Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Extreme value Birnbaum-Saunders regression models applied to environmental data

Extreme value models are widely used in different areas. The Birnbaum–Saunders distribution is receiving considerable attention due to its physical arguments and its good properties. We propose a methodology based on extreme value Birnbaum–Saunders regression models, which includes model formulation, estimation, inference and checking. We further conduct a simulation study for evaluating its performance. A statistical analysis with real-world extreme value environmental data using the methodology is provided as illustration.

Random walk forecast of urban water in Iran under uncertainty

There are two significant reasons for the uncertainties of water demand. On one hand, an evolving technological world is plagued with accelerated change in lifestyles and consumption patterns; and on the other hand, intensifying climate change. Therefore, with an uncertain future, what enables policymakers to define the state of water resources, which are affected by withdrawals and demands? Through a case study based on thirteen years of observation data in the Zayandeh Rud River basin in Isfahan province located in Iran, this paper forecasts a wide range of urban water demand possibilities in order to create a portfolio of plans which could be utilized by different water managers. A comparison and contrast of two existing methods are discussed, demonstrating the Random Walk Methodology, which will be referred to as the â On uncertainty pathâ , because it takes the uncertainties into account and can be recommended to managers. This On Uncertainty Path is composed of both dynamic forecasting method and system simulation. The outcomes show the advantage of such methods particularly for places that climate change will aggravate their water scarcity, such as Iran.