The Impact of Artificial Intelligence and Machine Learning in Radiation Therapy: Considerations for Future Curriculum Enhancement

Artificial intelligence (AI) and machine learning (ML) approaches have caught the attention of many in health care. Current literature suggests there are many potential benefits that could transform future clinical workflows and decision making. Embedding AI and ML concepts in radiation therapy education could be a fundamental step in equipping radiation therapists (RTs) to engage in competent and safe practice as they utilise clinical technologies. In this discussion paper, the authors provide a brief review of some applications of AI and ML in radiation therapy and discuss pertinent considerations for radiation therapy curriculum enhancement. As the current literature suggests, AI and ML approaches will impose changes to routine clinical radiation therapy tasks. The emphasis in RT education could be on critical evaluation of AI and ML application in routine clinical workflows and gaining an understanding of the impact on quality assurance, provision of quality of care and safety in radiation therapy as well as research. It is also imperative RTs have a broader understanding of AI/ML impact on health care, including ethical and legal considerations. The paper concludes with recommendations and suggestions to deliberately embed AI and ML aspects in RT education to empower future RT practitioners.     

Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging

Artificial intelligence (AI) in medical imaging is a potentially disruptive technology. An understanding of the principles and application of radiomics, artificial neural networks, machine learning, and deep learning is an essential foundation to weave design solutions that accommodate ethical and regulatory requirements, and to craft AI-based algorithms that enhance outcomes, quality, and efficiency. Moreover, a more holistic perspective of applications, opportunities, and challenges from a programmatic perspective contributes to ethical and sustainable implementation of AI solutions.     

Identifying Goals of Care Conversations in the Electronic Health Record Using Natural Language Processing and Machine Learning

ContextGoals-of-care discussions are an important quality metric in palliative care. However, goals-of-care discussions are often documented as free text in diverse locations. It is difficult to identify these discussions in the electronic health record (EHR) efficiently.ObjectivesTo develop, train, and test an automated approach to identifying goals-of-care discussions in the EHR, using natural language processing (NLP) and machine learning (ML).MethodsFrom the electronic health records of an academic health system, we collected a purposive sample of 3183 EHR notes (1435 inpatient notes and 1748 outpatient notes) from 1426 patients with serious illness over 2008–2016, and manually reviewed each note for documentation of goals-of-care discussions. Separately, we developed a program to identify notes containing documentation of goals-of-care discussions using NLP and supervised ML. We estimated the performance characteristics of the NLP/ML program across 100 pairs of randomly partitioned training and test sets. We repeated these methods for inpatient-only and outpatient-only subsets.ResultsOf 3183 notes, 689 contained documentation of goals-of-care discussions. The mean sensitivity of the NLP/ML program was 82.3% (SD 3.2%), and the mean specificity was 97.4% (SD 0.7%). NLP/ML results had a median positive likelihood ratio of 32.2 (IQR 27.5–39.2) and a median negative likelihood ratio of 0.18 (IQR 0.16–0.20). Performance was better in inpatient-only samples than outpatient-only samples.ConclusionUsing NLP and ML techniques, we developed a novel approach to identifying goals-of-care discussions in the EHR. NLP and ML represent a potential approach toward measuring goals-of-care discussions as a research outcome and quality metric.     

Artificial intelligence (AI) and machine learning (ML) based decision support systems in mental health: An integrative review

An integrative review investigating the incorporation of artificial intelligence (AI) and machine learning (ML) based decision support systems in mental health care settings was undertaken of published literature between 2016 and 2021 across six databases. Four studies met the research question and the inclusion criteria. The primary theme identified was trust and confidence. To date, there is limited research regarding the use of AI-based decision support systems in mental health. Our review found that significant barriers exist regarding its incorporation into practice primarily arising from uncertainty related to clinician's trust and confidence, end-user acceptance and system transparency. More research is needed to understand the role of AI in assisting treatment and identifying missed care. Researchers and developers must focus on establishing trust and confidence with clinical staff before true clinical impact can be determined. Finally, further research is required to understand the attitudes and beliefs surrounding the use of AI and related impacts for the wellbeing of the end-users of care. This review highlights the necessity of involving clinicians in all stages of research, development and implementation of artificial intelligence in care delivery. Earning the trust and confidence of clinicians should be foremost in consideration in implementation of any AI-based decision support system. Clinicians should be motivated to actively embrace the opportunity to contribute to the development and implementation of new health technologies and digital tools that assist all health care professionals to identify missed care, before it occurs as a matter of importance for public safety and ethical implementation. AI-basesd decision support tools in mental health settings show most promise as trust and confidence of clinicians is achieved.     

