Review
Agriculture, Dairy & Animal Science
Giovanni Franzo, Matteo Legnardi, Giulia Faustini, Claudia Maria Tucciarone, Mattia Cecchinato
Summary: In the future, the demand for poultry meat and eggs is predicted to increase with population growth. This expansion brings both opportunities and challenges such as pollution, competition for resources, animal welfare concerns, and infectious diseases. Optimization and increased efficiency are needed in poultry production, and the use of big data offers the opportunity to develop tools to maximize farm profitability and reduce impacts. Sensor technologies and advanced statistical techniques are discussed, as well as the progress in pathogen genome sequencing and analysis.
Review
Clinical Neurology
Yuzhe Liu, Yuan Luo, Andrew M. Naidech
Summary: Significant advances in medical data accumulation, computational techniques, and management have been made in the last decade. Big data and computational methods can address gaps in patient selection, complications prediction, and outcome understanding. Automated neuroimaging analysis can help triage patients, and data-intensive techniques enable accurate risk calculations for timely prediction of adverse events.
Review
Oncology
Adrienne N. Cobb, Haroon M. Janjua, Paul C. Kuo
Summary: The digital world of data is rapidly expanding, with health care being one of the fastest growing sectors, where big data can be utilized to improve health care outcomes.
CLINICAL BREAST CANCER
(2021)
Review
Chemistry, Multidisciplinary
Hadas Shalit Peleg, Anat Milo
Summary: The chemistry community is experiencing a surge in scientific discoveries in organic chemistry with the support of machine learning. However, the use of machine learning techniques is often limited by small datasets in experimental organic chemistry. This article highlights the limitations of small data in machine learning and emphasizes the impact of bias and variance on constructing reliable predictive models. It aims to raise awareness of these potential pitfalls and provides an introductory guideline for good practice. Ultimately, the article stresses the great value of statistical analysis of small data and advocates for a holistic data-centric approach in chemistry.
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION
(2023)
Article
Chemistry, Analytical
Theodoros Alexakis, Nikolaos Peppes, Konstantinos Demestichas, Evgenia Adamopoulou
Summary: The increasing needs for data acquisition, storage and analysis in transportation systems have led to the adoption of new technologies and methods, such as big data techniques and analytics tools. This study aims to provide a distributed architecture platform that addresses the deficiencies in data gathering, storage, and analysis for intelligent transportation systems (ITS). The proposed system utilizes big data frameworks and tools as well as analytics tools to offer continuous collection, storage, and data analysis capabilities, providing a comprehensive solution for ITS applications.
Article
Oncology
Savino Cilla, Carmela Romano, Gabriella Macchia, Mariangela Boccardi, Donato Pezzulla, Milly Buwenge, Augusto Di Castelnuovo, Francesca Bracone, Amalia De Curtis, Chiara Cerletti, Licia Iacoviello, Maria Benedetta Donati, Francesco Deodato, Alessio Giuseppe Morganti
Summary: This study developed a predictive model for acute radiation toxicity using quantitative spectrophotometric markers in supervised machine learning models. The model showed good classification performance in predicting the severity of skin toxicity.
FRONTIERS IN ONCOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Murat Dener, Gokce Ok, Abdullah Orman
Summary: The study suggests using memory data in malware detection and applying deep learning and machine learning approaches in a big data environment. Results show that the Logistic Regression algorithm achieved the most successful malware detection in memory analysis.
APPLIED SCIENCES-BASEL
(2022)
Review
Engineering, Biomedical
Jacob Kerner, Alan Dogan, Horst von Recum
Summary: Machine learning has been widely utilized in various fields, including biomaterials, optimizing data collection and analysis. Recent advances in biomaterials have focused on quantitative structure properties relationships, introducing four basic models for rapid development and addressing the lack of machine learning implementation in the field. This article aims to spark greater interest and awareness in utilizing computational methods for biomaterials research.
ACTA BIOMATERIALIA
(2021)
Review
Medicine, General & Internal
Ana F. Pina, Maria Joao Meneses, Ines Sousa-Lima, Roberto Henriques, Joao F. Raposo, Maria Paula Macedo
Summary: This review examines the relationship between cluster analysis and T2D and highlights the complexity and heterogeneity of diabetes. It proposes an integrative model for understanding individual pathology. To achieve precision medicine and prevent complications, more factors such as etiological factors, pathophysiological mechanisms, and environmental factors should be considered.
