Format

Send to

Choose Destination
Artif Intell Med. 2018 Dec 5. pii: S0933-3657(17)30151-3. doi: 10.1016/j.artmed.2018.11.005. [Epub ahead of print]

Optimal testing policies for diagnosing patients with intermediary probability of disease.

Author information

1
Universidade Federal do Rio de Janeiro, Instituto Alberto Luiz Coimbra de Pós Graduação e Pesquisa de Engenharia, Programa de Engenharia de Produção, Caixa Postal 68507, Rio de Janeiro RJ 21941-972, Brazil. Electronic address: efarruda@po.coppe.ufrj.br.
2
Universidade Federal do Rio de Janeiro, Instituto Alberto Luiz Coimbra de Pós Graduação e Pesquisa de Engenharia, Programa de Engenharia de Produção, Caixa Postal 68507, Rio de Janeiro RJ 21941-972, Brazil; Americas Medical City, Hospital Samaritano, Departamento de Clinica Médica, Rio de Janeiro RJ, Brazil. Electronic address: basilio@hucff.ufrj.br.
3
Instituto Nacional de Cardiologia, Rua das Laranjeiras 374, Laranjeiras, Rio de Janeiro, RJ, 22.240-006, Brazil; Instituto do Coração Edson Saad, Rua Professor Rodolpho Paulo Rocco nº 255, 8º andar, Cidade Universitária, Ilha do Fundão, Rio de Janeiro RJ 21941-913, Brazil. Electronic address: clarissa@cardiol.br.
4
Instituto Nacional de Cardiologia, Rua das Laranjeiras 374, Laranjeiras, Rio de Janeiro, RJ, 22.240-006, Brazil. Electronic address: tura@centroin.com.br.

Abstract

This paper proposes a stochastic shortest path approach to find an optimal sequence of tests to confirm or discard a disease, for any prescribed optimality criterion. The idea is to select the best sequence in which to apply a series of available tests, with a view at reaching a diagnosis with minimum expenditure of resources. The proposed approach derives an optimal policy whereby the decision maker is provided with a test strategy for each a priori probability of disease, aiming to reach posterior probabilities that warrant either immediate treatment or a not-ill diagnosis.

KEYWORDS:

Diagnosis; Healthcare problems; Stochastic shortest path

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center