AI-facilitated health care requires education of clinicians

Leading in the development, standardised evaluation, and adoption of artificial intelligence in clinical practice: regional anaesthesia as an example

A recent study by Suissa and colleagues explored the clinical relevance of a medical image segmentation metric (Dice metric) commonly used in the field of artificial intelligence (AI). They showed that pixel-wise agreement for physician identification of structures on ultrasound images is variable, and a relatively low Dice metric (0.34) correlated to a substantial agreement on subjective clinical assessment. We highlight the need to bring structure and clinical perspective to the evaluation of medical AI, which clinicians are best placed to direct.

When all computers shut down: the clinical impact of a major cyber-attack on a general hospital

Importance

Healthcare organizations operate in a data-rich environment and depend on digital computerized systems; thus, they may be exposed to cyber threats. Indeed, one of the most vulnerable sectors to hacks and malware is healthcare. However, the impact of cyberattacks on healthcare organizations remains under-investigated.

Objective

This study aims to describe a major attack on an entire medical center that resulted in a complete shutdown of all computer systems and to identify the critical actions required to resume regular operations.

Setting

This study was conducted on a public, general, and acute care referral university teaching hospital.

Methods

We report the different recovery measures on various hospital clinical activities and their impact on clinical work.

Results

The system malfunction of hospital computers did not reduce the number of heart catheterizations, births, or outpatient clinic visits. However, a sharp drop in surgical activities, emergency room visits, and total hospital occupancy was observed immediately and during the first postattack week. A gradual increase in all clinical activities was detected starting in the second week after the attack, with a significant increase of 30% associated with the restoration of the electronic medical records (EMR) and laboratory module and a 50% increase associated with the return of the imaging module archiving. One limitation of the present study is that, due to its retrospective design, there were no data regarding the number of elective internal care hospitalizations that were considered crucial.

Conclusions and relevance

The risk of ransomware cyberattacks is growing. Healthcare systems at all levels of the hospital should be aware of this threat and implement protocols should this catastrophic event occur. Careful evaluation of steady computer system recovery weekly enables vital hospital function, even under a major cyberattack. The restoration of EMR, laboratory systems, and imaging archiving modules was found to be the most significant factor that allowed the return to normal clinical hospital work.

Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial

Deep learning-based clinical imaging analysis underlies diagnostic artificial intelligence (AI) models, which can match or even exceed the performance of clinical experts, having the potential to revolutionize clinical practice. A wide variety of automated machine learning (autoML) platforms lower the technical barrier to entry to deep learning, extending AI capabilities to clinicians with limited technical expertise, and even autonomous foundation models such as multimodal large language models. Here, we provide a technical overview of autoML with descriptions of how autoML may be applied in education, research, and clinical practice. Each stage of the process of conducting an autoML project is outlined, with an emphasis on ethical and technical best practices. Specifically, data acquisition, data partitioning, model training, model validation, analysis, and model deployment are considered. The strengths and limitations of available code-free, code-minimal, and code-intensive autoML platforms are considered. AutoML has great potential to democratize AI in medicine, improving AI literacy by enabling "hands-on" education. AutoML may serve as a useful adjunct in research by facilitating rapid testing and benchmarking before significant computational resources are committed. AutoML may also be applied in clinical contexts, provided regulatory requirements are met. The abstraction by autoML of arduous aspects of AI engineering promotes prioritization of data set curation, supporting the transition from conventional model-driven approaches to data-centric development. To fulfill its potential, clinicians must be educated on how to apply these technologies ethically, rigorously, and effectively; this tutorial represents a comprehensive summary of relevant considerations.

Nurturing next generation physicians: A new Israeli healthtech fellowship

The Israeli Society for HealthTech aims at advancing the integration of innovation and healthcare entrepreneurship into medical practice and across traditional health professions, to benefit patients and improve quality of care. In 2021, the Society launched the first fellowship for board certified physicians in HealthTech. This backstory discusses the motivation of launching the program and reviews the design of the fellowship, including curriculum, the expertise of the lecturers, and initial tangible results of the program.

