1292: A Multivariate Machine Learning Algorithm for Occult Hemorrhage in a Porcine Model

Klein, Samuel J.; Rashedi, Navid; Sun, Yifei; Murphy, Ethan K.; Hamlin, Alexandra; Minichiello, Joseph M; Anderson, Justin; Lindqwister, Alexander; Moodie, Karen L; Borza, Victor; Wanken, Zachary J.; Vaze, Vikrant; Halter, Ryan J.; Elliott, Jonathan T.; Paradis, Norman A.

doi:10.1097/01.ccm.0000731056.53582.4c

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Project schedule control, like cost control and quality control, is one of the key control objects of the project and an important means to ensure that the project is completed on schedule, reasonably arrange resource allocation and control input costs. The progress control of the project lasts from the start of the project to the end of the project, which is a long-lasting and dynamic process management [8][9]. After completing the preparation of the project schedule, the actual project schedule fed back from the project construction is compared with the planned schedule, so as to clarify the progress speed of the project, so as to update the schedule in time and achieve the purpose of controlling the schedule [10].…”

Section: Project Schedule Control Principlementioning

confidence: 99%

Marine Engineering Project Planning Management Technology based on Machine Learning

2022

FOE

View full text Add to dashboard Cite

With the development of various marine exploration means, the ability to obtain marine environmental information has also been unprecedentedly improved. Marine data presents the characteristics of strong spatial-temporal correlation and diverse formats, but it brings problems such as complex relationships between data, difficult analysis of heterogeneous data, and low processing efficiency. Therefore, the marine project planning management technology has become the focus of research. This paper studies and analyzes the marine project planning management technology based on machine learning(ML) algorithm. The planning, classification, organizational structure and control principle of offshore engineering project(OEP) are discussed; This paper proposes a ML algorithm, optimizes the project schedule of marine engineering project(MEP) planning management technology through the training algorithm of smooth support vector regression model, and finally introduces each module of the system briefly in combination with the planning management of MEPs, which verifies the feasibility of the ML algorithm, improves the production efficiency of marine engineering, and has a certain reference significance for future development.

show abstract

Section: Project Schedule Control Principlementioning

confidence: 99%

Marine Engineering Project Planning Management Technology based on Machine Learning

2022

FOE

View full text Add to dashboard Cite

show abstract

“…Currently, none of the existing non-invasive technologies has adequate performance with respect to underlying false-positive and false-negative rates to function in such a role. We have previously hypothesized that a multiplexed combination of non-invasive technologies that incorporates anatomic and temporal patterns via machine learning may outperform existing solutions 9 and reported that such an approach had superior diagnostic performance 10 in a porcine model of occult hemorrhage 11 . In particular, we observed that direct change-from-baseline impedance measurements 12 and a multiplexed model built of absolute and impedance-change data appeared to have exceptional performances 9 .…”

Section: Introductionmentioning

confidence: 99%

Non-invasive biomarkers for detecting progression toward hypovolemic cardiovascular instability in a lower body negative pressure model

Murphy,

Bertsch,

Klein

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Occult hemorrhages after trauma can be present insidiously, and if not detected early enough can result in patient death. This study evaluated a hemorrhage model on 18 human subjects, comparing the performance of traditional vital signs to multiple off-the-shelf non-invasive biomarkers. A validated lower body negative pressure (LBNP) model was used to induce progression towards hypovolemic cardiovascular instability. Traditional vital signs included mean arterial pressure (MAP), electrocardiography (ECG), plethysmography (Pleth), and the test systems utilized electrical impedance via commercial electrical impedance tomography (EIT) and multifrequency electrical impedance spectroscopy (EIS) devices. Absolute and relative metrics were used to evaluate the performance in addition to machine learning-based modeling. Relative EIT-based metrics measured on the thorax outperformed vital sign metrics (MAP, ECG, and Pleth) achieving an area-under-the-curve (AUC) of 0.99 (CI 0.95–1.00, 100% sensitivity, 87.5% specificity) at the smallest LBNP change (0–15 mmHg). The best vital sign metric (MAP) at this LBNP change yielded an AUC of 0.6 (CI 0.38–0.79, 100% sensitivity, 25% specificity). Out-of-sample predictive performance from machine learning models were strong, especially when combining signals from multiple technologies simultaneously. EIT, alone or in machine learning-based combination, appears promising as a technology for early detection of progression toward hemodynamic instability.

show abstract

1292: A Multivariate Machine Learning Algorithm for Occult Hemorrhage in a Porcine Model

Cited by 2 publications

References 0 publications

Marine Engineering Project Planning Management Technology based on Machine Learning

Marine Engineering Project Planning Management Technology based on Machine Learning

Non-invasive biomarkers for detecting progression toward hypovolemic cardiovascular instability in a lower body negative pressure model

Contact Info

Product

Resources

About