National Cancer Institute Workshop on Artificial Intelligence in Radiation Oncology: Training the Next Generation

A systematic review of artificial intelligence-powered (AI-powered) chatbot intervention for managing chronic illness

BACKGROUND

Utilizing artificial intelligence (AI) in chatbots, especially for chronic diseases, has become increasingly prevalent. These AI-powered chatbots serve as crucial tools for enhancing patient communication, addressing the rising prevalence of chronic conditions, and meeting the growing demand for supportive healthcare applications. However, there is a notable gap in comprehensive reviews evaluating the impact of AI-powered chatbot interventions in healthcare within academic literature. This study aimed to assess user satisfaction, intervention efficacy, and the specific characteristics and AI architectures of chatbot systems designed for chronic diseases.

METHOD

A thorough exploration of the existing literature was undertaken by employing diverse databases such as PubMed MEDLINE, CINAHL, EMBASE, PsycINFO, ACM Digital Library and Scopus. The studies incorporated in this analysis encompassed primary research that employed chatbots or other forms of AI architecture in the context of preventing, treating or rehabilitating chronic diseases. The assessment of bias risk was conducted using Risk of 2.0 Tools.

RESULTS

Seven hundred and eighty-four results were obtained, and subsequently, eight studies were found to align with the inclusion criteria. The intervention methods encompassed health education (n = 3), behaviour change theory (n = 1), stress and coping (n = 1), cognitive behavioural therapy (n = 2) and self-care behaviour (n = 1). The research provided valuable insights into the effectiveness and user-friendliness of AI-powered chatbots in handling various chronic conditions. Overall, users showed favourable acceptance of these chatbots for self-managing chronic illnesses.

CONCLUSIONS

The reviewed studies suggest promising acceptance of AI-powered chatbots for self-managing chronic conditions. However, limited evidence on their efficacy due to insufficient technical documentation calls for future studies to provide detailed descriptions and prioritize patient safety. These chatbots employ natural language processing and multimodal interaction. Subsequent research should focus on evidence-based evaluations, facilitating comparisons across diverse chronic health conditions.

Global Workforce and Access: Demand, Education, Quality

There has long existed a substantial disparity in access to radiotherapy globally. This issue has only been exacerbated as the growing disparity of cancer incidence between high-income countries (HIC) and low and middle-income countries (LMICs) widens, with a pronounced increase in cancer cases in LMICs. Even within HICs, iniquities within local communities may lead to a lack of access to care. Due to these trends, it is imperative to find solutions to narrow global disparities. This requires the engagement of a diverse cohort of stakeholders, including working professionals, non-governmental organizations, nonprofits, professional societies, academic and training institutions, and industry. This review brings together a diverse group of experts to highlight critical areas that could help reduce the current global disparities in radiation oncology. Advancements in technology and treatment, such as artificial intelligence, brachytherapy, hypofractionation, and digital networks, in combination with implementation science and novel funding mechanisms, offer means for increasing access to care and education globally. Common themes across sections reveal how utilizing these new innovations and strengthening collaborative efforts among stakeholders can help improve access to care globally while setting the framework for the next generation of innovations.

Deep learning based clinical target volumes contouring for prostate cancer: Easy and efficient application

BACKGROUND

Radiotherapy has been crucial in prostate cancer treatment. However, manual segmentation is labor intensive and highly variable among radiation oncologists. In this study, a deep learning based automated contouring model is constructed for clinical target volumes (CTVs) of intact and postoperative prostate cancer.

METHODS

Computed tomography (CT) data sets of 197 prostate cancer patients were collected. Two auto-delineation models were built for radical radiotherapy and postoperative radiotherapy of prostate cancer respectively, and each model included CTVn for pelvic lymph nodes and CTVp for prostate tumors or prostate tumor beds.

RESULTS

In the radical radiotherapy model, the volumetric dice (VD) coefficient of CTVn calculated by AI, was higher than that of the one delineated by the junior physicians (0.85 vs. 0.82, p = 0.018); In the postoperative radiotherapy model, the quantitative parameter of CTVn and CTVp, counted by AI, was better than that of the junior physicians. The median delineation time for AI was 0.23 min in the postoperative model and 0.26 min in the radical model, which were significantly shorter than those of the physicians (50.40 and 45.43 min, respectively, p < 0.001). The correction time of the senior physician for AI was much shorter compared with that for the junior physicians in both models (p < 0.001).

