Browse
Search Research Outputs
Recent Additions
- PublicationImproving clinical documentation: automatic inference of ICD-10 codes from patient notes using BERT model(2023)Electronic health records provide a vast amount of text health data written by physicians as patient clinical notes. The world health organization released the international classification of diseases version 10 (ICD-10) system to monitor and analyze clinical notes. ICD-10 is system physicians and other healthcare providers use to classify and code all diagnoses and symptom records in conjunction with hospital care. Therefore, the data can be easily stored, retrieved, and analyzed for decision-making. In order to address the problem, this paper introduces a system to classify the clinical notes to ICD-10 codes. This paper examines 7541 clinical notes collected from a health institute in Jordan and annotated by ICD-10’s coders. In addition, the research uses another outsource dataset to augment the actual dataset. The research presented many approaches, such as the baseline and pipeline models. The Baseline model employed several methods like Word2vec embedding for representing the text. The model structure also involves long-short-term memory a convolutional neural network, and two fully-connected layers. The second Pipeline approach adopts the transformer model, such as Bidirectional Encoder Representations from Transformers (BERT), which is pre-trained on a similar health domain. The Pipeline model builds on two BERT models. The first model classifies the category codes representing the first three characters of ICD-10. The second BERT model uses the outputs from the general BERT model (first model) as input for the special BERT (second model) to classify the clinical notes into total codes of ICD-10. Moreover, Baseline and Pipeline models applied the Focal loss function to eliminate the imbalanced classes. However, The Pipeline model demonstrates a significant performance by evaluating it over the F1 score, recall, precision, and accuracy metric, which are 92.5%, 84.9%, 91.8%, and 84.97%, respectively.
- PublicationGraph-Guided Regularized Regression of Pacific Ocean Climate Variables to Increase Predictive Skill of Southwestern U.S. Winter Precipitation(2021)AbstractUnderstanding the physical drivers of seasonal hydroclimatic variability and improving predictive skill remains a challenge with important socioeconomic and environmental implications for many regions around the world. Physics-based deterministic models show limited ability to predict precipitation as the lead time increases, due to imperfect representation of physical processes and incomplete knowledge of initial conditions. Similarly, statistical methods drawing upon established climate teleconnections have low prediction skill due to the complex nature of the climate system. Recently, promising data-driven approaches have been proposed, but they often suffer from overparameterization and overfitting due to the short observational record, and they often do not account for spatiotemporal dependencies among covariates (i.e., predictors such as sea surface temperatures). This study addresses these challenges via a predictive model based on a graph-guided regularizer that simultaneously promotes similarity of predictive weights for highly correlated covariates and enforces sparsity in the covariate domain. This approach both decreases the effective dimensionality of the problem and identifies the most predictive features without specifying them a priori. We use large ensemble simulations from a climate model to construct this regularizer, reducing the structural uncertainty in the estimation. We apply the learned model to predict winter precipitation in the southwestern United States using sea surface temperatures over the entire Pacific basin, and demonstrate its superiority compared to other regularization approaches and statistical models informed by known teleconnections. Our results highlight the potential to combine optimally the space–time structure of predictor variables learned from climate models with new graph-based regularizers to improve seasonal prediction.
1 - PublicationAutokeras Approach: A Robust Automated Deep Learning Network for Diagnosis Disease Cases in Medical Images(2023)Automated deep learning is promising in artificial intelligence (AI). However, a few applications of automated deep learning networks have been made in the clinical medical fields. Therefore, we studied the application of an open-source automated deep learning framework, Autokeras, for detecting smear blood images infected with malaria parasites. Autokeras is able to identify the optimal neural network to perform the classification task. Hence, the robustness of the adopted model is due to it not needing any prior knowledge from deep learning. In contrast, the traditional deep neural network methods still require more construction to identify the best convolutional neural network (CNN). The dataset used in this study consisted of 27,558 blood smear images. A comparative process proved the superiority of our proposed approach over other traditional neural networks. The evaluation results of our proposed model achieved high efficiency with impressive accuracy, reaching 95.6% when compared with previous competitive models.
