Predictive modelling of transport decisions and resources optimisation in pre-hospital setting using machine learning techniques.

BACKGROUND: The global evolution of pre-hospital care systems faces dynamic challenges, particularly in multinational settings. Machine learning (ML) techniques enable the exploration of deeply embedded data patterns for improved patient care and resource optimisation. This study's objective was to accurately predict cases that necessitated transportation versus those that did not, using ML techniques, thereby facilitating efficient resource allocation. METHODS: ML algorithms were utilised to predict patient transport decisions in a Middle Eastern national pre-hospital emergency medical care provider. A comprehensive dataset comprising 93,712 emergency calls from the 999-call centre was analysed using R programming language. Demographic and clinical variables were incorporated to enhance predictive accuracy. Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) algorithms were trained and validated. RESULTS: All the trained algorithm models, particularly XGBoost (Accuracy = 83.1%), correctly predicted patients' transportation decisions. Further, they indicated statistically significant patterns that could be leveraged for targeted resource deployment. Moreover, the specificity rates were high; 97.96% in RF and 95.39% in XGBoost, minimising the incidence of incorrectly identified "Transported" cases (False Positive). CONCLUSION: The study identified the transformative potential of ML algorithms in enhancing the quality of pre-hospital care in Qatar. The high predictive accuracy of the employed models suggested actionable avenues for day and time-specific resource planning and patient triaging, thereby having potential to contribute to pre-hospital quality, safety, and value improvement. These findings pave the way for more nuanced, data-driven quality improvement interventions with significant implications for future operational strategies.

Epidemiology of prehospital emergency calls according to patient transport decision in a middle eastern emergency care environment: Retrospective cohort-based.

Background and Aim: Though emergency medical services (EMS) respond to all types of emergency calls, they do not always result in the patient being transported to the hospital. This study aimed to explore the determinants influencing emergency call-response-based conveyance decisions in a Middle Eastern ambulance service. Methods: This retrospective quantitative analysis of 93,712 emergency calls to the Hamad Medical Corporation Ambulance Service (HMCAS) between January 1 and May 31, 2023, obtained from the HMCAS electronic system, was analyzed to determine pertinent variables. Sociodemographic, emergency dispatch-related, clinical, and miscellaneous predictors were analyzed. Descriptive, bivariate, ridge logistic regression, and combination analyses were evaluated. Results: 23.95% (N = 21,194) and 76.05% (N = 67,285) resulted in patient nontransport and transportation, respectively. Sociodemographic analysis revealed that males predominantly activated EMS resources, and 60% of males (n = 12,687) were not transported, whilst 65% of females (n = 44,053) were transported. South Asians represented a significant proportion of the transported patients (36%, n = 24,007). "Home" emerged as the primary emergency location (56%, n = 37,725). Bivariate analysis revealed significant associations across several variables, though multicollinearity was identified as a challenge. Ridge regression analysis underscored the role of certain predictors, such as missing provisional diagnoses, in transportation decisions. The upset plot shows that hypertension and diabetes mellitus were the most common combinations in both groups. Conclusions: This study highlights the nuanced complexities governing conveyance decisions. By unveiling patterns such as male predominance, which reflects Qatar's expatriate population, and specific temporal EMS activity peaks, this study accentuates the importance of holistic patient assessment that transcends medical histories.

Exploring factors influencing time from dispatch to unit availability according to the transport decision in the pre-hospital setting: an exploratory study.

BACKGROUND: Efficient resource distribution is important. Despite extensive research on response timings within ambulance services, nuances of time from unit dispatch to becoming available still need to be explored. This study aimed to identify the determinants of the duration between ambulance dispatch and readiness to respond to the next case according to the patients' transport decisions. METHODS: Time from ambulance dispatch to availability (TDA) analysis according to the patients' transport decision (Transport versus Non-Transport) was conducted using R-Studio™ for a data set of 93,712 emergency calls managed by a Middle Eastern ambulance service from January to May 2023. Log-transformed Hazard Ratios (HR) were examined across diverse parameters. A Cox regression model was utilised to determine the influence of variables on TDA. Kaplan-Meier curves discerned potential variances in the time elapsed for both cohorts based on demographics and clinical indicators. A competing risk analysis assessed the probabilities of distinct outcomes occurring. RESULTS: The median duration of elapsed TDA was 173 min for the transported patients and 73 min for those not transported. The HR unveiled Significant associations in various demographic variables. The Kaplan-Meier curves revealed variances in TDA across different nationalities and age categories. In the competing risk analysis, the 'Not Transported' group demonstrated a higher incidence of prolonged TDA than the 'Transported' group at specified time points. CONCLUSIONS: Exploring TDA offers a novel perspective on ambulance services' efficiency. Though promising, the findings necessitate further exploration across diverse settings, ensuring broader applicability. Future research should consider a comprehensive range of variables to fully harness the utility of this period as a metric for healthcare excellence.

