Diverse patients' attitudes towards Artificial Intelligence (AI) in diagnosis

Comparing code-free and bespoke deep learning approaches in ophthalmology

AIM

Code-free deep learning (CFDL) allows clinicians without coding expertise to build high-quality artificial intelligence (AI) models without writing code. In this review, we comprehensively review the advantages that CFDL offers over bespoke expert-designed deep learning (DL). As exemplars, we use the following tasks: (1) diabetic retinopathy screening, (2) retinal multi-disease classification, (3) surgical video classification, (4) oculomics and (5) resource management.

METHODS

We performed a search for studies reporting CFDL applications in ophthalmology in MEDLINE (through PubMed) from inception to June 25, 2023, using the keywords 'autoML' AND 'ophthalmology'. After identifying 5 CFDL studies looking at our target tasks, we performed a subsequent search to find corresponding bespoke DL studies focused on the same tasks. Only English-written articles with full text available were included. Reviews, editorials, protocols and case reports or case series were excluded. We identified ten relevant studies for this review.

RESULTS

Overall, studies were optimistic towards CFDL's advantages over bespoke DL in the five ophthalmological tasks. However, much of such discussions were identified to be mono-dimensional and had wide applicability gaps. High-quality assessment of better CFDL applicability over bespoke DL warrants a context-specific, weighted assessment of clinician intent, patient acceptance and cost-effectiveness. We conclude that CFDL and bespoke DL are unique in their own assets and are irreplaceable with each other. Their benefits are differentially valued on a case-to-case basis. Future studies are warranted to perform a multidimensional analysis of both techniques and to improve limitations of suboptimal dataset quality, poor applicability implications and non-regulated study designs.

CONCLUSION

For clinicians without DL expertise and easy access to AI experts, CFDL allows the prototyping of novel clinical AI systems. CFDL models concert with bespoke models, depending on the task at hand. A multidimensional, weighted evaluation of the factors involved in the implementation of those models for a designated task is warranted.

Implementing an Early Detection Program for Autism Spectrum Disorders in the Polish Primary Healthcare Setting-Possible Obstacles and Experiences from Online ASD Screening

A screening questionnaire for autism symptoms is not yet available in Poland, and there are no recommendations regarding screening for developmental disorders in Polish primary healthcare. The aim of this study was to assess the opinions of parents and physicians on the legitimacy and necessity of screening for autism spectrum disorders, potential barriers to the implementation of the screening program, and the evaluation and presentation of the process of online ASD screening, which was part of the validation program for the Polish version of one of the screening tools. This study involved 418 parents whose children were screened online and 95 primary care physicians who expressed their opinions in prepared surveys. The results indicate that both parents and doctors perceive the need to screen children for ASD in the general population without a clear preference as to the screening method (online or in person). Moreover, online screening is considered by respondents as a satisfactory diagnostic method. Therefore, online screening may prove to be at least a partial method of solving numerous obstacles indicated by participants' systemic difficulties including time constraints, the lack of experienced specialists in the field of developmental disorders and organizational difficulties of healthcare systems.

Predicting which patients with cancer will see a psychiatrist or counsellor from their initial oncology consultation document using natural language processing

BACKGROUND

Patients with cancer often have unmet psychosocial needs. Early detection of who requires referral to a counsellor or psychiatrist may improve their care. This work used natural language processing to predict which patients will see a counsellor or psychiatrist from a patient's initial oncology consultation document. We believe this is the first use of artificial intelligence to predict psychiatric outcomes from non-psychiatric medical documents.

METHODS

This retrospective prognostic study used data from 47,625 patients at BC Cancer. We analyzed initial oncology consultation documents using traditional and neural language models to predict whether patients would see a counsellor or psychiatrist in the 12 months following their initial oncology consultation.

RESULTS

Here, we show our best models achieved a balanced accuracy (receiver-operating-characteristic area-under-curve) of 73.1% (0.824) for predicting seeing a psychiatrist, and 71.0% (0.784) for seeing a counsellor. Different words and phrases are important for predicting each outcome.

