It has been recently shown that sparse, nonnegative tensor factorization of multi-modal electronic health record data is a promising approach to high-throughput computational phenotyping. However, such approaches typically do not leverage available domain knowledge while extracting the phenotypes; hence, some of the suggested phenotypes may not map well to clinical concepts or may be very similar to other suggested phenotypes. To address these issues, we present a novel, automatic approach called PIVETed-Granite that mines existing biomedical literature (PubMed) to obtain cannot-link constraints that are then used as side-information during a tensor-factorization based computational phenotyping process. The resulting improvements are clearly observed in experiments using a large dataset from VUMC to identify phenotypes for hypertensive patients.
India has made significant advances in the field of medical sciences, in the availability of both, therapeutic and diagnostic solutions for numerous disorders. However, companies are now focusing on strategies that can diagnose medical conditions within minutes. This would enable a rapid onset of therapy and this saves human life. They have introduced a solution that can facilitate rapid diagnosis of a patient's medical condition. Here, medical data of a patient is obtained immediately through smarter, online technology.
Machine learning is an often-used term that has been promised to do everything from making workers more productive to taking over individuals' jobs entirely. Frankly, it will likely be many years before anyone should be concerned about being replaced by artificial intelligence (AI) at their job. However, doctors might find AI impinging upon their jobs sooner rather than later. The medical field has some characteristics that make it an attractive target for machine learning. The high stakes nature of correct disease diagnosis, coupled with over-worked and fatigued doctors, can lead to cases where patients with easily treatable diseases go undiagnosed and suffer greatly from this.
Matrix factorization in the presence of missing data is at the core of many computer vision problems such as structure from motion (SfM), non-rigid SfM and photometric stereo. We formulate the problem of matrix factorization with missing data as a low-rank semidefinite program (LRSDP) with the advantage that: $1)$ an efficient quasi-Newton implementation of the LRSDP enables us to solve large-scale factorization problems, and $2)$ additional constraints such as ortho-normality, required in orthographic SfM, can be directly incorporated in the new formulation. Our empirical evaluations suggest that, under the conditions of matrix completion theory, the proposed algorithm finds the optimal solution, and also requires fewer observations compared to the current state-of-the-art algorithms. We further demonstrate the effectiveness of the proposed algorithm in solving the affine SfM problem, non-rigid SfM and photometric stereo problems.
We present a general Bayesian approach to probabilistic matrix factorization subject to linear constraints. The approach is based on a Gaussian observation model and Gaussian priors with bilinear equality and inequality constraints. We present an efficient Markov chain Monte Carlo inference procedure based on Gibbs sampling. Special cases of the proposed model are Bayesian formulations of non-negative matrix factorization and factor analysis. The method is evaluated on a blind source separation problem. We demonstrate that our algorithm can be used to extract meaningful and interpretable features that are remarkably different from features extracted using existing related matrix factorization techniques.