Article
Infectious Diseases
Chang Hu, Lu Li, Yiming Li, Fengyun Wang, Bo Hu, Zhiyong Peng
Summary: This study aimed to develop and validate a machine learning model for predicting in-hospital mortality in septic patients readmitted to the ICU. The data from a clinical research database were used to develop nine ML models, and the model with the highest accuracy and AUC in the validation cohort was selected for further analysis.
INFECTIOUS DISEASES AND THERAPY
(2022)
Article
Management
Pierre Durand, Gaetan Le Quang
Summary: This paper argues that banking regulation should focus on simple equity requirements instead of complex rules, and provides evidence that the equity ratio has a positive effect on banks' performance in terms of return on assets. However, the impact on return on equity is mostly negative. Strong equity requirements do not hinder banks' performance but reduce shareholder value. Random Forest is found to be a better method for analyzing banks' balance sheet data.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Agronomy
Junliang Fan, Jing Zheng, Lifeng Wu, Fucang Zhang
Summary: Accurate estimation of plant transpiration (T) is crucial for agricultural production, and this study investigated the use of machine learning models to estimate daily T of summer maize. Incorporating soil water content and leaf area index variables improved model performance, with the deep neural network (DNN) model slightly outperforming others.
AGRICULTURAL WATER MANAGEMENT
(2021)
Article
Automation & Control Systems
Jesus N. S. Rubi, Paulo H. P. de Carvalho, Paulo R. L. Gondim
Summary: Ecosystems, settlements, and human lives are at risk from forest fires annually. This research focuses on predicting the spread and behavior of wildfires to help minimize damages. Machine Learning models, using a dataset compiled from various data sources, accurately predict the affected areas.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Biophysics
Shankarappa Sridhara, Konapura Nagaraja Manoj, Pradeep Gopakkali, Girish R. Kashyap, Bappa Das, Kamlesh Kumar Singh, Amit Kumar Srivastava
Summary: This study examines the prediction of pigeon pea yield using long-term weather data. Among the different approaches, the artificial neural network (ANN) model resulted in the highest accuracy with a high coefficient of determination and low error values. Temperature was identified as the most influential variable for pigeon pea yield. These methods can be effectively used for precise yield prediction in different districts of Karnataka, India.
INTERNATIONAL JOURNAL OF BIOMETEOROLOGY
(2023)
Article
Green & Sustainable Science & Technology
Jonathan Gumz, Diego Castro Fettermann, Enzo Morosini Frazzon, Mirko Kueck
Summary: Industry 4.0 and its technologies have significant implications for advancements in communication, production, and management efficiency. This study focuses on using smart meter data and household features data to identify the most appropriate methods for predicting energy consumption. Through the application of the CRISP-DM method, Python Platform, and multiple prediction methods, experiments were conducted using data from over 470 smart meters over a three-year period. Support vector machines, random forest regression, and neural networks were found to be the most effective prediction methods. The results have important implications for utilities in offering improved contracts to new households and managing their smart grid infrastructure based on forecasted demand.
Article
Environmental Sciences
Jan Pawel Musial, Jedrzej Stanislaw Bojanowski
Summary: The VEOR algorithm is a novel algorithm for efficient supervised classification of large Earth Observation datasets. It addresses shortcomings in existing machine learning methods and has several desirable characteristics. It performed well in comparison experiments with synthetic datasets and cloud discrimination, but had limitations with significantly distorted or small datasets.
Review
Computer Science, Information Systems
Arijit Chakraborty, Sajal Mitra, Debashis De, Anindya Jyoti Pal, Ferial Ghaemi, Ali Ahmadian, Massimiliano Ferrara
Summary: Protein-Protein Interaction (PPI) is a crucial network in biology that requires fast, accurate, and critical analysis, with Support Vector Machine (SVM) being an effective tool for solving complex classification problems.
