Article
Computer Science, Interdisciplinary Applications
Jin Duan, Panagiotis G. Asteris, Hoang Nguyen, Xuan-Nam Bui, Hossein Moayedi
Summary: Recycled aggregate concrete is being researched using artificial intelligence techniques to assess its compressive strength, with the ICA-XGBoost model proving to be the most effective among the developed models. This model can be utilized in construction engineering to ensure adequate mechanical performance and safe usage of recycled aggregate concrete for building purposes.
ENGINEERING WITH COMPUTERS
(2021)
Review
Biotechnology & Applied Microbiology
Ayleen Bertini, Rodrigo Salas, Steren Chabert, Luis Sobrevia, Fabian Pardo
Summary: Through analyzing 98 articles, 31 were selected for predicting perinatal complications with main features of electronic medical records, medical images, and biological markers. The studies mainly focus on pre-eclampsia and prematurity, using AUC as the main precision metric for accuracy measurement.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Nanoscience & Nanotechnology
Andrew J. Lew, Chi-Hua Yu, Yu-Chuan Hsu, Markus J. Buehler
Summary: This research utilizes machine learning methods to predict nanoscale fracture mechanisms, focusing on the study of graphene as a significant material system. The results validate the feasibility of deep learning methods in capturing its fracture behavior.
NPJ 2D MATERIALS AND APPLICATIONS
(2021)
Article
Geosciences, Multidisciplinary
Mahdi Shayan Nasr, Hossein Shayan Nasr, Milad Karimian, Ehsan Esmaeilnezhad
Summary: The study utilized artificial intelligence algorithms to screen EOR methods, improving experimental efficiency and accuracy, ultimately determining the ANFIS model as the best choice. This method can effectively predict the efficiency of silica nanofluid flooding experiments, saving time and cost.
NATURAL RESOURCES RESEARCH
(2021)
Article
Nanoscience & Nanotechnology
Xue Jiang, Yong Wang, Baorui Jia, Xuanhui Qu, Mingli Qin
Summary: This paper introduces a machine-learning-based method for predicting the OER activity of hydroxide catalysts and successfully fits the relationship among composition, morphology, phase, pH value of the electrolyte, type of the working electrode, and overpotential. A new high-activity hydroxide catalyst, Ni0.77Fe0.13La0.1, was designed and prepared, exhibiting excellent performance.
ACS APPLIED MATERIALS & INTERFACES
(2022)
Article
Multidisciplinary Sciences
Sung-Hwi Hur, Eun-Young Lee, Min-Kyung Kim, Somi Kim, Ji-Yeon Kang, Jae Seok Lim
Summary: This study aimed to develop and validate five machine learning models for predicting distal caries on adjacent mandibular second molars, and to determine the relative importance of predictive variables. The performance of these models was significantly better than single predictors, with area under the receiver operating characteristic curve ranging from 0.88 to 0.89. Six key features were identified as relevant predictors, offering valuable insights for clinical decision making.
SCIENTIFIC REPORTS
(2021)
Article
Medical Informatics
Lili Feng, Zhenyu Liu, Chaofeng Li, Zhenhui Li, Xiaoying Lou, Lizhi Shao, Yunlong Wang, Yan Huang, Haiyang Chen, Xiaolin Pang, Shuai Liu, Fang He, Jian Zheng, Xiaochun Meng, Peiyi Xie, Guanyu Yang, Yi Ding, Mingbiao Wei, Jingping Yun, Mien-Chie Hung, Weihua Zhou, Dantel R. Wahl, Ping Lan, Jie Tian, Xiangbo Wan
Summary: Accurate prediction of pathological complete response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer was achieved using an artificial intelligence radiopathomics integrated model based on pretreatment MRI and H&E-stained biopsy slides. The model, RAPIDS, showed high accuracy and outperformed single-modality prediction models, providing a novel tool for individualized management of locally advanced rectal cancer.
LANCET DIGITAL HEALTH
(2022)
Article
Engineering, Multidisciplinary
Michal Wieczorowski, Dawid Kucharski, Pawel Sniatala, Pawel Pawlus, Grzegorz Krolczyk, Bartosz Gapinski
Summary: The use of artificial intelligence is becoming increasingly important in the field of modern length and angle metrology, especially due to the shortage of skilled operators. This paper discusses the possibilities of using artificial intelligence in coordinate metrology, including selection of measurement strategy, filtering techniques, and self-verification or self-calibration. It also introduces the use of local and global databases in measurement procedures and presents a new application in interference fringes analysis.
