Machine Learning in Emergency Medicine: Keys to Future Success

Taylor, Richard A.; Haimovich, Adrian D.

doi:10.1111/acem.14189

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When applied to intermediate-risk PE, our results provided good evidence to support the continuation of this research using a larger dataset to develop a “final'' prediction model for clinical use in practice. The similar predictive performance between LR and RF is noteworthy because an equally accurate LR model would be more easily implemented in clinical practice than a machine learning RF model [ 47 ]. However, the prediction metrics of the RF model using the full dataset showed better performance than the average fit statistics of the LR model across 500 data splits.…”

Section: Discussionmentioning

confidence: 99%

Intermediate-risk pulmonary embolism: echocardiography predictors of clinical deterioration

et al. 2022

View full text Add to dashboard Cite

Background We determine the predictive value of transthoracic echocardiographic (TTE) metrics for clinical deterioration within 5 days in adults with intermediate-risk pulmonary embolism (PE). Methods This was a prospective observational study of intermediate-risk PE patients. To determine associations of TTE and clinical predictors with clinical deterioration, we used univariable analysis, Youden’s index for optimal thresholds, and multivariable analyses to report odds ratios (ORs) or area under the curve (AUC). Results Of 306 intermediate-risk PE patients, 115 (37.6%) experienced clinical deterioration. PE patients who had clinical deterioration within 5 days had greater baseline right ventricle (RV) dilatation and worse systolic function than the group without clinical deterioration as indicated by the following: RV basal diameter 4.46 ± 0.77 versus 4.20 ± 0.77 cm; RV/LV basal width ratio 1.14 ± 0.29 versus 1.02 ± 0.24; tricuspid annular plane systolic excursion (TAPSE) 1.56 ± 0.55 versus 1.80 ± 0.52 cm; and RV systolic excursion velocity 10.40 ± 3.58 versus 12.1 ± 12.5 cm/s, respectively. Optimal thresholds for predicting clinical deterioration were: RV basal width 3.9 cm (OR 2.85 [1.64, 4.97]), RV-to-left ventricle (RV/LV) ratio 1.08 (OR 3.32 [2.07, 5.33]), TAPSE 1.98 cm (OR 3.3 [2.06, 5.3]), systolic excursion velocity 10.10 cm/s (OR 2.85 [1.75, 4.63]), and natriuretic peptide 190 pg/mL (OR 2.89 [1.81, 4.62]). Significant independent predictors were: transient hypotension 6.1 (2.2, 18.9), highest heart rate 1.02 (1.00, 1.03), highest respiratory rate 1.02 (1.00, 1.04), and RV/LV ratio 1.29 (1.14, 1.47). By logistic regression and random forest analyses, AUCs were 0.80 (0.73, 0.87) and 0.78 (0.70, 0.85), respectively. Conclusions Basal RV, RV/LV ratio, and RV systolic function measurements were significantly different between intermediate-risk PE patients grouped by subsequent clinical deterioration.

show abstract

Section: Discussionmentioning

confidence: 99%

Intermediate-risk pulmonary embolism: echocardiography predictors of clinical deterioration

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Artificial Intelligence (AI) is the science and engineering of enabling computers to solve problems traditionally requiring human decision-making. 1 Within Emergency Medicine (EM) physicians recognize that AI will have an immense impact on patient care [ 1 , 2 ]. EM is one of a few specialties that manages both acute and sub-acute, undifferentiated patients, of all ages.…”

Section: Introductionmentioning

confidence: 99%

Needs and expectations for artificial intelligence in emergency medicine according to Canadian physicians

