Center for Healthcare Delivery Science Research Projects
About Our Research Projects
Investigator Led Projects
Principal Investigator, Steve Horng
Heart failure represents a significant and leading health problem in the United States and is one of the leading causes of hospitalization in the developed world, accounting for nearly 1 million hospitalizations annually and nearly $70 billion in annual costs. Despite its prevalence and importance, heart failure hospitalization is difficult to predict using existing metrics. Use of echocardiographic data may improve prediction of heart failure, but current prediction model performance is insufficient for clinical use. Current advances in machine learning, specifically in deep learning, have great potential to revolutionize heart failure prediction, but is limited by the lack of large publicly available data sets. This project will create an echocardiogram (MIMIC-ECHO) and electrocardiogram (MIMIC-ECG) extension to the MIMIC-IV database. The Medical Information Mart for Intensive Care (MIMIC) database was launched in 2003 as a freely-available database is now a widely used resource with over 12,000 credentialed users in academia and industry. The MIMIC-IV database includes newer data and features a modular structure that facilitates the linking of multiple data types. This project will add approximately ~145,000 transthoracic echocardiograms (50 terabytes) and ~980,000 ECGs (70 gigabytes) along with their associated reports, fully integrated with all of the clinical, waveform, laboratory data already found in the MIMIC-IV database. This work builds on the long-standing collaboration between BIDMC and MIT responsible for the MIMIC database, and in partnership with Philips Healthcare, a leading manufacturer of both echocardiogram and electrocardiogram equipment. This project is being funded by the Mass Life Sciences Center. The MIMIC-extensions generated from this work will be piloted in early release through the MIT Critical Data Consortium, then publicly release through the PhysioNet, similar to the release of previous versions and extensions of MIMIC. This project is funded by the Massachusetts Life Sciences Center through its 2020 Bits to Bytes Program.
Site Co-Principal Investigator, Jennifer P. Stevens
Studies have shown that low tidal volume ventilation (LTVV) is one of the most effective therapies for treating acute respiratory distress syndrome (ARDS), but its use remains low. This multi-site project, led by Dr. Curtis Weiss of NorthShore University HealthSystem, sought to identify the facilitators and barriers to LTVV adoption and the differences that exist between academic and community settings. The goal of the study was to advance implementation science by providing a model for how data science and network science can be applied to understand the adoption of complex interventions. This project was conducted across an international consortium of medical centers and was funded by the National Institutes of Health.
Principal Investigator, Mary T. LaSalvia
Missed or delayed cancer diagnoses represent a critical and costly patient safety issue in ambulatory care. Despite established guidelines for screening, diagnosis, referral, and treatment for various types of cancer, guideline-concordant care too often relies on the vigilance of individual clinicians equipped with inadequate tools and supporting resources to ensure reliable completion of critical steps needed to either detect or exclude early cancer. This project seeks to establish an ambulatory safety net to reduce the risk of missed or delayed diagnoses of colorectal cancer. The project includes a gap analysis to determine the prevalence and root causes of cancer screening care gaps in the BIDMC outpatient population at Health Care Associates (HCA). The project includes establishing a registry tool and implementing a patient navigator to track changes in rates of screening and follow up of abnormal results. This project is funded by The Risk Management Foundation of the Harvard Medical Institutions Incorporated (CRICO/RMF).
Principal Investigator, Jennifer P. Stevens
Hospitalized patients experience a wide range of preventable harms despite significant efforts to provide safe and effective healthcare. This project seeks to identify and predict stressed clinical environments – or “risky states” that predispose patients to preventable harms– initially in the intensive care unit, and then in the emergency department. This approach goes beyond the clinical specifics of any individual patient and any category of harm. It represents a departure from the historical “silo” approach of hospitals addressing specific harm categories, such as falls or infections. This project was funded as a Career Development Award by the Doris Duke Charitable Foundation.
Principal Investigator, Jennifer P. Stevens
Inpatient consultation is the primary mechanism by which specialists provide care to hospitalized patients. For example, more than 90% of Medicare patients have at least one consultation during an inpatient admission. Previous research has demonstrated that the scope of variation in inpatient consultation use across U.S. hospitals is substantial. This project sought to advance knowledge of inpatient consultation in three ways: by defining the characteristics of beneficial consultations from multiple perspectives, including those of patients and families; by investigating novel non-clinical factors that drive consultation for reasons other than patient or family need; and by quantifying the relationship between inpatient consultations and patient outcomes and costs. This project was funded by the Agency for Healthcare Research and Quality. This work was preceded by research focused on consult quality in the critical care setting, funded by the Gordon and Betty Moore Foundation.
