Browsing by Subject "EHRs"

Now showing 1 - 2 of 2

Mining structured matrices in high dimensions
(2016-08) Gunasekar, Suriya; Ghosh, Joydeep; Bovik, Alan C; Caramanis, Constantine; Ravikumar, Pradeep; Sanghavi, Sujay
Structured matrices refer to matrix valued data that are embedded in an inherent lower dimensional manifold with smaller degrees of freedom compared to the ambient or observed dimensions. Such hidden (or latent) structures allow for statistically consistent estimation in high dimensional settings, wherein the number of observations is much smaller than the number of parameters to be estimated. This dissertation makes significant contributions to statistical models, algorithms, and applications of structured matrix estimation in high dimensional settings. The proposed estimators and algorithms are motivated by and evaluated on applications in e--commerce, healthcare, and neuroscience. In the first line of contributions, substantial generalizations of existing results are derived for a widely studied problem of matrix completion. Tractable estimators with strong statistical guarantees are developed for matrix completion under (a) generalized observation models subsuming heterogeneous data--types, such as count, binary, etc., and heterogeneous noise models beyond additive Gaussian, (b) general structural constraints beyond low rank assumptions, and (c) collective estimation from multiple sources of data. The second line of contributions focuses on the algorithmic and application specific ideas for generalized structured matrix estimation. Two specific applications of structured matrix estimation are discussed: (a) a constrained latent factor estimation framework that extends the ideas and techniques hitherto discussed, and applies them for the task of learning clinically relevant phenotypes from Electronic Health Records (EHRs), and (b) a novel, efficient, and highly generalized algorithm for collaborative learning to rank (LETOR) applications.
Towards successful coordination of electronic health record based-referrals: a qualitative analysis
(Implementation Science, 2011-07-27) Hysong, Sylvia J.; Esquivel, Adol; Sittig, Dean F.; Paul, Lindsey A.; Espadas, Donna; Singh, Simran; Singh, Hardeep
Background: Successful subspecialty referrals require considerable coordination and interactive communication among the primary care provider (PCP), the subspecialist, and the patient, which may be challenging in the outpatient setting. Even when referrals are facilitated by electronic health records (EHRs) (i.e., e-referrals), lapses in patient follow-up might occur. Although compelling reasons exist why referral coordination should be improved, little is known about which elements of the complex referral coordination process should be targeted for improvement. Using Okhuysen and Bechky's coordination framework, this paper aims to understand the barriers, facilitators, and suggestions for improving communication and coordination of EHR-based referrals in an integrated healthcare system. Methods: We conducted a qualitative study to understand coordination breakdowns related to e-referrals in an integrated healthcare system and examined work-system factors that affect the timely receipt of subspecialty care. We conducted interviews with seven subject matter experts and six focus groups with a total of 30 PCPs and subspecialists at two tertiary care Department of Veterans Affairs (VA) medical centers. Using techniques from grounded theory and content analysis, we identified organizational themes that affected the referral process. Results: Four themes emerged: lack of an institutional referral policy, lack of standardization in certain referral procedures, ambiguity in roles and responsibilities, and inadequate resources to adapt and respond to referral requests effectively. Marked differences in PCPs' and subspecialists' communication styles and individual mental models of the referral processes likely precluded the development of a shared mental model to facilitate coordination and successful referral completion. Notably, very few barriers related to the EHR were reported. Conclusions: Despite facilitating information transfer between PCPs and subspecialists, e-referrals remain prone to coordination breakdowns. Clear referral policies, well-defined roles and responsibilities for key personnel, standardized procedures and communication protocols, and adequate human resources must be in place before implementing an EHR to facilitate referrals.