A Machine Learning-Based Model to Predict Acute Traumatic Coagulopathy in Trauma Patients Upon Emergency Hospitalization

Ten Machine Learning Models for Predicting Preoperative and Postoperative Coagulopathy in Patients With Trauma: Multicenter Cohort Study

BACKGROUND

Recent research has revealed the potential value of machine learning (ML) models in improving prognostic prediction for patients with trauma. ML can enhance predictions and identify which factors contribute the most to posttraumatic mortality. However, no studies have explored the risk factors, complications, and risk prediction of preoperative and postoperative traumatic coagulopathy (PPTIC) in patients with trauma.

OBJECTIVE

This study aims to help clinicians implement timely and appropriate interventions to reduce the incidence of PPTIC and related complications, thereby lowering in-hospital mortality and disability rates for patients with trauma.

METHODS

We analyzed data from 13,235 patients with trauma from 4 medical centers, including medical histories, laboratory results, and hospitalization complications. We developed 10 ML models in Python (Python Software Foundation) to predict PPTIC based on preoperative indicators. Data from 10,023 Medical Information Mart for Intensive Care patients were divided into training (70%) and test (30%) sets, with 3212 patients from 3 other centers used for external validation. Model performance was assessed with 5-fold cross-validation, bootstrapping, Brier score, and Shapley additive explanation values.

RESULTS

Univariate logistic regression identified PPTIC risk factors as (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) decreased levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) lower admission diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) emergency surgery and perioperative transfusion. Multivariate logistic regression revealed that patients with PPTIC faced significantly higher risks of sepsis (1.75-fold), heart failure (1.5-fold), delirium (3.08-fold), abnormal coagulation (3.57-fold), tracheostomy (2.76-fold), mortality (2.19-fold), and urinary tract infection (1.95-fold), along with longer hospital and intensive care unit stays. Random forest was the most effective ML model for predicting PPTIC, achieving an area under the receiver operating characteristic of 0.91, an area under the precision-recall curve of 0.89, accuracy of 0.84, sensitivity of 0.80, specificity of 0.88, precision of 0.88, F1-score of 0.84, and Brier score of 0.13 in external validation.

CONCLUSIONS

Key PPTIC risk factors include (1) prolonged activated partial thromboplastin time, prothrombin time, and international normalized ratio; (2) low levels of hemoglobin, hematocrit, red blood cells, calcium, and sodium; (3) low diastolic blood pressure; (4) elevated alanine aminotransferase and aspartate aminotransferase levels; (5) admission heart rate; and (6) the need for emergency surgery and transfusion. PPTIC is associated with severe complications and extended hospital stays. Among the ML models, the random forest model was the most effective predictor.

TRIAL REGISTRATION

Chinese Clinical Trial Registry ChiCTR2300078097; https://www.chictr.org.cn/showproj.html?proj=211051.

A dynamic online nomogram predicting post-traumatic arrhythmias: A retrospective cohort study

BACKGROUND

A nomogram is a visualized clinical prediction models, which offer a scientific basis for clinical decision-making. There is a lack of reports on its use in predicting the risk of arrhythmias in trauma patients. This study aims to develop and validate a straightforward nomogram for predicting the risk of arrhythmias in trauma patients.

METHODS

We retrospectively collected clinical data from 1119 acute trauma patients who were admitted to the Advanced Trauma Center of the Affiliated Hospital of Zunyi Medical University between January 2016 and May 2022. Data recorded included intra-hospital arrhythmia, ICU stay, and total hospitalization duration. Patients were classified into arrhythmia and non-arrhythmia groups. Data was summarized according to the occurrence and prognosis of post-traumatic arrhythmias, and randomly allocated into a training and validation sets at a ratio of 7:3. The nomogram was developed according to independent risk factors identified in the training set. Finally, the predictive performance of the nomogram model was validated.

