Search

The length of hospital stay (LOS) is an important measure of efficiency in the use of hospital resources. Acute Myocardial Infarction (AMI), as one of the diseases with higher mortality and LOS variability in the OECD countries, has been studied with predominant use of administrative data, particularly on mortality risk adjustment, failing investigation in the resource planning and specifically in LOS. This paper presents results of a predictive model for extended LOS (LOSE - above 75th percentile of LOS) using both administrative and clinical data, namely laboratory data, in order to develop a decision support system. Laboratory and administrative data of a Portuguese hospital were included, using logistic regression to develop this predictive model. A model with three laboratory data and seven administrative data variables (six comorbidities and age ≥ 69 years), with excellent discriminative ability and a good calibration, was obtained. The model validation shows also good results. Comorbidities were relevant predictors, mainly diabetes with complications, showing the highest odds of LOSE (OR = 37,83; p = 0,001). AMI patients with comorbidities (diabetes with complications, cerebrovascular disease, shock, respiratory infections, pulmonary oedema), with pO2 above level, aged 69 years or older, with cardiac dysrhythmia, neutrophils above level, pO2 below level, and prothrombin time above level, showed increased risk of extended LOS. Our findings are consistent with studies that refer these variables as predictors of increased risk. [ABSTRACT FROM AUTHOR]

Diagnosis tasks are among the most interesting activities in which to implement intelligent systems. The major objective of the paper is to be a guide for the readers, who want to develop an automated decision support system for detection of diabetics and subjects having risk factors of diabetes. The purpose was to determine an optimum classification scheme with high diagnostic accuracy for this problem. Several different classification algorithms were tested and their performances in detection of diabetics were compared. The performance of the classification algorithms was illustrated on the Pima Indians diabetes data set. The present research demonstrated that the modified mixture of experts (MME) achieved diagnostic accuracies which were higher than that of the other automated diagnostic systems. [ABSTRACT FROM AUTHOR]

In this paper we have discussed the application of artificial intelligence in telemedicine using mobile device. The main goal of our research is to develop methods and systems to collect, analyze, distribute and use medical diagnostics information from multiple knowledge sources and areas of expertise. Physicians may collect and analyze information obtained from experts worldwide with the help of a medical decision support system. In this information retrieval system, modern communication tools such as computers and mobile phones can be used efficiently. In this work we propose a medical decision support system using the general packet radio service (GPRS). GPRS, a data extension of the mobile telephony standard Global system for mobile communications (GSM) is emerging as the first true packet-switched architecture to allow mobile subscribers to benefit from high-speed transmission rates and run JAVA based applications from their mobile terminals. An academic prototype of a medical decision support system using mobile device was implemented. The results reveal that the system could find acceptance from the medical community and it could be an effective means of providing quality health care in developing countries. [ABSTRACT FROM AUTHOR]