CONCLUSION

These results suggest natural language processing can be used to predict psychosocial needs of patients with cancer from their initial oncology consultation document. Future research could extend this work to predict the psychosocial needs of medical patients in other settings.

Shaping the future of chronic disease management: Insights into patient needs for AI-based homecare systems

BACKGROUND

The rising demand for healthcare resources, especially in chronic disease management, has elevated the importance of Artificial Intelligence (AI) in healthcare. While AI-based homecare systems are being developed, the perspectives of chronic patients, who are one of the primary beneficiaries and risk bearers of these technologies, remain largely under-researched. While recent research has highlighted the importance of AI-based homecare systems, the current understanding of patients' desired designs and features is still limited.

OBJECTIVE

This paper explores chronic patients' perspectives regarding AI-based homecare systems, an area currently underrepresented in research. We aim to identify the factors influencing their decision to use such systems, elucidate the potential roles of government and other concerned authorities, and provide feedback to AI developers to enhance adoption, system design, and usability and improve the overall healthcare experiences of chronic patients.

METHOD

A web-based open-ended questionnaire was designed to gather the perspectives of chronic patients about AI-based homecare systems. In total, responses from 181 participants were collected. Using Krippendorff's clustering technique, an inductive thematic analysis was performed to identify the main themes and their respective subthemes.

RESULT

Through rigorous coding and thematic analysis of the collected responses, we identified four major themes further segmented into thirteen subthemes. These four primary themes were: 1) "Personalized Design", emphasizing the need for patients to manage their health condition better through personalized and educational resources and user-friendly interfaces; 2) "Emotional & Social Support", underscoring the desire for AI systems to facilitate social connectivity and provide emotional support to improve the well-being of chronic patients at home; 3) "System Integration & Proactive Care", addressing the importance of seamless communication, proactive patient monitoring and integration with existing healthcare platforms; and 4) "Ethics & Regulation", prioritizing ethical guidelines, regulatory compliance, and affordability in the design.

CONCLUSION

This study has offered significant insights into the needs and expectations of chronic patients regarding AI-based home care systems. 'The findings highlight the importance of personalized and accessible care, emotional and social support, seamless system integration, proactive care, and ethical considerations in designing and implementing such systems. By aligning the design and operation of these systems with the lived experiences and expectations of patients, we can better ensure their acceptance and effectiveness.

Adopting and expanding ethical principles for generative artificial intelligence from military to healthcare

In 2020, the U.S. Department of Defense officially disclosed a set of ethical principles to guide the use of Artificial Intelligence (AI) technologies on future battlefields. Despite stark differences, there are core similarities between the military and medical service. Warriors on battlefields often face life-altering circumstances that require quick decision-making. Medical providers experience similar challenges in a rapidly changing healthcare environment, such as in the emergency department or during surgery treating a life-threatening condition. Generative AI, an emerging technology designed to efficiently generate valuable information, holds great promise. As computing power becomes more accessible and the abundance of health data, such as electronic health records, electrocardiograms, and medical images, increases, it is inevitable that healthcare will be revolutionized by this technology. Recently, generative AI has garnered a lot of attention in the medical research community, leading to debates about its application in the healthcare sector, mainly due to concerns about transparency and related issues. Meanwhile, questions around the potential exacerbation of health disparities due to modeling biases have raised notable ethical concerns regarding the use of this technology in healthcare. However, the ethical principles for generative AI in healthcare have been understudied. As a result, there are no clear solutions to address ethical concerns, and decision-makers often neglect to consider the significance of ethical principles before implementing generative AI in clinical practice. In an attempt to address these issues, we explore ethical principles from the military perspective and propose the "GREAT PLEA" ethical principles, namely Governability, Reliability, Equity, Accountability, Traceability, Privacy, Lawfulness, Empathy, and Eutonomy, for generative AI in healthcare. Furthermore, we introduce a framework for adopting and expanding these ethical principles in a practical way that has been useful in the military and can be applied to healthcare for generative AI, based on contrasting their ethical concerns and risks. Ultimately, we aim to proactively address the ethical dilemmas and challenges posed by the integration of generative AI into healthcare practice.