi-task GP prior, which jointly minimizes the empirical error in factual outcomes and the uncertainty in (unobserved) counterfactual outcomes. We conduct experiments on observational datasets for an interventional social program applied to premature infants, and a left ventricular assist device applied to cardiac patients wait-listed for a heart transplant. In both experiments, we show that our method significantly outperforms the state-of-the-art.


IBM Watson aligns with 16 health systems and imaging firms to apply cognitive computing to battle cancer, diabetes, heart disease

#artificialintelligence

IBM Watson Health has formed a medical imaging collaborative with more than 15 leading healthcare organizations. The goal: To take on some of the most deadly diseases. The collaborative, which includes health systems, academic medical centers, ambulatory radiology providers and imaging technology companies, aims to help doctors address breast, lung, and other cancers; diabetes; eye health; brain disease; and heart disease and related conditions, such as stroke. Watson will mine insights from what IBM calls previously invisible unstructured imaging data and combine it with a broad variety of data from other sources, such as data from electronic health records, radiology and pathology reports, lab results, doctors' progress notes, medical journals, clinical care guidelines and published outcomes studies. As the work of the collaborative evolves, Watson's rationale and insights will evolve, informed by the latest combined thinking of the participating organizations.


How 3D Printing and IBM Watson Could Replace Doctors

#artificialintelligence

Health care executives from IBM Watson and Athenahealth athn debated that question onstage at Fortune's inaugural Brainstorm Health conference Tuesday. In addition to partnering with Celgene celg to better track negative drug side effects, IBM ibm is applying its cognitive computing AI technology to recommend cancer treatment in rural areas in the U.S., India, and China, where there is a dearth of oncologists, said Deborah DiSanzo, general manager for IBM Watson Health. For example, IBM Watson could read a patient's electronic medical record, analyze imagery of the cancer, and even look at gene sequencing of the tumor to figure out the optimal treatment plan for a particular person, she said. "That is the promise of AI--not that we are going to replace people, not that we're going to replace doctors, but that we really augment the intelligence and help," DiSanzo said. Athenahealth CEO Jonathan Bush, however, disagreed.


Solving the Empirical Bayes Normal Means Problem with Correlated Noise

arXiv.org Machine Learning

The Normal Means problem plays a fundamental role in many areas of modern high-dimensional statistics, both in theory and practice. And the Empirical Bayes (EB) approach to solving this problem has been shown to be highly effective, again both in theory and practice. However, almost all EB treatments of the Normal Means problem assume that the observations are independent. In practice correlations are ubiquitous in real-world applications, and these correlations can grossly distort EB estimates. Here, exploiting theory from Schwartzman (2010), we develop new EB methods for solving the Normal Means problem that take account of unknown correlations among observations. We provide practical software implementations of these methods, and illustrate them in the context of large-scale multiple testing problems and False Discovery Rate (FDR) control. In realistic numerical experiments our methods compare favorably with other commonly-used multiple testing methods.


Integrating Environmental Data, Citizen Science and Personalized Predictive Modeling to Support Public Health in Cities: The PULSE WebGIS

AAAI Conferences

The percentage of the world’s population living in urban areas is projected to increase significantly in the next decades. This makes the urban environment the perfect bench for research aiming to manage and respond to dramatic demographic and epidemiological transitions. In this context the PULSE project has partnered with five global cities to transform public health from a reactive to a predictive system focused on both risk and resilience. PULSE aims at producing an integrated data ecosystem based on continuous large-scale collection of information available within the smart city environment. The integration of environmental data, citizen science and location-specific predictive modeling of disease onset allows for richer analytics that promote informed, data-driven health policy decisions. In this paper we describe the PULSE ecosystem, with a special focus on its WebGIS component and its prototype version based on New York city data.