Research Data That Can Be Trusted
暫譯: 可信的研究數據
Bouzinier, Michael, Etin, Dmitry, Khoshnevis, Naeem
- 出版商: Springer
- 出版日期: 2026-06-11
- 售價: $2,230
- 貴賓價: 9.5 折 $2,118
- 語言: 英文
- 頁數: 202
- 裝訂: Quality Paper - also called trade paper
- ISBN: 3032210313
- ISBN-13: 9783032210319
-
相關分類:
Data-visualization
海外代購書籍(需單獨結帳)
相關主題
商品描述
In this book we argue for the need for a new approach to data provenance and explain how recent advancements in data processing workflow automation present an opportunity to address this need. We introduce descriptive dataflow operators - a novel approach based on integrating descriptive workflow languages with a data modeling Domain-Specific Language (DSL). We review the current workflow automation technologies and propose a DSL that supports complex data transformations, enhances reproducibility, and enables precise data lineage tracking. Within the framework we introduce the concept of descriptive dataflow operators for more flexible and expressive data transformations.
Modern healthcare increasingly relies on complex data pipelines to process diverse diagnostic information, clinical records, and research data. This growing complexity, combined with emerging AI/ML applications and stricter regulatory oversight, demands sophisticated approaches to data preparation, documentation, and validation. Healthcare organizations face mounting pressure to ensure granular traceability and reproducibility of their data transformations while maintaining regulatory compliance. These challenges are particularly acute in research settings, where data provenance and quality validation become critical for scientific reproducibility and regulatory adherence.
Given the increasing complexity of healthcare data, data ingestion and transformation workflows present significant technical challenges, particularly in ensuring the reproducibility and seamless integration of diverse datasets for ML and AI model development.
We introduce the Dorieh Data Platform as an exemplar implementation of a DSL, providing a comprehensive framework for reproducible research. The platform's infrastructure supports robust data lineage documentation, validation, and error logging, making it a powerful tool for healthcare data analysis by ensuring transparent, auditable data processes and regulatory conformance.
We show how to apply this framework to analyze healthcare claims data quality, revealing insights into inconsistencies and deficiencies. Our approach demonstrates the potential for improved data management and accountability in scientific research, underscoring the necessity for precise, reproducible data transformation methodologies to produce reliable research outcomes.
商品描述(中文翻譯)
在本書中，我們主張需要一種新的數據來源方法，並解釋最近在數據處理工作流程自動化方面的進展如何為滿足這一需求提供機會。我們介紹了描述性數據流運算子——這是一種基於將描述性工作流程語言與數據建模領域特定語言（Domain-Specific Language, DSL）整合的新方法。我們回顧了當前的工作流程自動化技術，並提出了一種支持複雜數據轉換、增強可重現性並實現精確數據來源追蹤的DSL。在這一框架內，我們引入了描述性數據流運算子的概念，以實現更靈活和表達力強的數據轉換。
現代醫療保健越來越依賴複雜的數據管道來處理多樣的診斷信息、臨床記錄和研究數據。這種日益增長的複雜性，加上新興的人工智慧/機器學習應用和更嚴格的監管監督，要求對數據準備、文檔和驗證採取更複雜的方法。醫療保健組織面臨著越來越大的壓力，必須確保其數據轉換的細粒度可追溯性和可重現性，同時保持合規性。這些挑戰在研究環境中特別明顯，因為數據來源和質量驗證對於科學可重現性和合規性至關重要。
考慮到醫療數據日益增長的複雜性，數據攝取和轉換工作流程面臨重大技術挑戰，特別是在確保多樣數據集的可重現性和無縫整合以進行機器學習和人工智慧模型開發方面。
我們介紹了Dorieh數據平台，作為DSL的一個示範實現，提供了一個全面的可重現研究框架。該平台的基礎設施支持穩健的數據來源文檔、驗證和錯誤日誌記錄，使其成為醫療數據分析的強大工具，確保透明、可審計的數據流程和合規性。
我們展示了如何應用這一框架來分析醫療索賠數據的質量，揭示不一致性和缺陷的見解。我們的方法展示了在科學研究中改善數據管理和問責制的潛力，強調了精確、可重現的數據轉換方法對於產生可靠研究結果的必要性。
作者簡介
Michael Bouzinier is a Senior Research Software Engineer within University Research Computing. He has over 30 years of diverse experience in software research and development and 10 years as a professional educator. His intellectual interests include semiotics, natural language processing and text analytics, data visualization, evolutionary and medical genetics, computer simulations, and explainable AI. Throughout his career, he has worked and led diverse international teams, successfully collaborating with developers and researchers from within the US, UK, Sweden, Finland, Belgium, The Netherlands, and Japan.