2 - PublicationElastic Organic Crystals as Bioinspired Hair‐Like Sensors(2023)One of the typical haptic elements are natural hairy structures that animals and plants rely on for feedback. Although these hair sensors are an admirable inspiration, the development of active flow sensing components having low elastic moduli and high aspect ratios remains a challenge. Here, we report a new sensing approach based on a flexible, thin and optically transmissive organic crystal of high aspect ratio, which is stamped with fluorescent dye for tracking. When subjected to gas flow and exposed to laser, the crystal bends due to exerted pressure and acts as an optical flow (hair) sensor with low detection limit (≈1.578 m s−1) and fast response time (≈2.70 s). The air-flow-induced crystal deformation and flow dynamics response are modelled by finite element analysis. Due to having a simple design and being lightweight and mechanically robust this prototypical crystal hair-like sensor opens prospects for a new class of sensing devices ranging from wearable electronics to aeronautics.
2 - PublicationDiabetes Monitoring System in Smart Health Cities Based on Big Data Intelligence(2023)Diabetes is a metabolic disorder in which the body is unable to properly regulate blood sugar levels. It can occur when the body does not produce enough insulin or when cells become resistant to insulin’s effects. There are two main types of diabetes, Type 1 and Type 2, which have different causes and risk factors. Early detection of diabetes allows for early intervention and management of the condition. This can help prevent or delay the development of serious complications associated with diabetes. Early diagnosis also allows for individuals to make lifestyle changes to prevent the progression of the disease. Healthcare systems play a vital role in the management and treatment of diabetes. They provide access to diabetes education, regular check-ups, and necessary medications for individuals with diabetes. They also provide monitoring and management of diabetes-related complications, such as heart disease, kidney failure, and neuropathy. Through early detection, prevention and management programs, healthcare systems can help improve the quality of life and outcomes for people with diabetes. Current initiatives in healthcare systems for diabetes may fail due to lack of access to education and resources for individuals with diabetes. There may also be inadequate follow-up and monitoring for those who have been diagnosed, leading to poor management of the disease and lack of prevention of complications. Additionally, current initiatives may not be tailored to specific cultural or demographic groups, resulting in a lack of effectiveness for certain populations. In this study, we developed a diabetes prediction system using a healthcare framework. The system employs various machine learning methods, such as K-nearest neighbors, decision tree, deep learning, SVM, random forest, AdaBoost and logistic regression. The performance of the system was evaluated using the PIMA Indians Diabetes dataset and achieved a training accuracy of 82% and validation accuracy of 80%.
4
Most viewed
- Publication
1106 - PublicationThe Late Holocene evolution of the Black Sea – a critical view on the so-called Phanagorian regression(2012)Throughout its geologic history, the Black Sea experienced major sea level changes accompanied by severe environmental modifications, including geomorphologic reshaping. The most spectacular changes were driven by the Quaternary glaciations and deglaciations that reflect responses to Milankovitch cycles of 100 and 20 ky periodicity. Major sea level changes were also considered for a shorter and more recent cyclicity. The concept of the Phanagorian re- and transgression cycle, supposedly with a minimum sea level stand of 5-6 m below its present position in the middle of the 1 st millennium BC, was established in 1963 by Fedorov for the Black Sea region. It was based on archaeological and palaeogeographical research conducted around the ancient Greek colonies of the Cimmerian Bosporus, in particular at the name giving site of Phanagoria, where underwater prospection had revealed the presence of a large number of submerged relics of the Classical Greek era. Analyses of sediment cores as well as 14C-dated fossil coastal bars in the western and southern parts of Taman Peninsula show that contemporary coastal bars are related to different sea levels. The dissymmetry can reach up to 6 m around 500 BC. This and more evidence from drill cores confirms that on Taman Peninsula many of the apparent sea level changes are tectonically induced. The subsidence may have been initiated by the release of gas from mud volcanoes inherited along anticline axes. Other observations around the Black Sea confirm that submerged archaeological sites correspond to areas where subsidence has taken places, while the so-called Holocene highstand - said to have been located above the present-day sea level - is associated with uplift areas (triggered by the ongoing Caucasus orogeny). Recent oceanographic research carried out in the Black Sea area shows that since the Black Sea was reconnected with the Mediterranean Sea (i.e., 7500 14C BP at the latest), both marine water bodies have been in equilibrium. This fact and arguments from archaeology, history, hydrodynamics etc. lead us to question the existence of the Phanagorian regression. It is important to note that none of the sea level curves established for the (eastern) Mediterranean shows a comparable regression/transgression cycle of several metres during the 1 st millennium BC.
