Catálogo de publicaciones - libros

MIMIC II dataset offers a unique opportunity to develop and validate new severity scores. Non-parametric approaches are needed to model ICU mortality. Prediction of hospital mortality based on the Super Learner achieves significantly improved performance, both in terms of calibration and discrimination, as compared to conventional severity scores.

This case study describes how to construct mortality prediction models using typical clinical data available in MIMIC-II. Several predictive models are utilized and compared.

Algorithms for identification of deteriorating patients from electronic health records (EHRs) fuse vital sign data, which can be measured at the bedside, with additional physiological data from the EHR. It has been observed that these algorithms provide improved performance over traditional early warning scores (EWSs), which are restricted to the use of vital signs alone. This case study demonstrates the development of an algorithm which uses logistic regression to fuse vital signs with additional physiological parameters commonly found in an EHR to predict deterioration.

In this chapter, we use a case study conducted using the MIMIC-II database, “Efficacy of Rate Control Medications in Atrial Fibrillation with Rapid Ventricular Response (Afib with RVR) amongst Critically Ill Patients”, as an example to demonstrate the concepts of propensity score analysis in EHR data research. In this study we investigated which of the three most commonly used rate control agents performed best as a sole agent to reach rate control for patients with Afib with RVR.

This case study describes common Markov models, their specific application in medical research, health economics and cost-effectiveness analysis.

This chapter describes two different approaches—a case-control and a case-crossover design—to examine the effect of transient exposure of hypotension on the risk of acute kidney injury (AKI) in intensive care unit (ICU) patients. We highlight the key differences and the design rationale of these two approaches, and present preliminary findings from applying these techniques to study the relationship between hypotension and AKI using the MIMIC II database.

Several techniques have been developed for estimation of respiratory rate (RR) from physiological waveforms. This case study presents a comparison of exemplary techniques for estimation of RR from the electrocardiogram (ECG) and photoplethysmogram (PPG) waveforms.

Modern patient monitoring systems in intensive care produce frequent false alarms that can lead to reduced standard of care. In this case study we demonstrate the development of an algorithm which uses a data fusion and machine learning approach to reduce the number of false alarms, while avoiding the suppression of a significant number of true alarms.

Retrieving information from structured data tables in a large database may be performed with little to no difficulty, but structured data may not always contain all that is needed to retrieve accurate information compared to narratives from clinical notes. The large volume of clinical notes, however, requires special processing to access the information contained in their unstructured format. In this case study, we present a comparison of two techniques (structured data extraction and natural language processing) and we evaluate their utility in identifying a specific patient cohort from a large clinical database.

Algorithms and features in medical studies contain many “knobs” that govern the learning process from a high-level perspective: they are called hyperparameters, and investigators typically tune them by hand. In this case study, we present three mathematically grounded techniques to automatically optimize hyperparameters, and demonstrate their use in the problem of outcome prediction for ICU patients who suffer from sepsis.