Generative pretrained transformer 4:an innovative approach to facilitate value-based healthcare

Objective Appropriate medical imaging is important for value-based care.We aim to evaluate the performance of generative pretrained transformer 4(GPT-4),an innovative natural language processing model,providing appropriate medical imaging automatically in different clinical scenarios.Methods Institutional Review Boards(IRB)approval was not required due to the use of nonidentifiable data.Instead,we used 112 questions from the American College of Radiology(ACR)Radiology-TEACHES Program as prompts,which is an open-sourced question and answer program to guide appropriate medical imaging.We included 69 free-text case vignettes and 43 simplified cases.For the performance evaluation of GPT-4 and GPT-3.5,we considered the recommendations of ACR guidelines as the gold standard,and then three radiologists analyzed the consistency of the responses from the GPT models with those of the ACR.We set a five-score criterion for the evaluation of the consistency.A paired t-test was applied to assess the statistical significance of the findings.Results For the performance of the GPT models in free-text case vignettes,the accuracy of GPT-4 was 92.9%,whereas the accuracy of GPT-3.5 was just 78.3%.GPT-4 can provide more appropriate suggestions to reduce the overutilization of medical imaging than GPT-3.5(t=3.429,P=0.001).For the performance of the GPT models in simplified scenarios,the accuracy of GPT-4 and GPT-3.5 was 66.5%and 60.0%,respectively.The differences were not statistically significant(t=1.858,P=0.070).GPT-4 was characterized by longer reaction times(27.1 s in average)and extensive responses(137.1 words on average)than GPT-3.5.Conclusion As an advanced tool for improving value-based healthcare in clinics,GPT-4 may guide appropriate medical imaging accurately and efficiently。

Effect of arteriosclerotic intracranial arterial vessel wall enhancement on downstream collateral flow

Background:The effect of arteriosclerotic intracranial arterial vessel wall enhancement(IAVWE)on downstream collateral flow found in vessel wall imaging(VWI)is not clear.Regardless of the mechanism underlying IAVWE on VWI,damage to the patient’s nervous system caused by IAVWE is likely achieved by affecting downstream cerebral blood flow.The present study aimed to investigate the effect of arteriosclerotic IAVWE on downstream collateral flow.Methods:The present study recruited 63 consecutive patients at the Second Hospital of Hebei Medical University from January 2021 to November 2021 with underlying atherosclerotic diseases and unilateral middle cerebral artery(MCA)M1-segment stenosis who underwent an magnetic resonance scan within 3 days of symptom onset.The patients were divided into 4 groups according to IAVWE and the stenosis ratio(Group 1,n=17;Group 2,n=19;Group 3,n=13;Group 4,n=14),and downstream collateral flow was analyzed using three-dimensional pseudocontinuous arterial spin labeling(3D-pCASL)and RAPID software.The National Institutes of Health Stroke Scale(NIHSS)scores of the patients were also recorded.Two-factor multivariate analysis of variance using Pillai’s trace was used as the main statistical method.Results:No statistically significant difference was found in baseline demographic characteristics among the groups.IAVWE,but not the stenosis ratio,had a statistically significant significance on the late-arriving retrograde flow proportion(LARFP),hypoperfusion intensity ratio(HIR),and NIHSS scores(F=20.941,P<0.001,Pillai’s trace statistic=0.567).The between-subject effects test showed that IAVWE had a significant effect on the three dependent variables:LARFP(R^(2)=0.088,F=10.899,P=0.002),HIR(R^(2)=0.234,F=29.354,P<0.001),and NIHSS(R^(2)=114.339,F=33.338,P<0.001).Conclusions:Arteriosclerotic IAVWE significantly reduced downstream collateral flow and affected relevant neurological deficits.It was an independent factor affecting downstream collateral flow and NIHSS scores,which should be a focus of future studies.Trial Registration:ChiCTR.org.cn,ChiCTR2100053661.

Effects of irrigation water regime, soil clay content and their combination on growth,yield,and water use efficiency of rice grown in South China

To investigate the effect of irrigation regime,soil clay content and their combination on growth,yield,and water productivity of rice,a shelter experiment was conduct using Randomized Complete Block Design(RCBD)with a factorial arrangement of treatments with four replications.Irrigation regime was the main treatment investigated,set in three levels as R(30 mm-100%)(100%of saturation and 30 mm flooded),R(30 mm-90%)(90%of saturation and 30 mm flooded)and R(30 mm-70%)(70%saturation and 30 mm flooded),respectively.The sub-treatment was soil type,set in three levels as 40%,50%and 60%clay content,respectively.Results showed that irrigation regime and soil clay content had significant effects on growth,yield and water productivity of rice.However,their combination showed no significant impact on panicles number,root biomass,harvest index and irrigation water productivity.Higher soil clay content results in increase in growth,yield,and water productivity of rice.The total water consumption during R(30 mm-100%)was higher than that during R(30 mm-90%)and R(30 mm-70%)because the latter two saturation levels led to the cracking of soil and decrease of total number of irrigations.Cracks were consistently getting more serious with the reduction in soil water content and the increase in soil clay content.Cracks in soil will preferentially become the major routes of water losses,thus water percolation during R(30 mm-70%)was higher than that during R(30 mm-90%)and R(30 mm-100%)after each irrigation event.The total water use under R(30 mm-70%)exceeded the water consumption under R(30 mm-90%)due to the great amount of soil cracking as well as the excessive volume of standing water depth.Considering water consumption and grain yield,the following conclusion can be reached:(i)The reduction in water consumption was greater than the reduction in grain yield in the case of drying soil 10%below saturation before reflooding.(ii)The reduction in water consumption was less than the reduction in grain yield in the case of drying soil 30%below saturation before reflooding;(iii)The increase in water use was greater than the increase in grain yield in the case of maintaining soil moisture at 100%of saturation before reflooding.Therefore,the water use efficiency was recorded in the order of R(30 mm-90%)>R(30 mm-100%)>R(30 mm-70%).

