PubMed Health⌕ Search

Biomedical subjects

Peter Szolovits

Publications and source records attributed to Peter Szolovits.

5 recordsLinked to original sources

A Bayesian dynamic model for influenza surveillance.

The severe acute respiratory syndrome (SARS) epidemic, the growing fear of an influenza pandemic and the recent shortage of flu vaccine highlight the need for surveillance systems able to provide early, quantitative predictions of epidemic events. We use dynamic Bayesian networks to discover the interplay among four data sources that are monitored for influenza surveillance. By integrating these different data sources into a dynamic model, we identify in children and infants presenting to the pediatric emergency department with respiratory syndromes an early indicator of impending influenza morbidity and mortality. Our findings show the importance of modelling the complex dynamics of data collected for influenza surveillance, and suggest that dynamic Bayesian networks could be suitable modelling tools for developing epidemic surveillance systems.

Bayes Theorem↗

A susceptible-infected model of early detection of respiratory infection outbreaks on a background of influenza.

The threat of biological warfare and the emergence of new infectious agents spreading at a global scale have highlighted the need for major enhancements to the public health infrastructure. Early detection of epidemics of infectious diseases requires both real-time data and real-time interpretation of data. Despite moderate advancements in data acquisition, the state of the practice for real-time analysis of data remains inadequate. We present a nonlinear mathematical framework for modeling the transient dynamics of influenza, applied to historical data sets of patients with influenza-like illness. We estimate the vital time-varying epidemiological parameters of infections from historical data, representing normal epidemiological trends. We then introduce simulated outbreaks of different shapes and magnitudes into the historical data, and estimate the parameters representing the infection rates of anomalous deviations from normal trends. Finally, a dynamic threshold-based detection algorithm is devised to assess the timeliness and sensitivity of detecting the irregularities in the data, under a fixed low false-positive rate. We find that the detection algorithm can identify such designated abnormalities in the data with high sensitivity with specificity held at 97%, but more importantly, early during an outbreak. The proposed methodology can be applied to a broad range of influenza-like infectious diseases, whether naturally occurring or a result of bioterrorism, and thus can be an integral component of a real-time surveillance system.

Algorithms↗

Implementing electronic medical record systems in developing countries.

The developing world faces a series of health crises including HIV/AIDS and tuberculosis that threaten the lives of millions of people. Lack of infrastructure and trained, experienced staff are considered important barriers to scaling up treatment for these diseases. In this paper we explain why information systems are important in many healthcare projects in the developing world. We discuss pilot projects demonstrating that such systems are possible and can expand to manage hundreds of thousands of patients. We also pass on the most important practical lessons in design and implementation from our experience in doing this work. Finally, we discuss the importance of collaboration between projects in the development of electronic medical record systems rather than reinventing systems in isolation, and the use of open standards and open source software.

Computer Security↗

Copy fees and patients' rights to obtain a copy of their medical records: from law to reality.

Patients have a legal right under HIPAA to a copy of their medical records. Personal life-long medical records rely on patients' ability to exercise this right inexpensively and in a timely manner. We surveyed 73 hospitals across the US, with a geographic concentration around Boston, to determine their policies about fees for copying medical records and the expected time it takes to fulfill such requests. Fees range very widely, from $2-55 for short records of 15 pages to $15-585 for long ones of 500 pages. Times also range widely, from 1-30 days (or longer for off-site records). A few institutions provide records for free and even fewer make them accessible on-line. We argue that electronic records will help solve the problem of giving patients access to their own records, will do so inexpensively and in a format more likely to be useful than paper.

Confidentiality↗

Adding a medical lexicon to an English Parser.

We present a heuristic method to map lexical (syntactic) information from one lexicon to another, and apply the technique to augment the lexicon of the Link Grammar Parser with an enormous medical vocabulary drawn from the Specialist lexicon developed by the National Library of Medicine. This paper presents and justifies the mapping method and addresses technical problems that have to be overcome. It illustrates the utility of the method with respect to a large corpus of emergency department notes.

Terminology as Topic↗