EUROPEAN JOURNAL OF CLINICAL INVESTIGATION
(2023)
Article
Computer Science, Hardware & Architecture
Mohammad Hassan Almaspoor, Ali A. Safaei, Afshin Salajegheh, Behrouz Minaei-Bidgoli
Summary: This paper presents a novel distributed method for SVM training to address the efficiency issue in large-scale datasets. The method uses a small subset of training samples for classification, reducing the problem size and required resources. It also works effectively on unbalanced datasets.
JOURNAL OF SUPERCOMPUTING
(2023)
Review
Green & Sustainable Science & Technology
Sara Barja-Martinez, Monica Aragues-Penalba, Ingrid Munne-Collado, Pau Lloret-Gallego, Eduard Bullich-Massague, Roberto Villafafila-Robles
Summary: This paper provides a comprehensive analysis of artificial intelligence applications in distribution power systems, covering various aspects such as operation, monitoring, maintenance, and planning. It identifies potential AI techniques for power system applications and needed data sources. The study also examines data-driven services for distribution networks, highlighting interdependencies between different services and the importance of enhanced sensorization for better service outcomes.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2021)
Review
Nanoscience & Nanotechnology
Lihao Chen, Chuwen Lan, Ben Xu, Ke Bi
Summary: Material characterization is essential for high-throughput computational material science under big data environment. By analyzing element composition, molecular structure, and energy band distribution, researchers can predict the physical properties of materials, improve the quality of machine learning models, save computing resources, and enhance the understanding of the correlation of material attributes.
ADVANCED COMPOSITES AND HYBRID MATERIALS
(2021)
Review
Green & Sustainable Science & Technology
Ania Cravero, Sebastian Pardo, Patricio Galeas, Julio Lopez Fenner, Monica Caniupan
Summary: Sustainable agriculture is facing challenges due to climate change, and Machine Learning and Agricultural Big Data analysis can provide insights into agricultural production. However, understanding and handling different types of data is necessary for agricultural scientists.
Article
Computer Science, Artificial Intelligence
William C. Sleeman, Bartosz Krawczyk
Summary: This paper proposes a compound framework for dealing with multi-class big data problems, addressing the existence of multiple classes and high volumes of data simultaneously. By analyzing instance-level difficulties in each class and embedding this information in popular resampling algorithms, informative balancing of multiple classes is achieved. Extensive experimental study shows that using instance-level information significantly improves learning from multi-class imbalanced big data.
KNOWLEDGE-BASED SYSTEMS
(2021)
Review
Engineering, Biomedical
Ana Barragan-Montero, Adrien Bibal, Margerie Huet Dastarac, Camille Draguet, Gilmer Valdes, Dan Nguyen, Siri Willems, Liesbeth Vandewinckele, Mats Holmstrom, Fredrik Lofman, Kevin Souris, Edmond Sterpin, John A. Lee
Summary: This paper discusses the application of machine learning in radiation oncology, emphasizing the importance of the dependency between data and models as well as the interpretability of models for clinical implementation. Specific requirements for the construction of risk assessment and quality assurance tools are proposed.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Health Care Sciences & Services
Ross McGurk, Katherine Woch Naheedy, Tara Kosak, Amy Hobbs, Brandon T. Mullins, Kelly C. Paradis, Meghan Kearney, Donald Roback, Jeffrey Durney, Karthik Adapa, Bhishamjit S. Chera, Lawrence B. Marks, Jean M. Moran, Raymond H. Mak, Lukasz M. Mazur
Summary: This study utilized an incident learning system (ILS) coupled with a Human Factor Analysis and Classification System (HFACS) to investigate the origin and detection of SBRT events and to identify factors contributing to safeguard failures. The results suggest that improvements in communication, documentation, and reducing time pressures and distractions can enhance safeguards in radiation oncology.
JOURNAL OF PATIENT SAFETY
(2023)
Article
Oncology
Elizabeth M. Jaworski, Michelle L. Mierzwa, Karen A. Vineberg, John Yao, Jennifer L. Shah, Caitlin A. Schonewolf, Dale Litzenberg, Laila A. Gharzai, Martha M. Matuszak, Kelly C. Paradis, Ashley Dougherty, Pamela Burger, Daniel Tatro, George Spencer Arnould, Jean M. Moran, Choonik Lee, Avraham Eisbruch, Charles S. Mayo
Summary: This study developed an automated virtual integrative (AVI) knowledge-based planning application to reduce planning time, increase consistency, and improve baseline quality. AVI planner reliably generated clinically acceptable radiotherapy plans for head and neck cancers, significantly reducing interactive optimization time.
