Search results for: classification

Authors: Dawid Jakimiuk, Krzysztof Mitura, Leszek Szpakowski, Sławomir Pilip, Daniel Celiński

Abstract:

The Emergency Medical Teams (EMS) of the Ambulance Service in Siedlce serve the population living in the Mazowieckie Voivodeship (the area of eastern Poland with approximately 550,000 inhabitants). They provide health services at the pre-hospital stage to all life-threatening patients. The analysis covered the interventions of emergency medical teams in cases of suicide attempts that occurred in the years 2015-2018. The study was retrospective. The data was obtained on the basis of digital medical records of completed call-outs. When defining the disease entity, the International Statistical Classification of Diseases and Health Problems ICD-10 prepared by WHO was used. The relationship between selected disease entities and the area of EMT intervention, the patient's sex and age, and the time of occurrence of the event were investigated. Non-urban area was defined as the area inhabited by a population below 10,000 residents. Statistical analysis was performed using Pearson's Chi ^ 2 test and presenting the percentage of cases in the study group. Of all the suicide attempts, drug abuse cases were the most frequent, including: X60 (Intentional self-poisoning by and exposure to nonopioid analgesics, antipyretics and antirheumatics); X61 (Intentional self-poisoning by and exposure to antiepileptic, sedative-hypnotic, antiparkinsonian and psychotropic drugs, not elsewhere classified); X62 (Intentional self-poisoning by and exposure to narcotics and psycholeptics [hallucinogens], not elsewhere classified); X63 (Intentional self-poisoning by and exposure to other drugs acting on the autonomic nervous system); X64 (Intentional self-poisoning by and exposure to other and unspecified drugs, medicaments and biological substance) oraz X70 (Intentional self-harm by hanging, strangulation and suffocation). In total, they accounted for 69.4% of all interventions to suicide attempts in the studied period. Statistical analysis shows significant differences (χ2 = 39.30239, p <0.0001, n = 561) between the area of EMT intervention and the type of suicide attempt. In non-urban areas, a higher percentage of X70 diagnoses was recorded (55.67%), while in urban areas, X60-X64 (72.53%). In non-urban areas, a higher proportion of patients attempting suicide was observed compared to patients living in urban areas. For X70 and X60 - X64 in total, the incidence rates in non-urban areas were 80.8% and 56%, respectively. Significant differences were found (χ2 = 119.3304, p <0.0001, n = 561) depending on the method of attempting suicide in relation to the patient's sex. The percentage of women diagnosed with X60-X64 versus X70 was 87.50%, which was the largest number of patients (n = 154) as compared to men. In the case of X70 in relation to X60-X64, the percentage of men was 62.08%, which was the largest number of patients (n = 239) as compared to women (n = 22). In the case of X70, the percentage of men compared to women was as high as 92%. Significant differences were observed (χ2 = 14.94848, p <0.01058) between the hour of EMT intervention and the type of suicide attempt. The highest percentage of X70 occurred between 04:01 - 08:00 (64.44%), while X60-X64 between 00:01 - 04:00 (70.45%). The largest number of cases of all tested suicide attempts was recorded between 16:01 - 20:00 for X70 (n = 62), X60 - X64 (n = 82), respectively. The highest percentage of patients undertaking all suicide attempts studied at work was observed in the age range of 18-30 (31.5%), while the lowest was in the age group over 60 years of age. (11%). There was no significant correlation between the day of the week or individual months of the year and the type of suicide attempt - respectively (χ2 = 6.281729, p <0.39238, n = 561) and (χ2 = 3.348913, p <0.9857, n = 561). There were also no significant differences in the incidence of suicide attempts for each year in the study period (χ2 = 3.348913, p <0.9857 n = 561). The obtained results suggest the necessity to undertake preventive measures in order to minimize the number of suicide attempts. Such activities should be directed especially at young patients living in non-urban areas.

