AIM: To build and evaluate predictive models for contrast-enhanced ultrasound(CEUS) of the breast to distinguish between benign and malignant lesions. METHODS: A total of 235 breast imaging reporting and data system(B...AIM: To build and evaluate predictive models for contrast-enhanced ultrasound(CEUS) of the breast to distinguish between benign and malignant lesions. METHODS: A total of 235 breast imaging reporting and data system(BI-RADS) 4 solid breast lesions were imaged via CEUS before core needle biopsy or surgical resection. CEUS results were analyzed on 10 enhancing patterns to evaluate diagnostic performance of three benign and three malignant CEUS models, with pathological results used as the gold standard. A logistic regression model was developed basing on the CEUS results, and then evaluated with receiver operating curve(ROC). RESULTS: Except in cases of enhanced homogeneity, the rest of the 9 enhancement appearances were statistically significant(P < 0.05). These 9 enhancement patterns were selected in the final step of the logistic regression analysis, with diagnostic sensitivity and specificity of 84.4% and 82.7%, respectively, and the area under the ROC curve of 0.911. Diagnostic sensitivity, specificity, and accuracy of the malignant vs benign CEUS models were 84.38%, 87.77%, 86.38% and 86.46%, 81.29% and 83.40%, respectively. CONCLUSION: The breast CEUS models can predict risk of malignant breast lesions more accurately, decrease false-positive biopsy, and provide accurate BIRADS classification.展开更多
The audit profession field is the dominant force to push forward every revision of audit reporting model during many significant revisions before the beginning of the 21 st century, and they have a prominent tendency ...The audit profession field is the dominant force to push forward every revision of audit reporting model during many significant revisions before the beginning of the 21 st century, and they have a prominent tendency to protect auditing industry instead of a response to the users＇ information demand for investment decision. Traditional audit reporting model cannot satisfy the need of modem auditing, and it is essential to reconstruct current audit reporting model of modem risk-oriented auditing （MRA） during the post-financial crisis era, because it lacks communication value, valuable information, and effective alert information. The study provides the main contents about the reconstruction plan of the Public Company Accounting Oversight Board （PCAOB）： auditor＇s discussion and analysis （AD＆A）, required and expanded use of emphasis paragraphs in the auditor＇s report, auditor assurance on other information outside the financial statements, and clarification of language in the standard auditor＇s report. Then, the study discusses the effects of the reconstruction of audit reporting model on different stakeholders of audit including the auditors, the investors, the regulators, and the researchers.展开更多
大语言模型(large language model,LLM)医学研究数量激增,建立标准化、透明化的报告规范变得尤为重要。2025年1月,Nature Medicine发表LLM医学研究报告指南(TRIPOD-LLM),是首个专门针对基于LLM构建预测模型研究的综合性报告框架,其内容...大语言模型(large language model,LLM)医学研究数量激增,建立标准化、透明化的报告规范变得尤为重要。2025年1月,Nature Medicine发表LLM医学研究报告指南(TRIPOD-LLM),是首个专门针对基于LLM构建预测模型研究的综合性报告框架,其内容包括1个清单(19个主条目、50个子条目)、1个流程图和摘要清单(12个条目)。本文从TRIPOD-LLM的制订方法、主要内容、适用范围及各条目的具体内容进行解读,帮助研究者、临床医生、编辑、医疗决策者深入理解并正确使用TRIPOD-LLM,提高LLM医学研究报告质量和透明度,促进LLM规范、伦理地融入医疗领域。展开更多
