Nature Machine Intelligence
·
2021
·Vol. 3
·期 3
·199-217
·
IF 15.508
Roberts Michael,Driggs Derek,Thorpe Matthew,Gilbey Julian,Yeung Michael,Ursprung Stephan,Aviles-Rivero Angelica I.,Etmann Christian,McCague Cathal,Beer Lucian,Weir-McCall Jonathan R.,Teng Zhongzhao,Gkrania-Klotsas Effrossyni,Rudd James H. F.,Sala Evis,Schönlieb Carola-Bibiane
Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts.
研究领域:
医学影像学
·
人工智能
·
流行病学
✓ 已验证
DOI
高影响因子
POWDER TECHNOLOGY
·
2020
·
IF 4.142
Yafeng Fu,Bin Yang,Yingqiang Ma,Qianyu Sun,Jin Yao,Wenbiao Fu,Wanzhong Yin
This research focused on the effect of particle size and flotation time on magnesite flotation, and the flotation performance of various size fractions were predicted by a machine learning (ML) method. Four kinetic models were used to fit the recovery of MgO and SiO 2 in various size fractions of magnesite flotation. The results demonstrated that the flotation of magnesite exhibits good agreement with the classical first-order kinetic model. Besides, the effect of various particle sizes on MgO recovery and selectivity index was predicted by ML method. It was shown that the proposed ML model could accurately reproduce the effects of particle size and flotation time on magnesite flotation performance. Furthermore, the developed model revealed that the optimal mean size range for magnesite flotation is 30 to 48 μm. Therefore, this paper is of great significance to the application of ML methods in the prediction of various magnesite size flotation performance.
研究领域:
矿物加工工程
·
人工智能应用
✓ 已验证
DOI
高影响因子
FOOD CONTROL
·
2023
·
IF 6
Lei He,Qian Hu,Yue Yu,Yaoxian Yu,Ning Yu,Ying Chen
Mung bean is an important pulse in China owing to its nutritional and bioactive properties, however, the quality characteristics of mung beans from different climate zones and growing regions in China remain unknown. In the present study, an untargeted metabolomics approach based on ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry (UPLC-QTOF-MS) coupled with machine learning was used to compare and discriminate mung beans from different climate zones and growing regions. Based on orthogonal partial least squares-discriminant analysis (OPLS-DA), 39 and 35 differential metabolites were identified in mung bean samples among three climate zones and 11 growing regions, respectively. The differential metabolites mainly included lipids, flavonoids , soyasaponins, amino acids , peptides, indoles and their derivatives, and acids. Random forest (RF) and support vector machine (SVM) models were established, optimized, and used to discriminate mung beans from different climate zones and growing regions. The SVM models performed better than the RF models in predicting both the climate zone and growing region of mung beans, with accuracies of 100% and 98.72%, respectively. Our results demonstrate that untargeted metabolomics coupled with machine learning could be a powerful tool for discriminating of mung beans from different climate zones and growing regions.
研究领域:
植物学
·
食品科学
·
分析化学
·
人工智能
✓ 已验证
DOI
高影响因子
Advanced Science
·
2024
·Vol. 11
·期 30
·2401123
·
IF 14.3
Xuewei Shi,Alamusi Lee,Bo Yang,Huiming Ning,Haowen Liu,Kexu An,Hansheng Liao,Kaiyan Huang,Jie Wen,Xiaolin Luo,Lidan Zhang,Bin Gu,Ning Hu
Soft robots have the advantage of adaptability and flexibility in various scenarios and tasks due to their inherent flexibility and mouldability, which makes them highly promising for real-world applications. The development of electronic skin (E-skin) perception systems is crucial for the advancement of soft robots. However, achieving both exteroceptive and proprioceptive capabilities in E-skins, particularly in terms of decoupling and classifying sensing signals, remains a challenge. This study presents an E-skin with mixed electronic and ionic conductivity that can simultaneously achieve exteroceptive and proprioceptive, based on the resistance response of conductive hydrogels. It is integrated with soft robots to enable state perception, with the sensed signals further decoded using the machine learning model of decision trees and random forest algorithms. The results demonstrate that the newly developed hydrogel sensing system can accurately predict attitude changes in soft robots when subjected to varying degrees of pressing, hot pressing, bending, twisting, and stretching. These findings that multifunctional hydrogels combine with machine learning to decode signals may serve as a basis for improving the sensing capabilities of intelligent soft robots in future advancements.
