MISDP:多任务融合访问间隔序列诊断预测。

IF 2.9 3区 生物学 Q2 BIOCHEMICAL RESEARCH METHODS BMC Bioinformatics Pub Date : 2024-12-20 DOI:10.1186/s12859-024-05998-x
Shengrong Zhu, Ruijia Yang, Zifeng Pan, Xuan Tian, Hong Ji
{"title":"MISDP:多任务融合访问间隔序列诊断预测。","authors":"Shengrong Zhu, Ruijia Yang, Zifeng Pan, Xuan Tian, Hong Ji","doi":"10.1186/s12859-024-05998-x","DOIUrl":null,"url":null,"abstract":"<p><strong>Backgrounds: </strong>Diagnostic prediction is a central application that spans various medical specialties and scenarios, sequential diagnosis prediction is the process of predicting future diagnoses based on patients' historical visits. Prior research has underexplored the impact of irregular intervals between patient visits on predictive models, despite its significance.</p><p><strong>Method: </strong>We developed the Multi-task Fusion Visit Interval for Sequential Diagnosis Prediction (MISDP) framework to address this research gap. The MISDP framework integrated sequential diagnosis prediction with visit interval prediction within a multi-task learning paradigm. It uses positional encoding and interval encoding to handle irregular patient visit intervals. Furthermore, it incorporates historical attention residue to enhance the multi-head self-attention mechanism, focusing on extracting long-term dependencies from clinical historical visits.</p><p><strong>Results: </strong>The MISDP model exhibited superior performance across real-world healthcare dataset, irrespective of the training data scarcity or abundance. With only 20% training data, MISDP achieved a 4. 2% improvement over KAME; when training data ranged from 60 to 80%, MISDP surpassed SETOR, the top baseline, by 0. 8% in accuracy, underscoring its robustness and efficacy in sequential diagnosis prediction task.</p><p><strong>Conclusions: </strong>The MISDP model significantly improves the accuracy of Sequential Diagnosis Prediction. The result highlights the advantage of multi-task learning in synergistically enhancing the performance of individual sub-task. Notably, irregular visit interval factors and historical attention residue has been particularly instrumental in refining the precision of sequential diagnosis prediction, suggesting a promising avenue for advancing clinical decision-making through data-driven modeling approaches.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"25 1","pages":"387"},"PeriodicalIF":2.9000,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11662528/pdf/","citationCount":"0","resultStr":"{\"title\":\"MISDP: multi-task fusion visit interval for sequential diagnosis prediction.\",\"authors\":\"Shengrong Zhu, Ruijia Yang, Zifeng Pan, Xuan Tian, Hong Ji\",\"doi\":\"10.1186/s12859-024-05998-x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Backgrounds: </strong>Diagnostic prediction is a central application that spans various medical specialties and scenarios, sequential diagnosis prediction is the process of predicting future diagnoses based on patients' historical visits. Prior research has underexplored the impact of irregular intervals between patient visits on predictive models, despite its significance.</p><p><strong>Method: </strong>We developed the Multi-task Fusion Visit Interval for Sequential Diagnosis Prediction (MISDP) framework to address this research gap. The MISDP framework integrated sequential diagnosis prediction with visit interval prediction within a multi-task learning paradigm. It uses positional encoding and interval encoding to handle irregular patient visit intervals. Furthermore, it incorporates historical attention residue to enhance the multi-head self-attention mechanism, focusing on extracting long-term dependencies from clinical historical visits.</p><p><strong>Results: </strong>The MISDP model exhibited superior performance across real-world healthcare dataset, irrespective of the training data scarcity or abundance. With only 20% training data, MISDP achieved a 4. 2% improvement over KAME; when training data ranged from 60 to 80%, MISDP surpassed SETOR, the top baseline, by 0. 8% in accuracy, underscoring its robustness and efficacy in sequential diagnosis prediction task.</p><p><strong>Conclusions: </strong>The MISDP model significantly improves the accuracy of Sequential Diagnosis Prediction. The result highlights the advantage of multi-task learning in synergistically enhancing the performance of individual sub-task. Notably, irregular visit interval factors and historical attention residue has been particularly instrumental in refining the precision of sequential diagnosis prediction, suggesting a promising avenue for advancing clinical decision-making through data-driven modeling approaches.</p>\",\"PeriodicalId\":8958,\"journal\":{\"name\":\"BMC Bioinformatics\",\"volume\":\"25 1\",\"pages\":\"387\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2024-12-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11662528/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Bioinformatics\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1186/s12859-024-05998-x\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOCHEMICAL RESEARCH METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Bioinformatics","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s12859-024-05998-x","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0

