PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 9929360

Data mining by clinicians.

D J Nigrin·I S Kohane
View original source ↗Export metadata ↓

Abstract

Clinical databases are becoming commonplace in healthcare environments. However, clinicians have been unable to readily explore these information sources, because currently available data retrieval tools require substantial technical skill, as well as knowledge of the underlying database structures. To address this, we have defined a group of "atomic" queries, including both population-based and temporal predicates, to enable the extraction of clinically meaningful information form these databases. DXtractor is an application that incorporates this functionality, and allows clinicians to simply combine these atomic queries. In doing so, arbitrarily complex data retrieval and exploration becomes possible for the non-programming clinician.

Explore related subjects

Databases as TopicHospital Information SystemsHumansInformation Storage and RetrievalMedical Records Systems, ComputerizedMethodsJournal ArticleResearch Support, Non-U.S. Gov'tResearch Support, U.S. Gov't, P.H.S.

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

D J Nigrin, I S Kohane. 1998. Data mining by clinicians.. https://pubmed.ncbi.nlm.nih.gov/9929360/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1999

[Smart card systems in health care (protection, key-functions, divided data bases, applications)].

Barely more than 15 years have passed since electronic memory cards appeared, their popularity has grown rapidly (first of all as a cash-saving device and later for other purposes, as well). This is due also to the growing interest towards development of the intelligence of information systems for the follow-up of patients' health condition and medical care in countries with a highly developed health and insurance system (need for the creation of data bases divided for individuals) and also to their commitment towards a better control of the quality and costs of health care. We can come to the conclusion that the aim of research, development and the creation of systems in health informatics is to prevent illness and to give a direct informatic support to medical and nursing activity carried out in the patients' interests. The smart card and the surrounding application systems are certainly the appropriate means for the achievement of these aims.

Databases as Topic↗
PubMed1999

Hidden neural networks.

A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear performance gains compared to standard HMMs tested on the same task.

Databases as Topic↗