Hospital preparedness assessment for road traffic accidents with mass casualties: a cross-sectional study in Kurdistan Province, Iran.

BACKGROUND: Road traffic accidents (RTAs) are predicted to become the world's seventh leading cause of death by 2030. Given the significant impact of RTAs on public health, effective hospital preparedness plays a pivotal role in managing and mitigating associated health and life-threatening issues. This study aims to meticulously evaluate the preparedness of selected hospitals in western Iran to handle road traffic accidents with mass casualties (RTAs-MC). METHODS: The study employed a descriptive-analytical approach, utilizing a reliable and valid questionnaire to measure hospitals' preparedness levels. Descriptive statistics (frequency distribution and mean) were utilized to provide an overview of the data, followed by analytical statistics (Spearman correlation test) to examine the relationship between hospital preparedness and its dimensions with the hospital profile. Data analysis, performed using SPSS software, categorized preparedness levels as weak, moderate, or high. RESULTS: The study found that hospitals in Kurdistan province had a favorable preparedness level (70.30) to respond to RTAs-MC. The cooperation and coordination domain had the highest preparedness level (98.75), while the human resource management (59.44) and training and exercise (54.00) domains had the lowest preparedness levels. The analysis revealed a significant relationship between hospital preparedness and hospital profile, including factors such as hospital specialty, number of beds, ambulances, staff, and specialized personnel, such as emergency medicine specialists. CONCLUSION: Enhancing preparedness for RTAs-MC necessitates developing response plans to improve hospital profile, considering the region's geographic and topographic features, utilizing past experiences and lessons learned, implementing of Hospital Incident Command System (HICS), providing medical infrastructure and equipment, establishing communication channels, promoting cooperation and coordination, and creating training and exercise programs.

Assessing prevalence, factors and health consequences and academic performance of undergraduate students with breakfast skipping during COVID-19 using statistical modeling: a cross-sectional study.

The study was conducted in order to study breakfast skipping (BKS) frequency, factors associated with, health consequence and undergraduate students academic performance during Covid-19 pandemic as earliest studies focusing on this area. A cross-sectional study was carried out among 2225 of undergraduate students. The study was carried between the period of 15/1/2020 to 3/4/2020 using an online self-report Breakfast Eating Habit Survey (BEHS). The BEHS survey was divided into two sections. The first sections included sociodemographic information (gender, BMI, age, smoking, residency, parental education, family income, studying system and stage (public or private), and studying institution (university or institute) academic performance. The second part included questions regarding breakfast eating habits including frequency of skipping meals, factors related to BKS health consequences and types of snacks. Logistic regression is a common technique used for modeling outcomes that fall into the range of 1 and 0. For this purpose, a logistic regression was performed to find adjusted odds ratio and crude odds ratio. The results showed that the majority of participants were female (1238, 55.7%). Out of 2,224 students, 2059 are aged between 18 to 24 years. Most of the participants were from first level (26.5%), second level (32.8%), third level (17.6%) or the fourth level (21.3%). Over 92% of participants were single and about 68% came from families of medium income families. The statistical analysis showed that the odds of BKS is reduced among students who live in accommodation by 54% (odds ratio = 54%, CI (41-71%), p value = 0.000). It seems that students with low income and normal or higher BMI are more likely to skip breakfast more regularly. The odds of skipping breakfast among students with BMI of 18-24.9 is reduced by 41% (odds ratio = 59%, CI (27%-93%), p value = 0.027) and the odds of BKS is reduced among students with BMI of 25-29.9 by 45% (odds ratio = 55%, CI (31-95%). Additionally, students with medium or high incomes are more likely to skip breakfast as much as twofold in comparison with students with low income (medium income (odds ratio = 1.85, CI (1.08-3.17), p-value = 0.024), high income (odds ratio = 1.98, CI (1.12-3.51), p-value = 0.019). The most common reasons for skipping breakfast included include time constraint, not hungry, breakfast is not ready, afraid to be overweight and lack of appetite. The consequences of skipping breakfast were feeling hungry throughout the day, feeling tired, and not paying attention in class and low academic performance. To concluded, BKS during Covid-19 is more common among students with higher BMI, higher income and living in accommodation. The main reason is time constraint and the most common health problems are being tired and luck of attention.

