Ethical and regulatory challenges of large language models in medicine.

With the rapid growth of interest in and use of large language models (LLMs) across various industries, we are facing some crucial and profound ethical concerns, especially in the medical field. The unique technical architecture and purported emergent abilities of LLMs differentiate them substantially from other artificial intelligence (AI) models and natural language processing techniques used, necessitating a nuanced understanding of LLM ethics. In this Viewpoint, we highlight ethical concerns stemming from the perspectives of users, developers, and regulators, notably focusing on data privacy and rights of use, data provenance, intellectual property contamination, and broad applications and plasticity of LLMs. A comprehensive framework and mitigating strategies will be imperative for the responsible integration of LLMs into medical practice, ensuring alignment with ethical principles and safeguarding against potential societal risks.

Critical Bias in Critical Care Devices.

Critical care data contain information about the most physiologically fragile patients in the hospital, who require a significant level of monitoring. However, medical devices used for patient monitoring suffer from measurement biases that have been largely underreported. This article explores sources of bias in commonly used clinical devices, including pulse oximeters, thermometers, and sphygmomanometers. Further, it provides a framework for mitigating these biases and key principles to achieve more equitable health care delivery.

Moving towards vertically integrated artificial intelligence development.

Substantial interest and investment in clinical artificial intelligence (AI) research has not resulted in widespread translation to deployed AI solutions. Current attention has focused on bias and explainability in AI algorithm development, external validity and model generalisability, and lack of equity and representation in existing data. While of great importance, these considerations also reflect a model-centric approach seen in published clinical AI research, which focuses on optimising architecture and performance of an AI model on best available datasets. However, even robustly built models using state-of-the-art algorithms may fail once tested in realistic environments due to unpredictability of real-world conditions, out-of-dataset scenarios, characteristics of deployment infrastructure, and lack of added value to clinical workflows relative to cost and potential clinical risks. In this perspective, we define a vertically integrated approach to AI development that incorporates early, cross-disciplinary, consideration of impact evaluation, data lifecycles, and AI production, and explore its implementation in two contrasting AI development pipelines: a scalable "AI factory" (Mayo Clinic, Rochester, United States), and an end-to-end cervical cancer screening platform for resource poor settings (Paps AI, Mbarara, Uganda). We provide practical recommendations for implementers, and discuss future challenges and novel approaches (including a decentralised federated architecture being developed in the NHS (AI4VBH, London, UK)). Growth in global clinical AI research continues unabated, and introduction of vertically integrated teams and development practices can increase the translational potential of future clinical AI projects.

Let all know: insights from a digital storytelling facilitator training in Uganda.

BACKGROUND: Digital storytelling (DST) is a participatory, arts-based methodology that facilitates the creation of short films called digital stories. Both the DST process and resulting digital stories can be used for education, research, advocacy, and therapeutic purposes in public health. DST is widely used in Europe and North America, and becoming increasingly common in Africa. In East Africa, there is currently limited in-country DST facilitation capacity, which restricts the scope of use. Through a Ugandan-Canadian partnership, six Ugandan faculty and staff from Mbarara University of Science and Technology participated in a pilot DST facilitation training workshop to enhance Ugandan DST capacity. OBJECTIVE: This Participatory Action Research (PAR) study assessed the modification of DST methodology, and identified the future potential of DST in Uganda and other East African settings. METHODS: In the two-week DST Facilitator Training, trainees created their own stories, learned DST technique and theory, facilitated DST with community health workers, and led a community screening. All trainees were invited to contribute to this study. Data was collected through daily reflection and journaling which informed a final, post-workshop focus group where participants and researchers collaboratively analyzed observations and generated themes. RESULTS: In total, twelve stories were created, six by trainees and six by community health workers. Three key themes emerged from PAR analysis: DST was a culturally appropriate way to modernize oral storytelling traditions and had potential for broad use in Uganda; DST could be modified to address ethical and logistical challenges of working with vulnerable groups in-country; training in-country facilitators was perceived as advantageous in addressing community priorities. CONCLUSION: This pilot study suggests DST is a promising methodology that can potentially be used for many purposes in an East African setting. Building in-country DST facilitation capacity will accelerate opportunities for addressing community health priorities through amplifying local voices.

A pap-smear analysis tool (PAT) for detection of cervical cancer from pap-smear images.