Eastwood

May

Andreou

et al. 2023

BMC Health Serv Res

View full text Add to dashboard Cite

Background Artificial Intelligence (AI) is recognized by emergency physicians (EPs) as an important technology that will affect clinical practice. Several AI-tools have already been developed to aid care delivery in emergency medicine (EM). However, many EM tools appear to have been developed without a cross-disciplinary needs assessment, making it difficult to understand their broader importance to general-practice. Clinician surveys about AI tools have been conducted within other medical specialties to help guide future design. This study aims to understand the needs of Canadian EPs for the apt use of AI-based tools. Methods A national cross-sectional, two-stage, mixed-method electronic survey of Canadian EPs was conducted from January-May 2022. The survey includes demographic and physician practice-pattern data, clinicians’ current use and perceptions of AI, and individual rankings of which EM work-activities most benefit from AI. Results The primary outcome is a ranked list of high-priority AI-tools for EM that physicians want translated into general use within the next 10 years. When ranking specific AI examples, ‘automated charting/report generation’, ‘clinical prediction rules’ and ‘monitoring vitals with early-warning detection’ were the top items. When ranking by physician work-activities, ‘AI-tools for documentation’, ‘AI-tools for computer use’ and ‘AI-tools for triaging patients’ were the top items. For secondary outcomes, EPs indicated AI was ‘likely’ (43.1%) or ‘extremely likely’ (43.7%) to be able to complete the task of ‘documentation’ and indicated either ‘a-great-deal’ (32.8%) or ‘quite-a-bit’ (39.7%) of potential for AI in EM. Further, EPs were either ‘strongly’ (48.5%) or ‘somewhat’ (39.8%) interested in AI for EM. Conclusions Physician input on the design of AI is essential to ensure the uptake of this technology. Translation of AI-tools to facilitate documentation is considered a high-priority, and respondents had high confidence that AI could facilitate this task. This study will guide future directions regarding the use of AI for EM and help direct efforts to address prevailing technology-translation barriers such as access to high-quality application-specific data and developing reporting guidelines for specific AI-applications. With a prioritized list of high-need AI applications, decision-makers can develop focused strategies to address these larger obstacles.

show abstract

“…With the growing demand for high-quality healthcare, embedding artificial intelligence (AI) into healthcare systems is a solution which promises to improve productivity and efficiency 8 , 9 . Since in-hospital cardiac arrest (IHCA) has a low survival rate, and is a major public healthcare burden that causes intensive consumption of medical resources, it is valuable to predict and minimize the occurrence of IHCA 10 , 11 .…”

Section: Introductionmentioning

confidence: 99%

Development of a machine-learning algorithm to predict in-hospital cardiac arrest for emergency department patients using a nationwide database

Kim

Choi

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

In this retrospective observational study, we aimed to develop a machine-learning model using data obtained at the prehospital stage to predict in-hospital cardiac arrest in the emergency department (ED) of patients transferred via emergency medical services. The dataset was constructed by attaching the prehospital information from the National Fire Agency and hospital factors to data from the National Emergency Department Information System. Machine-learning models were developed using patient variables, with and without hospital factors. We validated model performance and used the SHapley Additive exPlanation model interpretation. In-hospital cardiac arrest occurred in 5431 of the 1,350,693 patients (0.4%). The extreme gradient boosting model showed the best performance with area under receiver operating curve of 0.9267 when incorporating the hospital factor. Oxygen supply, age, oxygen saturation, systolic blood pressure, the number of ED beds, ED occupancy, and pulse rate were the most influential variables, in that order. ED occupancy and in-hospital cardiac arrest occurrence were positively correlated, and the impact of ED occupancy appeared greater in small hospitals. The machine-learning predictive model using the integrated information acquired in the prehospital stage effectively predicted in-hospital cardiac arrest in the ED and can contribute to the efficient operation of emergency medical systems.

show abstract

Machine Learning in Emergency Medicine: Keys to Future Success

Cited by 6 publications

References 21 publications

Intermediate-risk pulmonary embolism: echocardiography predictors of clinical deterioration

Intermediate-risk pulmonary embolism: echocardiography predictors of clinical deterioration

Needs and expectations for artificial intelligence in emergency medicine according to Canadian physicians

Development of a machine-learning algorithm to predict in-hospital cardiac arrest for emergency department patients using a nationwide database

Contact Info

Product

Resources

About