The Quality and Utility of Artificial Intelligence in Patient Care

BACKGROUND

Artificial intelligence (AI) is increasingly being used in patient care. In the future, physicians will need to understand not only the basic functioning of AI applications, but also their quality, utility, and risks.

METHODS

This article is based on a selective review of the literature on the principles, quality, limitations, and benefits AI applications in patient care, along with examples of individual applications.

RESULTS

The number of AI applications in patient care is rising, with more than 500 approvals in the United States to date. Their quality and utility are based on a number of interdependent factors, including the real-life setting, the type and amount of data collected, the choice of variables used by the application, the algorithms used, and the goal and implementation of each application. Bias (which may be hidden) and errors can arise at all these levels. Any evaluation of the quality and utility of an AI application must, therefore, be conducted according to the scientific principles of evidence-based medicine-a requirement that is often hampered by a lack of transparency.

CONCLUSION

AI has the potential to improve patient care while meeting the challenge of dealing with an ever-increasing surfeit of information and data in medicine with limited human resources. The limitations and risks of AI applications require critical and responsible consideration. This can best be achieved through a combination of scientific.

Artificial intelligence, machine learning, and deep learning in liver transplantation

Liver transplantation (LT) is a life-saving treatment for individuals with end-stage liver disease. The management of LT recipients is complex, predominantly because of the need to consider demographic, clinical, laboratory, pathology, imaging, and omics data in the development of an appropriate treatment plan. Current methods to collate clinical information are susceptible to some degree of subjectivity; thus, clinical decision-making in LT could benefit from the data-driven approach offered by artificial intelligence (AI). Machine learning and deep learning could be applied in both the pre- and post-LT settings. Some examples of AI applications pre-transplant include optimising transplant candidacy decision-making and donor-recipient matching to reduce waitlist mortality and improve post-transplant outcomes. In the post-LT setting, AI could help guide the management of LT recipients, particularly by predicting patient and graft survival, along with identifying risk factors for disease recurrence and other associated complications. Although AI shows promise in medicine, there are limitations to its clinical deployment which include dataset imbalances for model training, data privacy issues, and a lack of available research practices to benchmark model performance in the real world. Overall, AI tools have the potential to enhance personalised clinical decision-making, especially in the context of liver transplant medicine.

Optical Biopsy of Dysplasia in Barrett's Oesophagus Assisted by Artificial Intelligence

Optical biopsy in Barrett's oesophagus (BE) using endocytoscopy (EC) could optimize endoscopic screening. However, the identification of dysplasia is challenging due to the complex interpretation of the highly detailed images. Therefore, we assessed whether using artificial intelligence (AI) as second assessor could help gastroenterologists in interpreting endocytoscopic BE images. First, we prospectively videotaped 52 BE patients with EC. Then we trained and tested the AI pm distinct datasets drawn from 83,277 frames, developed an endocytoscopic BE classification system, and designed online training and testing modules. We invited two successive cohorts for these online modules: 10 endoscopists to validate the classification system and 12 gastroenterologists to evaluate AI as second assessor by providing six of them with the option to request AI assistance. Training the endoscopists in the classification system established an improved sensitivity of 90.0% (+32.67%, p < 0.001) and an accuracy of 77.67% (+13.0%, p = 0.020) compared with the baseline. However, these values deteriorated at follow-up (-16.67%, p < 0.001 and -8.0%, p = 0.009). Contrastingly, AI-assisted gastroenterologists maintained high sensitivity and accuracy at follow-up, subsequently outperforming the unassisted gastroenterologists (+20.0%, p = 0.025 and +12.22%, p = 0.05). Thus, best diagnostic scores for the identification of dysplasia emerged through human-machine collaboration between trained gastroenterologists with AI as the second assessor. Therefore, AI could support clinical implementation of optical biopsies through EC.