研究领域:
材料科学
·
人工智能
·
机器人学
✓ 已验证
DOI
高影响因子
Journal of Materials Informatics
·
2024
·Vol. 4
·期 4
·N
·
IF 0
Hongwei Liu,Zhenming Cui,Zhennan Qiao,Xiaokang An,Yongzhen Wang
Porous carbon materials (PCMs) are preferred as electrode materials for supercapacitor energy storage applications due to their superior characteristics. However, the optimal performance of these electrodes requires trial and error experimental exploration due to the complexity of influencing factors. To address this limitation, we develop a machine learning (ML) combined experimental validation approach to predict, screen and interpret ideal PCMs for supercapacitors. Four ML models are used for predicting the specific capacitance (SC) properties of PCMs and the light gradient boosting machine (LGBM) model exhibits the best prediction performance with an R2 value of 0.92. Through comprehensive interpretability analysis of ML, important variables influencing SC properties are identified and their impact range is determined. By analyzing the deviation of key values during experimental verification, accurate predictions of SC properties of PCMs are made, facilitating precise material screening. Additionally, the accuracy and applicability of the ML model predictions are evaluated. This research pioneered a key eigenvalue fall-point screening approach based on a combination of ML experiments for accurately predicting SC performance and screening of superior energy storage materials, providing a compelling strategy for advancing energy storage materials technology.
研究领域:
材料科学
·
能源存储
·
人工智能应用
✓ 已验证
DOI
NEW JOURNAL OF CHEMISTRY
·
2023
·Vol. 47
·期 22
·10875-10883
·
IF 3.3
Cong Ding,Zhongfa Li,Wenjun Zhang,Jun Ou,Xue Wen,Chengyue Xin,Min Su
The optical properties of Mn4+-activated phosphors are heavily affected by the host and the related data are difficult to obtain, which makes quantitative design of novel phosphors with required wavelength particularly challenging. In the era of big data, computation is emerging as a vital complement to materials development. Compared with traditional calculation routes, machine learning (ML) models provide better solutions for the problems wherein understanding the underlying physics is complicated with sparse data. In this study, we developed six ML models based on a sparse and small data set to rapidly predict the peak emission wavelength of novel phosphors and use Recursive Feature Elimination (RFE) to select the best features. Among them, the K-nearest neighbors regression (KNN.r) algorithm using non-parametric regression technology can predict the value of the target variable based on the similarity between the target value and its spatial neighbors, which can tackle sparse data sets with no obvious linear relationship well and has the best prediction accuracy. These models were then used to predict 278 potential Mn4+-activated phosphor hosts extracted from the inorganic crystal structure database (ICSD), and 19 samples were selected to validate these methods. In order to overcome the lack of physical and chemical insight of KNN, a visual data analysis was carried out based on hierarchical clustering analysis (HCA), and the rule between the peak emission wavelength and the structure of host was proposed. Guided by the results of KNN and HCA, six samples were selected for the synthesis and characterization to verify our conclusions. The measured values of all these phosphors exhibit good agreement with the predicted results, suggesting the success of our methodology. Thus, the model established and the rule proposed in this paper provide a new pathway for the rapid discovery of novel phosphors.