Enhancing Patient Safety in Prehospital Environment: Analyzing Patient Perspectives on Non-Transport Decisions With Natural Language Processing and Machine Learning.

OBJECTIVE: This research explored the experiences and perspectives of patients declining hospital transportation after receiving prehospital emergency care using advanced computational techniques. METHOD: Between 15th June and 1st August 2023, 210 patients in Qatar, treated by Hamad Medical Corporation Ambulance Service (HMCAS) but refusing transportation to hospital, were interviewed. Key outcome variables stratified by demographics included "reasons for refusing transport," "satisfaction with HMCAS service," and "postrefusal actions." Responses underwent sentiment analysis and topic modeling using latent Dirichlet allocation. Machine learning models, such as Naïve Bayes, K-nearest neighboring, random forest, and support vector machine, were used to predict patients' subsequent actions. RESULTS: Participants had an average age of 38.61 ± 19.91 years. The chief complaints were primarily chest and abdominal pains (18.49%; n = 39). Sentiment Analysis revealed a generally favorable perception of HMCAS-provided service. Latent Dirichlet allocation identified two main topics pertaining to refusal reasons and service satisfaction. Naïve Bayes and support vector machine algorithms were most effective in predicting postrefusal actions with an accuracy rate of 81.58%. CONCLUSIONS: This study highlighted the utility of Natural Language Processing and ML in enhancing our understanding of patient behaviors and sentiments in prehospital settings. These advanced computational methodologies allowed for a nuanced exploration of patient demographics and sentiments, providing insights for Quality Improvement initiatives. The study also advocates for continuously integrating automated feedback mechanisms to improve patient-centered care in the prehospital context. Continuous integration of automated feedback systems is recommended to improve prehospital patient-centered care.

Understanding patient non-transport decision theories in the pre-hospital setting: a narrative review.

BACKGROUND: In pre-hospital emergency care, decisions regarding patient non-conveyance emerged as significant determinants of healthcare outcomes and resource utilization. These complex decisions became integral to the progress of emergency medical services, thus warranting an evolving exploration within the medical discourse. OBJECTIVES AND METHODS: This narrative review aimed to synthesize and critically evaluate various theoretical stances on patient non-conveyance in the pre-hospital emergency. The focus on studies published between January 2012 and August 2022 was intentional to capture contemporary practices and insights. PubMed and Google Scholar served as the primary databases for the investigation, while the AL-Rayyan® software facilitated a thorough screening process. RESULTS AND DISCUSSION: Twenty-nine studies-encompassing articles, books, and theses-were discovered through our search, each presenting unique perspectives on patient non-transport, thus highlighting its criticality as a healthcare concern. Predominant factors influencing non-transport decisions were classified into patient-initiated refusals (PIR), clinician-initiated decisions (CID), and dispatcher-initiated decisions (DID). CONCLUSIONS: The issue of patient non-conveyance to hospitals continues to pose a crucial challenge to the seamless operation of emergency healthcare systems, warranting increased attention from various healthcare entities. To comprehend and pinpoint potential areas of improvement, a comprehensive analysis of pre-hospital non-transport events is imperative. A well-informed, strategic approach could prevent resource waste while ensuring patients receive the required and definitive care. KEY MESSAGES: Why is this topic important? Some studies have suggested that non-transport to hospitals following emergency calls is safe. However, it is a concerning issue for health systems. It is also considered a key performance metric for health systems. What does this review attempt to show? This review aimed to map the various factors discussed in the literature regarding the decisions not to transport patients following emergency calls in a pre-hospital setting. What are the key findings? The existing theories regarding non-transport to hospitals after the provision of emergency care in the pre-hospital setting were identified. Non-transport due to non-clinical decisions jeopardizes emergency care outcomes for paediatric and elderly patients in particular. Hence, further research is required to identify and control the factors governing these decisions. How is patient care impacted? The decisions regarding patient transport following emergency calls in a pre-hospital setting are crucial for patient outcomes. They could impact the pre-hospital emergency care outcomes as well as patient safety. They can also affect the emergency services resources' ability to respond to other critical emergencies.