Article
Computer Science, Interdisciplinary Applications
Shih-Hui Huang, Chao-Yu Chu, Yu-Chia Hsu, San-Yuan Wang, Li-Na Kuo, Kuan-Jen Bai, Ming-Chih Yu, Jer-Hwa Chang, Eugene H. Liu, Hsiang-Yin Chen
Summary: Machine learning models with clinical and genomic features can be used as a preliminary tool for predicting platinum-induced nephrotoxicity in non-small cell lung cancer patients and providing preventive strategies in advance.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Construction & Building Technology
Anna Hola, Slawomir Czarnecki
Summary: The article presents the results of experimental research and numerical analyses, and also shows the usefulness of the random forest algorithm and the support vector machine for the non-destructive identification of the moisture content of brick walls in historic buildings. To train and test the models, a representative dataset, including 290 sample sets and 7 predictor variables, was used. The analyses showed that the random forest algorithm is the most predisposed model for the non-destructive assessment of the Umc mass moisture content of brick walls in historic buildings, with the highest value of R2 and the lowest values of RMSE, MAE, and MAPE.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Medicine, Research & Experimental
Wen He, Xianghong Fu, Song Chen
Summary: This study developed and validated machine learning models for predicting 72-hour mortality in adult polytrauma patients using readily available clinical parameters. The random forest model exhibited the best performance and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making.
JOURNAL OF TRANSLATIONAL MEDICINE
(2023)
Article
Engineering, Environmental
Fangyuan Peng, Yi Lu, Yingyang Wang, Long Yang, Zhaoguang Yang, Haipu Li
Summary: Controlling the formation of disinfection byproducts (DBPs) requires accurate prediction of DBP formation potential. Mathematical models can reduce laboratory tests and costs, but previous models lack evaluation using external data sets or focus on emerging DBPs. This study developed predictive models for specific DBPs using linear regression and machine learning algorithms, highlighting the dominance of UV254 as a parameter for predicting DBP formation. The ML algorithms outperformed traditional linear regression, indicating their viability in DBP management.
JOURNAL OF ENVIRONMENTAL CHEMICAL ENGINEERING
(2023)
Article
Chemistry, Applied
Reuben James Buenafe, Anjana Rathnam, Joanne Jerenice Anonuevo, Shanmugasundram Sundar, Nese Sreenivasulu
Summary: A classification tool was developed to identify high-yielding hybrids with good cooking and eating quality, achieving accuracies of 63.9%, 69.4%, and 69.4% using different models. The tool was based on routine grain quality parameters and key properties like gelatinization temperature and viscosity.
JOURNAL OF FOOD COMPOSITION AND ANALYSIS
(2021)
Article
Thermodynamics
Meng An, Kunliang Zhang, Fuxin Song, Xiangquan Chen, Swellam W. Sharshir, A. W. Kandeal, Amrit Kumar Thakur, A. S. Abdullah, Mohamed R. Elkadeem, Cheng Chi, Elbager M. A. Edreis, A. E. Kabeel, Weigang Ma
Summary: This study presents a comprehensive investigation on the freshwater productivity of a solar-driven HDH unit using experimental and machine learning methods. The average accumulated productivity was found to be 10.8 L/m2 based on 20 outdoor experiments. Machine learning models, including artificial neural network and random forest, were developed to predict the hourly freshwater productivity, cost, and GOR of the HDH system.
APPLIED THERMAL ENGINEERING
(2023)
Article
Chemistry, Analytical
Qingwan Xue, Xingyue Wang, Yinghong Li, Weiwei Guo
Summary: This paper conducts a driving simulator experiment to examine the impact of cognitive distractions on traffic safety for young drivers and analyze the mechanism of distracting effects on their driving process. The results show that the comprehensive model can effectively identify drivers' distracted state and provide theoretical support for control strategies of driving distraction.
