External validation of a smartphone app model to predict the need for massive transfusion using five different definitions

AI algorithm for personalized resource allocation and treatment of hemorrhage casualties

A deep neural network-based artificial intelligence (AI) model was assessed for its utility in predicting vital signs of hemorrhage patients and optimizing the management of fluid resuscitation in mass casualties. With the use of a cardio-respiratory computational model to generate synthetic data of hemorrhage casualties, an application was created where a limited data stream (the initial 10 min of vital-sign monitoring) could be used to predict the outcomes of different fluid resuscitation allocations 60 min into the future. The predicted outcomes were then used to select the optimal resuscitation allocation for various simulated mass-casualty scenarios. This allowed the assessment of the potential benefits of using an allocation method based on personalized predictions of future vital signs versus a static population-based method that only uses currently available vital-sign information. The theoretical benefits of this approach included up to 46% additional casualties restored to healthy vital signs and a 119% increase in fluid-utilization efficiency. Although the study is not immune from limitations associated with synthetic data under specific assumptions, the work demonstrated the potential for incorporating neural network-based AI technologies in hemorrhage detection and treatment. The simulated injury and treatment scenarios used delineated possible benefits and opportunities available for using AI in pre-hospital trauma care. The greatest benefit of this technology lies in its ability to provide personalized interventions that optimize clinical outcomes under resource-limited conditions, such as in civilian or military mass-casualty events, involving moderate and severe hemorrhage.

Digitalization in orthopaedics: a narrative review

Advances in technology and digital tools like the Internet of Things (IoT), artificial intelligence (AI), and sensors are shaping the field of orthopaedic surgery on all levels, from patient care to research and facilitation of logistic processes. Especially the COVID-19 pandemic, with the associated contact restrictions was an accelerator for the development and introduction of telemedical applications and digital alternatives to classical in-person patient care. Digital applications already used in orthopaedic surgery include telemedical support, online video consultations, monitoring of patients using wearables, smart devices, surgical navigation, robotic-assisted surgery, and applications of artificial intelligence in forms of medical image processing, three-dimensional (3D)-modelling, and simulations. In addition to that immersive technologies like virtual, augmented, and mixed reality are increasingly used in training but also rehabilitative and surgical settings. Digital advances can therefore increase the accessibility, efficiency and capabilities of orthopaedic services and facilitate more data-driven, personalized patient care, strengthening the self-responsibility of patients and supporting interdisciplinary healthcare providers to offer for the optimal care for their patients.

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.

Decision support by machine learning systems for acute management of severely injured patients: A systematic review

Introduction

Treating severely injured patients requires numerous critical decisions within short intervals in a highly complex situation. The coordination of a trauma team in this setting has been shown to be associated with multiple procedural errors, even of experienced care teams. Machine learning (ML) is an approach that estimates outcomes based on past experiences and data patterns using a computer-generated algorithm. This systematic review aimed to summarize the existing literature on the value of ML for the initial management of severely injured patients.

Methods

We conducted a systematic review of the literature with the goal of finding all articles describing the use of ML systems in the context of acute management of severely injured patients. MESH search of Pubmed/Medline and Web of Science was conducted. Studies including fewer than 10 patients were excluded. Studies were divided into the following main prediction groups: (1) injury pattern, (2) hemorrhage/need for transfusion, (3) emergency intervention, (4) ICU/length of hospital stay, and (5) mortality.

Results

Thirty-six articles met the inclusion criteria; among these were two prospective and thirty-four retrospective case series. Publication dates ranged from 2000 to 2020 and included 32 different first authors. A total of 18,586,929 patients were included in the prediction models. Mortality was the most represented main prediction group (n = 19). ML models used were artificial neural network ( n = 15), singular vector machine (n = 3), Bayesian network (n = 7), random forest (n = 6), natural language processing (n = 2), stacked ensemble classifier [SuperLearner (SL), n = 3], k-nearest neighbor (n = 1), belief system (n = 1), and sequential minimal optimization (n = 2) models. Thirty articles assessed results as positive, five showed moderate results, and one article described negative results to their implementation of the respective prediction model.

