CLCraig M. Lilly

Craig M. Lilly

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Craig M. Lilly has a total of 114 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Advancing Point-of-Care Testing by Application of Machine Learning Techniques and Artificial Intelligence

    by Craig M. Lilly, Apurv V. Soni, Denise Dunlap, Nathaniel Hafer, Mary Ann Picard, Bryan Buchholz, David D. McManus


  • Application of Machine Learning Models to Biomedical and Information System Signals From Critically Ill Adults

    by Craig M. Lilly, David Kirk, Itai M. Pessach, Gurudev Lotun, Ofer Chen, Ari Lipsky, Iris Lieder, Gershon Celniker, Eric W. Cucchi, James M. Blum


  • Open Access

    2021 Patient Preferences for Point of Care Testing Survey: More Acceptance and Less Concern

    by Craig M Lilly, Ziyue Wang, Denise Dunlap, Jeffrey Kaye, Sarah Gohtard, Sean Teebagy, Nathaniel Hafer, Eugene J Rogers, Bryan Buchholz, David McManus

    Background: The evolving opinions of our community members provide insights into how end-users perceive the value and identify key point-of-care test (POCT) characteristics. Methods: We deployed our validated 45-item English-language survey to uncompensated volunteers and compared the results from 1264 respondents in 2021 with those obtained in 2020. Results: Average responses for items regarding the benefits of POCTs demonstrated that the 2021 respondents indicated agreement with all 14 potential benefits. Average responses for items regarding concerns were distinctly different from those for benefits. The only concern item that scored in the agree range was “not having insurance coverage for POCTs.” Average responses to the other 13 concern items were in the disagree range. For 8 of these items, the magnitude of disagreement was greater in the 2021 survey than was observed for the 2020 survey. Differences in POCT exposure over time and by US regions suggest that higher levels of exposure to POCTs in the East are associated with stronger public support. Conclusions: Community members strongly support the development of accurate, convenient, easy-to-use, affordable, equitably available, in-home POCTs that produce immediate results. This empowers patients and home caregivers to diagnose, manage, enhance their adherence to medical treatments, and more efficiently engage their physicians.


  • COVID-19 and the Transformation of Intensive Care Unit Telemedicine

    by Eric W. Cucchi, Scott E. Kopec, Craig M. Lilly


  • Open Access

    Understanding Healthcare Professionals’ Perspectives on Point-of-Care Testing

    by Sean Teebagy, Ziyue Wang, Denise Dunlap, Connor Saleeba, Danielle DiMezza, JoAnn Crain, Craig M. Lilly, Bryan Buchholz, David D. McManus, Nathaniel Hafer

    Point-of-care testing (POCT) is an emerging technology that provides crucial assistance in delivering healthcare. The COVID-19 pandemic led to the accelerated importance of POCT technology due to its in-home accessibility. While POCT use and implementation has increased, little research has been published about how healthcare professionals perceive these technologies. The objective of our study was to examine the current perspectives of healthcare professionals towards POCT. We surveyed healthcare professionals to quantify perceptions of POCT usage, adoption, benefits, and concerns between October 2020 and November 2020. Questions regarding POCT perception were assessed on a 5-point Likert Scale. We received a total of 287 survey responses. Of the respondents, 53.7% were male, 66.6% were white, and 30.7% have been in practice for over 20 years. We found that the most supported benefit was POCTs ability to improve patient management (92%) and that the most supported concern was that POCTs lead to over-testing (30%). This study provides a better understanding of healthcare workers’ perspectives on POCT. To improve patient outcomes through the usage of POCT, greater research is needed to assess the needs and concerns of industry and healthcare stakeholders.


