From a public-health perspective, the occurrence of drug-drug-interactions (DDI) from multiple drug prescriptions is a serious problem, especially in the elderly population. This is true both for individuals and the system itself since patients with complications due to DDI will likely re-enter the system at a costlier level. We conducted an 18-month study of DDI occurrence in Blumenau (Brazil; pop. 340,000) using city-wide drug dispensing data from both primary and secondary-care level. Our goal is also to identify possible risk factors in a large population, ultimately characterizing the burden of DDI for patients, doctors and the public system itself. We found 181 distinct DDI being prescribed concomitantly to almost 5% of the city population. We also discovered that women are at a 60% risk increase of DDI when compared to men, while only having a 6% co-administration risk increase. Analysis of the DDI co-occurrence network reveals which DDI pairs are most associated with the observed greater DDI risk for females, demonstrating that contraception and hormone therapy are not the main culprits of the gender disparity, which is maximized after the reproductive years. Furthermore, DDI risk increases dramatically with age, with patients age 70-79 having a 50-fold risk increase in comparison to patients aged 0-19. Interestingly, several null models demonstrate that this risk increase is not due to increased polypharmacy with age. Finally, we demonstrate that while the number of drugs and co-administrations help predict a patient's number of DDI ($R^2=.413$), they are not sufficient to flag these patients accurately, which we achieve by training classifiers with additional data (MCC=.83,F1=.72). These results demonstrate that accurate warning systems for known DDI can be devised for public and private systems alike, resulting in substantial prevention of DDI-related ADR and savings.
This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: (1) identification of novel regulatory variants located in noncoding domains and their function as applied to pharmacoepigenomics; (2) patient stratification from medical records; and (3) prediction of drugs, targets, and their interactions. Deep learning encapsulates a family of machine learning algorithms that over the last decade has transformed many important subfields of artificial intelligence (AI) and has demonstrated breakthrough performance improvements on a wide range of tasks in biomedicine. We anticipate that in the future deep learning will be widely used to predict personalized drug response and optimize medication selection and dosing, using knowledge extracted from large and complex molecular, epidemiological, clinical, and demographic datasets.
Matrices of low rank are pervasive in big data, appearing in recommender systems, movie preferences, topic models, medical records, and genomics. While there is a vast literature on how to exploit low rank structure in these datasets, there is less attention on explaining why the low rank structure appears in the first place. We explain the abundance of low rank matrices in big data by proving that certain latent variable models associated to piecewise analytic functions are of log-rank. A large matrix from such a latent variable model can be approximated, up to a small error, by a low rank matrix.
Except for those folks living under rocks (sounds uncomfortable), everyone knows about or at least has heard of bitcoin. However, not everyone understands the technology of bitcoin, which extends well beyond Internet-based currency. For the rock people, bitcoin is an Internet-based currency that allows for transparency with respect to each transfer of the currency through the use of a distributed database. Each transaction is locked in a block, and blocks are connected to form a "blockchain." Blockchain is an open source technology that facilitates creating each block, locking each block, and connecting the resulting string of blocks.
When we asked dozens of venture capitalists where they see the most potential for applied artificial intelligence, they unanimously agreed on health care. Technology has already been used to incrementally improve patient medical records, care delivery, diagnostic accuracy, and drug development, but with AI we could achieve exponential breakthroughs. Deep learning first caught the media's attention when a team from the lab of Geoffrey Hinton at the University of Toronto won a Merck drug discovery competition despite having no experience with molecular biology and pharmaceutical development. Recently, a multidisciplinary research team at Stanford's School of Medicine comprised of pathologists, biomedical engineers, geneticists, and computer scientists developed deep learning algorithms that diagnose lung cancer more accurately than human pathologists. The ultimate dream in health care is to eradicate disease entirely.
Last spring the startup Flow Health began a five-year contract with the Department of Veteran Affairs to examine all historic and ongoing medical records. The startup will use information obtained from those records to train artificial intelligence to, among other things, fight illness and predict disease for the more than eight million people cared for by the Department of Veteran Affairs. Advice and predictions from Flow Health will be presented to health care professionals through Vista, the DoD's open source system for electronic medical records. Doctors can then choose to apply or ignore the advice drawn from the VA's vast storage of medical records. "When a veteran comes in and presents certain clinical symptoms, we can better understand and make predictions about'What is the likely diagnosis?
When it comes to artificial intelligence, forget the scary movies about rebellious robots or the dire warnings of a dystopian world of disconnected humanity imagined by some popular writers. AI promises, rather, to change our lives in profound ways we are just beginning to experience, according to a ground-breaking survey produced by Stanford University. Stanford is taking the long view of AI, with a project called One Hundred Study on Artificial Intelligence (AI100). The study, written by a panel of AI experts from multiple fields including healthcare, will continue as an ongoing activity, with periodic reports examining how AI will touch different aspects of daily life. The first of those reports, "Artificial Intelligence and Life in 2030," looks into the effects that AI advancements will have on a typical North American city a little more than a decade from now.
This paper presents an example of how demographical characteristics of patients influence their susceptibility to certain medical conditions. In this paper, we investigate the association of health conditions to age of patients in a heterogeneous population. We show that besides the symptoms a patients is having, the age has the potential of aiding the diagnostic process in hospitals. Working with Electronic Health Records (EHR), we show that medical conditions group into clusters that share distinctive population age densities. We use Electronic Health Records from Brazil for a period of 15 months from March of 2013 to July of 2014. The number of patients in the data is 1.7 million patients and the number of records is 47 million records. The findings has the potential of helping in a setting where an automated system undergoes the task of predicting the condition of a patient given their symptoms and demographical information.
Clinical trials, the largest of which may enroll a few thousand patients with hematology or oncology diagnoses, represent the gold standard of clinical research. But what if clinical decisions could be made, or research questions answered, using data from tens of thousands or even a million patients? Initiatives are springing up across the country to examine the power and promise of big data – massive amounts of information that can be analyzed to provide an overview of trends or patterns – to revolutionize health care and transform how patients are diagnosed, treated, and even involved in their own care. For instance, in 2012, the National Institutes of Health (NIH) established the Big Data to Knowledge (BD2K) initiative, an effort to promote research and development of tools and approaches that would accelerate the use of big data in biomedical research.1 This spring, IBM launched IBM Watson Health and the Watson Health Cloud platform, a new unit of the IBM Watson cognitive computing system that will analyze and extract large volumes of health data from structured and unstructured medical systems.2