摘要

背景:诊断预测是一种跨越各种医学专业和场景的核心应用,顺序诊断预测是基于患者历史就诊预测未来诊断的过程。先前的研究没有充分探讨患者就诊之间的不规则间隔对预测模型的影响,尽管它很重要。方法:我们开发了多任务融合访问间隔序列诊断预测(MISDP)框架来解决这一研究空白。MISDP框架在多任务学习范式中集成了顺序诊断预测和访问间隔预测。它采用位置编码和间隔编码来处理不规则的患者就诊间隔。此外,纳入历史注意残留,增强多头自注意机制,重点从临床历史就诊中提取长期依赖关系。结果:MISDP模型在真实世界的医疗数据集中表现出优异的性能,无论训练数据稀缺或丰富。只有20%的训练数据,MISDP达到了4。比KAME提高2%;当训练数据范围在60%到80%之间时,MISDP比最高基线SETOR高出0。准确率达到8%,表明该方法在序列诊断预测任务中的稳健性和有效性。结论:MISDP模型显著提高了序列诊断预测的准确性。结果表明,多任务学习在协同提高单个子任务绩效方面具有优势。值得注意的是,不规律的就诊间隔因素和历史注意力残留在提高顺序诊断预测的精度方面特别有用,这表明通过数据驱动的建模方法推进临床决策是一条有前途的途径。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
MISDP: multi-task fusion visit interval for sequential diagnosis prediction.

Backgrounds: Diagnostic prediction is a central application that spans various medical specialties and scenarios, sequential diagnosis prediction is the process of predicting future diagnoses based on patients' historical visits. Prior research has underexplored the impact of irregular intervals between patient visits on predictive models, despite its significance.

Method: We developed the Multi-task Fusion Visit Interval for Sequential Diagnosis Prediction (MISDP) framework to address this research gap. The MISDP framework integrated sequential diagnosis prediction with visit interval prediction within a multi-task learning paradigm. It uses positional encoding and interval encoding to handle irregular patient visit intervals. Furthermore, it incorporates historical attention residue to enhance the multi-head self-attention mechanism, focusing on extracting long-term dependencies from clinical historical visits.

Results: The MISDP model exhibited superior performance across real-world healthcare dataset, irrespective of the training data scarcity or abundance. With only 20% training data, MISDP achieved a 4. 2% improvement over KAME; when training data ranged from 60 to 80%, MISDP surpassed SETOR, the top baseline, by 0. 8% in accuracy, underscoring its robustness and efficacy in sequential diagnosis prediction task.

Conclusions: The MISDP model significantly improves the accuracy of Sequential Diagnosis Prediction. The result highlights the advantage of multi-task learning in synergistically enhancing the performance of individual sub-task. Notably, irregular visit interval factors and historical attention residue has been particularly instrumental in refining the precision of sequential diagnosis prediction, suggesting a promising avenue for advancing clinical decision-making through data-driven modeling approaches.

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
BMC Bioinformatics
BMC Bioinformatics 生物-生化研究方法
CiteScore
5.70
自引率
3.30%
发文量
506
审稿时长
4.3 months
期刊介绍: BMC Bioinformatics is an open access, peer-reviewed journal that considers articles on all aspects of the development, testing and novel application of computational and statistical methods for the modeling and analysis of all kinds of biological data, as well as other areas of computational biology. BMC Bioinformatics is part of the BMC series which publishes subject-specific journals focused on the needs of individual research communities across all areas of biology and medicine. We offer an efficient, fair and friendly peer review service, and are committed to publishing all sound science, provided that there is some advance in knowledge presented by the work.
期刊最新文献
Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis. HDN-DDI: a novel framework for predicting drug-drug interactions using hierarchical molecular graphs and enhanced dual-view representation learning. BAC-browser: the tool for synthetic biology. A comprehensive survey of scoring functions for protein docking models. Joint embedding-classifier learning for interpretable collaborative filtering.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1