Trends of Artificial Intelligence in Emergency and Critical Care Medicine

Topic Information

Dear Colleagues,

Summary: The Topic "Trends of Artificial Intelligence in Emergency and Critical Care Medicine" aims to explore the cutting-edge advancements and practical applications of AI in the fast-paced and high-stakes environments of emergency and critical care. This Topic seeks to serve as a comprehensive resource for healthcare professionals, researchers, and AI developers, highlighting the transformative potential of AI in enhancing patient care, streamlining hospital operations, and improving outcomes in critical situations.

Background: Emergency and critical care medicine is at the forefront of healthcare delivery, often dealing with life-or-death decisions under immense time pressure. The integration of AI presents an opportunity to augment clinical judgment, optimize resource allocation, and predict patient deterioration, thereby improving patient safety and clinical efficiency.

Aims:

1. Innovation Showcase: To present novel AI-driven technologies and algorithms designed to address specific challenges in emergency and critical care settings.
2. Clinical Integration: To discuss strategies for the successful implementation of AI in clinical workflows, focusing on interoperability with existing systems and user-centered design principles.
3. Data-Driven Insights: To examine the role of AI in analyzing complex medical data to predict patient outcomes, personalize treatment plans, and facilitate real-time decision-making.
4. Ethical Considerations: To explore the ethical implications of AI in emergency medicine, including issues of privacy, consent, and the potential for algorithmic bias.
5. Future Directions: To provide a forward-looking perspective on how AI might evolve and shape the future of emergency and critical care medicine.

Call for Contributions: We invite original research, review articles, and case studies that align with the aims of the Topic. Potential authors are encouraged to submit manuscripts that provide evidence-based insights, innovative solutions, and thoughtful discourse on the role of AI in emergency and critical care medicine. The editorial team will prioritize submissions that demonstrate a clear understanding of clinical needs, rigorous scientific methodology, and a commitment to improving patient care through AI.

Submission Guidelines: Authors should adhere to the journal's guidelines for manuscript preparation, ensuring that their work is both scientifically rigorous and accessible to a multidisciplinary audience. The Topic will undergo a thorough peer-review process to maintain the highest standards of academic integrity and clinical relevance.

Topic editors introduction:

Zhongheng Zhang's research program aims to enable precision treatment for critically ill adults, with the hypothesis that gene expression profiles generate clinical phenotypes and such networks could be determined by the integration of clinical and multi-omics data, such as those from RNA-seq and electronic healthcare records. Machine learning algorithms such as reinforcement learning and supervised and unsupervised learning can help to discover new knowledge and give more insights into precision medicine.

Dr. Hong Yucai is a distinguished medical professional with the title of Chief Physician and a supervisor for doctoral candidates at the Sir Run Run Shaw Hospital, affiliated with Zhejiang University School of Medicine. He holds a medical doctorate and has been recognized for his significant contributions to emergency medicine. With a long-standing commitment to the support and comprehensive treatment of critically ill patients and those suffering from severe trauma, Dr. Hong has been at the forefront of emergency and critical care medicine. He initiated the clinical application of and research into critical care ultrasound in 2004 and pioneered the PENLIGHT minimally invasive technique for the treatment of intractable aspiration pneumonia in 2006. His innovative spirit led him to explore standardized diagnosis and treatment protocols for critical illnesses based on daily checklists and goal-oriented approaches in 2015. Dr. Hong has also made significant strides in academia and professional associations. In 2017, he established the Asia Society of Emergency and Critical Care Medicine and launched the "Journal of Emergency and Critical Care Medicine", serving as its editor-in-chief. Additionally, he developed the SEED simulation teaching program for critical emergency conditions and has been instrumental in promoting these educational initiatives both within and outside of Zhejiang province. His leadership extends to various medical committees and societies, including serving as the Deputy Director of the Emergency Medicine Research Institute at Zhejiang University, the Vice Chairman of the Emergency Medicine Branch of the Chinese Medical Education Association, and a member of the Chinese Medical Doctor Association's Emergency Physicians Branch.

Dr. Wei Shao is from Nanjing University of Aeronautics and Astronautics. His main research areas are machine learning and medical image processing.

Dr. Zhongheng Zhang
Prof. Dr. Yucai Hong
Dr. Wei Shao
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
AI ai	3.1	7.2	2020	18.9 Days	CHF 1600	Submit
Algorithms algorithms	1.8	4.1	2008	18.9 Days	CHF 1600	Submit
Diagnostics diagnostics	3.0	4.7	2011	20.3 Days	CHF 2600	Submit
Emergency Care and Medicine ecm	-	-	2024	20.3 Days	CHF 1000	Submit

MDPI Topics is cooperating with Preprints.org and has built a direct connection between MDPI journals and Preprints.org. Authors are encouraged to enjoy the benefits by posting a preprint at Preprints.org prior to publication:

1. Immediately share your ideas ahead of publication and establish your research priority;
2. Protect your idea from being stolen with this time-stamped preprint article;
3. Enhance the exposure and impact of your research;
4. Receive feedback from your peers in advance;
5. Have it indexed in Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (2 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All AI Algorithms Diagnostics Emergency Care and Medicine

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

attachment

Supplementary material:
Supplementary File 1 (ZIP, 93 KiB)

16 pages, 2345 KiB  

Open AccessArticle

Personalized Predictions of Therapeutic Hypothermia Outcomes in Cardiac Arrest Patients with Shockable Rhythms Using Explainable Machine Learning

by Chien-Tai Hong, Oluwaseun Adebayo Bamodu, Hung-Wen Chiu, Wei-Ting Chiu, Lung Chan and Chen-Chih Chung

Diagnostics 2025, 15(3), 267; https://doi.org/10.3390/diagnostics15030267 - 23 Jan 2025

Viewed by 497

Abstract

Background: Therapeutic hypothermia (TH) represents a critical therapeutic intervention for patients with cardiac arrest, although treatment efficacy and prognostic factors may vary between individuals. Precise, personalized outcome predictions can empower better clinical decisions. Methods: In this multi-center retrospective cohort study involving nine medical [...] Read more.