CONCLUSION

Using deep learning and attention mechanism, a highly consistent and time-saving contouring model was built for CTVs of pelvic lymph nodes and prostate tumors or prostate tumor beds for prostate cancer, which also might be a good approach to train junior radiation oncologists.

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

BACKGROUND AND PURPOSE

Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap.

METHODS AND MATERIALS

A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended.

RESULTS

The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated.

CONCLUSION

A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

Radiologic Technology Students' Perceptions on Adoption of Artificial Intelligence Technology in Radiology

Study Purpose

This study aims to analyze radiologic technology student's perceptions of artificial intelligence (AI) and its applications in radiology.

Methods

A quantitative cross-sectional survey was conducted. A pre-validated survey questionnaire with 17 items related to students perceptions of AI and its applications was used. The sample included radiologic technology students from three universities in Saudi Arabia. The survey was conducted online for several weeks, resulting in a sample of 280 radiologic technology students.

Results

Of the participants, 63.9% were aware of AI and its applications. T-tests revealed a statistically significant difference (p = 0.0471) between genders with male participants reflecting slightly higher AI awareness than female participants. Regarding the choice of radiology as specialization, 35% of the participants stated that they would not choose radiology, whereas 65% preferred it. Approximately 56% of the participants expressed concerns about the potential replacement of radiology technologists with AI, and 62.1% strongly agreed on the necessity of incorporating known ethical principles into AI.

Conclusion

The findings reflect a positive evaluation of the applications of this technology, which is attributed to its essential support role. However, tailored education and training programs are necessary to prepare future healthcare professionals for the increasing role of AI in medical sciences.

Evolutionary Strategies AI Addresses Multiple Technical Challenges in Deep Learning Deployment: Proof-of-Principle Demonstration for Neuroblastoma Brain Metastasis Detection

Two significant obstacles hinder the advancement of Radiology AI. The first is the challenge of overfitting, where small training data sets can result in unreliable outcomes. The second challenge is the need for more generalizability, the lack of which creates difficulties in implementing the technology across various institutions and practices. A recent innovation, deep neuroevolution (DNE), has been introduced to tackle the overfitting issue by training on small data sets and producing accurate predictions. However, the generalizability of DNE has yet to be proven. This paper strives to overcome this barrier by demonstrating that DNE can achieve satisfactory results in diverse external validation sets. The main innovation of the work is thus showing that DNE can generalize to varied outside data. Our example use case is predicting brain metastasis from neuroblastoma, emphasizing the importance of AI with limited data sets. Despite image collection and labeling advancements, rare diseases will always constrain data availability. We optimized a convolutional neural network (CNN) with DNE to demonstrate generalizability. We trained the CNN with 60 MRI images and tested it on a separate diverse collection of images from over 50 institutions. For comparison, we also trained with the more traditional stochastic gradient descent (SGD) method, with the two variants of (1) training from scratch and (2) transfer learning. Our results show that DNE demonstrates excellent generalizability with 97% accuracy on the heterogeneous testing set, while neither form of SGD could reach 60% accuracy. DNE's ability to generalize from small training sets to external and diverse testing sets suggests that it or similar approaches may play an integral role in improving the clinical performance of AI.

Bladder Cancer Radiation Oncology of the Future: Prognostic Modelling, Radiomics, and Treatment Planning With Artificial Intelligence

Machine learning (ML) and artificial intelligence (AI) have demonstrated potential to improve the care of radiation oncology patients. Here we review recent advances applicable to the care of bladder cancer, with an eye towards studies that may suggest next steps in clinical implementation. Algorithms have been applied to clinical records, pathology, and radiology data to generate accurate predictive models for prognosis and clinical outcomes. AI has also shown increasing utility for auto-contouring and efficient creation of workflows involving multiple treatment plans. As technologies progress towards routine clinical use for bladder cancer patients, we also discuss emerging methods to improve interpretability and reliability of algorithms.