RESULTS

Arrhythmias were observed in 326 (29.1%) of the 1119 patients. Compared to the non-arrhythmia group, patients with arrhythmias had longer ICU and hospital stays and higher in-hospital mortality rates. Significant factors associated with post-traumatic arrhythmias included cardiovascular disease, catecholamine use, glasgow coma scale (GCS) score, abdominal abbreviated injury scale (AIS) score, injury severity score (ISS), blood glucose (GLU) levels, and international normalized ratio (INR). The area under the receiver operating characteristic curve (AUC) values for both the training and validation sets exceeded 0.7, indicating strong discriminatory power. The calibration curve showed good alignment between the predicted and actual probabilities of arrhythmias. Decision curve analysis (DCA) indicated a high net benefit for the model in predicting arrhythmias. The Hosmer-Lemeshow goodness-of-fit test confirmed the model's good fit.

CONCLUSION

The nomogram developed in this study is a valuable tool for accurately predicting the risk of post-traumatic arrhythmias, offering a novel approach for physicians to tailor risk assessments to individual patients.

The AI Future of Emergency Medicine

In the coming years, artificial intelligence (AI) and machine learning will likely give rise to profound changes in the field of emergency medicine, and medicine more broadly. This article discusses these anticipated changes in terms of 3 overlapping yet distinct stages of AI development. It reviews some fundamental concepts in AI and explores their relation to clinical practice, with a focus on emergency medicine. In addition, it describes some of the applications of AI in disease diagnosis, prognosis, and treatment, as well as some of the practical issues that they raise, the barriers to their implementation, and some of the legal and regulatory challenges they create.

Artificial intelligence and machine learning for hemorrhagic trauma care

Artificial intelligence (AI), a branch of machine learning (ML) has been increasingly employed in the research of trauma in various aspects. Hemorrhage is the most common cause of trauma-related death. To better elucidate the current role of AI and contribute to future development of ML in trauma care, we conducted a review focused on the use of ML in the diagnosis or treatment strategy of traumatic hemorrhage. A literature search was carried out on PubMed and Google scholar. Titles and abstracts were screened and, if deemed appropriate, the full articles were reviewed. We included 89 studies in the review. These studies could be grouped into five areas: (1) prediction of outcomes; (2) risk assessment and injury severity for triage; (3) prediction of transfusions; (4) detection of hemorrhage; and (5) prediction of coagulopathy. Performance analysis of ML in comparison with current standards for trauma care showed that most studies demonstrated the benefits of ML models. However, most studies were retrospective, focused on prediction of mortality, and development of patient outcome scoring systems. Few studies performed model assessment via test datasets obtained from different sources. Prediction models for transfusions and coagulopathy have been developed, but none is in widespread use. AI-enabled ML-driven technology is becoming integral part of the whole course of trauma care. Comparison and application of ML algorithms using different datasets from initial training, testing and validation in prospective and randomized controlled trials are warranted for provision of decision support for individualized patient care as far forward as possible.

Intelligent injury prediction for traumatic airway obstruction

Airway obstruction is one of the crucial causes of death in trauma patients during the first aid. It is extremely challenging to accurately treat a great deal of casualties with airway obstruction in hospitals. The diagnosis of airway obstruction in an emergency mostly relies on the medical experience of physicians. In this paper, we propose the feature selection approach genetic algorithm-mean decrease impurity (GA-MDI) to effectively minimize the number of features as well as ensure the accuracy of prediction. Furthermore, we design a multi-modal neural network, called fully convolutional network with squeeze-and-excitation and multilayer perceptron (FCN-SE + MLP), to help physicians to predict the severity of airway obstruction. We validate the effectiveness of the proposed feature selection approach and multi-modal model on the emergency medical database from the Chinese General Hospital of the PLA. The experimental results show that GA-MDI outperforms the existing feature selection algorithms, while it is also validated that the model FCN-SE + MLP can effectively and accurately achieve the prediction of the severity of airway obstruction, which can assist clinicians in making treatment decisions for airway obstruction casualties.