Conclusions

While the majority of articles show a generally positive result with high accuracy and precision, there are several requirements that need to be met to make the implementation of such models in daily clinical work possible. Furthermore, experience in dealing with on-site implementation and more clinical trials are necessary before the implementation of ML techniques in clinical care can become a reality.

Predictors of transfusion in trauma and their utility in the prehospital environment: a scoping review

Background: Hemorrhage is a leading cause of preventable mortality from trauma, necessitating resuscitation through blood product transfusions. Early and accurate identification of patients requiring transfusions in the prehospital setting may reduce delays in time to transfusion upon arrival to hospital, reducing mortality. The purpose of this study is to characterize existing literature on predictors of transfusion and analyze their utility in the prehospital context.Objectives: The objectives of this study are to characterize the existing quantity and quality of literature regarding predictor scores for transfusion in injured patients, and to analyse the utility of predictor scores for massive transfusions in the prehospital setting and identify prehospital predictor scores for future research.Methods: A search strategy was developed in consultation with information specialists. A literature search of OVID MEDLINE from 1946 to present was conducted for primary studies evaluating the predictive ability of scoring systems or single variables in predicting transfusion in all trauma settings.Results: Of the 5824 studies were identified, 5784 studies underwent title and abstract screening, 94 studies underwent full text review, and 72 studies were included in the final review. We identified 16 single variables and 52 scoring systems for predicting transfusion. Amongst single predictor variables, fluids administered and systolic blood pressure had the highest reported sensitivity (100%) and specificity (89%) for massive transfusion protocol (MTP) activation respectively. Amongst scoring systems for transfusion, the Shock Index and Modified Shock Index had the highest reported sensitivity (96%), while the Pre-arrival Model had the highest reported specificity (95%) for MTP activation. Overall, 20 scores were identified as being applicable to the prehospital setting, 25 scores were identified as being potentially applicable, and seven scores were identified as being not applicable.Conclusions: We identified an extensive list of predictive single variables, validated scoring systems, and derived models for massive transfusion, presented their properties, and identified those with potential utility in the prehospital setting. By further validating applicable scoring tools in the prehospital setting, we may begin to administer more timely transfusions in the trauma population.

Massive Transfusion Protocol Predictive Modeling in the Modern Electronic Medical Record

Objectives

Integrate a predictive model for massive transfusion protocol (MTP) activation and delivery in the electronic medical record (EMR) using prospectively gathered data; externally validate the model and assess the accuracy and precision of the model over time.

Background

The Emory model for predicting MTP using only four input variables was chosen to be integrated into our hospital's EMR to provide a real time clinical decision support tool. The continuous variable output allows for periodic re-calibration of the model to optimize sensitivity and specificity.

Methods

Prospectively collected data from level 1 and 2 trauma activations were used to input heart rate, systolic blood pressure, base excess (BE) and mechanism of injury into the EMR-integrated model for predicting MTP activation and delivery. MTP delivery was defined as: 6 units of packed red blood cells/6 hours (MTP1) or 10 units in 24 hours (MTP2). The probability of MTP was reported in the EMR. ROC and PR curves were constructed at 6, 12, and 20 months to assess the adequacy of the model.

Results

Data from 1162 patients were included. Areas under ROC for MTP activation, MTP1 and MTP2 delivery at 6, 12, and 20 months were 0.800, 0.821, and 0.831; 0.796, 0.861, and 0.879; and 0.809, 0.875, and 0.905 (all P < 0.001). The areas under the PR curves also improved, reaching values at 20 months of 0.371, 0.339, and 0.355 for MTP activation, MTP1 delivery, and MTP2 delivery.

Conclusions

A predictive model for MTP activation and delivery was integrated into our EMR using prospectively collected data to externally validate the model. The model's performance improved over time. The ability to choose the cut-points of the ROC and PR curves due to the continuous variable output of probability of MTP allows one to optimize sensitivity or specificity.