Keywords: emergency med, emergency medical team, attempted suicide, pre-hospital

Procedia PDF Downloads 92

Authors: Mohamed Gazzeh, Bradley Null, Fethi Tlili, Hichem Besbes

Abstract:

The burgeoning global ownership of personal vehicles has posed a significant strain on urban infrastructure, notably parking facilities, leading to traffic congestion and environmental concerns. Effective parking management systems (PMS) are indispensable for optimizing urban traffic flow and reducing emissions. The most commonly deployed systems nowadays rely on computer vision technology. This paper explores the integration of radar sensors and simulation in the context of smart parking management. We concentrate on radar sensors due to their versatility and utility in automotive applications, which extends to PMS. Additionally, radar sensors play a crucial role in driver assistance systems and autonomous vehicle development. However, the resource-intensive nature of radar data collection for algorithm development and testing necessitates innovative solutions. Simulation, particularly the monoDrive simulator, an internal development tool used by NI the Test and Measurement division of Emerson, offers a practical means to overcome this challenge. The primary objectives of this study encompass simulating radar sensors to generate a substantial dataset for algorithm development, testing, and, critically, assessing the transferability of models between simulated and real radar data. We focus on occupancy detection in parking as a practical use case, categorizing each parking space as vacant or occupied. The simulation approach using monoDrive enables algorithm validation and reliability assessment for virtual radar sensors. It meticulously designed various parking scenarios, involving manual measurements of parking spot coordinates, orientations, and the utilization of TI AWR1843 radar. To create a diverse dataset, we generated 4950 scenarios, comprising a total of 455,400 parking spots. This extensive dataset encompasses radar configuration details, ground truth occupancy information, radar detections, and associated object attributes such as range, azimuth, elevation, radar cross-section, and velocity data. The paper also addresses the intricacies and challenges of real-world radar data collection, highlighting the advantages of simulation in producing radar data for parking lot applications. We developed classification models based on Support Vector Machines (SVM) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), exclusively trained and evaluated on simulated data. Subsequently, we applied these models to real-world data, comparing their performance against the monoDrive dataset. The study demonstrates the feasibility of transferring models from a simulated environment to real-world applications, achieving an impressive accuracy score of 92% using only one radar sensor. This finding underscores the potential of radar sensors and simulation in the development of smart parking management systems, offering significant benefits for improving urban mobility and reducing environmental impact. The integration of radar sensors and simulation represents a promising avenue for enhancing smart parking management systems, addressing the challenges posed by the exponential growth in personal vehicle ownership. This research contributes valuable insights into the practicality of using simulated radar data in real-world applications and underscores the role of radar technology in advancing urban sustainability.

Keywords: autonomous vehicle simulator, FMCW radar sensors, occupancy detection, smart parking management, transferability of models

Procedia PDF Downloads 81

Authors: Sam Weber, Deepak Mishra, Susan Wilde, Elizabeth Kramer

Abstract:

The frequency and severity of cyanobacteria harmful blooms (CyanoHABs) have been increasing over time, with point and non-point source eutrophication and shifting climate paradigms being blamed as the primary culprits. Excessive nutrients, warm temperatures, quiescent water, and heavy and less regular rainfall create more conducive environments for CyanoHABs. CyanoHABs have the potential to produce a spectrum of toxins that cause gastrointestinal stress, organ failure, and even death in humans and animals. To promote enhanced, proactive CyanoHAB management, risk modeling using geospatial tools can act as predictive mechanisms to supplement current CyanoHAB monitoring, management and mitigation efforts. The risk maps would empower water managers to focus their efforts on high risk water bodies in an attempt to prevent CyanoHABs before they occur, and/or more diligently observe those waterbodies. For this research, exploratory spatial data analysis techniques were used to identify the strongest predicators for CyanoHAB blooms based on remote sensing-derived cyanobacteria cell density values for 771 waterbodies in the Georgia Piedmont and landscape characteristics of their watersheds. In-situ datasets for cyanobacteria cell density, nutrients, temperature, and rainfall patterns are not widely available, so free gridded geospatial datasets were used as proxy variables for assessing CyanoHAB risk. For example, the percent of a watershed that is agriculture was used as a proxy for nutrient loading, and the summer precipitation within a watershed was used as a proxy for water quiescence. Cyanobacteria cell density values were calculated using atmospherically corrected images from the European Space Agency’s Sentinel-2A satellite and multispectral instrument sensor at a 10-meter ground resolution. Seventeen explanatory variables were calculated for each watershed utilizing the multi-petabyte geospatial catalogs available within the Google Earth Engine cloud computing interface. The seventeen variables were then used in a multiple linear regression model, and the strongest predictors of cyanobacteria cell density were selected for the final regression model. The seventeen explanatory variables included land cover composition, winter and summer temperature and precipitation data, topographic derivatives, vegetation index anomalies, and soil characteristics. Watershed maximum summer temperature, percent agriculture, percent forest, percent impervious, and waterbody area emerged as the strongest predictors of cyanobacteria cell density with an adjusted R-squared value of 0.31 and a p-value ~ 0. The final regression equation was used to make a normalized cyanobacteria cell density index, and a Jenks Natural Break classification was used to assign waterbodies designations of low, medium, or high risk. Of the 771 waterbodies, 24.38% were low risk, 37.35% were medium risk, and 38.26% were high risk. This study showed that there are significant relationships between free geospatial datasets representing summer maximum temperatures, nutrient loading associated with land use and land cover, and the area of a waterbody with cyanobacteria cell density. This data analytics approach to CyanoHAB risk assessment corroborated the literature-established environmental triggers for CyanoHABs, and presents a novel approach for CyanoHAB risk mapping in waterbodies across the greater southeastern United States.

Keywords: cyanobacteria, land use/land cover, remote sensing, risk mapping

Procedia PDF Downloads 211

Authors: Federica Verna, Alessandra Pautasso, Maria Caramelli, Cristiana Maurella, Walter Mignone, Cristina Casalone

Abstract:

Mosquito-Borne Diseases (MBDs) are dangerously increasing in prevalence, geographical distribution and severity, representing an emerging threat for both humans and animals. Interaction between multiple disciplines is needed for an effective early warning, surveillance and control of MBDs, according to the One Health concept. This work reports the integrated surveillance system enforced by IZSPLV in Piedmont, Liguria and Valle d’Aosta regions (Northwestern Italy) in order to control MDBs spread. Veterinary services and local human health authority are involved in an information network, to connect the surveillance of human clinical cases with entomological surveillance and veterinary monitoring in order to implement control measures in case of outbreak. A systematic entomological surveillance is carried out during the vector season using mosquitoes traps located in sites selected according to risk factors. Collected mosquitoes are counted, identified to species level by morphological standard classification keys and pooled by collection site, date and species with a maximum of 100 individuals. Pools are analyzed, after RNA extraction, by Real Time RT-PCR distinctive for West Nile Virus (WNV) Lineage 1 and Lineage 2, Real Time RT-PCR USUTU virus (USUV) and a traditional flavivirus End-point RT-PCR. Positive pools are sequenced and the related sequences employed to perform a basic local alignment search tool (BLAST) in the GenBank library. Positive samples are sent to the National Reference Centre for Animal Exotic Diseases (CESME, Teramo) for confirmation. With particular reference to WNV, after the confirmation, as provided by national legislation, control measures involving both local veterinary and human health services are activated: equine sera are randomly sampled within a 4 km radius from the positive collection sites and tested with ELISA kit and WNV NAT screening of blood donors is introduced. This surveillance network allowed to detect since 2011 USUV circulation in this area of Italy. WNV was detected in Piedmont and Liguria for the first time in 2014 in mosquitoes. During the 2015 vector season, we observed the expansion of its activity in Piedmont. The virus was detected in almost all Provinces both in mosquitoes (6 pools) and animals (19 equine sera, 4 birds). No blood bag tested resulted infected. The first neuroinvasive human case occurred too. Competent authorities should be aware of a potentially increased risk of MBDs activity during the 2016 vector season. This work shows that this surveillance network allowed to early detect the presence of MBDs in humans and animals, and provided useful information to public authorities, in order to apply control measures. Finally, an additional value of our diagnostic protocol is the ability to detect all viruses belonging to the Flaviviridae family, considering the emergence caused by other Flaviviruses in humans such as the recent Zika virus infection in South America. Italy has climatic and environmental features conducive to Zika virus transmission, the competent vector and many travellers from Brazil reported every year.

