Development of a machine learning-based clinical decision support system to predict clinical deterioration in patients visiting the emergency department

A pre-trained language model for emergency department intervention prediction using routine physiological data and clinical narratives

INTRODUCTION

The urgency and complexity of emergency room (ER) settings require precise and swift decision-making processes for patient care. Ensuring the timely execution of critical examinations and interventions is vital for reducing diagnostic errors, but the literature highlights a need for innovative approaches to optimize diagnostic accuracy and patient outcomes. In response, our study endeavors to create predictive models for timely examinations and interventions by leveraging the patient's symptoms and vital signs recorded during triage, and in so doing, augment traditional diagnostic methodologies.

METHODS

Focusing on four key areas-medication dispensing, vital interventions, laboratory testing, and emergency radiology exams, the study employed Natural Language Processing (NLP) and seven advanced machine learning techniques. The research was centered around the innovative use of BioClinicalBERT, a state-of-the-art NLP framework.

RESULTS

BioClinicalBERT emerged as the superior model, outperforming others in predictive accuracy. The integration of physiological data with patient narrative symptoms demonstrated greater effectiveness compared to models based solely on textual data. The robustness of our approach was confirmed by an Area Under the Receiver Operating Characteristic curve (AUROC) score of 0.9.

CONCLUSION

The findings of our study underscore the feasibility of establishing a decision support system for emergency patients, targeting timely interventions and examinations based on a nuanced analysis of symptoms. By using an advanced natural language processing technique, our approach shows promise for enhancing diagnostic accuracy. However, the current model is not yet fully mature for direct implementation into daily clinical practice. Recognizing the imperative nature of precision in the ER environment, future research endeavors must focus on refining and expanding predictive models to include detailed timely examinations and interventions. Although the progress achieved in this study represents an encouraging step towards a more innovative and technology-driven paradigm in emergency care, full clinical integration warrants further exploration and validation.

Development and validation of a machine learning-based model to assess probability of systemic inflammatory response syndrome in patients with severe multiple traumas

BACKGROUND

Systemic inflammatory response syndrome (SIRS) is a predictor of serious infectious complications, organ failure, and death in patients with severe polytrauma and is one of the reasons for delaying early total surgical treatment. To determine the risk of SIRS within 24 h after hospitalization, we developed six machine learning models.

MATERIALS AND METHODS

Using retrospective data about the patient, the nature of the injury, the results of general and standard biochemical blood tests, and coagulation tests, six models were developed: decision tree, random forest, logistic regression, support vector and gradient boosting classifiers, logistic regressor, and neural network. The effectiveness of the models was assessed through internal and external validation.

RESULTS

Among the 439 selected patients with severe polytrauma in 230 (52.4%), SIRS was diagnosed within the first 24 h of hospitalization. The SIRS group was more strongly associated with class II bleeding (39.5% vs. 60.5%; OR 1.81 [95% CI: 1.23-2.65]; P = 0.0023), long-term vasopressor use (68.4% vs. 31.6%; OR 5.51 [95% CI: 2.37-5.23]; P < 0.0001), risk of acute coagulopathy (67.8% vs. 32.2%; OR 2.4 [95% CI: 1.55-3.77]; P < 0.0001), and greater risk of pneumonia (59.5% vs. 40.5%; OR 1.74 [95% CI: 1.19-2.54]; P = 0.0042), longer ICU length of stay (5 ± 6.3 vs. 2.7 ± 4.3 days; P < 0.0001) and mortality rate (64.5% vs. 35.5%; OR 10.87 [95% CI: 6.3-19.89]; P = 0.0391). Of all the models, the random forest classifier showed the best predictive ability in the internal (AUROC 0.89; 95% CI: 0.83-0.96) and external validation (AUROC 0.83; 95% CI: 0.75-0.91) datasets.

CONCLUSIONS

The developed model made it possible to accurately predict the risk of developing SIRS in the early period after injury, allowing clinical specialists to predict patient management tactics and calculate medication and staffing needs for the patient.

