Machine learning applications in healthcare clinical practice and research

Machine learning(ML)is a type of artificial intelligence that assists computers in the acquisition of knowledge through data analysis,thus creating machines that can complete tasks otherwise requiring human intelligence.Among its various applications,it has proven groundbreaking in healthcare as well,both in clinical practice and research.In this editorial,we succinctly introduce ML applications and present a study,featured in the latest issue of the World Journal of Clinical Cases.The authors of this study conducted an analysis using both multiple linear regression(MLR)and ML methods to investigate the significant factors that may impact the estimated glomerular filtration rate in healthy women with and without non-alcoholic fatty liver disease(NAFLD).Their results implicated age as the most important determining factor in both groups,followed by lactic dehydrogenase,uric acid,forced expiratory volume in one second,and albumin.In addition,for the NAFLD-group,the 5th and 6th most important impact factors were thyroid-stimulating hormone and systolic blood pressure,as compared to plasma calcium and body fat for the NAFLD+group.However,the study's distinctive contribution lies in its adoption of ML methodologies,showcasing their superiority over traditional statistical approaches(herein MLR),thereby highlighting the potential of ML to represent an invaluable advanced adjunct tool in clinical practice and research.

Synthetic data as an investigative tool in hypertension and renal diseases research

There is a growing body of clinical research on the utility of synthetic data derivatives,an emerging research tool in medicine.In nephrology,clinicians can use machine learning and artificial intelligence as powerful aids in their clinical decision-making while also preserving patient privacy.This is especially important given the epidemiology of chronic kidney disease,renal oncology,and hypertension worldwide.However,there remains a need to create a framework for guidance regarding how to better utilize synthetic data as a practical application in this research.

Harnessing artificial intelligence for identifying conflicts of interest in research

This editorial explores the transformative potential of artificial intelligence(AI)in identifying conflicts of interest(COIs)within academic and scientific research.By harnessing advanced data analysis,pattern recognition,and natural language processing techniques,AI offers innovative solutions for enhancing transparency and integrity in research.This editorial discusses how AI can automatically detect COIs,integrate data from various sources,and streamline reporting processes,thereby maintaining the credibility of scientific findings.

Real-world efficacy and safety of tofacitinib treatment in Asian patients with ulcerative colitis

BACKGROUND Real-world data on tofacitinib(TOF)covering a period of more than 1 year for a sufficient number of Asian patients with ulcerative colitis(UC)are scarce.AIM To investigate the long-term efficacy and safety of TOF treatment for UC,including clinical issues.METHODS We performed a retrospective single-center observational analysis of 111 UC patients administered TOF at Hyogo Medical University as a tertiary inflammatory bowel disease center.All consecutive UC patients who received TOF between May 2018 and February 2020 were enrolled.Patients were followed up until August 2020.The primary outcome was the clinical response rate at week 8.Secondary outcomes included clinical remission at week 8,cumulative persistence rate of TOF administration,colectomy-free survival,relapse after tapering of TOF and predictors of clinical response at week 8 and week 48.RESULTS The clinical response and remission rates were 66.3%and 50.5%at week 8,and 47.1%and 43.5%at week 48,respectively.The overall cumulative clinical remission rate was 61.7%at week 48 and history of anti-tumor necrosis factor-alpha(TNF-α)agents use had no influence(P=0.25).The cumulative TOF persistence rate at week 48 was significantly lower in patients without clinical remission than in those with remission at week 8(30.9%vs 88.1%;P<0.001).Baseline partial Mayo Score was significantly lower in responders vs non-responders at week 8(odds ratio:0.61,95%confidence interval:0.45-0.82,P=0.001).Relapse occurred in 45.7%of patients after TOF tapering,and 85.7%of patients responded within 4 wk after re-increase.All 6 patients with herpes zoster(HZ)developed the infection after achieving remission by TOF.CONCLUSION TOF was more effective in UC patients with mild activity at baseline and its efficacy was not affected by previous treatment with anti-TNF-αagents.Most relapsed patients responded again after re-increase of TOF and nearly half relapsed after tapering off TOF.Special attention is needed for tapering and HZ.