ADVANCES IN RADIATION ONCOLOGY
(2023)
Article
Oncology
Kelly C. Paradis, Kerry A. Ryan, Elizabeth L. Covington, Spencer Schmid, Samantha J. Simiele, Christina H. Chapman, Richard Castillo, Jean M. Moran, Martha M. Matuszak, Terri Bott-Kothari, James M. Balter, Reshma Jagsi
Summary: Gender-based discrimination and sexual harassment in the field of medical physics were investigated through in-depth interviews with 32 medical physicists and residents. The results revealed polarized views and personal experiences of discrimination and harassment.
INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS
(2023)
Article
Oncology
Jean M. Moran, Jose G. Bazan, Samantha L. Dawes, Ksenija Kujundzic, Brian Napolitano, Kristin J. Redmond, Ying Xiao, Yoshiya Yamada, Jay Burmeister
Summary: This article presents an updated report on intensity modulated radiation therapy (IMRT), which is part of a series of consensus-based white papers on patient safety published by the American Society for Radiation Oncology (ASTRO). IMRT has evolved from widespread use to becoming the main delivery technique for many treatment sites. It allows for higher radiation doses to be delivered to precise targets while minimizing damage to normal tissue, but requires additional planning and safety checks.
PRACTICAL RADIATION ONCOLOGY
(2023)
Article
Health Care Sciences & Services
Alex Koong, Ulysses Grant Gardner, Jason Burton, Caleb Stewart, Petria Thompson, Clifton David Fuller, Ethan Bernard Ludmir, Michael Kevin Rooney
Summary: In this observational cohort study, the authors aimed to characterize the landscape of open access (OA) publishing in oncology and identify characteristics of oncology journals predictive of article processing charges (APCs). The results showed that oncology journals with more citable articles, a hybrid OA model, higher impact factors, and based in North America or Europe tend to have higher APCs.
JMIR FORMATIVE RESEARCH
(2023)
Article
Oncology
Robbe Saesen, Mieke Van Hemelrijck, Jan Bogaerts, Christopher M. Booth, Jan J. Cornelissen, Andre Dekker, Elizabeth A. Eisenhauer, Andre Freitas, Alessandro Gronchi, Miguel A. Hernan, Frank Hulstaert, Piet Ost, Petr Szturz, Helena M. Verkooijen, Michael Weller, Roger Wilson, Denis Lacombe, Winette T. van der Graaf
Summary: The precision medicine paradigm in oncology has sparked interest in integrating real-world data (RWD) into cancer research. RWD studies tend to focus on collecting and analyzing observational data, but randomized controlled trials (RCTs) have the potential to generate strong evidence. The European Organisation for Research and Treatment of Cancer (EORTC) prioritizes pragmatic trials and trials-within-cohorts to generate robust RWD, but will consider observational research based on the target trial principle if random allocation is not feasible. New EORTC-sponsored trials may also include concurrent prospective cohorts.
EUROPEAN JOURNAL OF CANCER
(2023)
Article
Otorhinolaryngology
Houda Bahig, Hanna Y. Y. Ehab, Adam S. S. Garden, Sweet Ping Ng, Steven J. J. Frank, Theresa Nguyen, Gary B. B. Gunn, David I. I. Rosenthal, Clifton D. D. Fuller, Renata Ferrarotto, Diana Bell, Shirley Su, Jack Phan
Summary: This study retrospectively analyzed the long-term outcomes of patients with sinonasal tumors treated with modern radiotherapy. The results showed favorable disease control rate and acceptable toxicity profile in patients treated with modern radiotherapy.
HEAD AND NECK-JOURNAL FOR THE SCIENCES AND SPECIALTIES OF THE HEAD AND NECK
(2023)
Article
Engineering, Biomedical
Pinar Dursun, Linda Hong, Gourav Jhanwar, Qijie Huang, Ying Zhou, Jie Yang, Hai Pham, Laura Cervino, Jean M. Moran, Joseph O. Deasy, Masoud Zarepisheh
Summary: Objective: To develop and implement a fully automated treatment planning system for volumetric modulated arc therapy (VMAT). Approach: Two constrained optimization problems are solved sequentially to maximize tumor coverage and reduce dose at surrounding organs-at-risk. The system utilizes convex approximation problems and novel surrogate metrics to improve plan delivery efficiency. The program has been tested on 60 patients and found to be comparable or superior to manual plans.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Health Care Sciences & Services
Sander Puts, Martijn Nobel, Catharina Zegers, Inigo Bermejo, Simon Robben, Andre Dekker
Summary: This study describes the implementation and validation of an N-stage classifier for pulmonary oncology based on free-text radiological reports. The classifier achieved high accuracy in extracting the N-stage according to the TNM classification system, comparable to the T-stage classifier. This highlights the potential of NLP in structuring and classifying pulmonary oncology reports.