Improving preoperative prediction of surgery duration.

BACKGROUND: Operating rooms (ORs) are one of the costliest units in a hospital, therefore the cumulative consequences of any kind of inefficiency in OR management lead to a significant loss of revenue for the hospital, staff dissatisfaction, and patient care disruption. One of the possible solutions to improving OR efficiency is knowing a reliable estimate of the duration of operations. The literature suggests that the current methods used in hospitals, e.g., a surgeon's estimate for the given surgery or taking the average of only five previous records of the same procedure, have room for improvement. METHODS: We used over 4 years of elective surgery records (n = 52,171) from one of the major metropolitan hospitals in Australia. We developed robust Machine Learning (ML) approaches to provide a more accurate prediction of operation duration, especially in the absence of surgeon's estimation. Individual patient characteristics and historic surgery information attributed to medical records were used to train predictive models. A wide range of algorithms such as Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were tested for predicting operation duration. RESULTS: The results show that the XGBoost model provided statistically significantly less error than other compared ML models. The XGBoost model also reduced the total absolute error by 6854 min (i.e., about 114 h) compared to the current hospital methods. CONCLUSION: The results indicate the potential of using ML methods for reaching a more accurate estimation of operation duration compared to current methods used in the hospital. In addition, using a set of realistic features in the ML models that are available at the point of OR scheduling enabled the potential deployment of the proposed approach.

A discrete event simulation for improving operating theatre efficiency.

BACKGROUND: Increasing demand in healthcare services has posed excessive burden on healthcare professionals and hospitals with finite capacity. Operating theatres are critical resources within hospitals that can become bottlenecks in patient flow during high demand conditions. There are substantial costs associated with running operating theatres that include keeping professional staff ready, maintaining operating theatres and equipment, environmental services and cleaning of operating theatres and recovery rooms, and these costs can increase if theatres are not used efficiently. In addition to cost, operating theatre inefficiency can result in surgery cancelations and delays, and eventually, poor patient outcomes, which can be exacerbated under the increase in demand. METHODS: The allocation of surgeries to operating theatres is explored using a simulation model for patients admitted to inpatient beds and sent for surgery. We proposed a discrete event simulation (DES) to model incoming flow to operating theatres of a major metropolitan hospital. We assessed how changing the configuration of surgery at the target hospital affects Key Performance Indicators relating to theatre efficiency. In particular, the model was used to assess impacts of six different scenarios by defining new/hypothetical theatre case-mix, opening and closing times of theatres, turnaround (changeover) time, and repurposing the theatres. Target performance metrics included theatre utilisation, pre-operative length-of-stay, average reclaimable time, the percentage of total theatre time in a year that could be reclaimed, and patient waiting time. A web-based application was developed that allows testing user-defined scenarios and interactive analysis of the results. RESULTS: Extending the opening hours of operating theatres by 1 hour almost halved the number of deferred electives as well as over-run cases but at the expense of reduced theatre utilisation. A one-hour reduction in opening hours resulted in 10 times more deferred elective cases and a negligible increase in theatre utilisation. Reducing turnaround time by 50% had positive effects on theatre management: increased utilisation and less deferred and over-run elective cases. Pooling emergency theatres did not affect theatre utilisation but resulted in a considerable reduction in average wait time and the proportion of the delayed emergency cases. CONCLUSIONS: The developed DES-based simulation model of operating theatres along with the web-based user interface provided a useful interrogation tool for theatre management and hospital executive teams to assess new operational strategies. The next step is to embed simulation as ongoing practices in theatre planning workflow, allowing operational managers to use the model outputs to increase theatre utilisation, and reduce cancellations and schedule changes. This can support hospitals in providing services as efficiently and effectively as possible.

Daily surgery caseload prediction: towards improving operating theatre efficiency.