Clinical manifestation,lifestyle,and treatment patterns of chronic erosive gastritis:A multicenter real-world study in China

BACKGROUND Although chronic erosive gastritis(CEG)is common,its clinical characteristics have not been fully elucidated.The lack of consensus regarding its treatment has resulted in varied treatment regimens.AIM To explore the clinical characteristics,treatment patterns,and short-term outcomes in CEG patients in China.METHODS We recruited patients with chronic non-atrophic or mild-to-moderate atrophic gastritis with erosion based on endoscopy and pathology.Patients and treating physicians completed a questionnaire regarding history,endoscopic findings,and treatment plans as well as a follow-up questionnaire to investigate changes in symptoms after 4 wk of treatment.RESULTS Three thousand five hundred sixty-three patients from 42 centers across 24 cities in China were included.Epigastric pain(68.0%),abdominal distension(62.6%),and postprandial fullness(47.5%)were the most common presenting symptoms.Gastritis was classified as chronic non-atrophic in 69.9%of patients.Among those with erosive lesions,72.1%of patients had lesions in the antrum,51.0%had multiple lesions,and 67.3%had superficial flat lesions.In patients with epigastric pain,the combination of a mucosal protective agent(MPA)and proton pump inhibitor was more effective.For those with postprandial fullness,acid regurgitation,early satiety,or nausea,a MPA appeared more promising.CONCLUSION CEG is a multifactorial disease which is common in Asian patients and has non-specific symptoms.Gastroscopy may play a major role in its detection and diagnosis.Treatment should be individualized based on symptom profile.

Research funding and citations in papers of Nobel Laureates in Physics, Chemistry and Medicine, 2019-2020

Purpose:The goal of this study is a comparative analysis of the relation between funding(a main driver for scientific research)and citations in papers of Nobel Laureates in physics,chemistry and medicine over 2019-2020 and the same relation in these research fields as a whole.Design/methodology/approach:This study utilizes a power law model to explore the relationship between research funding and citations of related papers.The study here analyzes 3,539 recorded documents by Nobel Laureates in physics,chemistry and medicine and a broader dataset of 183,016 documents related to the fields of physics,medicine,and chemistry recorded in the Web of Science database.Findings:Results reveal that in chemistry and medicine,funded researches published in papers of Nobel Laureates have higher citations than unfunded studies published in articles;vice versa high citations of Nobel Laureates in physics are for unfunded studies published in papers.Instead,when overall data of publications and citations in physics,chemistry and medicine are analyzed,all papers based on funded researches show higher citations than unfunded ones.Originality/value:Results clarify the driving role of research funding for science diffusion that are systematized in general properties:a)articles concerning funded researches receive more citations than(un)funded studies published in papers of physics,chemistry and medicine sciences,generating a high Matthew effect(a higher growth of citations with the increase in the number of papers);b)research funding increases the citations of articles in fields oriented to applied research(e.g.,chemistry and medicine)more than fields oriented towards basic research(e.g.,physics).Practical implications:The results here explain some characteristics of scientific development and diffusion,highlighting the critical role of research funding in fostering citations and the expansion of scientific knowledge.This finding can support decision-making of policymakers and R&D managers to improve the effectiveness in allocating financial resources in science policies to generate a higher positive scientific and societal impact.

General laws of funding for scientific citations:how citations change in funded and unfunded research between basic and applied sciences

Purpose:The goal of this study is to analyze the relationship between funded and unfunded papers and their citations in both basic and applied sciences.Design/methodology/approach:A power law model analyzes the relationship between research funding and citations of papers using 831,337 documents recorded in the Web of Science database.Findings:The original results reveal general characteristics of the diffusion of science in research fields:a)Funded articles receive higher citations compared to unfunded papers in journals;b)Funded articles exhibit a super-linear growth in citations,surpassing the increase seen in unfunded articles.This finding reveals a higher diffusion of scientific knowledge in funded articles.Moreover,c)funded articles in both basic and applied sciences demonstrate a similar expected change in citations,equivalent to about 1.23%,when the number of funded papers increases by 1%in journals.This result suggests,for the first time,that funding effect of scientific research is an invariant driver,irrespective of the nature of the basic or applied sciences.Originality/value:This evidence suggests empirical laws of funding for scientific citations that explain the importance of robust funding mechanisms for achieving impactful research outcomes in science and society.These findings here also highlight that funding for scientific research is a critical driving force in supporting citations and the dissemination of scientific knowledge in recorded documents in both basic and applied sciences.Practical implications:This comprehensive result provides a holistic view of the relationship between funding and citation performance in science to guide policymakers and R&D managers with science policies by directing funding to research in promoting the scientific development and higher diffusion of results for the progress of human society.

