Methods in informatics: using data derived from a systematic review of health care texts to develop a concept map for use in the neonatal intensive care setting

Time series analysis as input for clinical predictive modeling: modeling cardiac arrest in a pediatric ICU

Background

Thousands of children experience cardiac arrest events every year in pediatric intensive care units. Most of these children die. Cardiac arrest prediction tools are used as part of medical emergency team evaluations to identify patients in standard hospital beds that are at high risk for cardiac arrest. There are no models to predict cardiac arrest in pediatric intensive care units though, where the risk of an arrest is 10 times higher than for standard hospital beds. Current tools are based on a multivariable approach that does not characterize deterioration, which often precedes cardiac arrests. Characterizing deterioration requires a time series approach. The purpose of this study is to propose a method that will allow for time series data to be used in clinical prediction models. Successful implementation of these methods has the potential to bring arrest prediction to the pediatric intensive care environment, possibly allowing for interventions that can save lives and prevent disabilities.

Methods

We reviewed prediction models from nonclinical domains that employ time series data, and identified the steps that are necessary for building predictive models using time series clinical data. We illustrate the method by applying it to the specific case of building a predictive model for cardiac arrest in a pediatric intensive care unit.

Results

Time course analysis studies from genomic analysis provided a modeling template that was compatible with the steps required to develop a model from clinical time series data. The steps include: 1) selecting candidate variables; 2) specifying measurement parameters; 3) defining data format; 4) defining time window duration and resolution; 5) calculating latent variables for candidate variables not directly measured; 6) calculating time series features as latent variables; 7) creating data subsets to measure model performance effects attributable to various classes of candidate variables; 8) reducing the number of candidate features; 9) training models for various data subsets; and 10) measuring model performance characteristics in unseen data to estimate their external validity.

Conclusions

We have proposed a ten step process that results in data sets that contain time series features and are suitable for predictive modeling by a number of methods. We illustrated the process through an example of cardiac arrest prediction in a pediatric intensive care setting.

Health care interventions for intimate partner violence: What women want

OBJECTIVE

We sought to determine what women want from health care interventions for intimate partner violence (IPV) and understand why they found certain interventions useful or not useful.

METHODS

We conducted interviews with 21 women who have a past or current history of intimate partner violence. Participants were given cards describing various IPV interventions and asked to perform a pile sort by placing cards into three categories ("definitely yes," "maybe," and "definitely no") indicating whether they would want that resource available. They were then asked to explain their categorizations.

RESULTS

The pile sort identified that the majority of participants supported informational interventions and individual counseling. Only 9 of 17, however, felt couple's counseling was a good idea with seven reporting it was definitely not useful. Half wanted help with substance use and treatment for depression. Interventions not well regarded included "Receiving a follow-up telephone call from the doctor's office/clinic" and "Go stay at shelter" with only 7 and 5 of the 21 women placing these cards in the "definitely yes" pile. "Health provider reporting to police" was the intervention most often placed in the "definitely no" pile, with 9 of 19 women doing so. The women described several elements that affected their likelihood of using particular IPV interventions. One theme related stages of "readiness" for change. Another theme dealt with the complexity of many women's lives. Interventions that could accommodate various stages of "readiness" and helped address concomitant issues were deemed more useful. Characteristics of such interventions included: 1) not requiring disclosure or identification as IPV victims, 2) presenting multiple options, and 3) preserving respect for autonomy.

CONCLUSIONS

Women who had experienced IPV described not only what they wanted from IPV interventions but how they wished to receive these services and why they would chose to use certain resources. They advised providing a variety of options to allow individualizing according to different needs and readiness to seek help. They emphasized interventions that protected safety, privacy, and autonomy.