Epidemiological Determinants of Patient Non-Conveyance to the Hospital in an Emergency Medical Service Environment.

BACKGROUND: The increasing prevalence of comorbidities worldwide has spurred the need for time-effective pre-hospital emergency medical services (EMS). Some pre-hospital emergency calls requesting EMS result in patient non-conveyance. Decisions for non-conveyance are sometimes driven by the patient or the clinician, which may jeopardize the patients' healthcare outcomes. This study aimed to explore the distribution and determinants of patient non-conveyance to hospitals in a Middle Eastern national Ambulance Service that promotes the transportation of all emergency call patients and does not adopt clinician-based non-conveyance decision. METHODS: Using R Language, descriptive, bivariate, and binary logistic regression analyses were conducted for 334,392 multi-national patient non-conveyance emergency calls from June 2018 to July 2022, from a total of 1,030,228 calls to which a response unit was dispatched. RESULTS: After data pre-processing, 237,862 cases of patient non-conveyance to hospital were retained, with a monthly average of 41.96% (n = 8799) of the emergency service demands and a standard deviation of 5.49% (n = 2040.63). They predominantly involved South Asians (29.36%, n = 69,849); 64.50% (n = 153,427) were of the age category from 14 to 44 years; 61.22% (n = 145,610) were male; 74.59% (n = 177,424) from the urban setting; and 71.28% (n = 169,552) had received on-scene treatment. Binary logistic regression with full variables and backward methods identified the final models of the determinants of patient non-conveyance decisions with an Akaike information criterion prediction estimator, respectively, of (250,200) and (250,169), indicating no significant difference between both models (Chi-square test; p-value = 0.63). CONCLUSIONS: Despite exercising a cautious protocol by encouraging patient transportation to hospital, patient non-conveyance seems to be a problem in the healthcare system that strains the pre-hospital medical response teams' resources. Policies and regulations should be adopted to encourage individuals to access other primary care centers when required rather than draining emergency services for non-emergency situations.

Exploring pre-hospital healthcare workers' readiness for chemical, biological, radiological, and nuclear threats in the State of Qatar: A cross-sectional study.

Background: Hazardous Material-Chemical, Biological, Radiological, and Nuclear (HazMat-CBRN) incidents, though infrequent, are environmentally precarious and perilous to living beings. They can be deliberate or accidental or follow the re-emergence of highly contagious diseases. Successful management of such incidents in pre-hospital settings requires having well-trained and prepared healthcare workers. Aims: This study aimed to explore the reliability and validity of a satisfaction survey, answered by Specialized Emergency Management (SEM) personnel from a national Middle Eastern ambulance service, with a "Hazardous Material Incident Management" course offered to them as a continuing professional development activity and seek their opinion regarding Hamad Medical Corporation Ambulance Service personnel needs for other HazMat-CBRN related training topics. Method: In the cross-sectional study, we conducted an online satisfaction survey for this group of course participants to obtain their feedback as subject matter experts. Aiken's content validity coefficient (CVC) was calculated to assess the content validity. Cronbach's α coefficient was determined to explore the survey's reliability. IBM®-SPSS® version 26 was utilized to explore the data. Results: The SEM satisfaction survey demonstrated important satisfaction with the implemented training with its robust reliability and content validity (Cronbach's α = 0.922 and CVC = 0.952). The participants also recommended additional related topics. Conclusion: Sustaining and reinforcing the HazMat-CBRN Incident Management course was strongly recommended, considering the increase of HazMat-CBRN threats worldwide.

Risk assessment of occupational exposure to heavy metal mixtures: a study protocol.

BACKGROUND: Sfax is a very industrialized city located in the southern region of Tunisia where heavy metals (HMs) pollution is now an established matter of fact. The health of its residents mainly those engaged in industrial metals-based activities is under threat. Indeed, such workers are being exposed to a variety of HMs mixtures, and this exposure has cumulative properties. Whereas current HMs exposure assessment is mainly carried out using direct air monitoring approaches, the present study aims to assess health risks associated with chronic occupational exposure to HMs in industry, using a modeling approach that will be validated later on. METHODS: To this end, two questionnaires were used. The first was an identification/descriptive questionnaire aimed at identifying, for each company: the specific activities, materials used, manufactured products and number of employees exposed. The second related to the job-task of the exposed persons, workplace characteristics (dimensions, ventilation, etc.), type of metals and emission configuration in space and time. Indoor air HMs concentrations were predicted, based on the mathematical models generally used to estimate occupational exposure to volatile substances (such as solvents). Later on, and in order to validate the adopted model, air monitoring will be carried out, as well as some biological monitoring aimed at assessing HMs excretion in the urine of workers volunteering to participate. Lastly, an interaction-based hazard index HIint and a decision support tool will be used to predict the cumulative risk assessment for HMs mixtures. DISCUSSION: One hundred sixty-one persons working in the 5 participating companies have been identified. Of these, 110 are directly engaged with HMs in the course of the manufacturing process. This model-based prediction of occupational exposure represents an alternative tool that is both time-saving and cost-effective in comparison with direct air monitoring approaches. Following validation of the different models according to job processes, via comparison with direct measurements and exploration of correlations with biological monitoring, these estimates will allow a cumulative risk characterization.