Research Progress and Prospects of Total Factor Productivity in the Construction Industry

The high-quality development of the construction industry fundamentally stems from the significant improvement of total factor productivity.Therefore,it is of crucial significance for promoting the development of the construction industry to a higher level by scientifically and accurately measuring the total factor productivity of the construction industry and deeply analyzing the influencing factors behind it.Based on a comprehensive consideration of research methods and influencing factors,this paper systematically reviews the existing relevant literature on total factor productivity in the construction industry,aiming to reveal the current research development trend in this field and point out potential problems.This effort aims to provide a solid theoretical foundation and valuable reference for further in-depth research,and jointly promote the continuous progress and development of total factor productivity research in the construction industry.

Recent Ventures in Interdisciplinary Arctic Research:The ARCPATH Project

This paper celebrates Professor Yongqi GAO's significant achievement in the field of interdisciplinary studies within the context of his final research project Arctic Climate Predictions: Pathways to Resilient Sustainable Societies-ARCPATH(https://www.svs.is/en/projects/finished-projects/arcpath). The disciplines represented in the project are related to climatology, anthropology, marine biology, economics, and the broad spectrum of social-ecological studies. Team members were drawn from the Nordic countries, Russia, China, the United States, and Canada. The project was transdisciplinary as well as interdisciplinary as it included collaboration with local knowledge holders. ARCPATH made significant contributions to Arctic research through an improved understanding of the mechanisms that drive climate variability in the Arctic. In tandem with this research, a combination of historical investigations and social, economic, and marine biological fieldwork was carried out for the project study areas of Iceland, Greenland, Norway, and the surrounding seas, with a focus on the joint use of ocean and sea-ice data as well as social-ecological drivers. ARCPATH was able to provide an improved framework for predicting the near-term variation of Arctic climate on spatial scales relevant to society, as well as evaluating possible related changes in socioeconomic realms. In summary, through the integration of information from several different disciplines and research approaches, ARCPATH served to create new and valuable knowledge on crucial issues, thus providing new pathways to action for Arctic communities.

关于现阶段我国英文期刊办刊模式的思考——以Research等期刊为例

近年来,国内兴起了创办英文科技期刊热潮。本文以此为视角,分析了我国创办英文期刊现状及问题。通过查阅文献和新闻报道,以中国科协和美国科学促进会合作共同创办的英文期刊Research等近年来国内创办的高水平英文新刊为例,详细分析了案例从创刊到快速发展成为高影响力科技期刊的路径,主要包括选择办刊人才、明确办刊定位、组建编委会、邀约优质稿源、加大媒体宣传等,以期为正在筹备创办新刊的同行提供借鉴,也为相关部门决策提供建议参考。

Can ChatGPT evaluate research quality?

Purpose:Assess whether ChatGPT 4.0 is accurate enough to perform research evaluations on journal articles to automate this time-consuming task.Design/methodology/approach:Test the extent to which ChatGPT-4 can assess the quality of journal articles using a case study of the published scoring guidelines of the UK Research Excellence Framework(REF)2021 to create a research evaluation ChatGPT.This was applied to 51 of my own articles and compared against my own quality judgements.Findings:ChatGPT-4 can produce plausible document summaries and quality evaluation rationales that match the REF criteria.Its overall scores have weak correlations with my self-evaluation scores of the same documents(averaging r=0.281 over 15 iterations,with 8 being statistically significantly different from 0).In contrast,the average scores from the 15 iterations produced a statistically significant positive correlation of 0.509.Thus,averaging scores from multiple ChatGPT-4 rounds seems more effective than individual scores.The positive correlation may be due to ChatGPT being able to extract the author’s significance,rigour,and originality claims from inside each paper.If my weakest articles are removed,then the correlation with average scores(r=0.200)falls below statistical significance,suggesting that ChatGPT struggles to make fine-grained evaluations.Research limitations:The data is self-evaluations of a convenience sample of articles from one academic in one field.Practical implications:Overall,ChatGPT does not yet seem to be accurate enough to be trusted for any formal or informal research quality evaluation tasks.Research evaluators,including journal editors,should therefore take steps to control its use.Originality/value:This is the first published attempt at post-publication expert review accuracy testing for ChatGPT.