随着大语言模型(large language models,LLMs)在医学诊断、科研与教育等领域的广泛应用,其卓越的生成与推理能力已显著展现优势。然而,医学领域对伦理、隐私保护及模型准确性的严格标准,也使LLMs的实际应用面临严峻挑战。尽管个体预后...随着大语言模型(large language models,LLMs)在医学诊断、科研与教育等领域的广泛应用,其卓越的生成与推理能力已显著展现优势。然而,医学领域对伦理、隐私保护及模型准确性的严格标准,也使LLMs的实际应用面临严峻挑战。尽管个体预后或诊断的多变量模型透明报告(transparent reporting of a multivariable prediction model for individual prognosis or diagnosis,TRIPOD)+人工智能(artificial intelligence,AI)为预后或诊断预测模型提供了报告规范,但其在生成式人工智能研究中的适用性仍显不足。本文解读了在TRIPOD+AI基础上扩展形成的TRIPOD-LLM报告指南,系统梳理了其在模型构建、验证、任务适应性及人类监督等方面的报告要素,为提升医学领域LLMs研究的透明度、规范性与可复现性提供了参考。展开更多
背景围绝经期抑郁障碍(PDD)是发生在绝经前后的一种严重情绪障碍,中医药治疗PDD具有整体调节、辨证论治等优势,但目前缺乏专用的中医药治疗PDD疗效评价工具。目的引入患者报告结局(PROs),在中医理论指导下构建PDD-PROs量表及其理论模型...背景围绝经期抑郁障碍(PDD)是发生在绝经前后的一种严重情绪障碍,中医药治疗PDD具有整体调节、辨证论治等优势,但目前缺乏专用的中医药治疗PDD疗效评价工具。目的引入患者报告结局(PROs),在中医理论指导下构建PDD-PROs量表及其理论模型。方法2022年4—6月,使用计算机检索中国知网、万方数据知识服务平台、维普网、中国生物医学文献服务系统(SinoMed)、PubMed、Web of Science、Cochrane Library建库至2022-04-17发表的中医药治疗PDD相关文献,并进行文献分析;2022年9—11月,选取2017年1月—2022年8月在北京中医药大学深圳医院(龙岗)、北京中医药大学东方医院门诊就诊的136例PDD患者的病历进行回顾性分析,并根据自拟访谈提纲对PDD患者进行一对一半结构化访谈,建立条目池;筛选并建立PDD相关多学科专家咨询小组,2022年12月开始进行3轮Delphi法专家论证。结果最终纳入文献123篇,涉及5类12个PPD结局评价量表;回顾性病历分析与患者访谈结果显示,PPD临床症状累计出现频次为1465次,共涉及176个临床症状,经3轮Delphi法专家论证后,最终形成包含4个维度(心理维度、生理维度、社会维度、整体评价)43个条目的PDD中医PROs量表及理论模型。结论本研究引入国际上应用较为成熟的PROs,运用文献分析法、病历回顾法、患者访谈法等构建条目池,通过3轮Delphi法专家论证,在中医理论指导下成功构建PDD-PROs量表及其理论模型,可供中医药治疗PDD疗效评价研究等参考使用。展开更多
随着临床和生物大数据的极大丰富,机器学习技术通过结合多方面的信息以预测个体的健康结局,在科研及学术论文中应用日益广泛,但关键信息报告的不足也逐渐显现,包括数据偏倚、模型对不同群体的公平性、数据质量和适用性问题,以及在真实...随着临床和生物大数据的极大丰富,机器学习技术通过结合多方面的信息以预测个体的健康结局,在科研及学术论文中应用日益广泛,但关键信息报告的不足也逐渐显现,包括数据偏倚、模型对不同群体的公平性、数据质量和适用性问题,以及在真实临床环境中保持预测准确性和可解释性的难度等,增加了将预测模型安全有效地应用于临床实践的复杂性。针对这些问题,多变量预测模型个体预后或诊断的透明报告(transparent reporting of a multivariable prediction model for individual prognosis or diagnosis,TRIPOD)+人工智能(artificial intelligence,AI)声明在TRIPOD的基础上提出了针对机器学习模型的报告规范,以提升模型的透明性、可重复性和健康公平性,从而改善机器学习模型的应用质量。当前,国内基于机器学习技术的预测模型研究日益增多。为帮助国内读者更好地理解和应用TRIPOD+AI,笔者结合实例对其进行了解读,希望为研究人员报告质量提升提供支持。展开更多
文摘AIM: To build and evaluate predictive models for contrast-enhanced ultrasound(CEUS) of the breast to distinguish between benign and malignant lesions. METHODS: A total of 235 breast imaging reporting and data system(BI-RADS) 4 solid breast lesions were imaged via CEUS before core needle biopsy or surgical resection. CEUS results were analyzed on 10 enhancing patterns to evaluate diagnostic performance of three benign and three malignant CEUS models, with pathological results used as the gold standard. A logistic regression model was developed basing on the CEUS results, and then evaluated with receiver operating curve(ROC). RESULTS: Except in cases of enhanced homogeneity, the rest of the 9 enhancement appearances were statistically significant(P < 0.05). These 9 enhancement patterns were selected in the final step of the logistic regression analysis, with diagnostic sensitivity and specificity of 84.4% and 82.7%, respectively, and the area under the ROC curve of 0.911. Diagnostic sensitivity, specificity, and accuracy of the malignant vs benign CEUS models were 84.38%, 87.77%, 86.38% and 86.46%, 81.29% and 83.40%, respectively. CONCLUSION: The breast CEUS models can predict risk of malignant breast lesions more accurately, decrease false-positive biopsy, and provide accurate BIRADS classification.
基金The authors are grateful for research supports from the Humanities and Social Sciences Research Planning Fund Project of the Ministry of Education of China （Grant No. llYJA790179） and Shandong Provincial Natural Science Foundation, China （Grant No. ZR2010GM010）.
