开发使用机器学习模型优化自动全血细胞计数人工涂片检查的标准。

IF 1.2 4区 农林科学 Q3 VETERINARY SCIENCES
Jennifer M Hayes, Mitchell R Hayes, Kristen R Friedrichs, Heather A Simmons
{"title":"开发使用机器学习模型优化自动全血细胞计数人工涂片检查的标准。","authors":"Jennifer M Hayes, Mitchell R Hayes, Kristen R Friedrichs, Heather A Simmons","doi":"10.1111/vcp.13400","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>In this study, we aim to determine if machine learning can reduce manual smear review (MSR) rates while meeting or exceeding the performance of traditional MSR criteria.</p><p><strong>Method: </strong>9938 automated CBCs with paired MSRs were performed on samples from rhesus and cynomolgus macaques. The definition of a positive (abnormal) smear was determined. Two expert-derived MSR criteria were created: criteria adapted from published, standardized human laboratory criteria (Adapted International Consensus Guidelines[aICG]) and internally generated criteria (Center Consensus Guidelines [CCG]). An ensemble machine learning model was trained on an independent subset of the data to optimize the balanced accuracy of classification, a combined measure of sensitivity and specificity. The resulting machine learning model and the two expert-derived MSR criteria were applied to a test dataset, and their performance compared.</p><p><strong>Results: </strong>aICG criteria demonstrated high sensitivity (80.8%) and MSR rate (74.2%) while CCG criteria demonstrated lower sensitivity (57.1%) and MSR rate (36.1%). The machine learning model integrated with CCG criteria had a superior combination of both sensitivity (76.8%) and MSR rate (45.1%) achieving a false negative rate of 1.6%.</p><p><strong>Conclusion: </strong>Machine learning in combination with expert-derived criteria can optimize the selection of samples for MSR thus decreasing MSR rates and labor efforts required for CBC performance.</p>","PeriodicalId":23593,"journal":{"name":"Veterinary clinical pathology","volume":" ","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development of criteria to optimize manual smear review of automated complete blood counts using a machine learning model.\",\"authors\":\"Jennifer M Hayes, Mitchell R Hayes, Kristen R Friedrichs, Heather A Simmons\",\"doi\":\"10.1111/vcp.13400\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>In this study, we aim to determine if machine learning can reduce manual smear review (MSR) rates while meeting or exceeding the performance of traditional MSR criteria.</p><p><strong>Method: </strong>9938 automated CBCs with paired MSRs were performed on samples from rhesus and cynomolgus macaques. The definition of a positive (abnormal) smear was determined. Two expert-derived MSR criteria were created: criteria adapted from published, standardized human laboratory criteria (Adapted International Consensus Guidelines[aICG]) and internally generated criteria (Center Consensus Guidelines [CCG]). An ensemble machine learning model was trained on an independent subset of the data to optimize the balanced accuracy of classification, a combined measure of sensitivity and specificity. The resulting machine learning model and the two expert-derived MSR criteria were applied to a test dataset, and their performance compared.</p><p><strong>Results: </strong>aICG criteria demonstrated high sensitivity (80.8%) and MSR rate (74.2%) while CCG criteria demonstrated lower sensitivity (57.1%) and MSR rate (36.1%). The machine learning model integrated with CCG criteria had a superior combination of both sensitivity (76.8%) and MSR rate (45.1%) achieving a false negative rate of 1.6%.</p><p><strong>Conclusion: </strong>Machine learning in combination with expert-derived criteria can optimize the selection of samples for MSR thus decreasing MSR rates and labor efforts required for CBC performance.</p>\",\"PeriodicalId\":23593,\"journal\":{\"name\":\"Veterinary clinical pathology\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2024-12-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Veterinary clinical pathology\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.1111/vcp.13400\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"VETERINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Veterinary clinical pathology","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1111/vcp.13400","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"VETERINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

目的:在本研究中,我们旨在确定机器学习是否可以降低人工涂片审查(MSR)率,同时达到或超过传统MSR标准的性能。方法:对恒河猴和食蟹猴进行9938例自动血细胞计数和配对MSRs。确定了阳性(异常)涂片的定义。创建了两个专家衍生的MSR标准:标准改编自已发布的标准化人体实验室标准(改编国际共识指南[aICG])和内部生成的标准(中心共识指南[CCG])。在一个独立的数据子集上训练一个集成机器学习模型,以优化分类的平衡准确性,即灵敏度和特异性的组合度量。将生成的机器学习模型和两个专家派生的MSR标准应用于测试数据集,并对其性能进行比较。结果:aICG标准的敏感性(80.8%)和MSR率(74.2%)较高,CCG标准的敏感性(57.1%)和MSR率(36.1%)较低。结合CCG标准的机器学习模型在灵敏度(76.8%)和MSR率(45.1%)方面都有较好的组合,假阴性率为1.6%。结论:机器学习与专家衍生标准相结合可以优化MSR样本的选择,从而降低MSR率和CBC性能所需的劳动力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Development of criteria to optimize manual smear review of automated complete blood counts using a machine learning model.

Objective: In this study, we aim to determine if machine learning can reduce manual smear review (MSR) rates while meeting or exceeding the performance of traditional MSR criteria.

Method: 9938 automated CBCs with paired MSRs were performed on samples from rhesus and cynomolgus macaques. The definition of a positive (abnormal) smear was determined. Two expert-derived MSR criteria were created: criteria adapted from published, standardized human laboratory criteria (Adapted International Consensus Guidelines[aICG]) and internally generated criteria (Center Consensus Guidelines [CCG]). An ensemble machine learning model was trained on an independent subset of the data to optimize the balanced accuracy of classification, a combined measure of sensitivity and specificity. The resulting machine learning model and the two expert-derived MSR criteria were applied to a test dataset, and their performance compared.

Results: aICG criteria demonstrated high sensitivity (80.8%) and MSR rate (74.2%) while CCG criteria demonstrated lower sensitivity (57.1%) and MSR rate (36.1%). The machine learning model integrated with CCG criteria had a superior combination of both sensitivity (76.8%) and MSR rate (45.1%) achieving a false negative rate of 1.6%.

Conclusion: Machine learning in combination with expert-derived criteria can optimize the selection of samples for MSR thus decreasing MSR rates and labor efforts required for CBC performance.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Veterinary clinical pathology
Veterinary clinical pathology 农林科学-兽医学
CiteScore
1.70
自引率
16.70%
发文量
133
审稿时长
18-36 weeks
期刊介绍: Veterinary Clinical Pathology is the official journal of the American Society for Veterinary Clinical Pathology (ASVCP) and the European Society of Veterinary Clinical Pathology (ESVCP). The journal''s mission is to provide an international forum for communication and discussion of scientific investigations and new developments that advance the art and science of laboratory diagnosis in animals. Veterinary Clinical Pathology welcomes original experimental research and clinical contributions involving domestic, laboratory, avian, and wildlife species in the areas of hematology, hemostasis, immunopathology, clinical chemistry, cytopathology, surgical pathology, toxicology, endocrinology, laboratory and analytical techniques, instrumentation, quality assurance, and clinical pathology education.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信