Machine intelligence in peptide therapeutics: A next-generation tool for rapid disease screening

Discovery and development of biopeptides are time-consuming, laborious, and dependent on various factors. Data-driven computational methods, especially machine learning (ML) approach, can rapidly and efficiently predict the utility of therapeutic peptides. ML methods offer an array of tools that can accelerate and enhance decision making and discovery for well-defined queries with ample and sophisticated data quality. Various ML approaches, such as support vector machines, random forest, extremely randomized tree, and more recently deep learning methods, are useful in peptide-based drug discovery. These approaches leverage the peptide data sets, created via high-throughput sequencing and computational methods, and enable the prediction of functional peptides with increased levels of accuracy. The use of ML approaches in the development of peptide-based therapeutics is relatively recent; however, these techniques are already revolutionizing protein research by unraveling their novel therapeutic peptide functions. In this review, we discuss several ML-based state-of-the-art peptide-prediction tools and compare these methods in terms of their algorithms, feature encodings, prediction scores, evaluation methodologies, and software utilities. We also assessed the prediction performance of these methods using well-constructed independent data sets. In addition, we discuss the common pitfalls and challenges of using ML approaches for peptide therapeutics. Overall, we show that using ML models in peptide research can streamline the development of targeted peptide therapies.     

Machine Learning Methods to Extract Documentation of Breast Cancer Symptoms From Electronic Health Records

Context

Clinicians document cancer patients' symptoms in free-text format within electronic health record visit notes. Although symptoms are critically important to quality of life and often herald clinical status changes, computational methods to assess the trajectory of symptoms over time are woefully underdeveloped.

Enhanced Point‐of‐Care Ultrasound Applications by Integrating Automated Feature‐Learning Systems Using Deep Learning

Recent applications of artificial intelligence (AI) and deep learning (DL) in health care include enhanced diagnostic imaging modalities to support clinical decisions and improve patients’ outcomes. Focused on using automated DL‐based systems to improve point‐of‐care ultrasound (POCUS), we look at DL‐based automation as a key field in expanding and improving POCUS applications in various clinical settings. A promising additional value would be the ability to automate training model selections for teaching POCUS to medical trainees and novice sonologists. The diversity of POCUS applications and ultrasound equipment, each requiring specialized AI models and domain expertise, limits the use of DL as a generic solution. In this article, we highlight the most advanced potential applications of AI in POCUS tailored to high‐yield models in automated image interpretations, with the premise of improving the accuracy and efficacy of POCUS scans.     

Artificial intelligence in clinical and translational science: Successes,challenges and opportunities

Artificial intelligence (AI) is transforming many domains, including finance, agriculture, defense, and biomedicine. In this paper, we focus on the role of AI in clinical and translational research (CTR), including preclinical research (T1), clinical research (T2), clinical implementation (T3), and public (or population) health (T4). Given the rapid evolution of AI in CTR, we present three complementary perspectives: (1) scoping literature review, (2) survey, and (3) analysis of federally funded projects. For each CTR phase, we addressed challenges, successes, failures, and opportunities for AI. We surveyed Clinical and Translational Science Award (CTSA) hubs regarding AI projects at their institutions. Nineteen of 63 CTSA hubs (30%) responded to the survey. The most common funding source (48.5%) was the federal government. The most common translational phase was T2 (clinical research, 40.2%). Clinicians were the intended users in 44.6% of projects and researchers in 32.3% of projects. The most common computational approaches were supervised machine learning (38.6%) and deep learning (34.2%). The number of projects steadily increased from 2012 to 2020. Finally, we analyzed 2604 AI projects at CTSA hubs using the National Institutes of Health Research Portfolio Online Reporting Tools (RePORTER) database for 2011–2019. We mapped available abstracts to medical subject headings and found that nervous system (16.3%) and mental disorders (16.2) were the most common topics addressed. From a computational perspective, big data (32.3%) and deep learning (30.0%) were most common. This work represents a snapshot in time of the role of AI in the CTSA program.     