Research on Retrospective Studies of Real-World Study and Its Selection Bias

Objective To provide references for improving the authenticity and reliability of the retrospective study results,thus improving the quality of evidence in the real world and strengthening drug supervision and decision-making.Methods Literature review was used to study the data sources,the characteristics of retrospective research,the sources and the corrections of selective bias in the real world.Results and Conclusion The biases in retrospective study mainly come from admission rate bias,patient rate bias,survivors bias,health user bias and symptom bias.

Clinical outcomes of second-line chemotherapy in patients with advanced pancreatic adenocarcinoma:a real-world study

Objective:Little progress has been made in recent years using first-line chemotherapy,including gemcitabine combined with nab-paclitaxel,FOLFIRINOX,and NALIRIFOX,for advanced pancreatic adenocarcinoma(APC).In addition,the optimal second-line chemotherapy regimen has not been determined.This study aimed to compare the effectiveness of different types of second-line chemotherapy for APC.Methods:Patients with APC who received first-line treatment from January 2008 to January 2021 were considered eligible for this retrospective analysis.The primary and secondary endpoints were overall survival(OS)and progression-free survival(PFS),respectively.Results:Four hundred and thirty-seven and 617 patients were treated with 5-fluorouracil-and gemcitabine-based chemotherapy as first-line treatment,respectively.Demographic and clinical features,except age and liver metastasis,were comparable between the two groups(P<0.05).The median OS was 8.8 and 7.8 months in patients who received a 5-fluorouracil-and gemcitabine-based combined regimen for first-line therapy,respectively(HR=1.244,95%CI=1.090–1.419;P<0.001).The median OS was 5.6 and 1.9 months in patients who received second-line chemotherapy and supportive care,respectively(HR=0.766,95%CI=0.677–0.867;P<0.001).The median PFS was not significantly differently between gemcitabine or 5-fluorouracil monotherapy and combination therapy.Conclusions:A 5-fluorouracil-or gemcitabine-based combined regimen was shown to be as effective as a single 5-fluorouracil or gemcitabine regimen as second-line therapy for patients with APC.

EU Real-World Evidence Supports New Drug Research and Development Decisions and Its Implications for China

Objective To analyze the application of EU real-world evidence in the decision-making of new drug research and development(R&D),and to provide policy recommendations for China’s government to make new drug R&D decisions.Methods The relevant policy documents of the EU on the development of new drugs and other domestic and foreign literature on the real-world evidence were analyzed to obtain the role and application of the current EU real-world evidence in the implementation of new drug development policies.Results and Conclusion At present,the EU is carrying out the national synchronous scientific advisory policy,urging the formation of a European innovation framework,and providing decision-making for new drug R&D selection and program design based on real-world evidence.It is recommended that China build a real-world medical database and design a new drug screening platform to help companies,scientific research institutions assess target drugs.In addition,a national scientific advisory platform should be set up to integrate scientific research strength and provide technical support for new drug R&D institutions.

Citation distributions and research evaluations:The impossibility of formulating a universal indicator

Purpose:To analyze the diversity of citation distributions to publications in different research topics to investigate the accuracy of size-independent,rank-based indicators.The top percentile-based indicators are the most common indicators of this type,and the evaluations of Japan are the most evident misjudgments.Design/methodology/approach:The distributions of citations to publications from countries and journals in several research topics were analyzed along with the corresponding global publications using histograms with logarithmic binning,double rank plots,and normal probability plots of log-transformed numbers of citations.Findings:Size-independent,top percentile-based indicators are accurate when the global ranks of local publications fit a power law,but deviations in the least cited papers are frequent in countries and occur in all journals with high impact factors.In these cases,a single indicator is misleading.Comparisons of the proportions of uncited papers are the best way to predict these deviations.Research limitations:This study is fundamentally analytical,and its results describe mathematical facts that are self-evident.Practical implications:Respectable institutions,such as the OECD,the European Commission,and the U.S.National Science Board,produce research country rankings and individual evaluations using size-independent percentile indicators that are misleading in many countries.These misleading evaluations should be discontinued because they can cause confusion among research policymakers and lead to incorrect research policies.Originality/value:Studies linking the lower tail of citation distribution,including uncited papers,to percentile research indicators have not been performed previously.The present results demonstrate that studies of this type are necessary to find reliable procedures for research assessments.

Performance evaluation of seven multi-label classification methods on real-world patent and publication datasets

Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.

