Andrew T. Reisner

Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*

Objective:We sought to develop an intensive care unit research database applying automated techniques to aggregate high-resolution diagnostic and therapeutic data from a large, diverse population of adult intensive care unit patients. This freely available database is intended to support epidemiologic research in critical care medicine and serve as a resource to evaluate new clinical decision support and monitoring algorithms. Design:Data collection and retrospective analysis. Setting:All adult intensive care units (medical intensive care unit, surgical intensive care unit, cardiac care unit, cardiac surgery recovery unit) at a tertiary care hospital. Patients:Adult patients admitted to intensive care units between 2001 and 2007. Interventions:None. Measurements and Main Results:The Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database consists of 25,328 intensive care unit stays. The investigators collected detailed information about intensive care unit patient stays, including laboratory data, therapeutic intervention profiles such as vasoactive medication drip rates and ventilator settings, nursing progress notes, discharge summaries, radiology reports, provider order entry data, International Classification of Diseases, 9th Revision codes, and, for a subset of patients, high-resolution vital sign trends and waveforms. Data were automatically deidentified to comply with Health Insurance Portability and Accountability Act standards and integrated with relational database software to create electronic intensive care unit records for each patient stay. The data were made freely available in February 2010 through the Internet along with a detailed users guide and an assortment of data processing tools. The overall hospital mortality rate was 11.7%, which varied by critical care unit. The median intensive care unit length of stay was 2.2 days (interquartile range, 1.1–4.4 days). According to the primary International Classification of Diseases, 9th Revision codes, the following disease categories each comprised at least 5% of the case records: diseases of the circulatory system (39.1%); trauma (10.2%); diseases of the digestive system (9.7%); pulmonary diseases (9.0%); infectious diseases (7.0%); and neoplasms (6.8%). Conclusions:MIMIC-II documents a diverse and very large population of intensive care unit patient stays and contains comprehensive and detailed clinical data, including physiological waveforms and minute-by-minute trends for a subset of records. It establishes a new public-access resource for critical care research, supporting a diverse range of analytic studies spanning epidemiology, clinical decision-rule development, and electronic tool development.

Mobile monitoring with wearable photoplethysmographic biosensors

We address both technical and clinical issues of wearable biosensors (WBS). First, design concepts of a WBS are presented, with emphasis on the ring sensor developed by the authors group at MIT. The ring sensor is an ambulatory, telemetric, continuous health-monitoring device. This WBS combines miniaturized data acquisition features with advanced photoplethysmographic (PPG) techniques to acquire data related to the patients cardiovascular state using a method that is far superior to existing fingertip PPG sensors. In particular, the ring sensor is capable of reliably monitoring a patients heart rate, oxygen saturation, and heart rate variability. Technical issues, including motion artifact, interference with blood circulation, and battery power issues, are addressed, and effective engineering solutions to alleviate these problems are presented. Second, based on the ring sensor technology the clinical potentials of WBS monitoring are addressed.

Utility of the Photoplethysmogram in Circulatory Monitoring

The photoplethysmogram is a noninvasive circulatory signal related to the pulsatile volume of blood in tissue and is displayed by many pulse oximeters and bedside monitors, along with the computed arterial oxygen saturation. The photoplethysmogram is similar in appearance to an arterial blood pressure waveform. Because the former is noninvasive and nearly ubiquitous in hospitals whereas the latter requires invasive measurement, the extraction of circulatory information from the photoplethysmogram has been a popular subject of contemporary research. The photoplethysmogram is a function of the underlying circulation, but the relation is complicated by optical, biomechanical, and physiologic covariates that affect the appearance of the photoplethysmogram. Overall, the photoplethysmogram provides a wealth of circulatory information, but its complex etiology may be a limitation in some novel applications.