A Systematic Review on Healthcare Artificial Intelligent Conversational Agents for Chronic Conditions

This paper reviews different types of conversational agents used in health care for chronic conditions, examining their underlying communication technology, evaluation measures, and AI methods. A systematic search was performed in February 2021 on PubMed Medline, EMBASE, PsycINFO, CINAHL, Web of Science, and ACM Digital Library. Studies were included if they focused on consumers, caregivers, or healthcare professionals in the prevention, treatment, or rehabilitation of chronic diseases, involved conversational agents, and tested the system with human users. The search retrieved 1087 articles. Twenty-six studies met the inclusion criteria. Out of 26 conversational agents (CAs), 16 were chatbots, seven were embodied conversational agents (ECA), one was a conversational agent in a robot, and another was a relational agent. One agent was not specified. Based on this review, the overall acceptance of CAs by users for the self-management of their chronic conditions is promising. Users’ feedback shows helpfulness, satisfaction, and ease of use in more than half of included studies. Although many users in the studies appear to feel more comfortable with CAs, there is still a lack of reliable and comparable evidence to determine the efficacy of AI-enabled CAs for chronic health conditions due to the insufficient reporting of technical implementation details.

Application of Machine Learning Methods to Improve the Performance of Ultrasound in Head and Neck Oncology: A Literature Review

Simple Summary

Ultrasound (US) is a non-invasive imaging method that is routinely utilized in head and neck cancer patients to assess the anatomic extent of tumors, nodal and non-nodal neck masses and for imaging the salivary glands. In this review, we summarize the present evidence on whether the application of machine learning (ML) methods can potentially improve the performance of US in head and neck cancer patients. We found that published clinical literature on ML methods applied to US datasets was limited but showed evidence of improved diagnostic and prognostic performance. However, a majority of these studies were based on retrospective evaluation and conducted at a single center with a limited number of datasets. The conduct of multi-center studies could help better validate the performance of ML-based US radiomics and facilitate the integration of these approaches into routine clinical practice.

Abstract

Radiomics is a rapidly growing area of research within radiology that involves the extraction and modeling of high-dimensional quantitative imaging features using machine learning/artificial intelligence (ML/AI) methods. In this review, we describe the published clinical evidence on the application of ML methods to improve the performance of ultrasound (US) in head and neck oncology. A systematic search of electronic databases (MEDLINE, PubMed, clinicaltrials.gov) was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Of 15,080 initial articles identified, 34 studies were selected for in-depth analysis. Twenty-five out of 34 studies (74%) focused on the diagnostic application of US radiomics while 6 (18%) studies focused on response assessment and 3 (8%) studies utilized US radiomics for modeling normal tissue toxicity. Support vector machine (SVM) was the most commonly employed ML method (47%) followed by multivariate logistic regression (24%) and k-nearest neighbor analysis (21%). Only 11/34 (~32%) of the studies included an independent validation set. A majority of studies were retrospective in nature (76%) and based on single-center evaluation (85%) with variable numbers of patients (12–1609) and imaging datasets (32–1624). Despite these limitations, the application of ML methods resulted in improved diagnostic and prognostic performance of US highlighting the potential clinical utility of this approach.

Artificial Intelligence Education Programs for Health Care Professionals: Scoping Review

BACKGROUND

As the adoption of artificial intelligence (AI) in health care increases, it will become increasingly crucial to involve health care professionals (HCPs) in developing, validating, and implementing AI-enabled technologies. However, because of a lack of AI literacy, most HCPs are not adequately prepared for this revolution. This is a significant barrier to adopting and implementing AI that will affect patients. In addition, the limited existing AI education programs face barriers to development and implementation at various levels of medical education.

OBJECTIVE

With a view to informing future AI education programs for HCPs, this scoping review aims to provide an overview of the types of current or past AI education programs that pertains to the programs' curricular content, modes of delivery, critical implementation factors for education delivery, and outcomes used to assess the programs' effectiveness.

METHODS

After the creation of a search strategy and keyword searches, a 2-stage screening process was conducted by 2 independent reviewers to determine study eligibility. When consensus was not reached, the conflict was resolved by consulting a third reviewer. This process consisted of a title and abstract scan and a full-text review. The articles were included if they discussed an actual training program or educational intervention, or a potential training program or educational intervention and the desired content to be covered, focused on AI, and were designed or intended for HCPs (at any stage of their career).

RESULTS

Of the 10,094 unique citations scanned, 41 (0.41%) studies relevant to our eligibility criteria were identified. Among the 41 included studies, 10 (24%) described 13 unique programs and 31 (76%) discussed recommended curricular content. The curricular content of the unique programs ranged from AI use, AI interpretation, and cultivating skills to explain results derived from AI algorithms. The curricular topics were categorized into three main domains: cognitive, psychomotor, and affective.