Scopus© Citations 29 1023 61 - PublicationNon-linear relationship between real commodity price volatility and real effective exchange rate: The case of commodity-exporting countries(2019)The aim of this paper is to contribute to the existing literature by exploring the relationship between the real commodity price volatilities and the real effective exchange rate (REER) of commodity-exporting countries, taking into account the transition variable of financial market integration. To this end, we consider a sample of 42 commodity-exporting countries subdivided into 4 panels: food and beverages, energy, metals, and raw materials. Our results highlight that the relationship between real commodity price volatility and REER is non-linear and depends on the degree of financialization of the commodity market. Specifically, when a country is poorly integrated financially, the volatility of the real commodity price has a strong and negative impact on the variation in REER. However, for periods when a country is better integrated financially, we observe a decrease in the impact of real commodity price volatility on REER, especially for the two panels of food and beverages as well as energy. Our findings also highlight the growth of financialization of commodities post-2000, particularly in the case of the energy sector.
Scopus© Citations 16 842 - PublicationCoral Reefs of Abu Dhabi, United Arab Emirates: Analysis of Management Approaches in Light of International Best Practices and a Changing Climate(2020)The coasts and islands that flank Abu Dhabi, the United Arab Emirates (UAE)’s largest emirate, host the country’s most significant coastal and marine habitats including coral reefs. These reefs, although subject to a variety of pressures from urban and industrial encroachment and climate change, exhibit the highest thresholds for coral bleaching and mortality in the world. By reviewing and benchmarking global, regional and local coral reef conservation efforts, this study highlights the ecological importance and economic uniqueness of the UAE corals in light of the changing climate. The analysis provides a set of recommendations for coral reef management that includes an adapted institutional framework bringing together stakeholders, scientists, and managers. These recommendations are provided to guide coral reef conservation efforts regionally and in jurisdictions with comparable environmental challenges.
Scopus© Citations 3 780 40 - PublicationThe globalization of social sciences? Evidence from a quantitative analysis of 30 years of production, collaboration and citations in the social sciences (1980-2009)(SAGE Publications Ltd, 2014)This article addresses the issue of internationalization of social sciences by studying the evolution of production (of academic articles), collaboration and citations patterns among main world regions over the period 1980-2009 using the SSCI. The results confirm the centre-periphery model and indicate that the centrality of the two major regions that are North America and Europe is largely unchallenged, Europe having become more important and despite the growing development of Asian social sciences. The authors' quantitative approach shows that the growing production in the social sciences but also the rise of international collaborations between regions have not led to a more homogeneous circulation of the knowledge produced by different regions, or to a substantial increase in the visibility of the contributions produced by peripheral regions. Social scientists from peripheral regions, while producing more papers in the core journals compiled by the SSCI, have a stronger tendency to cite journals from the two central regions, thus losing at least partially their more locally embedded references, and to collaborate more with western social scientists. In other words, the dynamic of internationalization of social science research may also lead to a phagocytosis of the periphery into the two major centers, which brings with it the danger of losing interest in the local objects specific to those peripheral regions. © The Author(s) 2013.
Scopus© Citations 80 696 90
Discover
Author
Zitar, Raed 26
Journal
Discipline
Geography 100