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.

Future of biomarker evaluation in the realm of artificial intelligence algorithms: application in improved therapeutic stratification of patients with breast and prostate cancer.

Clinical workflows in oncology depend on predictive and prognostic biomarkers. However, the growing number of complex biomarkers contributes to costly and delayed decision-making in routine oncology care and treatment. As cancer is expected to rank as the leading cause of death and the single most important barrier to increasing life expectancy in the 21st century, there is a major emphasis on precision medicine, particularly individualisation of treatment through better prediction of patient outcome. Over the past few years, both surgical and pathology specialties have suffered cutbacks and a low uptake of pathology specialists means a solution is required to enable high-throughput screening and personalised treatment in this area to alleviate bottlenecks. Digital imaging in pathology has undergone an exponential period of growth. Deep-learning (DL) platforms for hematoxylin and eosin (H&E) image analysis, with preliminary artificial intelligence (AI)-based grading capabilities of specimens, can evaluate image characteristics which may not be visually apparent to a pathologist and offer new possibilities for better modelling of disease appearance and possibly improve the prediction of disease stage and patient outcome. Although digital pathology and AI are still emerging areas, they are the critical components for advancing personalised medicine. Integration of transcriptomic analysis, clinical information and AI-based image analysis is yet an uncultivated field by which healthcare professionals can make improved treatment decisions in cancer. This short review describes the potential application of integrative AI in offering better detection, quantification, classification, prognosis and prediction of breast and prostate cancer and also highlights the utilisation of machine learning systems in biomarker evaluation.

Vitamin D Deficiency Is Associated With Impaired Muscle Strength And Physical Performance In Community-Dwelling Older Adults: Findings From The English Longitudinal Study Of Ageing.

PURPOSE: Maintaining skeletal muscle function throughout life is a crucial component of successful ageing. Adequate vitamin D status may be important in preserving muscle function. We aimed to determine the association between impaired muscle function and serum vitamin D status in community-dwelling older adults. Falls were explored as a secondary aim. METHODS: Data were analyzed from adults aged ≥60 years, from Wave 6 of the English Longitudinal Study of Aging (ELSA). Handgrip strength (HGS) and the short physical performance battery (SPPB) were employed as measures of muscle strength and physical function, respectively. Serum 25-hydroxyvitamin D [25(OH)D] was assessed with concentration <30 nmol/L classed as vitamin D deficient. RESULTS: The study comprised 4157 community-dwelling adults with a mean age of 69.8 (SD 6.9). Overall, 30.6% had low HGS and 12.7% had low SPPB (≤6). Participants with the lowest serum 25(OH)D (<30 nmol/L) had the highest prevalence of impaired muscle strength and performance (40.4% and 25.2%) compared with participants with levels ≥50 nmol/L (21.6% and 7.9%). Consistent with this, vitamin D deficiency (<30 nmol/L) was a significant determinant of low HGS (OR 1.44 [1.22, 1.71], p<0.001) and poor physical performance (OR 1.65 [1.31, 2.09], p<0.001) in the logistic regression models. Older adults partaking in regular moderate physical activity had significantly lower odds of impaired muscle strength (OR 0.65 [0.58, 0.79]) and physical function (OR 0.30 [0.24, 0.38]), p <0.001, respectively. Single or multiple falls (15.8% and 10.5% in past year) were not associated with vitamin D status. CONCLUSION: Vitamin D deficiency was associated with impaired muscle strength and performance in a large study of community-dwelling older people. It is generally accepted that vitamin D deficiency at the <30 nmol/L cut-off should be reversed to prevent bone disease, a strategy that may also protect skeletal muscle function in ageing.

The Prevalence and Determinants of Vitamin D Status in Community-Dwelling Older Adults: Results from the English Longitudinal Study of Ageing (ELSA).

Vitamin D deficiency is often associated with adverse health outcomes in older adults. The circulating 25-hydroxyvitamin D (25(OH)D) status predominately relies on UV exposure. However, the extent of which northerly latitude exasperates deficiency is less explored in ageing. We aimed to investigate vitamin D deficiency in community-dwelling, older adults, residing at latitudes 50-55° north. This study was comprised of 6004 adults, aged >50 years from wave 6 (2012-2013) of the English Longitudinal Study of Ageing (ELSA). Deficiency was categorised by two criteria: Institute of Medicine (IOM) (<30 nmol/L) and Endocrine Society (ES) (<50 nmol/L). The overall prevalence of Institute of Medicine (IOM) and Endocrine Society (ES) definitions of deficiency were 26.4% and 58.7%, respectively. Females (odds ratio (OR) 1.23; CI: 1.04-1.44), those aged 80+ (OR: 1.42; CI: 1.01-1.93), smoking (OR: 1.88; CI: 1.51-2.34); of non-white ethnicity (OR: 3.8; CI:2.39-6.05); being obese (OR: 1.32; CI:1.09-1.58), and of poor self-reported health (OR:1.99; CI:1.33, 2.96), were more likely to be vitamin D deficient (by IOM). Residents in the south of England had a reduced risk of deficiency (OR: 0.78; CI:0.64-0.95), even after adjustment for socioeconomic and traditional predictors (obesity, age, lifestyle, etc.) of vitamin D status. Other factors, such as being retired, having a normal BMI, engaging in regular vigorous physical activity, vitamin D supplement use, sun travel, and summer season were also significantly positive correlates of deficiency. Similar results were observed for the ES cut-off definition. Importantly, more than half of adults aged >50 years had 25(OH)D concentrations <50 nmol/L. These findings demonstrate that low vitamin D status is highly prevalent in older English adults and the crucial importance of public health strategies throughout midlife and older age to achieve optimal vitamin D status.