  • Open Access

    Validation of an Automatic Tagging System for Identifying Respiratory and Hemodynamic Deterioration Events in the Intensive Care Unit

    by Danielle Jeddah, Ofer Chen, Ari M. Lipsky, Andrea Forgacs, Gershon Celniker, Craig M. Lilly, Itai M. Pessach

    Objectives: Predictive models for critical events in the intensive care unit (ICU) might help providers anticipate patient deterioration. At the heart of predictive model development lies the ability to accurately label significant events, thereby facilitating the use of machine learning and similar strategies. We conducted this study to establish the validity of an automated system for tagging respiratory and hemodynamic deterioration by comparing automatic tags to tagging by expert reviewers.Methods: This retrospective cohort study included 72,650 unique patient stays collected from Electronic Medical Records of the University of Massachusetts’ eICU. An enriched subgroup of stays was manually tagged by expert reviewers. The tags generated by the reviewers were compared to those generated by an automated system.Results: The automated system was able to rapidly and efficiently tag the complete database utilizing available clinical data. The overall agreement rate between the automated system and the clinicians for respiratory and hemodynamic deterioration tags was 89.4% and 87.1%, respectively. The automatic system did not add substantial variability beyond that seen among the reviewers.Conclusions: We demonstrated that a simple rule-based tagging system could provide a rapid and accurate tool for mass tagging of a compound database. These types of tagging systems may replace human reviewers and save considerable resources when trying to create a validated, labeled database used to train artificial intelligence algorithms. The ability to harness the power of artificial intelligence depends on efficient clinical validation of targeted conditions; hence, these systems and the methodology used to validate them are crucial.


  • ICU Telemedicine Nighttime Support

    by Craig M. Lilly, Jason A. Kovacevic

  • Open Access

    Patient Preferences for Point-of-Care Testing

    by Craig M. Lilly, Emily Bs Ensom, Sean Ba Teebagy, Danielle BA DiMezza, Denise Dunlap, Nathaniel Hafer, Bryan Buchholz, David MD McManus

    Background Studies of current opinion of our community members for the characteristics, mode, and location of use, use cases, and overall enthusiasm for point-of-care testing (POCT) diagnosis and management tools are needed. Study Design and Methods Qualitative research methods were used to develop, refine, and evaluate hardcopy and electronic versions of a 45-item English language survey. The accuracy of the instrument was measured by recorded structured interview, and its precision was measured by comparison to its administration to a group of uncompensated volunteers. Main Findings and Results Comparison of survey and structured interview data demonstrated high levels of accuracy. Highly concordant with significant levels of correlation and of direct association indicated favorable precision. Ninety-three percent of respondents believed that POCT could improve their care, and 56% identified having a POCT in their home as a top priority. Accuracy, insurance coverage, immediacy of results, and ease of use were identified as the most important characteristics of a POCT. Conclusions Community members strongly support the development of accurate, in-home devices that produce immediate results that can be used to diagnose, manage, and encourage their adherence to treatments for their medical conditions.


  • Workforce, Workload, and Burnout in Critical Care Organizations: Survey Results and Research Agenda*

    by Craig M. Lilly, John M. Oropello, Stephen M. Pastores, Craig M. Coopersmith, Roozehra A. Khan, Curtis N. Sessler, John W. Christman

    Objectives: This report provides analyses and perspective of a survey of critical care workforce, workload, and burnout among the intensivists and advanced practice providers of established U.S. and Canadian critical care organizations and provides a research agenda. Design: A 97-item electronic survey questionnaire was distributed to the leaders of 27 qualifying organizations. Setting: United States and Canada. Participants: Leaders of critical care organizations in the United States and Canada. Interventions: None. Data Synthesis and Main Results: We received 23 responses (85%). The critical care organization survey recorded substantial variability of most organizational aspects that were not restricted by the critical care organization definition or regulatory mandates. The most common physician staffing model was a combination of full-time and part-time intensivists. Approximately 80% of critical care organizations had dedicated advanced practice providers that staffed some or all their ICUs. Full-time intensivists worked a median of 168 days (range 42–192 d) in the ICU (168 shifts = 24 7-d wk). The median shift duration was 12 hours (range, 7–14 hr), and the median number of consecutive shifts allowed was 7 hours (range 7–14 hr). More than half of critical care organizations reported having burnout prevention programs targeted to ICU physicians, advanced practice providers, and nurses. Conclusions: The variability of current approaches suggests that systematic comparative analyses could identify best organizational practices. The research agenda for the study of critical care organizations should include studies that provide insights regarding the effects of the integrative structure of critical care organizations on outcomes at the levels of our patients, our workforce, our work practices, and sustainability.


  • The Evolution of Tele-ICU to Tele-Critical Care*

    by Craig M. Lilly, Bruce Md Greenberg