Dmitry Etin is a digital health strategist specializing in interoperability and health data management at the intersection of technology, medicine, and policy. He guides organizations and policymakers through the complexities of health data governance and large-scale interoperability initiatives, bringing practical solutions to critical challenges in digital health.He is deeply involved in shaping the European Health Data Space, working with the European Commission and supporting the European Medicines Agency in enabling an interoperable European Medicines Regulatory Network. Dmitry is also involved in several Horizon-funded research initiatives, accelerating the adoption of interoperable EHR systems in the EU. As a co-founder of Forome, an open-source initiative for genomics, health data management, and regulatory compliance, he helps develop data provenance and analysis tools for complex healthcare and clinical research cases.
Naeem Khoshnevis is a Research Software Engineer within University Research Computing. In this role, Naeem designs, builds, and optimizes software applications for researchers across Harvard University. Naeem has a superior mathematical and numerical analysis background and has developed, documented, debugged, extended, and refactored numerous scientific software applications for research groups, helping them successfully carry out their projects.
Max Shad is the Director of Engineering at the Kempner Institute for the Study of Natural and Artificial Intelligence and University Research Computing and Data (RCD) at Harvard University. In this role, he leads the computational program of the Kempner Institute, ensuring the provision of advanced Research Computing (RC) tools/services and expert Research Software Engineering (RSE) support. His efforts are instrumental in leveraging High-Performance Computing (HPC), particularly in Machine Learning (ML) and AI research, to facilitate pioneering discoveries in AI, ML, and computational biology.
Scott Yockel is the University Research Computing Officer at Harvard. In this role, Scott works with researchers across campus to develop and champion a university-wide research computing strategy in support of Harvard's research mission. He is focused on identifying emerging needs, engaging with faculty, school, and university leadership to articulate those needs, and identifying possible solutions and funding mechanisms. He is spearheading the implementation of these initiatives and articulating their success with concrete measures.
作者簡介(中文翻譯)
Michael Bouzinier 是哈佛大學研究計算部門的高級研究軟體工程師。他在軟體研究和開發方面擁有超過 30 年的多元經驗，以及 10 年的專業教育經驗。他的智識興趣包括符號學、自然語言處理和文本分析、數據可視化、進化和醫學遺傳學、計算機模擬以及可解釋的人工智慧。在他的職業生涯中，他曾與來自美國、英國、瑞典、芬蘭、比利時、荷蘭和日本的開發者和研究人員成功合作，並領導多元的國際團隊。
Dmitry Etin 是一位數位健康策略師，專注於技術、醫學和政策交匯處的互操作性和健康數據管理。他指導組織和政策制定者應對健康數據治理和大規模互操作性倡議的複雜性，為數位健康中的關鍵挑戰提供實用解決方案。他深度參與塑造歐洲健康數據空間，與歐洲委員會合作，並支持歐洲藥品管理局促進互操作的歐洲藥品監管網絡。Dmitry 也參與了幾個由 Horizon 資助的研究計畫，加速在歐盟內部採用互操作的電子健康紀錄系統。作為 Forome 的共同創辦人，這是一個針對基因組學、健康數據管理和法規遵循的開源倡議，他幫助開發數據來源和分析工具，以應對複雜的醫療保健和臨床研究案例。
Naeem Khoshnevis 是哈佛大學研究計算部門的研究軟體工程師。在這個角色中，Naeem 為哈佛大學的研究人員設計、建構和優化軟體應用程式。Naeem 擁有卓越的數學和數值分析背景，並為研究小組開發、記錄、除錯、擴展和重構了眾多科學軟體應用程式，幫助他們成功執行項目。
Max Shad 是哈佛大學 Kempner 自然與人工智慧研究所及研究計算和數據 (RCD) 的工程總監。在這個角色中，他負責 Kempner 研究所的計算計畫，確保提供先進的研究計算 (RC) 工具/服務和專業的研究軟體工程 (RSE) 支援。他的努力對於利用高效能計算 (HPC)，特別是在機器學習 (ML) 和人工智慧研究中，促進 AI、ML 和計算生物學的開創性發現至關重要。
Scott Yockel 是哈佛大學的研究計算官。在這個角色中，Scott 與校園內的研究人員合作，制定並推動全校的研究計算策略，以支持哈佛的研究使命。他專注於識別新興需求，與教職員、學校和大學領導層互動，以明確這些需求，並尋找可能的解決方案和資金機制。他正在推動這些倡議的實施，並用具體的指標來闡述其成功。