研究领域:
材料科学
·
光学
·
数据科学
✓ 已验证
DOI
高影响因子
JOURNAL OF HAZARDOUS MATERIALS
·
2023
·
IF 13.6
Yangmin Ren,Mingcan Cui,Yongyue Zhou,Yonghyeon Lee,Junjun Ma,Zhengchang Han,Jeehyeong Khim
The zero-valent iron (ZVI) based reactive materials are potential remediation reagents in permeable reactive barriers (PRB). Considering that reactive materials is the essential to determining the long-term stability of PRB and the emergence of a large number of new iron-based materials. Here, we present a new approach using machine learning to screen PRB reactive materials, which proposes to improve the efficiency and practicality of selection of ZVI-based materials. To compensate for the insufficient amount of existing machine learning source data and the real-world implementation, machine learning combines evaluation index (EI) and reactive material experimental evaluations. XGboost model is applied to estimate the kinetic data and SHAP is used to improve the accuracy of model. Batch and column tests were conducted to investigate the geochemical characteristics of groundwater. The study find that specific surface area is a fundamental factor correlated with the kinetic constants of ZVI-based materials, according to SHAP analysis. Reclassifying the data with specific surface area significantly improved prediction accuracy (reducing RMSE from 1.84 to 0.6). Experimental evaluation results showed that ZVI had 3.2 times higher anaerobic corrosion reaction kinetic constants and 3.8 times lower selectivity than AC-ZVI. Mechanistic studies revealed the transformation pathways and endpoint products of iron compounds. Overall, this study is a successful initial attempt to use machine learning for selecting reactive materials.
研究领域:
环境科学
·
材料科学
✓ 已验证
DOI
PubMed
高影响因子
Cell Reports Medicine
·
2023
·
IF 14.3
Yifan Chen,Wei Xu,Wei Zhang,Renyang Tong,Ancai Yuan,Zheng Li,Huiru Jiang,Liuhua Hu,Lin Huang,Yudian Xu,Ziyue Zhang,Mingze Sun,Xiaoxiang Yan,Alex F Chen,Kun Qian,Jun Pu
Direct diagnosis and accurate assessment of metabolic syndrome (MetS) allow for prompt clinical interventions. However, traditional diagnostic strategies overlook the complex heterogeneity of MetS. Here, we perform metabolomic analysis in 13,554 participants from the natural cohort and identify 26 hub plasma metabolic fingerprints (PMFs) associated with MetS and its early identification (pre-MetS). By leveraging machine-learning algorithms, we develop robust diagnostic models for pre-MetS and MetS with convincing performance through independent validation. We utilize these PMFs to assess the relative contributions of the four major MetS risk factors in the general population, ranked as follows: hyperglycemia, hypertension, dyslipidemia, and obesity. Furthermore, we devise a personalized three-dimensional plasma metabolic risk (PMR) stratification, revealing three distinct risk patterns. In summary, our study offers effective screening tools for identifying pre-MetS and MetS patients in the general community, while defining the heterogeneous risk stratification of metabolic phenotypes in real-world settings.
研究领域:
医学
·
代谢组学
✓ 已验证
DOI
PubMed
高影响因子
ENVIRONMENTAL SCIENCE & TECHNOLOGY
·
2023
·
IF 11.4
Hengjie Yu,Shiyu Tang,Sam Fong Yau Li,Fang Cheng
Understanding plant uptake and translocation of nanomaterials is crucial for ensuring the successful and sustainable applications of seed nanotreatment. Here, we collect a dataset with 280 instances from experiments for predicting the relative metal/metalloid concentration (RMC) in maize seedlings after seed priming by various metal and metalloid oxide nanoparticles. To obtain unbiased predictions and explanations on small datasets, we present an averaging strategy and add a dimension for interpretable machine learning. The findings in post-hoc interpretations of sophisticated LightGBM models demonstrate that solubility is highly correlated with model performance. Surface area, concentration, zeta potential, and hydrodynamic diameter of nanoparticles and seedling part and relative weight of plants are dominant factors affecting RMC, and their effects and interactions are explained. Furthermore, self-interpretable models using the RuleFit algorithm are established to successfully predict RMC only based on six important features identified by post-hoc explanations. We then develop a visualization tool called RuleGrid to depict feature effects and interactions in numerous generated rules. Consistent parameter-RMC relationships are obtained by different methods. This study offers a promising interpretable data-driven approach to expand the knowledge of nanoparticle fate in plants and may profoundly contribute to the safety-by-design of nanomaterials in agricultural and environmental applications.