Article
Rheumatology
Luis Alonso Gonzalez-Naranjo, Jaime Alberto Coral-Enriquez, Mauricio Restrepo-Escobar, Carlos Horacio Munoz-Vahos, Daniel Jaramillo-Arroyave, Adriana Lucia Vanegas-Garcia, Ruth Eraso, Gloria Vasquez, Fabian Jaimes
Summary: Among patients with systemic lupus erythematosus (SLE), factors associated with active tuberculosis (TB) included cumulative glucocorticoid dose, lymphopenia, and treatment with >= 2 immunosuppressants during the last 12 months.
CLINICAL RHEUMATOLOGY
(2021)
Article
Clinical Neurology
Monica B. Dhakar, Zubeda Sheikh, Polly Kumari, Eric C. Lawson, Valerie Jeanneret, Dhaval Desai, Andres Rodriguez Ruiz, Hiba A. Haider
Summary: This study aimed to examine the occurrence of seizures and epileptiform abnormalities in acute ischemic stroke (AIS) patients using continuous EEG monitoring. The findings show that epileptiform abnormalities are common in AIS patients, while the occurrence of seizures is relatively low and associated with specific types of epileptiform abnormalities. Continuous EEG findings resulted in changes to anti-seizure medication in approximately one-fifth of the patients. However, the presence of epileptiform abnormalities and seizures did not affect in-hospital mortality or discharge functional outcomes.
JOURNAL OF CLINICAL NEUROPHYSIOLOGY
(2022)
Article
Rheumatology
Mauricio Restrepo-Escobar, Paula A. Granda-Carvajal, Daniel C. Aguirre, Johanna Hernandez-Zapata, Gloria M. Vasquez, Fabian Jaimes
Summary: This study aimed to identify and analyze predictive models of infection prognosis in patients with SLE. Through structured searches and model evaluations, it was found that the number of published predictive models is limited, with a high risk of bias and methodological weaknesses.
Article
Immunology
Juan Sebastian Peinado-Acevedo, Juan Jose Hurtado-Guerra, Carolina Hincapie, Juanita Mesa-Abad, Jose Roberto Uribe-Delgado, Santiago Giraldo-Ramirez, Paula A. Lengerke-Diaz, Fabian Jaimes
Summary: VIRSTA score showed high sensitivity and negative predictive value in predicting IE, making echocardiography unnecessary in patients with negative results. On the other hand, despite the low frequency of IE in PREDICT-negative patients, echocardiography is still recommended to avoid missing potential cases.
CLINICAL INFECTIOUS DISEASES
(2021)
Letter
Immunology
Juan Sebastian Peinado-Acevedo, Juan Jose Hurtado-Guerra, Carolina Hincapie-Osorno, Juanita Mesa-Abad, Jose Roberto Uribe-Delgado, Santiago Giraldo-Ramirez, Paula A. Lengerke-Diaz, Fabian Jaimes
CLINICAL INFECTIOUS DISEASES
(2022)
Article
Respiratory System
Jaime A. Gomez-Rosero, Camilo Caceres-Galvis, Johana Ascuntar, Carlos Atencia, Carlos E. Vallejo, Fabian Jaimes
Summary: In patients hospitalized with AECOPD, a neutrophil/lymphocyte ratio greater than 5 is a strong predictor of mortality or ICU admissions and a longer hospital stay.
COPD-JOURNAL OF CHRONIC OBSTRUCTIVE PULMONARY DISEASE
(2021)
Article
Surgery
James S. Diaz, Fabian A. Jaimes
Summary: This retrospective study aimed to evaluate the association between CMV disease and risks of death, cardiovascular events, and graft loss in renal transplant recipients. After analyzing data from 865 patients, it was found that CMV disease was not a significant risk factor for mortality, cardiovascular events, or graft loss. The relationship between CMV and cardiovascular disease may involve individual risk factors and immune response rather than the direct effect of the virus.