Article
Radiology, Nuclear Medicine & Medical Imaging
I Skarping, M. Larsson, D. Fornvik
Summary: This proof of concept study investigated a deep learning-based method using digital mammograms to predict breast cancer patients' responses to neoadjuvant chemotherapy. The initial artificial intelligence model showed potential in aiding clinical decision-making. Further research, including method refinement and a larger sample size, is needed to explore the clinical utility of AI in predicting responses to neoadjuvant chemotherapy for breast cancer.
EUROPEAN RADIOLOGY
(2022)
Article
Materials Science, Multidisciplinary
Andre Rodrigues, Francisco J. G. Silva, Vitor F. C. Sousa, Arnaldo G. Pinto, Luis P. Ferreira, Teresa Pereira
Summary: This study introduces the application of artificial neural networks in estimating the machining time for standard injection mold parts. By training the neural network model with a large dataset of parts and their corresponding machining times, the research achieves quick and accurate prediction of cutting times, which is crucial for the company's success and overall production cost control.
Article
Ophthalmology
Philipp L. Mueller, Yuka Kihara, Abraham Olvera-Barrios, Alasdair N. Warwick, Catherine Egan, Katie M. Williams, Aaron Y. Lee, Adnan Tufail
Summary: This study investigated macular curvature and explored the factors associated with it, as well as the presence of dome-shaped macular configuration. The results showed that macular curvature was associated with demographic, functional, ocular, and infancy factors, and the prevalence of dome-shaped macular configuration was higher in individuals with high refractive error.
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2022)
Article
Computer Science, Information Systems
Matt Docherty, Stephane A. Regnier, Gorana Capkun, Maria-Magdalena Balp, Qin Ye, Nico Janssens, Andreas Tietz, Juergen Loeffler, Jennifer Cai, Marcos C. Pedrosa, Jorn M. Schattenberg
Summary: The study developed a computer model using machine learning to predict patients with nonalcoholic steatohepatitis (NASH). With a combination of retrospective study and two databases, the model exhibited high performance in predicting NASH.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2021)
Review
Pharmacology & Pharmacy
Shan Wang, Jinwei Di, Dan Wang, Xudong Dai, Yabing Hua, Xiang Gao, Aiping Zheng, Jing Gao
Summary: The rapid development of artificial neural networks in the field of pharmaceutical formulation allows them to replace hundreds of trial and error experiments and become an important method in pharmaceutical science research.
Article
Urology & Nephrology
Lazaros Tzelves, Lazaros Lazarou, Georgios Feretzakis, Dimitris Kalles, Panagiotis Mourmouris, Evangelos Loupelis, Spyridon Basourakos, Marinos Berdempes, Ioannis Manolitsis, Iraklis Mitsogiannis, Andreas Skolarikos, Ioannis Varkarakis
Summary: This study evaluates the performance of machine learning techniques in predicting bacterial resistance in a urology department. The results show that artificial intelligence technology can predict antibiotic resistance patterns with an accuracy of 77% when knowing Gram staining, and nearly 87% when identifying specific microorganisms.
WORLD JOURNAL OF UROLOGY
(2022)
Review
Immunology
Jindong Xie, Xiyuan Luo, Xinpei Deng, Yuhui Tang, Wenwen Tian, Hui Cheng, Junsheng Zhang, Yutian Zou, Zhixing Guo, Xiaoming Xie
Summary: Tumor immunotherapy, particularly the use of immune checkpoint inhibitors, has shown significant clinical benefits. Artificial intelligence (AI) has been increasingly used in the medical field to better predict the efficacy of immunotherapy and achieve precision medicine. This article reviews current prediction models based on histopathological slides, imaging-omics, genomics, and proteomics, and discusses the challenges and future directions of AI in immunotherapy, providing a reference for the implementation of AI-assisted diagnosis and treatment systems.
FRONTIERS IN IMMUNOLOGY
(2023)