Clinician's guide to trustworthy and responsible artificial intelligence in cardiovascular imaging

A growing number of artificial intelligence (AI)-based systems are being proposed and developed in cardiology, driven by the increasing need to deal with the vast amount of clinical and imaging data with the ultimate aim of advancing patient care, diagnosis and prognostication. However, there is a critical gap between the development and clinical deployment of AI tools. A key consideration for implementing AI tools into real-life clinical practice is their "trustworthiness" by end-users. Namely, we must ensure that AI systems can be trusted and adopted by all parties involved, including clinicians and patients. Here we provide a summary of the concepts involved in developing a "trustworthy AI system." We describe the main risks of AI applications and potential mitigation techniques for the wider application of these promising techniques in the context of cardiovascular imaging. Finally, we show why trustworthy AI concepts are important governing forces of AI development.

Informatics education for translational research teams: An unrealized opportunity to strengthen the national research infrastructure

Objective

To identify the informatics educational needs of clinical and translational research professionals whose primary focus is not informatics.

Introduction

Informatics and data science skills are essential for the full spectrum of translational research, and an increased understanding of informatics issues on the part of translational researchers can alleviate the demand for informaticians and enable more productive collaborations when informaticians are involved. Identifying the level of interest in different topics among various types of of translational researchers will help set priorities for development and dissemination of informatics education.

Methods

We surveyed clinical and translational science researchers in Clinical and Translational Science Award (CTSA) programs about their educational needs and preferences.

Results

Researchers from 23 out of the 62 CTSA hubs responded to the survey. 67% of respondents across roles and topics expressed interest in learning about informatics topics. There was high interest in all 30 topics included in the survey, with some variation in interest depending on the role of the respondents.

Discussion

Our data support the need to advance training in clinical and biomedical informatics. As the complexity and use of information technology and data science in research studies grows, informaticians will continue to be a limited resource for research collaboration, education, and training. An increased understanding of informatics issues across translational research teams can alleviate this burden and allow for more productive collaborations. To inform a roadmap for informatics education for research professionals, we suggest strategies to use the results of this needs assessment to develop future informatics education.

Practical Application of Artificial Intelligence Technology in Glaucoma Diagnosis

Purpose. By comparing the performance of different models between artificial intelligence (AI) and doctors, we aim to evaluate and identify the optimal model for future usage of AI. Methods. A total of 500 fundus images of glaucoma and 500 fundus images of normal eyes were collected and randomly divided into five groups, with each group corresponding to one round. The AI system provided diagnostic suggestions for each image. Four doctors provided diagnoses without the assistance of the AI in the first round and with the assistance of the AI in the second and third rounds. In the fourth round, doctor B and doctor D made diagnoses with the help of the AI and the other two doctors without the help of the AI. In the last round, doctor A and doctor B made diagnoses with the help of AI and the other two doctors without the help of the AI. Results. Doctor A, doctor B, and doctor D had a higher accuracy in the diagnosis of glaucoma with the assistance of AI in the second ( $p=0.036$ , $p=0.003$ , and $p\le 0.000$ ) and the third round ( $p=0.021$ , $p\le 0.000$ , and $p\le 0.000$ ) than in the first round. The accuracy of at least one doctor was higher than that of AI in the second and third rounds, in spite of no detectable significance ( $p=0.283$ , $p=0.727$ , $p=0.344$ , and $p=0.508$ ). The four doctors’ overall accuracy ( $p=0.004$ and $p\le 0.000$ ) and sensitivity ( $p=0.006$ and $p\le 0.000$ ) as a whole were significantly improved in the second and third rounds. Conclusions. This “Doctor + AI” model can clarify the role of doctors and AI in medical responsibility and ensure the safety of patients, and importantly, this model shows great potential and application prospects.

