Are you bleeding? Validation of a machine-learning algorithm for determination of blood volume status: application to remote triage

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.

Central Hypovolemia Detection During Environmental Stress-A Role for Artificial Intelligence?

The first step to exercise is preceded by the required assumption of the upright body position, which itself involves physical activity. The gravitational displacement of blood from the chest to the lower parts of the body elicits a fall in central blood volume (CBV), which corresponds to the fraction of thoracic blood volume directly available to the left ventricle. The reduction in CBV and stroke volume (SV) in response to postural stress, post-exercise, or to blood loss results in reduced left ventricular filling, which may manifest as orthostatic intolerance. When termination of exercise removes the leg muscle pump function, CBV is no longer maintained. The resulting imbalance between a reduced cardiac output (CO) and a still enhanced peripheral vascular conductance may provoke post-exercise hypotension (PEH). Instruments that quantify CBV are not readily available and to express which magnitude of the CBV in a healthy subject should remains difficult. In the physiological laboratory, the CBV can be modified by making use of postural stressors, such as lower body "negative" or sub-atmospheric pressure (LBNP) or passive head-up tilt (HUT), while quantifying relevant biomedical parameters of blood flow and oxygenation. Several approaches, such as wearable sensors and advanced machine-learning techniques, have been followed in an attempt to improve methodologies for better prediction of outcomes and to guide treatment in civil patients and on the battlefield. In the recent decade, efforts have been made to develop algorithms and apply artificial intelligence (AI) in the field of hemodynamic monitoring. Advances in quantifying and monitoring CBV during environmental stress from exercise to hemorrhage and understanding the analogy between postural stress and central hypovolemia during anesthesia offer great relevance for healthy subjects and clinical populations.

A review on utilizing machine learning technology in the fields of electronic emergency triage and patient priority systems in telemedicine: Coherent taxonomy, motivations, open research challenges and recommendations for intelligent future work

BACKGROUND

With the remarkable increasing in the numbers of patients, the triaging and prioritizing patients into multi-emergency level is required to accommodate all the patients, save more lives, and manage the medical resources effectively. Triaging and prioritizing patients becomes particularly challenging especially for the patients who are far from hospital and use telemedicine system. To this end, the researchers exploiting the useful tool of machine learning to address this challenge. Hence, carrying out an intensive investigation and in-depth study in the field of using machine learning in E-triage and patient priority are essential and required.

OBJECTIVES

This research aims to (1) provide a literature review and an in-depth study on the roles of machine learning in the fields of electronic emergency triage (E-triage) and prioritize patients for fast healthcare services in telemedicine applications. (2) highlight the effectiveness of machine learning methods in terms of algorithms, medical input data, output results, and machine learning goals in remote healthcare telemedicine systems. (3) present the relationship between machine learning goals and the electronic triage processes specifically on the: triage levels, medical features for input, outcome results as outputs, and the relevant diseases. (4), the outcomes of our analyses are subjected to organize and propose a cross-over taxonomy between machine learning algorithms and telemedicine structure. (5) present lists of motivations, open research challenges and recommendations for future intelligent work for both academic and industrial sectors in telemedicine and remote healthcare applications.

METHODS

An intensive research is carried out by reviewing all articles related to the field of E-triage and remote priority systems that utilise machine learning algorithms and sensors. We have searched all related keywords to investigate the databases of Science Direct, IEEE Xplore, Web of Science, PubMed, and Medline for the articles, which have been published from January 2012 up to date.

RESULTS

A new crossover matching between machine learning methods and telemedicine taxonomy is proposed. The crossover-taxonomy is developed in this study to identify the relationship between machine learning algorithm and the equivalent telemedicine categories whereas the machine learning algorithm has been utilized. The impact of utilizing machine learning is composed in proposing the telemedicine architecture based on synchronous (real-time/ online) and asynchronous (store-and-forward / offline) structure. In addition to that, list of machine learning algorithms, list of the performance metrics, list of inputs data and outputs results are presented. Moreover, open research challenges, the benefits of utilizing machine learning and the recommendations for new research opportunities that need to be addressed for the synergistic integration of multidisciplinary works are organized and presented accordingly.

DISCUSSION

The state-of-the-art studies on the E-triage and priority systems that utilise machine learning algorithms in telemedicine architecture are discussed. This approach allows the researchers to understand the modernisation of healthcare systems and the efficient use of artificial intelligence and machine learning. In particular, the growing worldwide population and various chronic diseases such as heart chronic diseases, blood pressure and diabetes, require smart health monitoring systems in E-triage and priority systems, in which machine learning algorithms could be greatly beneficial.

CONCLUSIONS

Although research directions on E-triage and priority systems that use machine learning algorithms in telemedicine vary, they are equally essential and should be considered. Hence, we provide a comprehensive review to emphasise the advantages of the existing research in multidisciplinary works of artificial intelligence, machine learning and healthcare services.

