Background:This study aimed to evaluate the impact of the clock drawing test(CDT)on postoperative delirium and compare the abilities of the mini-cognitive(Mini-Cog)test and the CDT for predicting postoperative deliriu...Background:This study aimed to evaluate the impact of the clock drawing test(CDT)on postoperative delirium and compare the abilities of the mini-cognitive(Mini-Cog)test and the CDT for predicting postoperative delirium after major urological cancer surgery.Materials and methods:In this single-center retrospective observational study,we collected the medical records of patients who underwent major urologic cancer surgery and preoperative cognitive screening based on the Mini-Cog test consisting of the CDT and the 3-word recall task at our department in 2020–2021(n=387).Univariate andmultivariate logistic regression analyses were used to identify the clinical risk factors for postoperative delirium.We also compared the ability of the CDT alone and the Mini-Cog test consisting of the CDT and 3-word recall task to predict postoperative delirium.Results:A total of 117 patients(30%)had abnormal CDT results.Postoperative delirium occurred in 29 patients(7%).On multivariate analysis,American Society of Anesthesiologists physical status≥3(odds ratio[OR],5.0;p=0.01),abnormal CDT(OR,4.8;p<0.001),preoperative benzodiazepine use(OR,4.9;p<0.001),and operative time≥237minutes(OR,3.0;p=0.01)were independent risk factors for postoperative delirium.The area under the curve for predicting postoperative deliriumwas 0.709 for CDT alone and 0.743 for the Mini-Cog test.No significant intergroup difference was observed(p=0.43).Conclusions:The CDT served as a formal but simple tool with adequate predictive power to identify the risk of postoperative delirium among patients undergoing major urological cancer surgery.Effective screening using the CDT might help provide optimal urological care for older patients.展开更多
Machine learning is applied to a large number of modern devices that are essential in building an energy-efficient smart society.Audio and face recognition are among the most well-known technologies that make use of s...Machine learning is applied to a large number of modern devices that are essential in building an energy-efficient smart society.Audio and face recognition are among the most well-known technologies that make use of such artificial intelligence.In materials research,machine learning is adapted to predict materials with certain functionalities,an approach often referred to as materials informatics.Here,we show that machine learning can be used to extract material parameters from a single image obtained in experiments.The Dzyaloshinskii–Moriya(DM)interaction and the magnetic anisotropy distribution of thin-film heterostructures,parameters that are critical in developing next-generation storage class magnetic memory technologies,are estimated from a magnetic domain image.Micromagnetic simulation is used to generate thousands of random images for training and model validation.A convolutional neural network system is employed as the learning tool.The DM exchange constant of typical Co-based thin-film heterostructures is studied using the trained system:the estimated values are in good agreement with experiments.Moreover,we show that the system can independently determine the magnetic anisotropy distribution,demonstrating the potential of pattern recognition.This approach can considerably simplify experimental processes and broaden the scope of materials research.展开更多
文摘Background:This study aimed to evaluate the impact of the clock drawing test(CDT)on postoperative delirium and compare the abilities of the mini-cognitive(Mini-Cog)test and the CDT for predicting postoperative delirium after major urological cancer surgery.Materials and methods:In this single-center retrospective observational study,we collected the medical records of patients who underwent major urologic cancer surgery and preoperative cognitive screening based on the Mini-Cog test consisting of the CDT and the 3-word recall task at our department in 2020–2021(n=387).Univariate andmultivariate logistic regression analyses were used to identify the clinical risk factors for postoperative delirium.We also compared the ability of the CDT alone and the Mini-Cog test consisting of the CDT and 3-word recall task to predict postoperative delirium.Results:A total of 117 patients(30%)had abnormal CDT results.Postoperative delirium occurred in 29 patients(7%).On multivariate analysis,American Society of Anesthesiologists physical status≥3(odds ratio[OR],5.0;p=0.01),abnormal CDT(OR,4.8;p<0.001),preoperative benzodiazepine use(OR,4.9;p<0.001),and operative time≥237minutes(OR,3.0;p=0.01)were independent risk factors for postoperative delirium.The area under the curve for predicting postoperative deliriumwas 0.709 for CDT alone and 0.743 for the Mini-Cog test.No significant intergroup difference was observed(p=0.43).Conclusions:The CDT served as a formal but simple tool with adequate predictive power to identify the risk of postoperative delirium among patients undergoing major urological cancer surgery.Effective screening using the CDT might help provide optimal urological care for older patients.
基金The authors thank H.Awano and S.Sumi for technical support.This work was partly supported by JSPS Grant-in-Aid(grant number:JP19H02553),the Center of Spintronics Research Network of Japan.
文摘Machine learning is applied to a large number of modern devices that are essential in building an energy-efficient smart society.Audio and face recognition are among the most well-known technologies that make use of such artificial intelligence.In materials research,machine learning is adapted to predict materials with certain functionalities,an approach often referred to as materials informatics.Here,we show that machine learning can be used to extract material parameters from a single image obtained in experiments.The Dzyaloshinskii–Moriya(DM)interaction and the magnetic anisotropy distribution of thin-film heterostructures,parameters that are critical in developing next-generation storage class magnetic memory technologies,are estimated from a magnetic domain image.Micromagnetic simulation is used to generate thousands of random images for training and model validation.A convolutional neural network system is employed as the learning tool.The DM exchange constant of typical Co-based thin-film heterostructures is studied using the trained system:the estimated values are in good agreement with experiments.Moreover,we show that the system can independently determine the magnetic anisotropy distribution,demonstrating the potential of pattern recognition.This approach can considerably simplify experimental processes and broaden the scope of materials research.
