Decision Support In Critical Care Research Articles

Analysis of Devices Authorized by the FDA for Clinical Decision Support in Critical Care

This case series study examines the clinical evidence cited for US Food and Drug Administration–approved clinical decision support devices for use in the critical care setting.

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review.

BackgroundDecision support systems based on reinforcement learning (RL) have been implemented to facilitate the delivery of personalized care. This paper aimed to provide a comprehensive review of RL applications in the critical care setting.ObjectiveThis review aimed to survey the literature on RL applications for clinical decision support in critical care and to provide insight into the challenges of applying various RL models.MethodsWe performed an extensive search of the following databases: PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, Web of Science, Medical Literature Analysis and Retrieval System Online (MEDLINE), and Excerpta Medica Database (EMBASE). Studies published over the past 10 years (2010-2019) that have applied RL for critical care were included.ResultsWe included 21 papers and found that RL has been used to optimize the choice of medications, drug dosing, and timing of interventions and to target personalized laboratory values. We further compared and contrasted the design of the RL models and the evaluation metrics for each application.ConclusionsRL has great potential for enhancing decision making in critical care. Challenges regarding RL system design, evaluation metrics, and model choice exist. More importantly, further work is required to validate RL in authentic clinical environments.

Machine Learning and Decision Support in Critical Care.

Clinical data management systems typically provide caregiver teams with useful information, derived from large, sometimes highly heterogeneous, data sources that are often changing dynamically. Over the last decade there has been a significant surge in interest in using these data sources, from simply re-using the standard clinical databases for event prediction or decision support, to including dynamic and patient-specific information into clinical monitoring and prediction problems. However, in most cases, commercial clinical databases have been designed to document clinical activity for reporting, liability and billing reasons, rather than for developing new algorithms. With increasing excitement surrounding “secondary use of medical records” and “Big Data” analytics, it is important to understand the limitations of current databases and what needs to change in order to enter an era of “precision medicine.” This review article covers many of the issues involved in the collection and preprocessing of critical care data. The three challenges in critical care are considered: compartmentalization, corruption, and complexity. A range of applications addressing these issues are covered, including the modernization of static acuity scoring; on-line patient tracking; personalized prediction and risk assessment; artifact detection; state estimation; and incorporation of multimodal data sources such as genomic and free text data.

Short-range wireless sensor network for critical care monitoring

A Scandinavian research consortium collaborated to develop a wireless clinical monitoring platform. A collection of experimental wireless sensor prototypes were implemented in complex, process-control software modified for the project. The objective was to facilitate real-time and historical point-of-care sensor data for clinical decision support in critical care. The short-range wireless radio frequency platform used in the project was the IEEE 802.15.4 wireless personal area network standard. Invasive sensors included an arterial blood pressure sensor, an epicardial three-axis accelerometer and a digital pulmonary air leakage system. Non-invasive sensor signals came from an electrocardiogram sensor, a pulse oximeter, a medical radar prototype and a temperature sensor. Radio frequency signals from sensors to base stations and onwards in the wireless sensor network architecture were scrutinised during experimental surgery. Qualitative assessment of the sensor data presentation was made. Shadowing effects influencing the radio frequency channel performance was quantified. The shadowing effects were caused by the dynamic work pattern of the clinical team in combination with stationary equipment in the operating room during surgery. Shadowing effects did not compromise the quality of wireless sensor data severely. An evaluation of the communication links between individual sensors and two separate base stations are provided in this paper.

Clinical decision support in critical care nursing.

A clinical decision support system (CDSS) is a computerized application that helps clinicians detect and prevent untoward clinical events such as drug interactions, errors of omission, and trends in symptomatology. A CDSS in healthcare usually is built around an alerting system based on rules of logic. The alerting system of a CDSS can notify clinicians immediately on clinical data entry, or it can generate alerts over time after relating data from multiple sources. A CDSS for nurses and patients offers immediate benefits for nurses and patients by detecting potential drug-laboratory and drug-drug combinations and impending pharmacologic complications, monitoring microbiology results, and helping nurses relate symptoms to pharmacology and medication side effects. Other benefits include savings in time and money and reductions in morbidity and mortality. A CDSS presents an opportunity for nursing informatics and critical care nursing to collaborate for the benefit of the patient and the profession.

Pattern Detection in Intensive Care Monitoring Time Series with Autoregressive Models: Influence of the Model Order

The detection of patterns in monitoring data of vital signs is of great importance for adequate bedside decision support in critical care. Currently used alarm systems, which are based on fixed thresholds and independency assumptions, are not satisfactory in clinical practice. Time series techniques such as AR-models consider autocorrelations within the series, which can be used for pattern recognition in the data. For practical applications in intensive care the data analysis has to be automated. An important issue is the suitable choice of the model order which is difficult to accomplish online. In a comparative case-study we analyzed 34564 univariate time series of hemodynamic variables in critically ill patients by autoregressive models of different orders and compared the results of pattern detection. AR(2)-models seem to be most suitable for the detection of clinically relevant patterns, thus affirming that treating the data as independent leads to false alarms. Moreover, using AR(2)-models affords only short estimation periods. These findings for pattern detection in intensive care data are of medical importance as they justify a preselection of a model order, easing further automated statistical online analysis.