A protocol for annotation of total body photography for machine learning to analyze skin phenotype and lesion classification.

Introduction: Artificial Intelligence (AI) has proven effective in classifying skin cancers using dermoscopy images. In experimental settings, algorithms have outperformed expert dermatologists in classifying melanoma and keratinocyte cancers. However, clinical application is limited when algorithms are presented with 'untrained' or out-of-distribution lesion categories, often misclassifying benign lesions as malignant, or misclassifying malignant lesions as benign. Another limitation often raised is the lack of clinical context (e.g., medical history) used as input for the AI decision process. The increasing use of Total Body Photography (TBP) in clinical examinations presents new opportunities for AI to perform holistic analysis of the whole patient, rather than a single lesion. Currently there is a lack of existing literature or standards for image annotation of TBP, or on preserving patient privacy during the machine learning process. Methods: This protocol describes the methods for the acquisition of patient data, including TBP, medical history, and genetic risk factors, to create a comprehensive dataset for machine learning. 500 patients of various risk profiles will be recruited from two clinical sites (Australia and Spain), to undergo temporal total body imaging, complete surveys on sun behaviors and medical history, and provide a DNA sample. This patient-level metadata is applied to image datasets using DICOM labels. Anonymization and masking methods are applied to preserve patient privacy. A two-step annotation process is followed to label skin images for lesion detection and classification using deep learning models. Skin phenotype characteristics are extracted from images, including innate and facultative skin color, nevi distribution, and UV damage. Several algorithms will be developed relating to skin lesion detection, segmentation and classification, 3D mapping, change detection, and risk profiling. Simultaneously, explainable AI (XAI) methods will be incorporated to foster clinician and patient trust. Additionally, a publicly released dataset of anonymized annotated TBP images will be released for an international challenge to advance the development of new algorithms using this type of data. Conclusion: The anticipated results from this protocol are validated AI-based tools to provide holistic risk assessment for individual lesions, and risk stratification of patients to assist clinicians in monitoring for skin cancer.

Dicing with data: the risks, benefits, tensions and tech of health data in the iToBoS project.

This paper will discuss the European funded iToBoS project, tasked by the European Commission to develop an AI diagnostic platform for the early detection of skin melanoma. The paper will outline the project, provide an overview of the data being processed, describe the impact assessment processes, and explain the AI privacy risk mitigation methods being deployed. Following this, the paper will offer a brief discussion of some of the more complex aspects: (1) the relatively low population clinical trial study cohort, which poses risks associated with data distinguishability and the masking ability of the applied anonymisation tools, (2) the project's ability to obtain informed consent from the study cohort given the complexity of the technologies, (3) the project's commitment to an open research data strategy and the additional privacy risk mitigations required to protect the multi-modal study data, and (4) the ability of the project to adequately explain the outputs of the algorithmic components to a broad range of stakeholders. The paper will discuss how the complexities have caused tension which are reflective of wider tensions in the health domain. A project level solution includes collaboration with a melanoma patient network, as an avenue for fair and representative qualification of risks and benefits with the patient stakeholder group. However, it is unclear how scalable this process is given the relentless pursuit of innovation within the health domain, accentuated by the continued proliferation of artificial intelligence, open data strategies, and the integration of multi-modal data sets inclusive of genomics.

Applying Artificial Intelligence Privacy Technology in the Healthcare Domain.

Regulations set out strict restrictions on processing personal data. ML models must also adhere to these restrictions, as it may be possible to infer personal information from trained models. In this paper, we demonstrate the use of two novel AI Privacy tools in a real-world healthcare application.

Evicase: an evidence-based case structuring approach for personalized healthcare.

The personalized medicine era stresses a growing need to combine evidence-based medicine with case based reasoning in order to improve the care process. To address this need we suggest a framework to generate multi-tiered statistical structures we call Evicases. Evicase integrates established medical evidence together with patient cases from the bedside. It then uses machine learning algorithms to produce statistical results and aggregators, weighted predictions, and appropriate recommendations. Designed as a stand-alone structure, Evicase can be used for a range of decision support applications including guideline adherence monitoring and personalized prognostic predictions.

Automatic detection of inconsistencies between free text and coded data in Sarcoma discharge letters.

Discordance between data stored in Electronic Health Records (EHR) may have a harmful effect on patient care. Automatic identification of such situations is an important yet challenging task, especially when the discordance involves information stored in free text fields. Here we present a method to automatically detect inconsistencies between data stored in free text and related coded fields. Using EHR data we train an ensemble of classifiers to predict the value of coded fields from the free text fields. Cases in which the classifiers predict with high confidence a code different from the clinicians' choice are marked as potential inconsistencies. Experimental results over discharge letters of sarcoma patients, verified by a domain expert, demonstrate the validity of our method.

Knowledge-analytics synergy in Clinical Decision Support.

Clinical Decision Support (CDS) systems hold tremendous potential for improving patient care. Most existing systems are knowledge-based tools that rely on relatively simple rules. More recent approaches rely on analytics techniques to automatically mine EHR data to reveal meaningful insights. Here, we propose the Knowledge-Analytics Synergy paradigm for CDS, in which we synergistically combine existing relevant knowledge with analytics applied to EHR data. We propose a framework for implementing such a paradigm and demonstrate its principles over real-world clinical and genomic data of hypertensive patients.