Reducing waiting time for remote patients in telemedicine with considering treated patients in emergency department based on body sensors technologies and hybrid computational algorithms: Toward scalable and efficient real time healthcare monitoring system

BACKGROUND

Scalability challenge in real time healthcare monitoring system relates to several issues. One of the insistent issues is the increasing in the number of patients. Increasing in the patients' number causes long queue and increase the waiting time for the patients in their seeking for healthcare services. Thus, an ethical issue raises as the healthcare providers should provide fast services for all patients. Recent studies have proposed scalable models that are limited to (1) triaging remote patients for the optimal emergency level and (2) prioritizing remote patients with the highest triage level to receive immediate healthcare services. However, these studies have shown limitations, that is, (1) they have not addressed the waiting time for all patients with different triage levels in the same waiting queue; and (2) they have not considered Emergency Department EDs patients. Therefore, considering the remote patients with the treated patients in EDs in one healthcare system is a demand, to efficiently handle all the patients' requests and productively manage the medical resources.

OBJECTIVE

This study aims to reduce the waiting time for the remote patients in telemedicine with considering treated patients in EDs. The study presents a scalable telemedicine model to improve the ability of real time healthcare monitoring system in accommodating the increasing number of patients with chronic heart disease by reducing their waiting time for healthcare services, prioritizing the patients who have the most emergency cases and provide all the patients by fast healthcare services. The proposed model called Triaging and Prioritizing Model "TPM".

METHOD

The proposed model "TPM" considers triaging and prioritizing all patients (remote and EDs patients) as two sequential processes. The TPM was formulated to triage the patients based on hybrid algorithms which combine Evidence-Theory with Fuzzy Cluster Means (FCM) and then prioritize the patients based on dedicated computational algorithm. A simulation, on 580 chronic heart diseases patients, was implemented. The patients considered as they have different emergency levels based on four vital data acquisition tools: electrocardiogram sensor, blood pressure sensor, oxygen saturation sensor and a text input as non-sensory based acquisition tool.

RESULTS

Computational results show the superiority of the proposed model (TPM) in accommodating large numbers of patients and reducing their waiting time for services compared with relevant benchmark studies. In 1,185 min, TPM managed the (580) patients' requests. By contrast, the benchmark managed only 256 patients at the same amount of time. In addition to that, TPM shows improvements in terms of waiting time and services provisioning rates compared with benchmark methods.

CONCLUSION

All patients with the different emergency levels receive services with less waiting time compared with the relevant studies. The proposed model (TPM) model considers both of remote patients and treated patients in EDs efficiently. TPM improves response time for the medical services, reduces waiting time for all patients and consequently, saves more lives.

Prediction of Recovery From Severe Hemorrhagic Shock Using Logistic Regression

This paper implements logistic regression models (LRMs) and feature selection for creating a predictive model for recovery form hemorrhagic shock (HS) with resuscitation using blood in the multiple experimental rat animal protocols. A total of 61 animals were studied across multiple HS experiments, which encompassed two different HS protocols and two resuscitation protocols using blood stored for short periods using five different techniques. Twenty-seven different systemic hemodynamics, cardiac function, and blood gas parameters were measured in each experiment, of which feature selection deemed only 25% of the them as relevant. The reduced feature set was used to train a final logistic regression model. A final test set accuracy is 84% compared to 74% for a baseline classifier using only MAP and HR measurements. Receiver operating characteristics (ROC) curve analysis and Cohens kappa statistics were also used as measures of performance, with the final reduced model outperforming the model, including all parameters. Our results suggest that LRMs trained with a combination of systemic hemodynamics, cardiac function, and blood gas parameters measured at multiple timepoints during HS can successfully classify HS recovery groups. Our results show the predictive ability of traditional and novel hemodynamic and cardiac function features and their combinations, many of which had not previously been taken into consideration, for monitoring HS. Furthermore, we have devised an effective methodology for feature selection and shown ways in which the performance of such predictive models should be assessed in future studies.

Activity modification in heat: critical assessment of guidelines across athletic, occupational, and military settings in the USA

Exertional heat illness (EHI) risk is a serious concern among athletes, laborers, and warfighters. US Governing organizations have established various activity modification guidelines (AMGs) and other risk mitigation plans to help ensure the health and safety of their workers. The extent of metabolic heat production and heat gain that ensue from their work are the core reasons for EHI in the aforementioned population. Therefore, the major focus of AMGs in all settings is to modulate the work intensity and duration with additional modification in adjustable extrinsic risk factors (e.g., clothing, equipment) and intrinsic risk factors (e.g., heat acclimatization, fitness, hydration status). Future studies should continue to integrate more physiological (e.g., valid body fluid balance, internal body temperature) and biometeorological factors (e.g., cumulative heat stress) to the existing heat risk assessment models to reduce the assumptions and limitations in them. Future interagency collaboration to advance heat mitigation plans among physically active population is desired to maximize the existing resources and data to facilitate advancement in AMGs for environmental heat.

