A rapidly deployable individualized system for augmenting ventilator capacity.

Strategies to split ventilators to support multiple patients requiring ventilatory support have been proposed and used in emergency cases in which shortages of ventilators cannot otherwise be remedied by production or procurement strategies. However, the current approaches to ventilator sharing lack the ability to individualize ventilation to each patient, measure pulmonary mechanics, and accommodate rebalancing of the airflow when one patient improves or deteriorates, posing safety concerns to patients. Potential cross-contamination, lack of alarms, insufficient monitoring, and inability to adapt to sudden changes in patient status have prevented widespread acceptance of ventilator sharing. We have developed an individualized system for augmenting ventilator efficacy (iSAVE) as a rapidly deployable platform that uses a single ventilator to simultaneously and more safely support two individuals. The iSAVE enables individual-specific volume and pressure control and the rebalancing of ventilation in response to improvement or deterioration in an individual's respiratory status. The iSAVE incorporates mechanisms to measure pulmonary mechanics, mitigate cross-contamination and backflow, and accommodate sudden flow changes due to individual interdependencies within the respiratory circuit. We demonstrate these capacities through validation using closed- and open-circuit ventilators on linear test lungs. We show that the iSAVE can temporarily ventilate two pigs on one ventilator as efficaciously as each pig on its own ventilator. By leveraging off-the-shelf medical components, the iSAVE could rapidly expand the ventilation capacity of health care facilities during emergency situations such as pandemics.

Development and evaluation of predictive alerts for hemodynamic instability in ICU patients.

This paper describes an algorithm for identifying ICU patients that are likely to become hemodynamically unstable. The algorithm consists of a set of rules that trigger alerts. Unlike most existing ICU alert mechanisms, it uses data from multiple sources and is often able to identify unstable patients earlier and with more accuracy than alerts based on a single threshold. The rules were generated using a machine learning technique and were tested on retrospective data in the MIMIC II ICU database, yielding a specificity of approximately 0.9 and a sensitivity of 0.6.

Predicting respiratory instability in the ICU.

Acute lung injury (ALI) and acute respiratory distress syndrome (ARDS) contribute to the morbidity and mortality of intensive care patients worldwide, and have large associated human and financial costs. We identified a reference data set of 624 mechanically-ventilated patients in the MIMIC-II intensive care database with and without low PaO(2)/FiO(2) ratios (termed respiratory instability), and developed prediction algorithms for distinguishing these patients prior to the critical event. In the end, we had four rule sets using mean airway pressure, plateau pressure, total respiratory rate and oxygen saturation (SpO(2)), where the specificity/sensitivity rates were either 80%/60% or 90%/50%.

Prioritizing the organization and management of intensive care services in the United States: the PrOMIS Conference.

OBJECTIVE: Adult critical care services are a large, expensive part of U.S. health care. The current agenda for response to workforce shortages and rising costs has largely been determined by members of the critical care profession without input from other stakeholders. We sought to elicit the perceived problems and solutions to the delivery of critical care services from a broad set of U.S. stakeholders. DESIGN: A consensus process involving purposive sampling of identified stakeholders, preconference Web-based survey, and 2-day conference. SETTING: Participants represented healthcare providers, accreditation and quality-oversight groups, federal sponsoring institutions, healthcare vendors, and institutional and individual payers. SUBJECTS: We identified 39 stakeholders for the field of critical care medicine. Thirty-six (92%) completed the preconference survey and 37 (95%) attended the conference. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Participants expressed moderate to strong agreement with the concerns identified by the critical care professionals and additionally expressed consternation that the critical care delivery system was fragmented, variable, and not patient-centered. Recommended solutions included regionalizing the adult critical care system into "tiers" defined by explicit triage criteria and professional competencies, achieved through voluntary hospital accreditation, supported through an expanded process of competency certification, and monitored through process and outcome surveillance; implementing mechanisms for improved communication across providers and settings and between providers and patients/families; and conducting market research and a public education campaign regarding critical care's promises and limitations. CONCLUSIONS: This consensus conference confirms that agreement on solutions to complex healthcare delivery problems can be achieved and that problem and solution frames expand with broader stakeholder participation. This process can be used as a model by other specialties to address priority setting in an era of shifting demographics and increasing resource constraints.

Frequency of laboratory test utilization in the intensive care unit and its implications for large-scale data collection efforts.

OBJECTIVE: Mapping local use names to standardized nomenclatures such as LOINC (Logical Observation Identifiers Names and Codes) is a time-consuming task when done retrospectively or during the configuration of new information systems. The author sought to identify a subset of intensive care unit (ICU) laboratory tests, which, because of their frequency of use, should be the focus of efforts to standardize test names in ICU information systems. DESIGN: The author reviewed the ordering practices in medical, surgical, and pediatric ICUs within a large university teaching hospital to identify the subset of laboratory tests that represented the majority of tests performed in these settings. The author compared the results of his findings with the laboratory tests required to complete several of the most frequently used ICU acuity scoring systems. RESULTS: It was found that between 104 and 202 tests and profiles represented 99% of all testing in the three ICUs. All the laboratory studies needed for six commonly used ICU scoring systems fell into the top 21 laboratory studies and profiles performed in each ICU. CONCLUSION: The author identified a small subset of the LOINC database that should be the focus of efforts to standardize test names in ICU information systems. Mapping this subset of laboratory tests and profiles to LOINC vocabulary will simplify the process of collecting data for large-scale databases such as ICU scoring systems and the configuration of new ICU information systems.

CIS: where are we going and what should we demand from industry?

Clinical information systems designed for use in the critical care setting have been available for many years. Yet, despite significant evidence that these systems contribute to patient safety and efficiency of care, they have not achieved widespread use. This paper examines some of the factors responsible for the slow growth in use of clinical information systems in the intensive care unit. We further examine the elements that will be necessary to support widespread adoption of future clinical information systems. We give an outline of functionalities, processes, and standards that users will demand from industry as they develop the information systems of the future.

Frequency of laboratory test utilization in the intensive care unit and its implications for large scale data collection efforts.

Mapping of local use names to standardized naming schemas such as LOINC" micro is a time consuming and difficult task when done retrospectively or during the configuration of new information systems. We found that a relatively small number of tests and profiles (106 to 205) represent 99% of all testing done in 3 ICUs studied. In addition, all of the lab studies needed for the most commonly used ICU scoring systems fell into the top 23 lab studies and profiles performed in each ICU studied. We have identified a subset of the LOINC database which, because of their frequency of use, should be the focus of efforts to bring naming uniformity to ICU information systems.