Background: Therapeutic hypothermia (TH) represents a critical therapeutic intervention for patients with cardiac arrest, although treatment efficacy and prognostic factors may vary between individuals. Precise, personalized outcome predictions can empower better clinical decisions. Methods: In this multi-center retrospective cohort study involving nine medical centers in Taiwan, we developed machine learning algorithms to predict neurological outcomes in patients who experienced cardiac arrest with shockable rhythms and underwent TH. The study cohort comprised 209 patients treated between January 2014 and September 2019. The models were trained on patients’ pre-treatment characteristics collected during this study period. The optimal artificial neural network (ANN) model was interpretable using the SHapley Additive exPlanations (SHAP) method. Results: Among the 209 enrolled patients, 79 (37.80%) demonstrated favorable neurological outcomes at discharge. The ANN model achieved an area under the curve value of 0.9089 (accuracy = 0.8330, precision = 0.7984, recall = 0.7492, specificity = 0.8846) for outcome prediction. SHAP analysis identified vital predictive features, including the dose of epinephrine during resuscitation, diabetes status, body temperature at return of spontaneous circulation (ROSC), whether the cardiac arrest was witnessed, and diastolic blood pressure at ROSC. Using real-life case examples, we demonstrated how the ANN model provides personalized prognostic predictions tailored to individuals’ distinct profiles. Conclusion: Our machine learning approach delivers personalized forecasts of TH outcomes in cardiac arrest patients with shockable rhythms. By accounting for each patient’s unique health history and cardiac arrest event details, the ANN model empowers more precise risk stratification, tailoring clinical decision-making regarding TH prognostication and optimizing personalized treatment planning. Full article

(This article belongs to the Topic Trends of Artificial Intelligence in Emergency and Critical Care Medicine)

►▼ Show Figures

Figure 1

13 pages, 851 KiB  

Open AccessArticle

Feasibility of GPT-3.5 versus Machine Learning for Automated Surgical Decision-Making Determination: A Multicenter Study on Suspected Appendicitis

by Sebastian Sanduleanu, Koray Ersahin, Johannes Bremm, Narmin Talibova, Tim Damer, Merve Erdogan, Jonathan Kottlors, Lukas Goertz, Christiane Bruns, David Maintz and Nuran Abdullayev

AI 2024, 5(4), 1942-1954; https://doi.org/10.3390/ai5040096 - 16 Oct 2024

Viewed by 1106

Abstract

Background: Nonsurgical treatment of uncomplicated appendicitis is a reasonable option in many cases despite the sparsity of robust, easy access, externally validated, and multimodally informed clinical decision support systems (CDSSs). Developed by OpenAI, the Generative Pre-trained Transformer 3.5 model (GPT-3) may provide enhanced [...] Read more.

Background: Nonsurgical treatment of uncomplicated appendicitis is a reasonable option in many cases despite the sparsity of robust, easy access, externally validated, and multimodally informed clinical decision support systems (CDSSs). Developed by OpenAI, the Generative Pre-trained Transformer 3.5 model (GPT-3) may provide enhanced decision support for surgeons in less certain appendicitis cases or those posing a higher risk for (relative) operative contra-indications. Our objective was to determine whether GPT-3.5, when provided high-throughput clinical, laboratory, and radiological text-based information, will come to clinical decisions similar to those of a machine learning model and a board-certified surgeon (reference standard) in decision-making for appendectomy versus conservative treatment. Methods: In this cohort study, we randomly collected patients presenting at the emergency department (ED) of two German hospitals (GFO, Troisdorf, and University Hospital Cologne) with right abdominal pain between October 2022 and October 2023. Statistical analysis was performed using R, version 3.6.2, on RStudio, version 2023.03.0 + 386. Overall agreement between the GPT-3.5 output and the reference standard was assessed by means of inter-observer kappa values as well as accuracy, sensitivity, specificity, and positive and negative predictive values with the “Caret” and “irr” packages. Statistical significance was defined as p < 0.05. Results: There was agreement between the surgeon’s decision and GPT-3.5 in 102 of 113 cases, and all cases where the surgeon decided upon conservative treatment were correctly classified by GPT-3.5. The estimated model training accuracy was 83.3% (95% CI: 74.0, 90.4), while the validation accuracy for the model was 87.0% (95% CI: 66.4, 97.2). This is in comparison to the GPT-3.5 accuracy of 90.3% (95% CI: 83.2, 95.0), which did not perform significantly better in comparison to the machine learning model (p = 0.21). Conclusions: This study, the first study of the “intended use” of GPT-3.5 for surgical treatment to our knowledge, comparing surgical decision-making versus an algorithm found a high degree of agreement between board-certified surgeons and GPT-3.5 for surgical decision-making in patients presenting to the emergency department with lower abdominal pain. Full article

(This article belongs to the Topic Trends of Artificial Intelligence in Emergency and Critical Care Medicine)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-2