CONCLUSIONS

This review provides an overview of the current landscape of AI in medical education and highlights the skills and competencies required by HCPs to effectively use AI in enhancing the quality of care and optimizing patient outcomes. Future education efforts should focus on the development of regulatory strategies, a multidisciplinary approach to curriculum redesign, a competency-based curriculum, and patient-clinician interaction.

Accelerating the Appropriate Adoption of Artificial Intelligence in Health Care: Protocol for a Multistepped Approach

BACKGROUND

Significant investments and advances in health care technologies and practices have created a need for digital and data-literate health care providers. Artificial intelligence (AI) algorithms transform the analysis, diagnosis, and treatment of medical conditions. Complex and massive data sets are informing significant health care decisions and clinical practices. The ability to read, manage, and interpret large data sets to provide data-driven care and to protect patient privacy are increasingly critical skills for today's health care providers.

OBJECTIVE

The aim of this study is to accelerate the appropriate adoption of data-driven and AI-enhanced care by focusing on the mindsets, skillsets, and toolsets of point-of-care health providers and their leaders in the health system.

METHODS

To accelerate the adoption of AI and the need for organizational change at a national level, our multistepped approach includes creating awareness and capacity building, learning through innovation and adoption, developing appropriate and strategic partnerships, and building effective knowledge exchange initiatives. Education interventions designed to adapt knowledge to the local context and address any challenges to knowledge use include engagement activities to increase awareness, educational curricula for health care providers and leaders, and the development of a coaching and practice-based innovation hub. Framed by the Knowledge-to-Action framework, we are currently in the knowledge creation stage to inform the curricula for each deliverable. An environmental scan and scoping review were conducted to understand the current state of AI education programs as reported in the academic literature.

RESULTS

The environmental scan identified 24 AI-accredited programs specific to health providers, of which 11 were from the United States, 6 from Canada, 4 from the United Kingdom, and 3 from Asian countries. The most common curriculum topics across the environmental scan and scoping review included AI fundamentals, applications of AI, applied machine learning in health care, ethics, data science, and challenges to and opportunities for using AI.

CONCLUSIONS

Technologies are advancing more rapidly than organizations, and professionals can adopt and adapt to them. To help shape AI practices, health care providers must have the skills and abilities to initiate change and shape the future of their discipline and practices for advancing high-quality care within the digital ecosystem.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/30940.

Educating Future Physicians in Artificial Intelligence (AI): An Integrative Review and Proposed Changes

BACKGROUND

As medicine and the delivery of healthcare enters the age of Artificial Intelligence (AI), the need for competent human-machine interaction to aid clinical decisions will rise. Medical students need to be sufficiently proficient in AI, its advantages to improve healthcare's expenses, quality, and access. Similarly, students must be educated about the shortfalls of AI such as bias, transparency, and liability. Overlooking a technology that will be transformative for the foreseeable future would place medical students at a disadvantage. However, there has been little interest in researching a proper method to implement AI in the medical education curriculum. This study aims to review the current literature that covers the attitudes of medical students towards AI, implementation of AI in the medical curriculum, and describe the need for more research in this area.

METHODS

An integrative review was performed to combine data from various research designs and literature. Pubmed, Medline (Ovid), GoogleScholar, and Web of Science articles between 2010 and 2020 were all searched with particular inclusion and exclusion criteria. Full text of the selected articles was analyzed using the Extension of Technology Acceptance Model and the Diffusions of Innovations theory. Data were successively pooled together, recorded, and analyzed quantitatively using a modified Hawkings evaluation form. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses was utilized to help improve reporting.

RESULTS

A total of 39 articles meeting inclusion criteria were identified. Primary assessments of medical students attitudes were identified (n = 5). Plans to implement AI in the curriculum for the purpose of teaching students about AI (n = 6) and articles reporting actual implemented changes (n = 2) were assessed. Finally, 26 articles described the need for more research on this topic or calling for the need of change in medical curriculum to anticipate AI in healthcare.

CONCLUSIONS

There are few plans or implementations reported on how to incorporate AI in the medical curriculum. Medical schools must work together to create a longitudinal study and initiative on how to successfully equip medical students with knowledge in AI.