PROGRESS IN TRANSPLANTATION
(2021)
Meeting Abstract
Rheumatology
Y. Santamaria-Alza, J. Sanchez-Bautista, T. Urrego Callejas, J. Moreno, F. Jaimes, J. Rodello, D. Fernandez, L. A. Gonzalez, G. Vasquez
ANNALS OF THE RHEUMATIC DISEASES
(2021)
Article
Emergency Medicine
Deibie Mendoza, Johana Ascuntar, Oriana Rosero, Fabian Jaimes
Summary: This study aimed to identify variables associated with the risk of in-hospital mortality or intensive care unit (ICU) admission according to various infection sites. The results showed that factors associated with the outcomes of sepsis varied depending on the site of infection. This suggests that a more individualized approach should be considered for the diagnosis and prognosis of sepsis in emergency care.
EMERGENCY MEDICINE JOURNAL
(2022)
Article
Rheumatology
Mauricio Restrepo-Escobar, Paula A. Granda-Carvajal, Daniel C. Aguirre-Acevedo, Fabian Jaimes, Gloria M. Vasquez
Summary: This study aimed to identify the predictive factors of hospital-acquired bacterial infections in patients with systemic lupus erythematosus (SLE). The results showed that age, SLE Disease Activity Index score, SLE International Collaborating Clinics damage score, blood urea nitrogen and C-reactive protein levels, dosage of steroid in the previous month, recent use of immunosuppressants, admission with a central venous catheter (or dialysis catheter), and use of central venous catheter or bladder catheter in the first 5 days were predictive factors of nosocomial infections.
JCR-JOURNAL OF CLINICAL RHEUMATOLOGY
(2023)
Article
Medicine, General & Internal
Santiago Alvarez-Lopez, Maria Fernanda Ariza-Gomez, Vanessa Lopez-Montoya, John Ubeimar Catano-Bedoya, Diana Giraldo-Mendez, Fabian Jaimes
Summary: This study aimed to characterize patients with antiphospholipid syndrome (APS) and evaluate their clinical manifestations and serological findings. The results showed that most patients were female and had venous thrombotic events. Primary APS was common, and Lupus coagulation inhibitor positivity was prevalent.
CUREUS JOURNAL OF MEDICAL SCIENCE
(2023)
Article
Medicine, General & Internal
Carlos A. Regino, Jonathan Cardona-Velez, Jesus D. Bello Simanca, Andres F. Miranda Arboleda, Juan G. Gamboa Arroyave, Fabian Jaimes
Summary: This study examined the clinical characteristics and cardio-oncological assessment of patients undergoing highly toxic chemotherapy and/or chest radiotherapy in a high-complexity hospital. The majority of high-risk patients were not previously evaluated by a cardiologist and the use of cardiovascular workup was not routine.
CUREUS JOURNAL OF MEDICAL SCIENCE
(2022)
Article
Endocrinology & Metabolism
Carlos S. Duque, Alejandro Velez, Jorge Cuartas, Fabian Jaimes, Juan Pablo Duenas, Miguel Agudelo, Marina N. Nikiforova, Yuri E. Nikiforov, Vincenzo Condello
Summary: The study investigated the molecular profiles of PTC patients with workplace exposure to ionizing radiation, revealing BRAF V600E point mutation as the most common event. This suggests that workplace radiation exposure may not play a role in the etiology of these tumors.
Article
Medicine, General & Internal
Carolina Hincapie, Johana Ascuntar, Alba Leon, Fabian Jaimes
Summary: The study compared the performance of CURB-65, CRB-65, and qSOFA scores in identifying emergency department patients with pneumonia at increased risk of mortality or ICU admission. None of the scores proved to be an appropriate predictor for mortality and ICU admission, with CRB 65 demonstrating the lowest discriminative ability.