Research Hotspots and Trends Analysis of Real-World Data Based on Social Network Analysis and Knowledge Graph

Objective To study the research status,research hotspots and development trends in the field of real-world data(RWD)through social network analysis and knowledge graph analysis.Methods RWD of the past 10 years were retrieved,and literature metrological analysis was made by using UCINET and CiteSpace from CNKI.Results and Conclusion The frequency and centrality of related keywords such as real-world study,hospital information system(HIS),drug combination,data mining and TCM are high.The clusters labeled as clinical medication and RWD contain more keywords.In recent 4 years,there are more articles involving the keywords of data specification,data authenticity,data security and information security.Among them,compound Kushen injection,HIS database and RWD are the top three keywords.It is a long-term research hotspot for Chinese and western medicine to use HIS to study clinical medication,clinical characteristics,diseases and injections.Besides,the research of RWD database has changed from construction to standardized collection and governance,which can make RWD effective.Data authenticity,data security and information security will become the new hotspots in the research of RWD.

Research on Real-World Evidence and Application in EU and Its Enlightment to China

Objective To analyze the research and application status of real-world evidence(RWE)in the European Union(EU)and provide a reference for China’s government.Methods By consulting the policy guidelines issued by EU EMA and the documents of European countries at home and abroad,the basic principles and case notes of EU RWE implementation were comprehensively analyzed.Results and Conclusion Research on RWE in EU is mainly carried out from four aspects:R&D decision,application of expanded trial certificate,medical insurance decision,and supervision decision,which plays an important role in the progress of European clinical medicine.Therefore,researchers in China should draw lessons from these four perspectives and design reasonable research directions and programs.

Patients Involved in Funding Research.A Look Back at the Unique Experience of the ECLAIR Working Group of Canceropole CLARA

This article aims to share an innovative experience of organizing and funding research involving those most directly affected:patients.The“ECLAIR”working group of the Canceropole Lyon Auvergne-Rhone-Alpes(CLARA)was created at the end of 2020 with the goal of contributing to the development of a call for projects on the patient experience in oncology,which was launched in January 2021.Initially composed of 8 members,including 7 patients,coordinated by a project manager from CLARA,the ECLAIR working group actively participated in drafting the specifications of the call for projects,developing the eligibility criteria for applications,revising the evaluation and selection criteria for projects,and monitoring the selected projects.This experience was repeated twice.With significant freedom of action,the working group made two decisions that strongly demonstrate the commitment to supporting research partnerships and the active involvement of those affected:firstly,by making partnership a mandatory requirement for the eligibility of applications,and secondly,by conducting the selection of projects themselves,after an independent scientific evaluation phase.Seeking to shed light on the“black box”of partnership,the article also presents the concrete modalities of interaction among the working group members,the adjustments made between different editions of the call for projects,and the relationships maintained with CLARA.

A hierarchical enhanced data-driven battery pack capacity estimation framework for real-world operating conditions with fewer labeled data

Battery pack capacity estimation under real-world operating conditions is important for battery performance optimization and health management,contributing to the reliability and longevity of batterypowered systems.However,complex operating conditions,coupling cell-to-cell inconsistency,and limited labeled data pose great challenges to accurate and robust battery pack capacity estimation.To address these issues,this paper proposes a hierarchical data-driven framework aimed at enhancing the training of machine learning models with fewer labeled data.Unlike traditional data-driven methods that lack interpretability,the hierarchical data-driven framework unveils the“mechanism”of the black box inside the data-driven framework by splitting the final estimation target into cell-level and pack-level intermediate targets.A generalized feature matrix is devised without requiring all cell voltages,significantly reducing the computational cost and memory resources.The generated intermediate target labels and the corresponding features are hierarchically employed to enhance the training of two machine learning models,effectively alleviating the difficulty of learning the relationship from all features due to fewer labeled data and addressing the dilemma of requiring extensive labeled data for accurate estimation.Using only 10%of degradation data,the proposed framework outperforms the state-of-the-art battery pack capacity estimation methods,achieving mean absolute percentage errors of 0.608%,0.601%,and 1.128%for three battery packs whose degradation load profiles represent real-world operating conditions.Its high accuracy,adaptability,and robustness indicate the potential in different application scenarios,which is promising for reducing laborious and expensive aging experiments at the pack level and facilitating the development of battery technology.