Nowadays, machine learning (ML) is being used in software systems with
multiple application fields, from medicine to software engineering (SE). On the
one hand, the popularity of ML in the industry can be seen in the statistics
showing its growth and adoption. On the other hand, its popularity can also be
seen in research, particularly in SE, where not only have multiple studies been
published in SE conferences and journals but also in the multiple workshops and
co-located conferences in software engineering conferences. At the same time,
researchers and practitioners have shown that machine learning has some
particular challenges and pitfalls. In particular, research has shown that
ML-enabled systems have a different development process than traditional SE,
which also describes some of the challenges of ML applications. In order to
mitigate some of the identified challenges and pitfalls, white and gray
literature has proposed a set of recommendations based on their own experiences
and focused on their domain (e.g., biomechanics), but for the best of our
knowledge, there is no guideline focused on the SE community. This thesis aims
to reduce this gap by answering research questions that help to understand the
practices used and discussed by practitioners and researchers in the SE
community by analyzing possible sources of practices such as question and
answer communities and also previous research studies to present a set of
practices with an SE perspective.

本文旨在通过分析机器学习在软件工程中的最佳实践，填补现有文献不足的空缺，并针对机器学习应用所面临的挑战和开发过程，提出一系列以软件工程视角为基础的建议。

循着最佳实践指引的机器学习

Towards machine learning guided by best practices

Healthcare is one of the most promising areas for machine learning models to
make a positive impact. However, successful adoption of AI-based systems in
healthcare depends on engaging and educating stakeholders from diverse
backgrounds about the development process of AI models. We present a broadly
accessible overview of the development life cycle of clinical AI models that is
general enough to be adapted to most machine learning projects, and then give
an in-depth case study of the development process of a deep learning based
system to detect aortic aneurysms in Computed Tomography (CT) exams. We hope
other healthcare institutions and clinical practitioners find the insights we
share about the development process useful in informing their own model
development efforts and to increase the likelihood of successful deployment and
integration of AI in healthcare.

本文介绍了临床人工智能模型的开发生命周期，并给出了一个基于深度学习的系统的开发过程案例。作者希望这些见解能帮助其他医疗机构和临床从业者，以增加在医疗领域成功部署和集成人工智能模型的可能性。