A cost-aware framework for the development of AI models for healthcare applications

Accurate artificial intelligence (AI) for disease diagnosis could lower healthcare workloads. However, when time or financial resources for gathering input data are limited, as in emergency and critical-care medicine, developing accurate AI models, which typically require inputs for many clinical variables, may be impractical. Here we report a model-agnostic cost-aware AI (CoAI) framework for the development of predictive models that optimize the trade-off between prediction performance and feature cost. By using three datasets, each including thousands of patients, we show that relative to clinical risk scores, CoAI substantially reduces the cost and improves the accuracy of predicting acute traumatic coagulopathy in a pre-hospital setting, mortality in intensive-care patients and mortality in outpatient settings. We also show that CoAI outperforms state-of-the-art cost-aware prediction strategies in terms of predictive performance, model cost, training time and robustness to feature-cost perturbations. CoAI uses axiomatic feature-attribution methods for the estimation of feature importance and decouples feature selection from model training, thus allowing for a faster and more flexible adaptation of AI models to new feature costs and prediction budgets.

Artificial Intelligence and Machine Learning in Patient Blood Management: A Scoping Review

Machine learning (ML) and artificial intelligence (AI) are widely used in many different fields of modern medicine. This narrative review gives, in the first part, a brief overview of the methods of ML and AI used in patient blood management (PBM) and, in the second part, aims at describing which fields have been analyzed using these methods so far. A total of 442 articles were identified by a literature search, and 47 of them were judged as qualified articles that applied ML and AI techniques in PBM. We assembled the eligible articles to provide insights into the areas of application, quality measures of these studies, and treatment outcomes that can pave the way for further adoption of this promising technology and its possible use in routine clinical decision making. The topics that have been investigated most often were the prediction of transfusion (30%), bleeding (28%), and laboratory studies (15%). Although in the last 3 years a constantly increasing number of questions of ML in PBM have been investigated, there is a vast scientific potential for further application of ML and AI in other fields of PBM.

State of the Art of Machine Learning-Enabled Clinical Decision Support in Intensive Care Units: Literature Review

Background

Modern clinical care in intensive care units is full of rich data, and machine learning has great potential to support clinical decision-making. The development of intelligent machine learning–based clinical decision support systems is facing great opportunities and challenges. Clinical decision support systems may directly help clinicians accurately diagnose, predict outcomes, identify risk events, or decide treatments at the point of care.

Objective

We aimed to review the research and application of machine learning–enabled clinical decision support studies in intensive care units to help clinicians, researchers, developers, and policy makers better understand the advantages and limitations of machine learning–supported diagnosis, outcome prediction, risk event identification, and intensive care unit point-of-care recommendations.

Methods

We searched papers published in the PubMed database between January 1980 and October 2020. We defined selection criteria to identify papers that focused on machine learning–enabled clinical decision support studies in intensive care units and reviewed the following aspects: research topics, study cohorts, machine learning models, analysis variables, and evaluation metrics.

Results

A total of 643 papers were collected, and using our selection criteria, 97 studies were found. Studies were categorized into 4 topics—monitoring, detection, and diagnosis (13/97, 13.4%), early identification of clinical events (32/97, 33.0%), outcome prediction and prognosis assessment (46/97, 47.6%), and treatment decision (6/97, 6.2%). Of the 97 papers, 82 (84.5%) studies used data from adult patients, 9 (9.3%) studies used data from pediatric patients, and 6 (6.2%) studies used data from neonates. We found that 65 (67.0%) studies used data from a single center, and 32 (33.0%) studies used a multicenter data set; 88 (90.7%) studies used supervised learning, 3 (3.1%) studies used unsupervised learning, and 6 (6.2%) studies used reinforcement learning. Clinical variable categories, starting with the most frequently used, were demographic (n=74), laboratory values (n=59), vital signs (n=55), scores (n=48), ventilation parameters (n=43), comorbidities (n=27), medications (n=18), outcome (n=14), fluid balance (n=13), nonmedicine therapy (n=10), symptoms (n=7), and medical history (n=4). The most frequently adopted evaluation metrics for clinical data modeling studies included area under the receiver operating characteristic curve (n=61), sensitivity (n=51), specificity (n=41), accuracy (n=29), and positive predictive value (n=23).

Conclusions

Early identification of clinical and outcome prediction and prognosis assessment contributed to approximately 80% of studies included in this review. Using new algorithms to solve intensive care unit clinical problems by developing reinforcement learning, active learning, and time-series analysis methods for clinical decision support will be greater development prospects in the future.