研究领域:
植物学
·
环境科学
·
数据科学
✓ 已验证
DOI
PubMed
高影响因子
iScience
·
2021
·
IF 5.458
Anhui Zheng,Yuxuan Wang,Fangfei Zhang,Chunnian He,Shan Zhu,Naiqin Zhao
To achieve net-zero emissions, a particular interest has been raised in the electrochemical evolution of H 2 by using catalysts. Considering the complexity of designing catalyst, we demonstrate a data-driven strategy to develop optimized catalysts for H 2 evolution. This work starts by collecting data of Pt/carbon catalysts, and applying machine learning to reveal the importance of ranking various features. The algorithms reveal that the Pt content and Pt size have the greatest impact on the catalyst overpotentials. Following the data-driven analysis, a space-confined method is used to fabricate the size-controllable Pt nanoclusters that anchor on nitrogen-doped (N-doped) mesoporous carbon nanosheet network. The obtained catalysts use less platinum and exhibit better catalytic activity than current commercial catalysts in alkaline electrolytes. Moreover, the data formed in this work can be used as feedback to further improve the data-driven model, thereby accelerating the development of high-performance catalysts.
研究领域:
电化学
·
材料科学
·
人工智能
✓ 已验证
DOI
PubMed
高影响因子
AAPS PHARMSCITECH
·
2022
·Vol. 23
·期 6
·1-12
·
IF 4.026
Sheng Han,Zhao Yinping,Long Xiangan,Chen Liwen,Li Bei,Fei Yiyan,Mi Lan,Ma Jiong
Visible particle identification is a crucial prerequisite step for process improvement and control during the manufacturing of injectable biotherapeutic drug products. Raman spectroscopy is a technology with several advantages for particle identification including high chemical sensitivity, minimal sample manipulation, and applicability to aqueous solutions. However, considerable effort and experience are required to extract and interpret Raman spectral data. In this study, we applied machine learning algorithms to analyze Raman spectral data for visible particle identification in order to minimize expert support and improve data analysis accuracy. We manually prepared ten types of particle standard solutions to simulate the particle types typically observed during manufacturing and established a Raman spectral library with accurate peak assignments for the visible particles. Five classification algorithms were trained using visible particle Raman spectral data. All models had high prediction accuracy of >98% for all types of visible particles. Our results demonstrate that the combination of Raman spectroscopy and machine learning can provide a simple and accurate data analysis approach for visible particle identification. Graphical abstract
研究领域:
制药工程
·
分析化学
·
生物技术
✓ 已验证
DOI
高影响因子
CRYSTAL GROWTH & DESIGN
·
2020
·
IF 4.089
Dingyan Wang,Zeen Yang,Bingqing Zhu,Xuefeng Mei,Xiaomin Luo
A machine-learning model trained on the whole Cambridge Structural Database was developed to assist high-throughput cocrystal screening. With only 2D structures taken as inputs, the probability of cocrystal formation is returned for two given molecules. All of the cocrystal records in the CSD were used as positive samples, while negative samples were constructed by randomly combining different molecules into chemical pairs. Our model showed a prediction ability comparable with that of a widely used ab initio method in a head-to-head comparison test. Both experimental and virtual cocrystal screening against captopril were conducted at the same time to further validate the model. Two cocrystals of captopril with l-proline and sarcosine were obtained and characterized by PXRD, DSC, and FT-IR. These two coformers were also successfully predicted by our model. These results suggest that the tool we developed can be used to effectively guide coformer selection in the discovery of new cocrystals.
研究领域:
化学信息学
·
材料科学
·
药物化学
✓ 已验证
DOI
高影响因子
危险品化学品经营许可证（带存储）