A data-driven artificial intelligence model for remote triage in the prehospital environment

In a mass casualty incident, the factors that determine the survival rate of injured patients are diverse, but one of the key factors is the time for triage. Additionally, the main factor that determines the time of triage is the number of medical personnel. However, when relying on a small number of medical personnel, the ability to increase survivability is limited. Therefore, developing a classification model for survival prediction that can quickly and precisely triage via wearable devices without medical personnel is important. In this study, we designed a consciousness index to substitute the factor by manpower and improved the classification accuracy by applying a machine learning algorithm. First, logistic regression analysis using vital signs and a consciousness index capable of remote monitoring through wearable devices confirmed the high efficiency of the consciousness index. We then developed a classification model with high accuracy which corresponds to existing injury severity scoring systems through the machine learning algorithms. We extracted 460,865 cases which met our criteria for developing the survival prediction from the national sample project in the national trauma databank which contains 408,316 cases of blunt injury and 52,549 cases of penetrating injury. Among the dataset, 17,918 (3.9%) cases died while the other survived. The AUCs with 95% confidence intervals (CIs) for the different models with the proposed simplified consciousness score as follows: RTS (as baseline), 0.78 (95% CI = 0.775 to 0.785); logistic regression, 0.87 (95% CI = 0.862 to 0.870); random forest, 0.87 (95% CI = 0.862 to 0.872); deep neural network, 0.89 (95% CI = 0.882 to 0.890). As a result, we confirmed the possibility of remote triage using a wearable device. It is expected that the time required for triage can be effectively reduced by using the developed classification model of survival prediction.

Physiological monitoring for healthy military personnel

Military employment commonly exposes personnel to strenuous physical exertion. The resulting interaction between occupational stress and individual susceptibility to illness demands careful management. This could extend to prospective identification of high physiological strain in healthy personnel, in addition to recognition and protection of vulnerable individuals. The emergence and ubiquitous uptake of ‘wearable’ physiological and medical monitoring devices might help to address this challenge, but requires that the right questions are asked in sourcing, developing, validating and applying such technologies. Issues that must be addressed include system requirements, such as the likelihood of end users deploying and using technology as intended; interpretation of data in relation to pretest probability, including the potential for false-positive results; differentiation of pathological states from normal physiology; responsibility for and consequences of acting on abnormal or unexpected results and cost-effectiveness. Ultimately, the performance of a single monitoring system, in isolation or alongside other measures, should be judged by whether any improvement is offered versus existing capabilities and at what cost to mission effectiveness.

Arterial pressure variations as parameters of brain perfusion in response to central blood volume depletion and repletion

Rationale: A critical reduction in central blood volume (CBV) is often characterized by hemodynamic instability. Restoration of a volume deficit may be established by goal-directed fluid therapy guided by respiration-related variation in systolic- and pulse pressure (SPV and PPV). Stroke volume index (SVI) serves as a surrogate end-point of a fluid challenge but tissue perfusion itself has not been addressed.

Objective: To delineate the relationship between arterial pressure variations, SVI and regional brain perfusion during CBV depletion and repletion in spontaneously breathing volunteers.

Methods: This study quantified in 14 healthy subjects (11 male) the effects of CBV depletion [by 30 and 70 degrees passive head-up tilt (HUT)] and a fluid challenge (by tilt back) on CBV (thoracic admittance), mean middle cerebral artery (MCA) blood flow velocity (V_mean), SVI, cardiac index (CI), PPV, and SPV.

Results: PPV (103 ± 89%, p < 0.05) and SPV (136 ± 117%, p < 0.05) increased with progression of central hypovolemia manifested by a reduction in thoracic admittance (11 ± 5%, p < 0.001), SVI (28 ± 6%, p < 0.001), CI (6 ± 8%, p < 0.001), and MCAV_mean (17 ± 7%, p < 0.05) but not in arterial pressure. The reduction in MCAV_mean correlated to the fall in SVI (R² = 0.52, p < 0.0001) and inversely to PPV and SPV [R² = 0.46 (p < 0.0001) and R² = 0.45 (p < 0.0001), respectively]. PPV and SPV predicted a ≥15% reduction in MCAV_mean and SVI with comparable sensitivity (67/67% vs. 63/68%, respectively) and specificity (89/94 vs. 89/94%, respectively). A rapid fluid challenge by tilt-back restored all parameters to baseline values within 1 min.

Conclusion: In spontaneously breathing subjects, a reduction in MCAV_mean was related to an increase in PPV and SPV during graded CBV depletion and repletion. Specifically, PPV and SPV predicted changes in both SVI and MCAV_mean with comparable sensitivity and specificity, however the predictive value is limited in spontaneously breathing subjects.