BACKGROUND: In many hospitals, operating theatres are not used to their full potential due to the dynamic nature of demand and the complexity of theatre scheduling. Theatre inefficiencies may lead to access block and delays in treating patients requiring critical care. This study aims to employ operating theatre data to provide decision support for improved theatre management. METHOD: Historical observations are used to predict long-term daily surgery caseload in various levels of granularity, from emergency versus elective surgeries to clinical specialty-level demands. A statistical modelling and a machine learning-based approach are developed to estimate daily surgery demand. The statistical model predicts daily demands based on historical observations through weekly rolling windows and calendar variables. The machine learning approach, based on regression algorithms, learns from a combination of temporal and sequential features. A de-identified data extract of elective and emergency surgeries at a major 783-bed metropolitan hospital over four years was used. The first three years of data were used as historical observations for training the models. The models were then evaluated on the final year of data. RESULTS: Daily counts of overall surgery at a hospital-level could be predicted with approximately 90% accuracy, though smaller subgroups of daily demands by medical specialty are less predictable. Predictions were generated on a daily basis a year in advance with consistent predictive performance across the forecast horizon. CONCLUSION: Predicting operating theatre demand is a viable component in theatre management, enabling hospitals to provide services as efficiently and effectively as possible to obtain the best health outcomes. Due to its consistent predictive performance over various forecasting ranges, this approach can inform both short-term staffing choices as well as long-term strategic planning.

Matching patients to clinical trials using semantically enriched document representation.

Recruiting eligible patients for clinical trials is crucial for reliably answering specific questions about medical interventions and evaluation. However, clinical trial recruitment is a bottleneck in clinical research and drug development. Our goal is to provide an approach towards automating this manual and time-consuming patient recruitment task using natural language processing and machine learning techniques. Specifically, our approach extracts key information from series of narrative clinical documents in patient's records and collates helpful evidence to make decisions on eligibility of patients according to certain inclusion and exclusion criteria. Challenges in applying narrative clinical documents such as differences in reporting styles and sub-languages are addressed by enriching them with knowledge from domain ontologies in the form of semantic vector representations. We show that a machine learning model based on Multi-Layer Perceptron (MLP) is more effective for the task than five other neural networks and four conventional machine learning models. Our approach achieves overall micro-F1-Score of 84% for 13 different eligibility criteria. Our experiments also indicate that semantically enriched documents are more effective than using original documents for cohort selection. Our system provides an end-to-end machine learning-based solution that achieves comparable results with the state-of-the-art which relies on hand-crafted rules or data-centric engineered features.

Quantifying semantic similarity of clinical evidence in the biomedical literature to facilitate related evidence synthesis.

OBJECTIVE: Published clinical trials and high quality peer reviewed medical publications are considered as the main sources of evidence used for synthesizing systematic reviews or practicing Evidence Based Medicine (EBM). Finding all relevant published evidence for a particular medical case is a time and labour intensive task, given the breadth of the biomedical literature. Automatic quantification of conceptual relationships between key clinical evidence within and across publications, despite variations in the expression of clinically-relevant concepts, can help to facilitate synthesis of evidence. In this study, we aim to provide an approach towards expediting evidence synthesis by quantifying semantic similarity of key evidence as expressed in the form of individual sentences. Such semantic textual similarity can be applied as a key approach for supporting selection of related studies. MATERIAL AND METHODS: We propose a generalisable approach for quantifying semantic similarity of clinical evidence in the biomedical literature, specifically considering the similarity of sentences corresponding to a given type of evidence, such as clinical interventions, population information, clinical findings, etc. We develop three sets of generic, ontology-based, and vector-space models of similarity measures that make use of a variety of lexical, conceptual, and contextual information to quantify the similarity of full sentences containing clinical evidence. To understand the impact of different similarity measures on the overall evidence semantic similarity quantification, we provide a comparative analysis of these measures when used as input to an unsupervised linear interpolation and a supervised regression ensemble. In order to provide a reliable test-bed for this experiment, we generate a dataset of 1000 pairs of sentences from biomedical publications that are annotated by ten human experts. We also extend the experiments on an external dataset for further generalisability testing. RESULTS: The combination of all diverse similarity measures showed stronger correlations with the gold standard similarity scores in the dataset than any individual kind of measure. Our approach reached near 0.80 average Pearson correlation across different clinical evidence types using the devised similarity measures. Although they were more effective when combined together, individual generic and vector-space measures also resulted in strong similarity quantification when used in both unsupervised and supervised models. On the external dataset, our similarity measures were highly competitive with the state-of-the-art approaches developed and trained specifically on that dataset for predicting semantic similarity. CONCLUSION: Experimental results showed that the proposed semantic similarity quantification approach can effectively identify related clinical evidence that is reported in the literature. The comparison with a state-of-the-art method demonstrated the effectiveness of the approach, and experiments with an external dataset support its generalisability.