Diagnostic Accuracy of the Apparent Diffusion Coefficient for Microvascular Invasion in Hepatocellular Carcinoma: A Meta-analysis

Background and Aims:Microvascular invasion(MVI)is a major risk factor for the early recurrence of hepatocel-lular carcinoma(HCC)and it seriously worsens the prog-nosis.Accurate preoperative evaluation of the presence of MVI could greatly benefit the treatment management and prognosis prediction of HCC patients.The study aim was to evaluate the diagnostic performance of the apparent dif-fusion coefficient(ADC),a quantitative parameter for the preoperative diagnosis MVI in HCC patients.Methods:Original articles about diffusion-weighted imaging(DWI)and/or intravoxel incoherent motion(IVIM)conducted on a 3.0 or 1.5 Tesla magnetic resonance imaging(MRI)system indexed through January 17,2021were collected from MED-LINE/PubMed,Web of Science,EMBASE,and the Cochrane Library.Methodological quality was evaluated using Quality Assessment of Diagnostic Accuracy Studies 2(QUADAS-2).The pooled sensitivity,specificity,and summary area un-der the receiver operating characteristic curve(AUROC)were calculated,and meta-regression analysis was per-formed using a bivariate random effects model through a meta-analysis.Results:Nine original articles with a total of 988 HCCs were included.Most studies had low bias risk and minimal applicability concerns.The pooled sensitivity,specificity and AUROC of the ADC value were 73%,70%,and 0.78,respectively.The time interval between the index test and the reference standard was identified as a pos-sible source of heterogeneity by subgroup meta-regression analysis.Conclusions:Meta-analysis showed that the ADC value had moderate accuracy for predicting MVI in HCC.The time interval accounted for the heterogeneity.

Performance evaluation of deep learning-based post-processing and diagnostic reporting system for coronary CT angiography: a clinical comparative study

To the Editor:Coronary computed tomography angiography(CCTA)has been increasingly,widely performed for diagnosing coronary artery,disease,lAnatomical diagnosis,that is,stenosis grading,is stillthe main diagnostic index provided'by most CCTA tests.Post-processing and interpretation of stenosis are 2 essential'steps that need to be performed bycardiovascular imaging professionals from scan completion to diagnosis conclusion,which is repetitive and time-consuming,taking an average of 30 minutes each case in China and becoming the bottleneck and gradually creating an imbalance between supply and demand.In ine with the rapid development of artificial intelligence(Al)technology in recent years,it has been expected to solve these specific problems.We developed an AI system for automating post-processing and diagnostic reporting of CCTA data using deep learning algorithms to establishanew1-clickworkflowforeverydayuse,namely,CCTA-AI(Figure 1).To further assess its capabilities,this study intends to answer 2 following questions:To what extent can it improve the efficiency of post-processing?To what extent can CCTA-AI detect and calculate coronary artery stenosis due to each atherosclerotic plaque?

Clinical practice guideline for body composition assessment based on upper abdominal magnetic resonance images annotated using artificial intelligence

Introduction Upper abdominal magnetic resonance(MR)imaging is appropriate for body composition analysis.111 Especially for individuals with obesity,it is of great value to quantify the hepatic proton density fat fraction(PDFF)and the amount of abdominal adipose tissue during clinical evaluation and for research on obesity-related risks.Analytical results may be used to determine the optimal choice of surgical procedure and evaluate treatment outcomes.Multiple artificial intelligence(Al)algorithms and systems have been developed for the automated measurement of body composition.The basis of Al development and application is to have uniform standards for clinical data acquisition and management.The uneven quality ofMR images is one ofthe major obstacles to Al system development and analytical results.A standardized process of MR scanning and clinical data management is urgently needed.

Spatial-temporal distribution and impact factors of irrigation water use efficiency in the grain production of China

The marginal water productivity(MWP)model for the real irrigation water use performance and productivity assessment,applies to the regional scale was established in this study.The temporal-spatial patterns and attribution analyses of the indicator were conducted using spatial autocorrelation and path analysis methods.The results showed that with an average annual increase of 3.4%,the national MWP was estimated to be 0.542 kg/m,between 1998 and 2010.The spatial autocorrelation analysis results showed the global Moran’s I inspection values(Z)were higher than the confidence level,and the provinces,municipalities and autonomous regions(PAMs)with similar MWP values showed significant aggregation.Regions with a high value are centered in the middle and lower streams of the Yellow River,and those regions with a lower MWP were distributed in northeastern China and south of the Yangtze River.The precipitation and temperature are the major meteorological factors that determined the indicator,while extending the fertilizer and agricultural machinery input is the effective approach for improving the regional MWP.The major grain producing areas of North and Northeast China should take measures to raise their MWP,ensure food security and the sustainable use of water resources.