Center Led Projects
COVID-19 has created catastrophic direct health harms, but a method known as excess death analysis has also shown tens of thousands of increased deaths during the pandemic not directly associated with the virus. These deaths are believed to be the result of delays in care for other conditions, which may worsen over time as delays in preventive care may not manifest health harms for many months or even years. Deferral of routine care may also be profoundly inequitable since more-advantaged patients are more likely to have access to certain interventions. This project sought to quantify the impact of COVID-19 on non-COVID-associated healthcare by analyzing national databases using econometric methods, assessing the health equity impact of delays in non-COVID-associated healthcare, and exploring the relationship of regional patterns with subsequent delays in non-COVID-associated healthcare. This project was led by Dr. Jennifer P. Stevens, Director of the Center for Healthcare Delivery Science at Beth Israel Deaconess Medical Center, and was funded by Google.org, Google’s Foundation.
Learn More
- Hospitalizations for Emergent Medical, Surgical, and Obstetric Conditions in Boston During the COVID-19 Pandemic J Gen Intern Med (July 22, 2020)
- Preventability of 30-day Hospital Revisits Following Admission with COVID-19 at an Academic Medical Center Jt Comm J Qual Patient Saf (August 24, 2021)
Optimizing ICU Safety through Patient Engagement, System Science and Information Technology, a Beth Israel Deaconess Medical Center (BIDMC) project funded by the Gordon and Betty Moore Foundation, addressed three fundamental, interrelated barriers to the elimination of preventable patient harm on a broader scale: (1) unreliable systems of care, coupled with a lack of sophistication in healthcare as to how to improve those systems; (2) failure to adequately engage patients and families in their own care; and (3) failure to spread successful innovation into non-academic settings, where the majority of healthcare is actually delivered in the United States. Through the work described below, BIDMC leveraged health information technology, system science and patient and family engagement to improve quality and safety in the critical care environment.
Managing Risky States to Prevent Harm
"Risky states" refers to the environmental drivers in a unit that can put that unit at risk for patient harm to occur. This project identified correlations between states and harms to present a risk level for a unit and developed a model that calculates the risk levels of by unit.
Patient-Specific Checklist (PSC)
Intensive care units (ICUs) use checklists of core quality measures during clinical rounds to ensure evidence-based care is provided to all patients. Typical checklists incorporate a range of quality measures but remain agnostic to the patient. This project developed an electronic decision-support tool, the Patient-Specific Checklist (PSC), to individualize patient care by providing clinicians a patient-specific view of pertinent data and daily care needs.
MyICU
Being a patient or having a family member in a hospital intensive care unit (ICU) can be a disorienting and confusing experience. This project developed a mobile-friendly application that promotes bi-directional communication between the patient and family, and the ICU care team. The application helps families learn more about the unit their family member is in, learn about their family member’s daily plan, connect directly to support services, and maintain a private journal of the ICU stay.
MyNICU
Stemming from the foundational work of MyICU, MyNICU was created to help improve families’ experiences in the Neonatal Intensive Care Unit (NICU). MyNICU is a mobile-friendly application that further engages parents in their infant’s care by providing them with information and resources that extend beyond the NICU stay. Family members can also request services, track their infant’s progress in a private journal, and review additional hospital resources. The team is currently working on Version 2.0 aimed at improving usability and expanding the application to non-English speaking parents in response to the needs of their diverse parent/infant population.
Respect is a critical element of safety, patient-centered care, and fostering a trusting patient-provider relationship. Most healthcare organizations’ efforts to reduce harm focus on physical harm, but other forms of harm are both prevalent and important. These “non-physical” harms can be framed using the concepts of respect and dignity. In healthcare, these concepts can be defined as follows: dignity is the intrinsic, unconditional value of all persons, and respect is the sum of the actions that honor or acknowledge a person’s dignity. Disrespect is an affront to dignity and can cause harm, and organizations and providers should strive to eliminate disrespect. Due to its importance, our team has dedicated various projects to improve this aspect of healthcare delivery.
A Roadmap for Advancing the Practice of Respect in Healthcare
In 2016, leaders at BIDMC convened a group of experts from around the world to strategize about expanding the definition of preventable harm to include non-physical harm, and to develop a more reliable approach to the “practice of respect.” These discussions, funded by the Gordon and Betty Moore Foundation, were the starting points for the development of a draft consensus statement to serve as a model for institutions implementing this work. A team at BIDMC then finalized a consensus statement and invited all convening attendees to participate in a modified Delphi process to finalize its language. This process included five rounds of surveys, by which participants identified key strategies. Strategies included hospital leadership championing a culture of respect and dignity; promoting accountability in this area; engaging and supporting the healthcare workforce; partnering with patients and families; establishing systems to learn about and improve the practice of respect; and expanding the research agenda and measurement tools, and disseminating what is learned.