Transferability of artificial neural networks for clinical document classification across hospitals: A case study on abnormality detection from radiology reports.

OBJECTIVE: Application of machine learning techniques for automatic and reliable classification of clinical documents have shown promising results. However, machine learning models require abundant training data specific to each target hospital and may not be able to benefit from available labeled data from each of the hospitals due to data variations. Such training data limitations have presented one of the major obstacles for maximising potential application of machine learning approaches in the healthcare domain. We investigated transferability of artificial neural network models across hospitals from different domains representing various age demographic groups (i.e., children, adults, and mixed) in order to cope with such limitations. MATERIALS AND METHODS: We explored the transferability of artificial neural networks for clinical document classification. Our case study was to detect abnormalities from limb X-ray reports obtained from the emergency department (ED) of three hospitals within different domains. Different transfer learning scenarios were investigated in order to employ a source hospital's trained model for addressing a target hospital's abnormality detection problem. RESULTS: A Convolutional Neural Network (CNN) model exhibited the best effectiveness compared to other networks when employing an embedding model trained on a large corpus of clinical documents. Furthermore, CNN models derived from a source hospital outperformed a conventional machine learning approach based on Support Vector Machines (SVM) when applied to a different (target) hospital. These models were further improved by leveraging available training data in target hospitals and outperformed the models that used only the target hospital data with F1-Score of 0.92-0.96 across three hospitals. DISCUSSION: Our transfer learning model used only simple vector representations of documents without any task-specific feature engineering. Transferring the CNN model significantly improved (approx.10% in F1-Score) the state-of-the-art approach for clinical document classification based on a trivial transferred model. In addition, the results showed that transfer learning techniques can further improve a CNN model that is trained only on either a source or target hospital's data. CONCLUSION: Transferring a pre-trained CNN model generated in one hospital to another facilitates application of machine learning approaches that alleviate both hospital-specific feature engineering and training data.

Identifying scientific artefacts in biomedical literature: the Evidence Based Medicine use case.

Evidence Based Medicine (EBM) provides a framework that makes use of the current best evidence in the domain to support clinicians in the decision making process. In most cases, the underlying foundational knowledge is captured in scientific publications that detail specific clinical studies or randomised controlled trials. Over the course of the last two decades, research has been performed on modelling key aspects described within publications (e.g., aims, methods, results), to enable the successful realisation of the goals of EBM. A significant outcome of this research has been the PICO (Population/Problem-Intervention-Comparison-Outcome) structure, and its refined version PIBOSO (Population-Intervention-Background-Outcome-Study Design-Other), both of which provide a formalisation of these scientific artefacts. Subsequently, using these schemes, diverse automatic extraction techniques have been proposed to streamline the knowledge discovery and exploration process in EBM. In this paper, we present a Machine Learning approach that aims to classify sentences according to the PIBOSO scheme. We use a discriminative set of features that do not rely on any external resources to achieve results comparable to the state of the art. A corpus of 1000 structured and unstructured abstracts - i.e., the NICTA-PIBOSO corpus - is used for training and testing. Our best CRF classifier achieves a micro-average F-score of 90.74% and 87.21%, respectively, over structured and unstructured abstracts, which represents an increase of 25.48 percentage points and 26.6 percentage points in F-score when compared to the best existing approaches.

A Step Towards Building Health Digital Twins: Patient Phenotype Representation for Health Outcome Prediction.

Precision medicine aims to provide more effective interventions and preventive options to patients by considering their individual risk factors and by employing available evidence. This proof of concept study presents an approach towards generating holistic virtual representations of patients, a.k.a. health digital twins. The developed virtual representations were applied in two health outcome prediction case studies for readmission and in-hospital mortality predictions. The results demonstrated the effectiveness of the virtual representations to facilitate predictive analysis in practicing precision medicine.