A case study on co-exposure to a mixture of organic solvents in a Tunisian adhesive-producing company.

OBJECTIVES: to assess environmental and biological monitoring of exposure to organic solvents in a glue-manufacturing company in Sfax, Tunisia. METHODS: Exposure of volunteer workers, in the solvented glue-work-stations, in the control laboratory and in the storage rooms of the finished products, was assessed through indoor-air and urine measurements. Informed consent of the workers was obtained. RESULTS AND DISCUSSION: The exposure indexes were found with high values in the solvented workshop as well as in the control laboratory and were respectively, 8.40 and 3.12. These indexes were also correlated with hexane and toluene indoor air concentrations. As to urine, the obtained results for the 2,5-hexandione and hippuric acid, metabolites of hexane and toluene, respectively, were in accord with the indoor-air measurements, with an average of 0.46 mg/l and 1240 mg/g of creatinine. CONCLUSION: This study assessed for the first time biological exposure to organic solvents used in Tunisian adhesive industries. Although values are likely to underestimate true exposure levels, some figures exceed European and American occupational exposure guidelines.

Effect of chronic and subchronic organic solvents exposure on balance control of workers in plant manufacturing adhesive materials.

High-level occupational exposure to volatile organic solvents may elicit neurotoxic effects, especially on central and peripheral structures involved in balance ability. Studies on balance control in relation with exposure levels close to the threshold limit values are scarce. This study aimed to assess the neurotoxic effects of chronic and subchronic exposure to organic solvents among workers in plant manufacturing adhesive materials. Balance control was evaluated in 18 subjects, mainly exposed to n-hexane and toluene, with current median exposure levels of 222 and 102 mg/m(3), respectively, and a median exposure duration of 21 years, and in 32 nonexposed controls, using posturography tests with and without sensory conflicting situations. Tests were undergone at the beginning of the work shift (chronic exposure) following a week end, and after 72 h (subchronic exposure). Balance control performance was lower in chronically exposed workers compared to controls, and got worse after subchronic exposure, particularly during situations, where vestibular information was important. Our study suggests that a low-level and prolonged exposure to volatile organic solvents, mainly n-hexane and toluene, in the workplace is associated with deleterious central effects involved in postural regulation. This neurotoxicity is characterized by difficulties to use the most relevant information to control balance, leading to altered management of sensory conflicting situations.

Automated method for clinic and morphologic analysis of bones using implicit modeling technique.

Bone morphology and moprhometric estimation provide important and useful information for computed assisted-surgery, follow-up evaluation and personalized prosthesis design. Obtaining this data without any operator supervision or setting remains a practical goal. We present here an automated method that estimates clinic, anatomic and morphometric parameters based on bone-mesh representation. The method uses 2 steps. In the first one, the bone of interest is introduced as an implicit function modeling its morphology as a quadric surface. This function blends together basic geometries such as spheres, cylinders, quadratics and superquadratics and approximates its external shape. Given a mesh representation of a patient-bone, Levenber-Marquardt optimization technique computes Cartesian coordinates of the basic geometries. In second step, heuristic plans use these spatial data to locate, through the mesh representation, punctual landmarks. In order to compute subsequently complex clinic and anatomic landmarks relatives to axes, curves, surfaces, and regions, compound-heuristic plans are dressed using implicit parameters and previous punctual landmarks. Each plan is expressed as a energy-cost function that involves geometric, radial and normal terms. The method has been successfully used to locate clinic, anatomic and morphometric parameters of femur bone. Validation of the technique is performed with qualitative and quantitative procedures. A total of 9 femurs are reconstructed using a retroprojection technique. In all models, the method converges to the same parameters with acceptable clinical accuracy. As automated method, this schema presents practical advantage and remains sufficiently general to be applied to other bones and tracks most of anatomic parameters.