A5037164097- Healthcare Technology and Patient Monitoring
- Sepsis Diagnosis and Treatment
- Respiratory Support and Mechanisms
- Hemodynamic Monitoring and Therapy
- Non-Invasive Vital Sign Monitoring
- Cardiac Arrest and Resuscitation
- Hydrogen's biological and therapeutic effects
- Machine Learning in Healthcare
- Electronic Health Records Systems
- Pharmaceutical studies and practices
- COVID-19 and healthcare impacts
- Heart Rate Variability and Autonomic Control
- Intensive Care Unit Cognitive Disorders
- COVID-19 epidemiological studies
- Clinical Reasoning and Diagnostic Skills
- Renal function and acid-base balance
- Child and Adolescent Health
- Meta-analysis and systematic reviews
- Clinical Laboratory Practices and Quality Control
- Cardiac, Anesthesia and Surgical Outcomes
- Quality and Safety in Healthcare
- Neuroscience of respiration and sleep
- Congenital Diaphragmatic Hernia Studies
- Tracheal and airway disorders
- Prenatal Substance Exposure Effects
Massachusetts Institute of Technology
2020-2024
Philips (United States)
2014-2021
Philips (India)
2021
Philips (Finland)
2008-2010
Harvard University Press
1994-2007
University of Massachusetts Chan Medical School
1998-2004
Massachusetts Academy of Math and Science
2000-2001
Boston Children's Hospital
1989-1991
Franciscan Hospital for Children
1989-1991
Boston University
1989-1991
Abstract Infectious threats, like the COVID-19 pandemic, hinder maintenance of a productive and healthy workforce. If subtle physiological changes precede overt illness, then proactive isolation testing can reduce labor force impacts. This study hypothesized that an early infection warning service based on wearable monitoring predictive models created with machine learning could be developed deployed. We prototype tool, first deployed June 23, 2020, delivered continuously updated scores risk...
This study utilized a historical cohort to examine the relationship between maternal cocaine use during pregnancy and occurrence of congenital cardiovascular abnormalities. All neonatal drug screens performed at Boston City Hospital an 18-month period were reviewed (n=554); for 214 (39%) screened high-risk neonates, results toxicologic positive cocaine, 340 (61%) neonates had no detectable cocaine. We compared cardio vascular malformations electrocardiographic abnormalities in these two...
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 the profession without input from other stakeholders. We sought elicit perceived problems solutions delivery broad set stakeholders.A consensus process involving purposive sampling identified stakeholders, preconference Web-based survey, 2-day conference.Participants represented healthcare providers,...
A system of valves and sensors provides individualized respiratory support for two individuals from one ventilator, with acute testing in pigs.
Abstract Heterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology process identify big data relationships, enabling era trial design. In this study, we designed ML model for predictively stratifying acute respiratory distress syndrome (ARDS) patients, ultimately reducing required number patients by increasing statistical power...
Early recognition and timely intervention are critical steps for the successful management of shock. The objective this study was to develop a model predict requirement hemodynamic in pediatric intensive care unit (PICU); thus, clinicians can direct their patients likely benefit from interventions prevent further deterioration. proposed trained on retrospective cohort all admitted tertiary PICU at single center United States, validated another Kingdom. clinical information system database...
Timely recognition of hemodynamic instability in critically ill patients enables increased vigilance and early treatment opportunities. We develop the Hemodynamic Stability Index (HSI), which highlights situational awareness possible occurring at bedside to prompt assessment for potential interventions.We used an ensemble decision trees obtain a real-time risk score that predicts initiation interventions hour into future. developed model using eICU Research Institute (eRI) database, based on...
<h3>Objectives:</h3> To describe the time of detection, electrophysiologic mechanism, and severity hemodynamic sequelae arrhythmias in infants children prenatally exposed to cocaine determine whether incidence severe neonatal arrhythmia is related prenatal exposure cocaine. <h3>Design:</h3> Characteristics are described for all significant detected at Boston (Mass) City Hospital with known exposure, as well a convenience sample from Children's Hospital, Boston. A historical cohort was used...
* Abbreviations: PICU = : pediatric intensive care unit • MRI magnetic resonance imaging OR operating room Congenital nasolacrimal duct obstruction with cystic extension into the nasopharynx (dacryocystocele) is a rare cause of respiratory distress in neonate. We describe (PICU) course newborn this disorder who had severe and whom diagnosis was originally missed. A 20-day-old female infant admitted to after several cyanotic episodes at home. The mother stated that child noisy breather...
There has been a high rate of false alarms for the critical electrocardiogram (ECG) arrhythmia events in intensive care units (ICUs), from which 'crying-wolf' syndrome may be resulted and patient safety jeopardized. This article presents an algorithm to reduce using arterial blood pressure (ABP) and/or photoplethysmogram (PPG) waveform features. We established long duration reference alarm datasets consist 573 ICU waveform-alarm records (283 development set 290 test set) with total length...
Healthcare-associated infection (HAI) remains a significant risk for hospitalized patients and challenging burden the healthcare system. This study presents clinical decision support tool that can be used in workflows to proactively engage secondary assessments of pre-symptomatic at-risk patients, thereby enabling earlier diagnosis treatment.
Abstract The COVID-19 pandemic is overwhelming healthcare systems worldwide. A significant portion of patients develop pneumonia and acute respiratory distress syndrome (ARDS), necessitating ventilator support. Some health do not have the capacity to accommodate this surge in demand, leading shortages inevitable mortality. clinicians have, necessity, jerry-rigged ventilators support multiple patients, but these devices lack protected air streams or individualized controls for each patient....
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 identify subset intensive care unit (ICU) laboratory tests, which, because their frequency use, should be focus efforts standardize test in ICU
Acute lung injury (ALI) and acute respiratory distress syndrome (ARDS) contribute to the morbidity mortality of intensive care patients worldwide, have large associated human financial costs. We identified a reference data set 624 mechanically-ventilated in MIMIC-II database with without low PaO(2)/FiO(2) ratios (termed instability), developed prediction algorithms for distinguishing these prior critical event. In end, we had four rule sets using mean airway pressure, plateau total rate...
ABSTRACT Background Healthcare-associated infection (HAI) remains a significant risk for hospitalized patients and challenging burden the healthcare system. This study presents clinical decision support tool that can be used in workflows to proactively engage secondary assessments of pre-symptomatic at-risk patients, thereby enabling earlier diagnosis treatment. Methods applies machine learning, specifically ensemble-based boosted trees, on large retrospective hospital datasets develop an...
In many critical care units, default patient monitor alarm settings are not fine-tuned to the vital signs of population. As a consequence there alarms. A large fraction alarms clinically actionable, thus contributing fatigue. Recent attention this phenomenon has resulted in attempts institutions decrease overall load clinicians by altering trigger thresholds for monitored parameters. Typically, new defined based on clinical knowledge and population norms tried empirically patients without...
Current algorithms identifying hemodynamically unstable intensive care unit patients typically are limited to detecting existing dangerous conditions and suffer from high false alert rates. Our objective was predict hemodynamic instability at least two hours before patient deterioration while maintaining a low rate, using minute‐by‐minute heart rate (HR) blood pressure (BP) data. We identified 66 stable 104 meeting our stability‐instability criteria the MIMIC II database, developed...
Experimental studies are widely considered as the gold standard for discovering new evidence. However, advances in computational science provide an opportunity to take advantage of large clinical datasets cases where randomized experiments not practical. In this study, we used a database train model capable detecting exposure opioid medication (AUROC=0.76). We designed and implemented study measure performance against unseen data from study. Our results show that based on hospital patient...