New meaning for NLP: the trials and tribulations of natural language processing with GPT-3 in ophthalmology

Natural language processing (NLP) is a subfield of machine intelligence focused on the interaction of human language with computer systems. NLP has recently been discussed in the mainstream media and the literature with the advent of Generative Pre-trained Transformer 3 (GPT-3), a language model capable of producing human-like text. The release of GPT-3 has also sparked renewed interest on the applicability of NLP to contemporary healthcare problems. This article provides an overview of NLP models, with a focus on GPT-3, as well as discussion of applications specific to ophthalmology. We also outline the limitations of GPT-3 and the challenges with its integration into routine ophthalmic care.

From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration

OBJECTIVE

Health care systems worldwide are challenged to provide adequate care for the 200 million individuals with age-related macular degeneration (AMD). Artificial intelligence (AI) has the potential to make a significant, positive impact on the diagnosis and management of patients with AMD; however, the development of effective AI devices for clinical care faces numerous considerations and challenges, a fact evidenced by a current absence of Food and Drug Administration (FDA)-approved AI devices for AMD.

PURPOSE

To delineate the state of AI for AMD, including current data, standards, achievements, and challenges.

METHODS

Members of the Collaborative Community on Ophthalmic Imaging Working Group for AI in AMD attended an inaugural meeting on September 7, 2020, to discuss the topic. Subsequently, they undertook a comprehensive review of the medical literature relevant to the topic. Members engaged in meetings and discussion through December 2021 to synthesize the information and arrive at a consensus.

RESULTS

Existing infrastructure for robust AI development for AMD includes several large, labeled data sets of color fundus photography and OCT images; however, image data often do not contain the metadata necessary for the development of reliable, valid, and generalizable models. Data sharing for AMD model development is made difficult by restrictions on data privacy and security, although potential solutions are under investigation. Computing resources may be adequate for current applications, but knowledge of machine learning development may be scarce in many clinical ophthalmology settings. Despite these challenges, researchers have produced promising AI models for AMD for screening, diagnosis, prediction, and monitoring. Future goals include defining benchmarks to facilitate regulatory authorization and subsequent clinical setting generalization.

CONCLUSIONS

Delivering an FDA-authorized, AI-based device for clinical care in AMD involves numerous considerations, including the identification of an appropriate clinical application; acquisition and development of a large, high-quality data set; development of the AI architecture; training and validation of the model; and functional interactions between the model output and clinical end user. The research efforts undertaken to date represent starting points for the medical devices that eventually will benefit providers, health care systems, and patients.

The Past, Present and Future of Surgical Education in Ireland

The Royal College of Surgeons in Ireland (RCSI) was founded primarily to advance the standards of surgical training and surgical practice in Ireland. Over the course of almost 240 years, the College evolved as a comprehensive University of Medicine and Health Sciences, delivering education not only in Surgery but also in Medicine, Physiotherapy, Pharmacy and Nursing. RCSI today has a large global footprint and runs healthcare education programmes in several international locations. The College works in close collaboration with the other surgical Royal Colleges in Great Britain and the four colleges have a common surgical curriculum. RCSI recognises the increasing challenges facing traditional surgical training models and therefore has developed structured education programmes to support the conventional apprenticeship model. Surgical training in Ireland includes comprehensive training in both technical (operative) skills and non-technical (human factors) skills. RCSI is committed to the integration of simulation in surgical training and has invested heavily in state-of-the-art simulation facilities and in next-generation education technologies such as virtual reality, augmented reality and Artificial Intelligence-based educational technologies. Formal surgical training programmes in Ireland are complemented by a range of Masters programmes in Surgical Science and Practice and also Human Factors in Patient Safety.