Keywords: integrated surveillance, mosquito borne disease, West Nile virus, Zika virus

Procedia PDF Downloads 361

Authors: Pei Yi Lin

Abstract:

Objective: The objective of this study is to use machine learning methods to build an early prediction classifier model for acute delirium to improve the quality of medical care for intensive care patients. Background: Delirium is a common acute and sudden disturbance of consciousness in critically ill patients. After the occurrence, it is easy to prolong the length of hospital stay and increase medical costs and mortality. In 2021, the incidence of delirium in the intensive care unit of internal medicine was as high as 59.78%, which indirectly prolonged the average length of hospital stay by 8.28 days, and the mortality rate is about 2.22% in the past three years. Therefore, it is expected to build a delirium prediction classifier through big data analysis and machine learning methods to detect delirium early. Method: This study is a retrospective study, using the artificial intelligence big data database to extract the characteristic factors related to delirium in intensive care unit patients and let the machine learn. The study included patients aged over 20 years old who were admitted to the intensive care unit between May 1, 2022, and December 31, 2022, excluding GCS assessment <4 points, admission to ICU for less than 24 hours, and CAM-ICU evaluation. The CAMICU delirium assessment results every 8 hours within 30 days of hospitalization are regarded as an event, and the cumulative data from ICU admission to the prediction time point are extracted to predict the possibility of delirium occurring in the next 8 hours, and collect a total of 63,754 research case data, extract 12 feature selections to train the model, including age, sex, average ICU stay hours, visual and auditory abnormalities, RASS assessment score, APACHE-II Score score, number of invasive catheters indwelling, restraint and sedative and hypnotic drugs. Through feature data cleaning, processing and KNN interpolation method supplementation, a total of 54595 research case events were extracted to provide machine learning model analysis, using the research events from May 01 to November 30, 2022, as the model training data, 80% of which is the training set for model training, and 20% for the internal verification of the verification set, and then from December 01 to December 2022 The CU research event on the 31st is an external verification set data, and finally the model inference and performance evaluation are performed, and then the model has trained again by adjusting the model parameters. Results: In this study, XG Boost, Random Forest, Logistic Regression, and Decision Tree were used to analyze and compare four machine learning models. The average accuracy rate of internal verification was highest in Random Forest (AUC=0.86), and the average accuracy rate of external verification was in Random Forest and XG Boost was the highest, AUC was 0.86, and the average accuracy of cross-validation was the highest in Random Forest (ACC=0.77). Conclusion: Clinically, medical staff usually conduct CAM-ICU assessments at the bedside of critically ill patients in clinical practice, but there is a lack of machine learning classification methods to assist ICU patients in real-time assessment, resulting in the inability to provide more objective and continuous monitoring data to assist Clinical staff can more accurately identify and predict the occurrence of delirium in patients. It is hoped that the development and construction of predictive models through machine learning can predict delirium early and immediately, make clinical decisions at the best time, and cooperate with PADIS delirium care measures to provide individualized non-drug interventional care measures to maintain patient safety, and then Improve the quality of care.

Keywords: critically ill patients, machine learning methods, delirium prediction, classifier model

Procedia PDF Downloads 75

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 42