BACKGROUND: Cervical cancer is preventable if effective screening measures are in place. Pap-smear is the commonest technique used for early screening and diagnosis of cervical cancer. However, the manual analysis of the pap-smears is error prone due to human mistake, moreover, the process is tedious and time-consuming. Hence, it is beneficial to develop a computer-assisted diagnosis tool to make the pap-smear test more accurate and reliable. This paper describes the development of a tool for automated diagnosis and classification of cervical cancer from pap-smear images. METHOD: Scene segmentation was achieved through a Trainable Weka Segmentation classifier and a sequential elimination approach was used for debris rejection. Feature selection was achieved using simulated annealing integrated with a wrapper filter, while classification was achieved using a fuzzy C-means algorithm. RESULTS: The evaluation of the classifier was carried out on three different datasets (single cell images, multiple cell images and pap-smear slide images from a pathology lab). Overall classification accuracy, sensitivity and specificity of '98.88%, 99.28% and 97.47%', '97.64%, 98.08% and 97.16%' and '95.00%, 100% and 90.00%' were obtained for each dataset, respectively. The higher accuracy and sensitivity of the classifier was attributed to the robustness of the feature selection method that accurately selected cell features that improved the classification performance and the number of clusters used during defuzzification and classification. Results show that the method outperforms many of the existing algorithms in sensitivity (99.28%), specificity (97.47%), and accuracy (98.88%) when applied to the Herlev benchmark pap-smear dataset. False negative rate, false positive rate and classification error of 0.00%, 10.00% and 5.00%, respectively were obtained when applied to pap-smear slides from a pathology lab. CONCLUSIONS: The major contribution of this tool in a cervical cancer screening workflow is that it reduces on the time required by the cytotechnician to screen very many pap-smears by eliminating the obvious normal ones, hence more time can be put on the suspicious slides. The proposed system has the capability of analyzing a full pap-smear slide within 3 min as opposed to the 5-10 min per slide in the manual analysis. The tool presented in this paper is applicable to many pap-smear analysis systems but is particularly pertinent to low-cost systems that should be of significant benefit to developing economies.

A review of image analysis and machine learning techniques for automated cervical cancer screening from pap-smear images.

BACKGROUND AND OBJECTIVE: Early diagnosis and classification of a cancer type can help facilitate the subsequent clinical management of the patient. Cervical cancer ranks as the fourth most prevalent cancer affecting women worldwide and its early detection provides the opportunity to help save life. To that end, automated diagnosis and classification of cervical cancer from pap-smear images has become a necessity as it enables accurate, reliable and timely analysis of the condition's progress. This paper presents an overview of the state of the art as articulated in prominent recent publications focusing on automated detection of cervical cancer from pap-smear images. METHODS: The survey reviews publications on applications of image analysis and machine learning in automated diagnosis and classification of cervical cancer from pap-smear images spanning 15 years. The survey reviews 30 journal papers obtained electronically through four scientific databases (Google Scholar, Scopus, IEEE and Science Direct) searched using three sets of keywords: (1) segmentation, classification, cervical cancer; (2) medical imaging, machine learning, pap-smear; (3) automated system, classification, pap-smear. RESULTS: Most of the existing algorithms facilitate an accuracy of nearly 93.78% on an open pap-smear data set, segmented using CHAMP digital image software. K-nearest-neighbors and support vector machines algorithms have been reported to be excellent classifiers for cervical images with accuracies of over 99.27% and 98.5% respectively when applied to a 2-class classification problem (normal or abnormal). CONCLUSION: The reviewed papers indicate that there are still weaknesses in the available techniques that result in low accuracy of classification in some classes of cells. Moreover, most of the existing algorithms work either on single or on multiple cervical smear images. This accuracy can be increased by varying various parameters such as the features to be extracted, improvement in noise removal, using hybrid segmentation and classification techniques such of multi-level classifiers. Combining K-nearest-neighbors algorithm with other algorithm(s) such as support vector machines, pixel level classifications and including statistical shape models can also improve performance. Further, most of the developed classifiers are tested on accurately segmented images using commercially available software such as CHAMP software. There is thus a deficit of evidence that these algorithms will work in clinical settings found in developing countries (where 85% of cervical cancer incidences occur) that lack sufficient trained cytologists and the funds to buy the commercial segmentation software.