JMIR FORMATIVE RESEARCH
(2023)
Article
Computer Science, Software Engineering
A. Wentzel, C. Floricel, G. Canahuate, M. A. Naser, A. S. Mohamed, C. D. Fuller, L. van Dijk, G. E. Marai
Summary: In this study, we developed a modeling system called DASS to support the development and validation of predictive models for estimating long-term toxicities related to radiotherapy doses in head and neck cancer patients. DASS incorporates human-in-the-loop visual steering, spatial data, and explainable AI to augment domain knowledge with automatic data mining. We demonstrated DASS by developing two practical clinical stratification models and received feedback from domain experts.
COMPUTER GRAPHICS FORUM
(2023)
Article
Biology
Jiening Zhu, Jung Hun Oh, Anish K. Simhal, Rena Elkin, Larry Norton, Joseph O. Deasy, Allen Tannenbaum
Summary: Geometric network analysis techniques combined with biological knowledge can predict the prognosis of cancer patients. We proposed a novel supervised deep learning method called geometric graph neural network (GGNN) that incorporates geometric features into deep learning, enhancing predictive power and interpretability.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Otorhinolaryngology
Kevin J. Contrera, Jack Phan, Steven G. Waguespack, Mohammed Aldehaim, Xin Wang, Tze Yee Lim, Dianna B. Roberts, C. David Fuller, Michael T. Spiotto, Shaan M. Raza, Franco DeMonte, Ehab Y. Hanna, Shirley Y. Su
Summary: This study investigated the prevalence of pituitary dysfunction in adults who underwent anterior skull base radiation. The results showed that 46% of patients had abnormal pituitary hormone levels, with 12% requiring treatment for symptomatic abnormalities. The most common abnormalities were hyperprolactinemia, central hypothyroidism, and central hypogonadism. The study also found a dose-dependent association between hormonal dysfunction and radiation.
HEAD AND NECK-JOURNAL FOR THE SCIENCES AND SPECIALTIES OF THE HEAD AND NECK
(2023)
Article
Oncology
Guadalupe Canahuate, Andrew Wentzel, Abdallah S. R. Mohamed, Lisanne V. van Dijk, David M. Vock, Baher Elgohari, Hesham Elhalawani, Clifton D. Fuller, G. Elisabeta Marai
Summary: This study evaluated the effectiveness of machine learning tools that incorporate spatial information in predicting survival and toxicity outcomes for HPV+ oropharyngeal cancer patients. Patient stratifications based on radiometric data and lymph node metastasis patterns were identified and included in predictive models along with clinical features. The results showed that including these patient stratifications significantly improved the performance of the models in predicting survival and toxicity outcomes.
Article
Food Science & Technology
Anand Gavai, Yamine Bouzembrak, Wenjuan Mu, Frank Martin, Rajaram Kaliyaperumal, Johan van Soest, Ananya Choudhury, Jaap Heringa, Andre Dekker, Hans J. P. Marvin
Summary: Artificial Intelligence (AI) based algorithms, particularly data driven Bayesian Network (BN) models, are suitable for predicting future food fraud and enabling timely actions by food producers. However, data sharing is hindered due to various concerns, such as interests, security, and privacy. Federated learning (FL) technology can address these issues, allowing integration of data from different sources while ensuring data privacy and confidentiality. This research demonstrates the potential of FL for food fraud control and decision-making in the food supply chain.
NPJ SCIENCE OF FOOD
(2023)
Article
Computer Science, Interdisciplinary Applications
Temitayo Ajayi, Seyedmohammadhossein Hosseinian, Andrew J. Schaefer, Clifton D. Fuller
Summary: This paper presents a mixed-integer program for optimizing combination chemotherapy. The model incorporates various important operational constraints and controls treatment toxicity and white blood cell count for dose adjustments. Chance constraints are proposed to address the uncertainty of tumor heterogeneity and ensure reaching an operable tumor size with a high probability in a neoadjuvant setting.
INFORMS JOURNAL ON COMPUTING
(2023)
