Applying temporal abstraction and case-based reasoning to predict approaching influenza waves.

Stud Health Technol Inform

Institut für Medizinische Informatik und Biometrie, Universität Rostock, D-18055 Rostock, Germany.

Published: November 2004

The goal of the TeCoMed project is to send early warnings against forthcoming waves or even epidemics of infectious diseases, especially of influenza, to interested practitioners, pharmacists etc. in the German federal state Mecklenburg-Western Pomerania. The forecast of these waves is based on written confirmations of unfitness for work of the main German health insurance company. Since influenza waves are difficult to predict because of their cyclic but not regular behaviour, statistical methods based on the computation of mean values are not helpful. Instead, we have developed a prognostic model that makes use of similar former courses. Our method combines Case-based Reasoning with Temporal Abstraction to decide whether early warning is appropriate.

Download full-text PDF

Source

Publication Analysis

Top Keywords

temporal abstraction
8
case-based reasoning
8
influenza waves
8
applying temporal
4
abstraction case-based
4
reasoning predict
4
predict approaching
4
approaching influenza
4
waves
4
waves goal
4

Similar Publications

The processing of stationary sounds relies on both local features and compact representations. As local information is compressed into summary statistics, abstract representations emerge. Whether the brain is endowed with distinct neural architectures predisposed to such computations is unknown.

View Article and Find Full Text PDF

[When tuberculosis makes you deaf].

Rev Mal Respir

January 2025

Centre de lutte antituberculeuse de Nice, Hôpital Pasteur, 30, Voie Romaine, 06000 Nice, France. Electronic address:

Introduction: Tuberculous otomastoiditis is a rare and serious infection that most often occurs in association with pulmonary involvement. It is easy to diagnose when the two pathologies are associated and isolated. We herein report the case of a patient initially hospitalized for Pseudomonas aeruginosa necrotising otitis externa (NOE), which delayed the diagnosis of tuberculous otomastoiditis.

View Article and Find Full Text PDF

In natural and artificial neural networks, modularity and distributed structure afford complementary but competing benefits. The former allows for hierarchical representations that can flexibly recombine modules to address novel problems, whereas the latter can benefit from less constrained training, potentially uncovering fruitful statistical regularities. Here, we investigate these competing demands in the context of human sequential behavior.

View Article and Find Full Text PDF

Background: Seizures, including status epilepticus (SE), are common in anti-NMDA receptor encephalitis (NMDARE). We aimed to describe clinical and electrographic features of patients with seizures with NMDARE, determine factors associated with SE, and describe long-term seizure outcomes.

Methods: We retrospectively identified patients with seizures in the setting of NMDARE treated at inpatient Mayo Clinic sites during the acute phase of encephalitis between October 2008 and March 2023.

View Article and Find Full Text PDF

[Exploring Turning Points in the Academic Lives of Health Sciences Students].

Rev Med Chil

May 2024

Departamento Educación Biomédica, Facultad de Ciencias Biomédicas, Universidad Austral, Argentina.

Unlabelled: This research set out to identify and describe turning points in the lives of medical, nursing, and psychology students in a school of health sciences at a private university in Argentina. Turning points refer to unexpected events and situations in people's lives where it is possible to determine a change or transformation.

Aim: to explore turning points originating in the health sciences school.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!