Effects of morphine analgesia on diagnostic accuracy in emergency department patients with abdominal pain: a prospective, randomized trial ☆

BACKGROUND Because of concerns about masking important physical findings, there is controversy surrounding whether it is safe to provide analgesia to patients with undifferentiated abdominal pain. The purpose of this study was to address the effects of analgesia on the physical examination and diagnostic accuracy for patients with abdominal pain. STUDY DESIGN The study was a prospective, double-blind clinical trial in which adult Emergency Department (ED) patients with undifferentiated abdominal pain were randomized to receive placebo (control group, n = 36) or morphine sulphate (MS group, n = 38). Diagnostic and physical examination assessments were recorded before and after a 60-minute period during which study medication was titrated. Diagnostic accuracy and physical examination changes were compared between groups using univariate statistical analyses. RESULTS There were no differences between control and MS groups with respect to changes in physical or diagnostic accuracy. The overall likelihood of change in severity of tenderness was similar in MS (37.7%) as compared with control (35.3%) patients (risk ratio [RR] 1.07, 95% confidence interval [CI] 0.64-1.78). MS patients were no more likely than controls to have a change in pain location (34.0% versus 41.2%, RR 0.82, 95% CI 0.50-1.36). Diagnostic accuracy did not differ between MS and control groups (64.2% versus 66.7%, RR 0.96, 95% CI 0.73-1.27). There were no differences between groups with respect to likelihood of any change occurring in the diagnostic list (37.7% versus 31.4%, RR 1.20, 95% CI 0.71-2.05). Correlation with clinical course and final diagnosis revealed no instance of masking of physical examination findings. CONCLUSIONS Results of this study support a practice of early provision of analgesia to patients with undifferentiated abdominal pain.

A method for automatic identification of reliable heart rates calculated from ECG and PPG waveforms.

OBJECTIVE The development and application of data-driven decision-support systems for medical triage, diagnostics, and prognostics pose special requirements on physiologic data. In particular, that data are reliable in order to produce meaningful results. The authors describe a method that automatically estimates the reliability of reference heart rates (HRr) derived from electrocardiogram (ECG) waveforms and photoplethysmogram (PPG) waveforms recorded by vital-signs monitors. The reliability is quantitatively expressed through a quality index (QI) for each HRr. DESIGN The proposed method estimates the reliability of heart rates from vital-signs monitors by (1) assessing the quality of the ECG and PPG waveforms, (2) separately computing heart rates from these waveforms, and (3) concisely combining this information into a QI that considers the physical redundancy of the signal sources and independence of heart rate calculations. The assessment of the waveforms is performed by a Support Vector Machine classifier and the independent computation of heart rate from the waveforms is performed by an adaptive peak identification technique, termed ADAPIT, which is designed to filter out motion-induced noise. RESULTS The authors evaluated the method against 158 randomly selected data samples of trauma patients collected during helicopter transport, each sample consisting of 7-second ECG and PPG waveform segments and their associated HRr. They compared the results of the algorithm against manual analysis performed by human experts and found that in 92% of the cases, the algorithm either matches or is more conservative than the humans QI qualification. In the remaining 8% of the cases, the algorithm infers a less conservative QI, though in most cases this was because of algorithm/human disagreement over ambiguous waveform quality. If these ambiguous waveforms were relabeled, the misclassification rate would drop from 8% to 3%. CONCLUSION This method provides a robust approach for automatically assessing the reliability of large quantities of heart rate data and the waveforms from which they are derived.

Adaptive blood pressure estimation from wearable PPG sensors using peripheral artery pulse wave velocity measurements and multi-channel blind identification of local arterial dynamics.

A method for estimating pulse wave velocity (PWV) using circulatory waveform signals derived from multiple photoplethysmograph (PPG) sensors is described. The method employs two wearable in-line PPG sensors placed at a known distance from one another at the ulnar and digital artery. A technique for calibrating the measured pulse wave velocity to arterial blood pressure using hydrostatic pressure variation is presented. Additionally, a framework is described for estimating local arterial dynamics using PPG waveforms and multi-channel blind system ID. Initial results implementing the method on data derived from a human subject at different arterial pressures is presented. Results show that the method is capable of measuring the changes in arterial PWV that result from fluctuations in mean arterial pressure

Wearable, cuff-less PPG-based blood pressure monitor with novel height sensor.