A review in radiomics: Making personalized medicine a reality via routine imaging

Radiomics is the quantitative analysis of standard-of?care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid “scientific pollution” and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.     

Artificial Intelligence in Pharmacovigilance: Scoping Points to Consider

Artificial intelligence (AI), a highly interdisciplinary science, is an increasing presence in pharmacovigilance (PV). A better understanding of the scope of artificial intelligence in pharmacovigilance (AIPV) may be advantageous to more sharply defining, for example, which terms, methods, tasks, and data sets are suitably subsumed under the application of AIPV. Accordingly, this article explores relevant points to consider regarding defining the scope of AIPV and offers a potential working definition of the scope of AIPV.     

基于深度学习的人工智能在肺结节诊断领域的进展

肺癌是死亡率最高的恶性肿瘤,肺结节的早期检测是降低肺癌死亡率的关键。基于深度学习的人工智能技术可通过自我学习,不断提高肺结节检测和诊断的准确率,是实现计算机辅助诊断的重要手段。本文介绍了人工智能、机器学习、深度学习的概念及三者间的关系,阐述了4种常见的深度学习模型：卷积神经网络、海量训练人工神经网络、自编码器和深度信念网络。卷积神经网络是最常用的深度学习模型,主要包括二维卷积神经网络、三维卷积神经网络和多流、多尺度的卷积神经网络,其中的多流、多尺度的卷积神经网络更有利于肺结节的分类;海量训练人工神经网络在有限的肺结节训练样本中具有优势;自编码器可以在较低维空间下对肺结节进行检测;深度信念网络是一种生成模式,与极限学习机结合可提高肺结节的诊断率。另外,本研究分析了目前人工智能存在的问题：标记图像过少、可解释性和可控制性不足、存在伦理和法律问题。总之,基于深度学习的人工智能不仅改变了影像学,也改变了所有其他的医学领域,具有广阔的应用前景。     

人工智能在功能与分子影像学的研究进展

功能与分子影像学能够提供组织器官功能变化及细胞或分子事件的时间和空间分布信息,而人工智能是一门新兴的计算机技术,在医学影像中具有广泛的应用。将人工智能应用到功能影像学,能够使影像科医生更加高效、充分地利用得到的信息,更加深入地挖掘图像的生物学本质,在疾病早期诊断、有效治疗、预后预测、探索发病机制等方面均具有重要意义。本文将重点阐述人工智能在功能与分子影像学中图像处理、图像解释及质量控制的应用与进展。      

When to err is inhuman: An examination of the influence of artificial intelligence-driven nursing care on patient safety

Artificial intelligence, as a nonhuman entity, is increasingly used to inform, direct, or supplant nursing care and clinical decision-making. The boundaries between human- and nonhuman-driven nursing care are blurred with the advent of sensors, wearables, camera devices, and humanoid robots at such an accelerated pace that the critical evaluation of its influence on patient safety has not been fully assessed. Since the pivotal release of To Err is Human, patient safety is being challenged by the dynamic healthcare environment like never before, with nursing at a critical juncture to steer the course of artificial intelligence integration in clinical decision-making. This paper presents an overview of artificial intelligence and its application in healthcare and highlights the implications which affect nursing as a profession, including perspectives on nursing education and training recommendations. The legal and policy challenges which emerge when artificial intelligence influences the risk of clinical errors and safety issues are discussed.     