Letter
Emergency Medicine
Zhao-Yu Hsieh, Chen-Xiong Hsu
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Editorial Material
Emergency Medicine
Laura E. Walker, Jessica A. Stanich, Fernanda Bellolio
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Letter
Emergency Medicine
E. Tekin
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Amanda S. Dupont, Patrick S. Walsh
Summary: Recent research indicates that children who unintentionally ingest cannabis often undergo extensive additional testing, such as head imaging or lumbar puncture. However, the yield of these tests is limited. While head imaging and lumbar puncture are frequently performed, diagnoses such as skull fracture, intracranial hemorrhage, intracranial neoplasm, meningitis, or intracranial abscess are rare. Additionally, discharge diagnoses related to other drugs are infrequent. The most common co-diagnoses are cocaine and opioids. Therefore, prompt consideration of cannabis ingestion and quick identification through testing may result in more effective neuroimaging outcomes.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Letter
Emergency Medicine
Mio Nagata, Shunsuke Kudo, Motoyasu Nakamura
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Andy Hung-Yi Lee, Katherine Dickerson Mayes, Regan Marsh, Christina Toledo-Cornell, Eric Goralnick, Michael Wilson, Leon D. Sanchez, Alice Bukhman, Damarcus Baymon, Dana Im, Paul C. Chen
Summary: This study assessed the disparities in transferring patients from an academic medical center emergency department to a community hospital general medical service, revealing healthcare disparities among different patient populations.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Annabelle Croskey, William Trautman, David Barton, Mary Kathleen Ratay, Joshua Shulman
Summary: This case report describes a successful management of ocular palytoxin exposure in a young male, highlighting the importance of prompt recognition and treatment of ocular PTX toxicity.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Matthew K. Kolbeck, Rachel F. Schult, Nicholas Nacca
Summary: This article presents four cases of adolescents who experienced seizures after acute fluoxetine overdose. Although seizures are an uncommon complication after fluoxetine overdose, they occurred in some patients at doses lower than those reported in the literature.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Editorial Material
Emergency Medicine
Daven Patel, John Bailitz, Simone Ymson, Jonas Neichin, Gary D. Peksa, Michael Gottlieb
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Amichai Gutgold, Shaden Salameh, Jeries Nashashibi, Yonatan Gershinsky
Summary: This study aimed to test the prognosis of patients with a pH lower than 6.9 on emergency department admission. The findings showed that a small but significant portion of these patients survived at least 24 hours and until hospital discharge.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Na-Yeon Emily Song, Ki Hong Kim, Ki Jeong Hong
Summary: This study aimed to evaluate the effect of the duration of no-flow (NF) interval on the vaso-pressor effect of initial epinephrine administration in a porcine model of cardiac arrest. The results showed that a shorter NF interval can enhance the vasopressor effect of epinephrine.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Kenneth A. Scheppke, Paul E. Pepe, Jonathan Jui, Remle P. Crowe, Eric K. Scheppke, Nancy G. Klimas, Aileen M. Marty
Summary: This study reported cases of rapid and complete remission of severe long COVID after receiving monoclonal antibody treatment. The findings suggest that monoclonal antibody infusions may be effective in treating severe debilitation caused by long COVID.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Suhrith Bhattaram, Varsha S. Shinde
Summary: Nerve blocks have emerged as promising options for targeted pain relief in the Emergency Department, providing effective analgesia without compromising motor function. The successful use of ultrasound-guided genicular nerve blocks (GNBs) in this case series demonstrates their potential as an alternative to traditional nerve blocks and opioid-based pain control strategies in the ED.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Rick Kye Gan, Jude Chukwuebuka Ogbodo, Yong Zheng Wee, Ann Zee Gan, Pedro Arcos Gonzalez
Summary: The aim of this study was to evaluate and compare the performance of ChatGPT, Google Bard, and medical students in performing START triage during mass casualty situations. The results showed that Google Bard had significantly higher accuracy compared to ChatGPT, while there was no significant difference between Google Bard and medical students.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)
Article
Emergency Medicine
Nancy Clemens, Paria M. Wilson, Matthew J. Lipshaw, Holly Depinet, Yin Zhang, Michelle Eckerle
Summary: This study compared clinical features and outcomes between pediatric sepsis patients with blood cultures positive versus negative for bacterial pathogens. The results showed that children with blood culture positive sepsis had higher rates of organ dysfunction, a larger base deficit, and higher procalcitonin levels.
AMERICAN JOURNAL OF EMERGENCY MEDICINE
(2024)