Stephanie Kuku

Artificial intelligence as a medical device is increasingly being applied to healthcare for diagnosis, risk stratification and resource allocation. However, a growing body of evidence has highlighted the risk of algorithmic bias, which may perpetuate existing health inequity. This problem arises in part because of systemic inequalities in dataset curation, unequal opportunity to participate in research and inequalities of access. This study aims to explore existing standards, frameworks and best practices for ensuring adequate data diversity in health datasets. Exploring the body of existing literature and expert views is an important step towards the development of consensus-based guidelines. The study comprises two parts: a systematic review of existing standards, frameworks and best practices for healthcare datasets; and a survey and thematic analysis of stakeholder views of bias, health equity and best practices for artificial intelligence as a medical device. We found that the need for dataset diversity was well described in literature, and experts generally favored the development of a robust set of guidelines, but there were mixed views about how these could be implemented practically. The outputs of this study will be used to inform the development of standards for transparency of data diversity in health datasets (the STANDING Together initiative).

Without careful dissection of the ways in which biases can be encoded into artificial intelligence (AI) health technologies, there is a risk of perpetuating existing health inequalities at scale. One major source of bias is the data that underpins such technologies. The STANDING Together recommendations aim to encourage transparency regarding limitations of health datasets and proactive evaluation of their effect across population groups. Draft recommendation items were informed by a systematic review and stakeholder survey. The recommendations were developed using a Delphi approach, supplemented by a public consultation and international interview study. Overall, more than 350 representatives from 58 countries provided input into this initiative. 194 Delphi participants from 25 countries voted and provided comments on 32 candidate items across three electronic survey rounds and one in-person consensus meeting. The 29 STANDING Together consensus recommendations are presented here in two parts. Recommendations for Documentation of Health Datasets provide guidance for dataset curators to enable transparency around data composition and limitations. Recommendations for Use of Health Datasets aim to enable identification and mitigation of algorithmic biases that might exacerbate health inequalities. These recommendations are intended to prompt proactive inquiry rather than acting as a checklist. We hope to raise awareness that no dataset is free of limitations, so transparent communication of data limitations should be perceived as valuable, and absence of this information as a limitation. We hope that adoption of the STANDING Together recommendations by stakeholders across the AI health technology lifecycle will enable everyone in society to benefit from technologies which are safe and effective.

BACKGROUND: The number of women surviving cancer who live with symptoms of bowel toxicity affecting their quality of life continues to rise. In this retrospective study, we sought to describe and analyse the presenting clinical features in our cohort, and evaluate possible predictors of severity and chronicity in women with radiation-induced bowel injury after treatment for cervical and endometrial cancers. METHODS: Review of records of 541 women treated within the North London Gynaecological Cancer Network between 2003 and 2010 with radiotherapy with or without chemotherapy for cervical and endometrial cancer identified 152 women who reported significant new bowel symptoms after pelvic radiation. RESULTS: Factor analysis showed that the 14 most common and important presenting symptoms could be 'clustered' into 3 groups with predictive significance for chronicity and severity of disease. Median follow-up for all patients was 60 months. Univariate analysis showed increasing age, smoking, extended field radiation, cervical cancer treatment and the need for surgical intervention to be significant predictors for severity of ongoing disease at last follow-up. On multivariate analysis, only age, cancer type (cervix) and symptom combinations/'cluster' of (bloating, flatulence, urgency, rectal bleeding and per-rectal mucus) were found to be significant predictors of disease severity. Fifteen (19%) women in the cervical cancer group had radiation-induced bowel injury requiring surgical intervention compared with five (6.7%) in the endometrial cancer group. CONCLUSION: Women with cervical cancer are younger and appear to suffer more severe symptoms of late bowel toxicity, whereas women treated for endometrial cancer suffer milder more chronic disease. The impact of radiation-induced bowel injury and the effect on cancer survivorship warrants further research into investigation of predictors of severe late toxicity. There is a need for prospective trials to aid early diagnosis, while identifying the underlying patho-physiological process of the bowel injury.