Machine learning for predicting preoperative red blood cell demand

BACKGROUND

The paucity of accurate quantitative standards for determining the quantity of red blood cells (RBCs) needed for perioperative patients and the predominant application of the "preoperative hemoglobin + surgery type" empirical decision-making model have led to widespread RBC application problems.

OBJECTIVE

The mathematical model of preoperative variables constructed by machine learning (ML) methods can help doctors decide preoperative RBC applications.

METHODS

We retrospectively analysed 130 996 records of patients who received surgery in our hospital from January 2011 to June 2017. Through the analysis of multiple preoperative parameters that may affect the RBC transfusion volume, we used ML algorithms to build up the artificial intelligence (AI) model to predict the accurate RBC demand quantity and compared each result with those predicted by clinicians.

RESULTS

Among the seven ML algorithms, the light gradient boosting machine (Lightgbm) algorithm was the best. The AI model predicted whether the patients needed RBC transfusion, and the area under curve (AUC) was 0.908 (95% CI 0.907-0.913). The AI model was more accurate than doctors in predicting RBC of 0, 2, and 4 units (85% data), with RMSEs of 1.61 vs. 2.15, 1.06 vs. 1.21, and 1.46 vs. 1.68, respectively. However, the AI model was not better than doctors in 1, 3, 5-6, 7-8, and 9-10 units (15% data), with RMSEs of 0.92 vs. 0.89, 0.92 vs. 0.89, 2.73 vs. 1.94, 4.53 vs. 3.92, and 6.26 vs. 5.08, respectively.

CONCLUSION

Through the comparison of seven ML methods, the Lightgbm algorithm-based model is more accurate than clinician experience-based in predicting preoperative RBC transfusion, which reduces the risk of untimely blood supply caused by insufficient preoperative blood preparation, and reduces the unnecessary cost of blood compatibility testing caused by excessive preoperative blood preparation.

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.

The Extremity/Mechanism/Shock Index/GCS (EMS-G) score: A novel pre-hospital scoring system for early and appropriate MTP activation

BACKGROUND

Numerous in-hospital scoring systems to activate massive transfusion protocols (MTP) have been proposed; however, to date, pre-hospital scoring systems have not been robustly validated. Many trauma centers do not have blood or pre-thawed plasma available in the trauma bay, leading to delays in balanced transfusion. This study aims to assess pre-hospital injury and physiologic parameters to develop a pre-hospital scoring system predictive of need for massive transfusion (MT) prior to patient arrival.

METHODS

A retrospective review of all adult full and partial trauma team activations from July 2014-July 2018 from an urban level 2 trauma center was performed utilizing our trauma registry. Stepwise logistic regression analysis was performed to develop a new scoring system, with point totals assigned proportional to the odds ratios of requiring MT for each variable. Internal validation of the EMS-G score was performed using a subset of the data which was not utilized for development of the scoring system, and sensitivity and specificity were compared to previously validated in-hospital scoring systems applied in the pre-hospital setting.

RESULTS

763 patients were included with 94 patients (12.3%) receiving early MT, defined as 4 units pRBC in 4 h or ED death. In-hospital models for predicting MT such as Assessment of Blood Consumption (ABC) or Shock Index (SI) have sensitivities and specificities of 46/85% and 94/79% respectively for early MTP utilization based on pre-hospital data. Pre-hospital variables found to be predictive of MT were used to develop the EMS-G (Extremity, Mechanism, Shock Index, GCS) score. This system assigns obvious extremity injury-1-point, penetrating mechanism -2 points, shock index ≥0.9-2 points, GCS ≤8-3 points. A score of 3 or greater was chosen to maximize sensitivity and specificity for pre-hospital MT activation. EMS-G score based on pre-hospital report is 89% sensitive, 84% specific, with a PPV of 44% and NPV of 98% for early MT. Using this system, 25% of full and partial trauma team activations met criteria for pre-hospital MTP activation.

CONCLUSION

The EMS-G Score has increased sensitivity and specificity compared to the ABC Score in the pre-hospital setting and appears more appropriate than shock index alone at predicting massive transfusion. This scoring system allows trauma centers to activate MTP prior to patient arrival to ensure early and appropriate blood product administration without blood product wastage.