A Study on the Application and Use of Artificial Intelligence to Support Drug Development

PurposeThe Tufts Center for the Study of Drug Development (CSDD) and the Drug Information Association (DIA) in collaboration with 8 pharmaceutical and biotechnology companies conducted a study examining the adoption and effect of artificial intelligence (AI), such as machine learning, on drug development. The study was conducted to clarify and understand AI adoption across the industry and to gather detailed insights into the spectrum of activities included in the definition of AI. The study investigated and identified analytical platforms and innovations across pharmaceutical and biotechnology companies currently being used or planned for in the future.MethodsA 2-part method was used that comprised in-depth interviews with AI industry experts and a global survey conducted across pharmaceutical and biotechnology organizations. Eleven in-depth interviews focused on use and implementation of AI across drug development. The survey assessed use of AI and included perceptions about current and future use. The survey also examined technology definitions, assessment of organizational and personal AI expertise, and use of partnerships. A total of 402 responses, including data from 217 unique organizations, were analyzed.FindingsAlthough 7 in 10 respondents reported using AI in some capacity, a wide range of use was reported by AI type. Patient selection and recruitment for clinical studies was the most commonly reported AI activity, with 34 respondents currently using AI for this activity. In addition, identification of medicinal products data gathering was the top activity being piloted or in the planning stages, reported by 49 respondents. The study also revealed that the most significant challenges to AI implementation included staff skills (55%), data structure (52%), and budgets (49%). Nearly 60% of respondents noted planned increases in staff within 1–2 years to support AI use or implementation.ImplicationsDespite the challenges to AI implementation, the survey revealed that most organizations use AI in some capacity and that it is important to the success of an organization's workforce. Many organizations reported expectations for increasing staff as implementation of AI expands. Further research should examine the changing development landscape as the role of AI evolves.     

人工智能如何改变指南的未来

近年来,人工智能的快速发展和进步对医学领域的影响日益加深。科技部发布的人工智能指南明确提出要加大人工智能技术在医药卫生领域应用的支持力度。临床实践指南作为医疗实践的重要指导性文件,可以规范医务人员的诊疗行为,缩小最佳研究证据与当前实践之间的差距,具有重要意义和价值。如何利用人工智能技术加速指南的制订流程,提高其制订效率,创新其传播与实施模式,乃至改变指南的未来发展,已引起国内外学者的广泛关注。本文就人工智能在临床实践指南领域的应用现状和发展前景进行分析和讨论,并在此基础上提出促进人工智能与临床实践指南结合的思考与建议。     

Electronic Task Management System: A Pediatric Institution's Experience

Background  Electronic medical task management systems (ETMs) have been adopted in health care institutions to improve health care provider communication. ETMs allow for the requesting and resolution of nonurgent tasks between clinicians of all craft groups. Visibility, ability to provide close-loop feedback, and a digital trail of all decisions and responsible clinicians are key features of ETMs. An embedded ETM within an integrated electronic health record (EHR) was introduced to the Royal Children''s Hospital Melbourne on April 30, 2016. The ETM is used hospital-wide for nonurgent tasks 24 hours a day. It facilitates communication of nonurgent tasks between clinical staff, with an associated designated timeframe in which the task needs to be completed (2, 4, and 8 hours). Objective  This study aims to examine the usage of the ETM at our institution since its inception. Methods  ETM usage data from the first 3 years of use (April 2016 to April 2019) were extracted from the EHR. Data collected included age of patient, date and time of task request, ward, unit, type of task, urgency of task, requestor role, and time to completion. Results  A total of 136,481 tasks were placed via the ETM in the study period. There were approximately 125 tasks placed each day (24-hour period). The most common time of task placement was around 6:00 p.m. Task placement peaked at approximately 8 a.m., 2 p.m., and 9 p.m.—consistent with nursing shift change times. In total, 63.16% of tasks were placed outside business hours, indicating predominant usage for after-hours task communication. The ETM was most highly utilized by surgical units. The majority of tasks were ordered by nurses for medical staff to complete (97.01%). A significant proportion (98.79%) of tasks was marked as complete on the ETM, indicating closed-loop feedback after tasks were requested. Conclusion  An ETM function embedded in our EHR has been highly utilized in our institution since its introduction. It has multiple benefits for the clinician in the form of efficiencies in workflow and improvement in communication and also workflow management. By allowing collection, tracking, audit, and prioritization of tasks, it also provides a stream of actionable data for quality-improvement activities.