A truly wearable non-invasive blood pressure (NIBP) sensor- light-weight, compact, unobstrusive, and essentially unnoticeable to the patient-could revolutionize healthcare delivered beyond the traditional walls of medical facilities, offering new ways to care for patients in their everyday surroundings. This paper presents results from our work towards the development of a self-contained, wearable blood pressure sensor. A PPG-based approach to blood pressure monitoring is presented. The design enables significant miniaturization of traditional oscillometric devices without the need for occlusive circumferential pressures. It will be shown how natural raising and lowering of the arm replaces the need for bulky actuators. Additionally, a dual-accelerometer height sensor that is tetherless is proposed and supported by experimental results

Cuffless Blood Pressure Monitoring Using Hydrostatic Pressure Changes

This paper presents a new principle for noninvasive blood pressure measurements through a modified volume-oscillometric technique that eliminates an inflatable pressure cuff, and instead takes advantage of natural hydrostatic pressure changes caused by raising and lowering the subjects arm. This new methodology provides the distinct advantage of using an absolute gauge pressure reference for measurements, and does not necessarily require additional actuation.

The effect of severe traumatic brain injury on the family

BACKGROUND The effects of traumatic brain injury on family dynamics and finances have not been extensively studied. We designed a 30-item survey to determine the effects of the injury on the child, parent(s), and siblings, and whether parents were retrospectively content with the decisions related to aggressiveness of care. METHODS A questionnaire written on a sixth-grade reading level was mailed to 46 families of children who survived a traumatic brain injury resulting in an initial Glasgow Coma Scale score < or = 7. This is a descriptive study without statistical analysis. Human Studies Committee review and informed consent were obtained. RESULTS Thirty-two of 46 (69.6%) surveys were completed by mail or telephone. Mean patient age at time of injury was 8.7 years, mean time since injury was 3 years, and mean Glasgow Coma Scale score was 3.7. Approximately one third of children have disabilities related to education, socialization, and/or self-care skills; require multiple health care visits each month; and require prescription medications. Over one third of families were impacted in a moderate to profoundly negative way; 30% of families reported a deterioration in finances or loss of job; and 16% reported a worsening of adult relationships. In 13 of 32 cases, modification of current housing or new housing was required to facilitate home care. Siblings were adversely affected in approximately 16 of 28 families, exhibiting behavioral problems, increased fear, and withdrawal from the injured child. Only 1 of 32 families stated that they would have considered less aggressive treatment, even if it led to the childs death. CONCLUSION Traumatic brain injury of a child had a negative impact on family dynamics and/or sibling behavior in more than one third of families. Despite this, most families would not limit or withdraw care if they could reconsider decisions regarding treatment. This information can be used to counsel families.

Decision tool for the early diagnosis of trauma patient hypovolemia

We present a classifier for use as a decision assist tool to identify a hypovolemic state in trauma patients during helicopter transport to a hospital, when reliable acquisition of vital-sign data may be difficult. The decision tool uses basic vital-sign variables as input into linear classifiers, which are then combined into an ensemble classifier. The classifier identifies hypovolemic patients with an area under a receiver operating characteristic curve (AUC) of 0.76 (standard deviation 0.05, for 100 randomly-reselected patient subsets). The ensemble classifier is robust; classification performance degrades only slowly as variables are dropped, and the ensemble structure does not require identification of a set of variables for use as best-feature inputs into the classifier. The ensemble classifier consistently outperforms best-features-based linear classifiers (the classification AUC is greater, and the standard deviation is smaller, p<0.05). The simple computational requirements of ensemble classifiers will permit them to function in small fieldable devices for continuous monitoring of trauma patients.