文摘The audit profession field is the dominant force to push forward every revision of audit reporting model during many significant revisions before the beginning of the 21 st century, and they have a prominent tendency to protect auditing industry instead of a response to the users＇ information demand for investment decision. Traditional audit reporting model cannot satisfy the need of modem auditing, and it is essential to reconstruct current audit reporting model of modem risk-oriented auditing （MRA） during the post-financial crisis era, because it lacks communication value, valuable information, and effective alert information. The study provides the main contents about the reconstruction plan of the Public Company Accounting Oversight Board （PCAOB）： auditor＇s discussion and analysis （AD＆A）, required and expanded use of emphasis paragraphs in the auditor＇s report, auditor assurance on other information outside the financial statements, and clarification of language in the standard auditor＇s report. Then, the study discusses the effects of the reconstruction of audit reporting model on different stakeholders of audit including the auditors, the investors, the regulators, and the researchers.
文摘大语言模型(large language model,LLM)医学研究数量激增,建立标准化、透明化的报告规范变得尤为重要。2025年1月,Nature Medicine发表LLM医学研究报告指南(TRIPOD-LLM),是首个专门针对基于LLM构建预测模型研究的综合性报告框架,其内容包括1个清单(19个主条目、50个子条目)、1个流程图和摘要清单(12个条目)。本文从TRIPOD-LLM的制订方法、主要内容、适用范围及各条目的具体内容进行解读,帮助研究者、临床医生、编辑、医疗决策者深入理解并正确使用TRIPOD-LLM,提高LLM医学研究报告质量和透明度,促进LLM规范、伦理地融入医疗领域。
文摘随着大语言模型(large language models,LLMs)在医学诊断、科研与教育等领域的广泛应用,其卓越的生成与推理能力已显著展现优势。然而,医学领域对伦理、隐私保护及模型准确性的严格标准,也使LLMs的实际应用面临严峻挑战。尽管个体预后或诊断的多变量模型透明报告(transparent reporting of a multivariable prediction model for individual prognosis or diagnosis,TRIPOD)+人工智能(artificial intelligence,AI)为预后或诊断预测模型提供了报告规范,但其在生成式人工智能研究中的适用性仍显不足。本文解读了在TRIPOD+AI基础上扩展形成的TRIPOD-LLM报告指南,系统梳理了其在模型构建、验证、任务适应性及人类监督等方面的报告要素,为提升医学领域LLMs研究的透明度、规范性与可复现性提供了参考。
文摘背景围绝经期抑郁障碍(PDD)是发生在绝经前后的一种严重情绪障碍,中医药治疗PDD具有整体调节、辨证论治等优势,但目前缺乏专用的中医药治疗PDD疗效评价工具。目的引入患者报告结局(PROs),在中医理论指导下构建PDD-PROs量表及其理论模型。方法2022年4—6月,使用计算机检索中国知网、万方数据知识服务平台、维普网、中国生物医学文献服务系统(SinoMed)、PubMed、Web of Science、Cochrane Library建库至2022-04-17发表的中医药治疗PDD相关文献,并进行文献分析;2022年9—11月,选取2017年1月—2022年8月在北京中医药大学深圳医院(龙岗)、北京中医药大学东方医院门诊就诊的136例PDD患者的病历进行回顾性分析,并根据自拟访谈提纲对PDD患者进行一对一半结构化访谈,建立条目池;筛选并建立PDD相关多学科专家咨询小组,2022年12月开始进行3轮Delphi法专家论证。结果最终纳入文献123篇,涉及5类12个PPD结局评价量表;回顾性病历分析与患者访谈结果显示,PPD临床症状累计出现频次为1465次,共涉及176个临床症状,经3轮Delphi法专家论证后,最终形成包含4个维度(心理维度、生理维度、社会维度、整体评价)43个条目的PDD中医PROs量表及理论模型。结论本研究引入国际上应用较为成熟的PROs,运用文献分析法、病历回顾法、患者访谈法等构建条目池,通过3轮Delphi法专家论证,在中医理论指导下成功构建PDD-PROs量表及其理论模型,可供中医药治疗PDD疗效评价研究等参考使用。
文摘随着临床和生物大数据的极大丰富,机器学习技术通过结合多方面的信息以预测个体的健康结局,在科研及学术论文中应用日益广泛,但关键信息报告的不足也逐渐显现,包括数据偏倚、模型对不同群体的公平性、数据质量和适用性问题,以及在真实临床环境中保持预测准确性和可解释性的难度等,增加了将预测模型安全有效地应用于临床实践的复杂性。针对这些问题,多变量预测模型个体预后或诊断的透明报告(transparent reporting of a multivariable prediction model for individual prognosis or diagnosis,TRIPOD)+人工智能(artificial intelligence,AI)声明在TRIPOD的基础上提出了针对机器学习模型的报告规范,以提升模型的透明性、可重复性和健康公平性,从而改善机器学习模型的应用质量。当前,国内基于机器学习技术的预测模型研究日益增多。为帮助国内读者更好地理解和应用TRIPOD+AI,笔者结合实例对其进行了解读,希望为研究人员报告质量提升提供支持。