Today’s Mistakes and Tomorrow’s Wisdom in Endoscopic Imaging of Barrett’s Esophagus

<b><i>Background:</i></b> Esophageal adenocarcinoma (EAC) is one of the main causes of cancer-related deaths worldwide and its incidence is rising. Barrett’s esophagus (BE) can develop low- and high-grade dysplasia which can progress to EAC overtime. The golden standard to detect dysplastic BE (DBE) or EAC is surveillance with high-definition white-light endoscopy (HD-WLE) and random biopsies according to the Seattle protocol. However, this method is time-consuming and associated with a remarkable miss rate. Therefore, there is great need for the development of novel reliable techniques to optimize surveillance strategies and improve detection rates. <b><i>Summary:</i></b> Optical chromoendoscopy (OC) techniques like narrow-band imaging have shown improved detection of DBE and EAC compared to HD-WLE and random biopsies. Most recent OC techniques, including the iSCAN optical enhancement system and linked color imaging, showed improved characterization of DBE and EAC retrospectively. Fluorescence molecular endoscopy (FME) presented promising results to highlight DBE and EAC. Moreover, with the establishment of well-performing delineation computer-aided detection (CAD) algorithms and the first real-time CAD system for EAC, we expect clinical application of CAD in the near future. <b><i>Key Messages:</i></b> Despite impressive progress made in the development of advanced endoscopic techniques, combined HD-WLE/OC followed by random biopsies remains the golden standard for BE surveillance. Surveillance depends on appropriate mucosal cleansing, sufficient inspection time, and competence of the performing gastroenterologist to improve detection of EAC. In addition, to facilitate the clinical implementation of advanced endoscopic techniques, multicenter prospective clinical studies are demanded for OC and FME. Meanwhile, further optimization of CAD algorithms, the education of gastroenterologists, and analysis of the interaction between the clinician and the computer should be performed.

Applications of artificial intelligence (AI) in ovarian cancer, pancreatic cancer, and image biomarker discovery

BACKGROUND

Artificial intelligence (AI), including machine learning (ML) and deep learning, has the potential to revolutionize biomedical research. Defined as the ability to "mimic" human intelligence by machines executing trained algorithms, AI methods are deployed for biomarker discovery.

OBJECTIVE

We detail the advancements and challenges in the use of AI for biomarker discovery in ovarian and pancreatic cancer. We also provide an overview of associated regulatory and ethical considerations.

METHODS

We conducted a literature review using PubMed and Google Scholar to survey the published findings on the use of AI in ovarian cancer, pancreatic cancer, and cancer biomarkers.

RESULTS

Most AI models associated with ovarian and pancreatic cancer have yet to be applied in clinical settings, and imaging data in many studies are not publicly available. Low disease prevalence and asymptomatic disease limits data availability required for AI models. The FDA has yet to qualify imaging biomarkers as effective diagnostic tools for these cancers.

CONCLUSIONS

Challenges associated with data availability, quality, bias, as well as AI transparency and explainability, will likely persist. Explainable and trustworthy AI efforts will need to continue so that the research community can better understand and construct effective models for biomarker discovery in rare cancers.

Developing, implementing and governing artificial intelligence in medicine: a step-by-step approach to prevent an artificial intelligence winter

Objective

Although the role of artificial intelligence (AI) in medicine is increasingly studied, most patients do not benefit because the majority of AI models remain in the testing and prototyping environment. The development and implementation trajectory of clinical AI models are complex and a structured overview is missing. We therefore propose a step-by-step overview to enhance clinicians’ understanding and to promote quality of medical AI research.

Methods

We summarised key elements (such as current guidelines, challenges, regulatory documents and good practices) that are needed to develop and safely implement AI in medicine.

Conclusion

This overview complements other frameworks in a way that it is accessible to stakeholders without prior AI knowledge and as such provides a step-by-step approach incorporating all the key elements and current guidelines that are essential for implementation, and can thereby help to move AI from bytes to bedside.

Knowledge, attitudes, and practices towards artificial intelligence among young pediatricians: A nationwide survey in France

OBJECTIVE

To assess the knowledge, attitudes, and practices (KAP) towards artificial intelligence (AI) among young pediatricians in France.