Intelligent prediction of RBC demand in trauma patients using decision tree methods

BACKGROUND

The vital signs of trauma patients are complex and changeable, and the prediction of blood transfusion demand mainly depends on doctors' experience and trauma scoring system; therefore, it cannot be accurately predicted. In this study, a machine learning decision tree algorithm [classification and regression tree (CRT) and eXtreme gradient boosting (XGBoost)] was proposed for the demand prediction of traumatic blood transfusion to provide technical support for doctors.

METHODS

A total of 1371 trauma patients who were diverted to the Emergency Department of the First Medical Center of Chinese PLA General Hospital from January 2014 to January 2018 were collected from an emergency trauma database. The vital signs, laboratory examination parameters and blood transfusion volume were used as variables, and the non-invasive parameters and all (non-invasive + invasive) parameters were used to construct an intelligent prediction model for red blood cell (RBC) demand by logistic regression (LR), CRT and XGBoost. The prediction accuracy of the model was compared with the area under the curve (AUC).

RESULTS

For non-invasive parameters, the LR method was the best, with an AUC of 0.72 [95% confidence interval (CI) 0.657-0.775], which was higher than the CRT (AUC 0.69, 95% CI 0.633-0.751) and the XGBoost (AUC 0.71, 95% CI 0.654-0.756, P < 0.05). The trauma location and shock index are important prediction parameters. For all the prediction parameters, XGBoost was the best, with an AUC of 0.94 (95% CI 0.893-0.981), which was higher than the LR (AUC 0.80, 95% CI 0.744-0.850) and the CRT (AUC 0.82, 95% CI 0.779-0.853, P < 0.05). Haematocrit (Hct) is an important prediction parameter.

CONCLUSIONS

The classification performance of the intelligent prediction model of red blood cell transfusion in trauma patients constructed by the decision tree algorithm is not inferior to that of the traditional LR method. It can be used as a technical support to assist doctors to make rapid and accurate blood transfusion decisions in emergency rescue environment, so as to improve the success rate of patient treatment.

Has the Flood Entered the Basement? A Systematic Literature Review about Machine Learning in Laboratory Medicine

This article presents a systematic literature review that expands and updates a previous review on the application of machine learning to laboratory medicine. We used Scopus and PubMed to collect, select and analyse the papers published from 2017 to the present in order to highlight the main studies that have applied machine learning techniques to haematochemical parameters and to review their diagnostic and prognostic performance. In doing so, we aim to address the question we asked three years ago about the potential of these techniques in laboratory medicine and the need to leverage a tool that was still under-utilised at that time.

Clinical Utility of Delta Lactate for Predicting Early In-Hospital Mortality in Adult Patients: A Prospective, Multicentric, Cohort Study

One of the challenges in the emergency department (ED) is the early identification of patients with a higher risk of clinical deterioration. The objective is to evaluate the prognostic capacity of ΔLA (correlation between prehospital lactate (pLA) and hospital lactate (hLA)) with respect to in-hospital two day mortality. We conducted a pragmatic, multicentric, prospective and blinded-endpoint study in adults who consecutively attended and were transported in advanced life support with high priority from the scene to the ED. The corresponding area under the receiver operating characteristics curve (AUROC) was obtained for each of the outcomes. In total, 1341 cases met the inclusion criteria. The median age was 71 years (interquartile range: 54–83 years), with 38.9% (521 cases) females. The total 2 day mortality included 106 patients (7.9%). The prognostic precision for the 2 day mortality of pLA and hLA was good, with an AUROC of 0.800 (95% CI: 0.74–0.85; p < 0.001) and 0.819 (95% CI: 0.76–0.86; p < 0.001), respectively. Of all patients, 31.5% (422 cases) had an ΔLA with a decrease of <10%, of which a total of 66 patients (15.6%) died. A lactate clearance ≥ 10% is associated with a lower risk of death in the ED, and this value could potentially be used as a guide to determine if a severely injured patient is improving in response to the established treatment.