Development of a Framework for Health Care Organizations to Describe Patient and Family Harm from Disrespect and Promote Improvement: A Scoping Review
This project used the current literature to develop a practical, improvement-oriented framework to recognize, describe, and prevent non-physical harm events that result from disrespectful interactions with the healthcare system. The team developed a framework designed to expand organizations’ ability to recognize, describe, and understand non-physical harm events using the concept of disrespect. The components of this framework include care processes, contributing factors, professional/organizational behaviors, and modifying factors and consequences, including consequences affecting patients and families, professionals, organizations and society. This project was funded by the Arnold P. Gold Foundation.
Innovations Grant Projects
2023
- Assessing the Implementation of the Healthcare Racial Justice Assessment Tool (HC-RJAT): A Novel Tool to Measure Structural and Institutional Racism in the Healthcare Setting
Principal Investigator, Yarden Fraiman - Machine Learning to Refine Heart Failure Endpoints
Principal Investigator, Jennifer Ho
2022
- Impact of Cultural Competency in Outpatient Surgical Care: Implementation of a Sustainable Latinx Colorectal Surgery Clinic
Principal Investigators, Ana Sofia Ore and Evangelos Messaris
2021
- Improving Care Disparities in Dementia Diagnosis and Treatment
Principal Investigator, Alexandra Stillman - Tele-Brain Interprofessional Consultation (TBIC)
Principal Investigator, Martina Stippler
2020
- Forging Interpersonal Education in the Perioperative Setting in the Time of COVID-19
Principal Investigator, Shahla Siddiqui - An Interprofessional Student-faculty Collaborative Telehealth Program to Address Poorly Controlled Diabetes and Social Determinants of Health Exacerbated by COVID-19 Pandemic
Principal Investigator, Amy Weinstein
2019
- Using the BIDMC@home Smartphone App to Track Opioid Use and Digital Phenotypes of Pain in Surgical Patients
Co-Principal Investigators, Gabriel Brat and Seth Berkowitz - Patient Engagement in the Emergency Department and Social Determinants of Health
Principal Investigator, Andrew Marshall
2018
- Anesthesia Innovation: The Digital Incentive Spirometer
Principal Investigator, John Pearson - Developing and Implementing a Comprehensive System for Preventing Non-Physical Harm from Disrespect Experienced by BIDMC's Patients and Families
Principal Investigator, Lauge Sokol-Hessner - New Innovations in Family-Centered Quality Improvement in the NICU
Principal Investigator, Emily Whitesel
2017
- Infection Prevention and Readiness for Discharge in ElectroPhysiology (INSPIRED-EP)
Principal Investigators, Steven Horng and Eugene Kim - Patient-Reported Outcomes and Symptom Management Pathways to Reduce Preventable ED Visits and Hospitalizations for Patients with Cancer
Principal Investigators, Jessica Zerillo and Mohana Roy
2016
- Patient Reported Outcomes in Cardiology
Principal Investigators, Robert Yeh and Jordan Strom - A Novel, Multi-disciplinary Hypertension Clinic Integrated within Primary Care
Principal Investigator, Jennifer Beach
2015
- Perioperative Surgical Home (PSH) Portal
Principal Investigator, Cullen D. Jackson - Chest Pain Clinical Pathway – Maximizing ED Efficiency and Quality through Standardizing the Approach to Low Risk Chest Pain and Leveraging a Common ED Infrastructure
Principal Investigator, Peter Smulowitz
2014
- Integration of Early Palliative Care in a Cancer Clinic
Principal Investigators, Mary K. Buss and Susan DeSanto-Madeya - Inflammatory Bowel Disease Medical Neighborhood – the new "model" of a primary care and specialty care working on shared quality goals
Principal Investigator, Joseph Feuerstein
2013
- Standardized Approach to Acute Respiratory Failure: the "intubation bundle"
Principal Investigators, Michael Donnino, Katherine Berg and Michael N. Cocchi - Minimizing Catheter-Associated Urinary Tract Infection Risk through Implementation of a Team-Generated Nurse-Directed Protocol
Principal Investigator, Graham Snyder - Implementation of a Phenobarbital-based Alcohol Withdrawal Pathway in Critical Care
Principal Investigator, Douglas J. Hsu
2012
- Moderate Sedation: The Final Frontier for Quality in Procedural Areas
Principal Investigators, Daniel Leffler and Sheila R. Barnett - KidneyTracker: Patient-centered Approach to Improving Care for Chronic Kidney Disease
Principal Investigator, Ali Poyan Mehr - Innovative Tools to Optimize OR Access and Resource Utilization
Principal Investigators, Brett Simon and Ryan Graue
Machine Learning Innovations Grant Projects
- Machine Learning to Refine Heart Failure Endpoints
Principal Investigator, Jennifer Ho Machine Learning to Refine Heart Failure Endpoints