LEVEL OF EVIDENCE

Level 3.

TRIAL REGISTRATION

The study was retrospectively registered in the ClinicalTrials.gov database of the National Library of Medicine (NCT06323096).

Development of early prediction model of in-hospital cardiac arrest based on laboratory parameters

BACKGROUND

In-hospital cardiac arrest (IHCA) is an acute disease with a high fatality rate that burdens individuals, society, and the economy. This study aimed to develop a machine learning (ML) model using routine laboratory parameters to predict the risk of IHCA in rescue-treated patients.

METHODS

This retrospective cohort study examined all rescue-treated patients hospitalized at the First Medical Center of the PLA General Hospital in Beijing, China, from January 2016 to December 2020. Five machine learning algorithms, including support vector machine, random forest, extra trees classifier (ETC), decision tree, and logistic regression algorithms, were trained to develop models for predicting IHCA. We included blood counts, biochemical markers, and coagulation markers in the model development. We validated model performance using fivefold cross-validation and used the SHapley Additive exPlanation (SHAP) for model interpretation.

RESULTS

A total of 11,308 participants were included in the study, of which 7779 patients remained. Among these patients, 1796 (23.09%) cases of IHCA occurred. Among five machine learning models for predicting IHCA, the ETC algorithm exhibited better performance, with an AUC of 0.920, compared with the other four machine learning models in the fivefold cross-validation. The SHAP showed that the top ten factors accounting for cardiac arrest in rescue-treated patients are prothrombin activity, platelets, hemoglobin, N-terminal pro-brain natriuretic peptide, neutrophils, prothrombin time, serum albumin, sodium, activated partial thromboplastin time, and potassium.

CONCLUSIONS

We developed a reliable machine learning-derived model that integrates readily available laboratory parameters to predict IHCA in patients treated with rescue therapy.

Enhancing Triage Efficiency and Accuracy in Emergency Rooms for Patients with Metastatic Prostate Cancer: A Retrospective Analysis of Artificial Intelligence-Assisted Triage Using ChatGPT 4.0

BACKGROUND

Accurate and efficient triage is crucial for prioritizing care and managing resources in emergency rooms. This study investigates the effectiveness of ChatGPT, an advanced artificial intelligence system, in assisting health providers with decision-making for patients presenting with metastatic prostate cancer, focusing on the potential to improve both patient outcomes and resource allocation.

METHODS

Clinical data from patients with metastatic prostate cancer who presented to the emergency room between 1 May 2022 and 30 April 2023 were retrospectively collected. The primary outcome was the sensitivity and specificity of ChatGPT in determining whether a patient required admission or discharge. The secondary outcomes included the agreement between ChatGPT and emergency medicine physicians, the comprehensiveness of diagnoses, the accuracy of treatment plans proposed by both parties, and the length of medical decision making.

RESULTS

Of the 147 patients screened, 56 met the inclusion criteria. ChatGPT had a sensitivity of 95.7% in determining admission and a specificity of 18.2% in discharging patients. In 87.5% of cases, ChatGPT made the same primary diagnoses as physicians, with more accurate terminology use (42.9% vs. 21.4%, p = 0.02) and more comprehensive diagnostic lists (median number of diagnoses: 3 vs. 2, p < 0.001). Emergency Severity Index scores calculated by ChatGPT were not associated with admission (p = 0.12), hospital stay length (p = 0.91) or ICU admission (p = 0.54). Despite shorter mean word count (169 ± 66 vs. 272 ± 105, p < 0.001), ChatGPT was more likely to give additional treatment recommendations than physicians (94.3% vs. 73.5%, p < 0.001).

CONCLUSIONS

Our hypothesis-generating data demonstrated that ChatGPT is associated with a high sensitivity in determining the admission of patients with metastatic prostate cancer in the emergency room. It also provides accurate and comprehensive diagnoses. These findings suggest that ChatGPT has the potential to assist health providers in improving patient triage in emergency settings, and may enhance both efficiency and quality of care provided by the physicians.