METHODS

We invited young French pediatricians to participate in an online survey. Invitees were identified through various email listings and social media. We conducted a descriptive analysis and explored whether survey responses varied according to respondents' previous training in AI and level of clinical experience (i.e., residents vs. experienced doctors).

RESULTS

In total, 165 French pediatricians participated in the study (median age 27 years, women 78%, residents 64%). While 90% of participants declared they understood the term "artificial intelligence", only 40% understood the term "deep learning". Most participants expected AI would lead to improvements in healthcare (e.g., better access to healthcare, 80%; diagnostic assistance, 71%), and 86% declared they would favor implementing AI tools in pediatrics. Fifty-nine percent of respondents declared seeing AI as a threat to medical data security and 35% as a threat to the ethical and human dimensions of medicine. Thirty-nine percent of respondents feared losing clinical skills because of AI, and 6% feared losing their job because of AI. Only 5% of respondents had received specific training in AI, while 87% considered implementing such programs would be necessary. Respondents who received training in AI had significantly better knowledge and a higher probability of having encountered AI tools in their medical practice (p < 0.05 for both). There was no statistically significant difference between residents' and experienced doctors' responses.

CONCLUSION

In this survey, most young French pediatricians had favorable views toward AI, but a large proportion expressed concerns regarding the ethical, societal, and professional issues linked with the implementation of AI.

Cyber-attacks are a permanent and substantial threat to health systems: Education must reflect that

Cyber-attacks on healthcare institutions have increased in recent years and have made headlines through the COVID-19 pandemic. With the fallout of attacks increasingly reported in academic research and in the media, there is a real urgency to address cyber-threats that must be augmented across and within health systems. Until now, clinical healthcare professionals have considered cyber-attacks on healthcare organisations a predominantly information and communication technology issue, but this perception is no longer fit-for-purpose. This commentary provides insights into the scale of cyber-attacks and their impact on staff wellbeing, arguing that cybersecurity education for all staff in healthcare organisations must be improved through online resources, simulation, and gaming. The role of national educators, policymakers, and multilateral organisations in achieving this is outlined alongside implications for future policy and practice.

Automated deep learning in ophthalmology: AI that can build AI

PURPOSE OF REVIEW

The purpose of this review is to describe the current status of automated deep learning in healthcare and to explore and detail the development of these models using commercially available platforms. We highlight key studies demonstrating the effectiveness of this technique and discuss current challenges and future directions of automated deep learning.

RECENT FINDINGS

There are several commercially available automated deep learning platforms. Although specific features differ between platforms, they utilise the common approach of supervised learning. Ophthalmology is an exemplar speciality in the area, with a number of recent proof-of-concept studies exploring classification of retinal fundus photographs, optical coherence tomography images and indocyanine green angiography images. Automated deep learning has also demonstrated impressive results in other specialities such as dermatology, radiology and histopathology.

SUMMARY

Automated deep learning allows users without coding expertise to develop deep learning algorithms. It is rapidly establishing itself as a valuable tool for those with limited technical experience. Despite residual challenges, it offers considerable potential in the future of patient management, clinical research and medical education.

VIDEO ABSTRACT

http://links.lww.com/COOP/A44.

Clinician-driven artificial intelligence in ophthalmology: resources enabling democratization

PURPOSE OF REVIEW

This article aims to discuss the current state of resources enabling the democratization of artificial intelligence (AI) in ophthalmology.

RECENT FINDINGS

Open datasets, efficient labeling techniques, code-free automated machine learning (AutoML) and cloud-based platforms for deployment are resources that enable clinicians with scarce resources to drive their own AI projects.

SUMMARY

Clinicians are the use-case experts who are best suited to drive AI projects tackling patient-relevant outcome measures. Taken together, open datasets, efficient labeling techniques, code-free AutoML and cloud platforms break the barriers for clinician-driven AI. As AI becomes increasingly democratized through such tools, clinicians and patients stand to benefit greatly.