Data Science in Critical Care, An Issue of Critical Care Clinics

1st Edition, Volume 39-4 - September 13, 2023
Editors: Rishikesan Kamaleswaran, Andre L. Holder
Language: English
Hardback ISBN:
9 7 8 - 0 - 4 4 3 - 1 8 1 9 3 - 1
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 8 1 9 4 - 8

In this issue of Critical Care Clinics, guest editors Drs. Rishikesan Kamaleswaran and Andre L. Holder bring their considerable expertise to the topic of Data Science in Critical… Read more

Data Science in Critical Care, An Issue of Critical Care Clinics

Purchase options

Info / Buy

Limited Offer

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code needed.

Institutional subscription on ScienceDirect

Request a sales quote

In this issue of Critical Care Clinics, guest editors Drs. Rishikesan Kamaleswaran and Andre L. Holder bring their considerable expertise to the topic of Data Science in Critical Care. Data science, the field of study dedicated to the principled extraction of knowledge from complex data, is particularly relevant in the critical care setting. In this issue, top experts in the field cover key topics such as refining our understanding and classification of critical illness using biomarker-based phenotyping; predictive modeling using AI/ML on EHR data; classification and prediction using waveform-based data; creating trustworthy and fair AI systems; and more.

Cover image
Title page
Table of Contents
Copyright
Contributors
Forthcoming Issues
Preface
Promise 1: Targeted, personalized bedside care
Leveraging Data Science and Novel Technologies to Develop and Implement Precision Medicine Strategies in Critical Care
Key points
Introduction
Uncovering relevant disease phenotypes from observational data
Implementing precision medicine strategies in the critical care setting
Challenges and opportunities of data science approaches to advance precision medicine in critical care
Summary
Clinics care points
Conflicts of interest
Predictive Modeling Using Artificial Intelligence and Machine Learning Algorithms on Electronic Health Record Data: Advantages and Challenges
Key points
Overview
Artificial intelligence and machine learning algorithms
Outcome prediction before the rise of machine learning
Progress and challenges in artificial intelligence and machine learning algorithms modeling: mortality outcome prediction
Progress and challenges in artificial intelligence and machine learning algorithmsmodeling: sepsis outcome prediction
Overcoming the ‘translation gap’ in artificial intelligence and machine learning algorithms-driven ehr tools
Summary
Author contributions
Clinics care points
Disclosure
Supplementary data
Machine Learning of Physiologic Waveforms and Electronic Health Record Data: A Large Perioperative Data Set of High-Fidelity Physiologic Waveforms
Key points
Introduction
Method
Results
Discussion
Summary
Author contribution
Conflict of interest disclosure
Role of the funding source
Supplementary data
The Learning Electronic Health Record
Key points
Mandates and the electronic health record
The promise of meaningful use
The electronic health record and the provider
Electronic health record and data science
The electronic health record and clinical decision support
Emerging technologies for electronic health records
The electronic health record in underresourced environments
Summary
Clinics care points
Disclosure
Promise 2: Better understanding of critical care deployment and epidemiology
The Role of Data Science in Closing the Implementation Gap
Key points
Introduction
The implementation gap
Role of data science
Data sources and enabling technologies
Limitations and challenges
Summary
Clinics care points
Disclosure
Promise 3: More efficient research practices and strategies
Designing and Implementing “Living and Breathing” Clinical Trials: An Overview and Lessons Learned from the COVID-19 Pandemic
Key points
Introduction
“Living, breathing” clinical trials and the COVID-19 pandemic
Evidence-based medicine and Bayesian inference in clinical decision making
Quality and performance improvement in medicine and the learning health care system
Leveraging health care information systems to deploy randomized, embedded, multifactorial, adaptive, platform trial for community-acquired pneumonia in the United States
Ethical considerations of “living, breathing” trials
Summary
Clinics care points
Funding
Disclosure
How Electronic Medical Record Integration Can Support More Efficient Critical Care Clinical Trials
Key points
Introduction
Current challenges in critical care research
Precision medicine and critical care research
Big data and its contribution to patient phenotypes
Clustering and precision medicine to identify treatable traits?
The use of electronic “sniffers” to identify subjects
Leveraging the electronic health records to supply clinical trial data
The role of virtual patients and simulated clinical trials in pilot testing
Using big data in trials to generate big data—the use of adaptive platform trials
Summary
Clinics care points
Disclosure
Funding
The challenges of integrating data science into critical care medicine
Making the Improbable Possible: Generalizing Models Designed for a Syndrome-Based, Heterogeneous Patient Landscape
Key points
Introduction
Challenges with syndromes
Clarifying terms
One size does not fit all: the generalizability problem
Machine learning-based solutions
Discussion
Summary
Clinics care points
Disclosure
Clinician Trust in Artificial Intelligence: What is Known and How Trust Can Be Facilitated
Key points
A motivating case
Review of artificial intelligence in healthcare
How do clinician and artificial intelligence predictions compare?
Examining trust in artificial intelligence
Facilitating trustworthy artificial intelligence
Supporting an environment conducive to trust locally and nationally
Summary
Clinics care points
Funding
Disclaimer
Conflicts of interest and source of funding
Bioethical dilemmas with data science in critical care
Implementing Artificial Intelligence: Assessing the Cost and Benefits of Algorithmic Decision-Making in Critical Care
Key points
Introduction
Artificial intelligence applications in critical care
Benefits
Challenges
Summary
Critical Bias in Critical Care Devices
Key points
Introduction
Critical measurements
Continuously monitoring medical device performance to mitigate potential harm in clinical practice
Assessing the performance of medical devices across patient subpopulations and improving the representation of minority subgroups
Moving away from post-hoc corrections
Increasing policy requirements for medical device deployment in clinical practice
Fostering collaborations among institutions and health systems
Amplifying organizational and educational investments: the need for continued training and quality assurance
Summary
Clinics care points

Life sciences

Physical sciences & Engineering

Social sciences & Humanities

Health

Data Science in Critical Care, An Issue of Critical Care Clinics

Purchase options

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code needed.

Institutional subscription on ScienceDirect

Rishikesan Kamaleswaran

Andre L. Holder