Predicting admission to long-term care and mortality among community-based, dependent older people in Ireland.

OBJECTIVE: To identify factors that predict admission to long-term care (LTC) and mortality among community-based, dependent older people in Ireland, who were in receipt of formal home support. METHODS: An audit was conducted of all community-dwelling older adults receiving government funded home support during 2017 in the Dublin North Central, Health Service Executive administrative area. Data were extracted from the Common Summary Assessment Report (CSAR), a mandatory form used in the provision of home support. Multiple logistic regression analysis was used to examine the factors associated with admission to LTC and mortality, with the results presented as odds ratios (OR) and 95% confidence intervals. RESULTS: The audit comprised 1597 community-dwelling older adults with a mean age of 83.3 (SD: 7.2) years. The prevalence of transition to LTC and mortality was 8% and 9%, respectively, during the 12-month period. Factors significantly associated with admission to LTC were "cognitive dysfunction" [OR 2.10 (1.41-3.14), P < .001] and the intensity of home support [OR 1.05 (1.01-1.06), P < .003], as measured by weekly formal care hours. Physical dependency and advanced age (aged 95 years +) were significantly associated with mortality in this population (P < .001). CONCLUSION: "Cognitive dysfunction" and intensity of formal home support were associated with transition to LTC, while physical dependency and advanced age were associated with mortality. Investment in personalised, cognitive-specific, services and supports are necessary to keep people with dementia and related cognitive impairments living at home for longer.

Is there a role for vitamin D in supporting cognitive function as we age?

Globally, an estimated 46 million people are currently living with dementia and this figure is projected to increase 3-fold by 2050, highlighting this major public health concern and its substantial associated healthcare costs. With pharmacological treatment yet to reach fruition, the emphasis on evidence-based preventative lifestyle strategies is becoming increasingly important and several modifiable lifestyle factors have been identified that may preserve cognitive health. These include good cardiovascular health, physical activity, low alcohol intake, smoking and a healthy diet, with growing interest in vitamin D. The aim of the present paper is to review the evidence supporting the potential roles of vitamin D in ageing and cognitive health in community-dwelling older adults. Furthermore, to describe the utility and challenges of cognitive assessments and outcomes when investigating vitamin D in this context. Evidence indicates that serum 25-hydroxyvitamin D (25(OH)D) may impact brain health. There is a biological plausibility from animal models that vitamin D may influence neurodegenerative disorders, through several mechanisms. Epidemiological evidence supports associations between low serum 25(OH)D concentrations and poorer cognitive performance in community-dwelling older populations, although an optimal 25(OH)D level for cognitive health could not be determined. The effect of raising 25(OH)D concentrations on cognitive function remains unclear, as there is a paucity of interventional evidence. At a minimum, it seems prudent to aim to prevent vitamin D deficiency in older adults, with other known common protective lifestyle factors, as a viable component of brain health strategies.

RelAte: pilot study of the effects of a mealtime intervention on social cognitive factors and energy intake among older adults living alone.

Mealtime interventions typically focus on institutionalised older adults, but we wanted to investigate whether they may also be effective among those living independently. Using a randomised controlled trial design, we assessed the effects of a novel mealtime intervention on self-efficacy, food enjoyment and energy intake. A total of 100 adults living alone aged over 60 years were randomised to the treatment or control conditions: all received a guidebook on nutrition and culinary skills. Treatment group participants received a weekly visit from a trained volunteer who prepared and shared a meal with them. Participants in the treatment group showed improvements relative to those in the control group at borderline significance (P=0·054) for self-efficacy and at significance for food enjoyment. Significant improvements were observed in female participants in the treatment but not in the control group in energy intake (although following corrections for multiple comparisons, only the effect on food enjoyment remained significant). These findings will inform the design of future complex interventions. For this type of intervention to be successful, more focus has to be placed on making interventions more personalised, potentially according to sex. Findings are important for nutritional sciences as they indicate that, in order to improve energy intake and food enjoyment among older adults, multimodal nutritional interventions including social components may be successful.

A shared mealtime approach to improving social and nutritional functioning among older adults living alone: study protocol for a randomized controlled trial.

BACKGROUND: Older adults living alone are at increased risk of malnutrition as well as social isolation. Previous research has evaluated psychosocial interventions aimed at improving social support for older adults living alone. One meta-analysis in particular has suggested that multimodal psychosocial interventions are more effective than unimodal interventions. As such, it may be more effective to deliver an intervention which combines nutritional and social support together. Consequently, we designed the RelAte intervention, which focuses on shared mealtimes as a source of combined social and nutritional support for older adults living alone who are at risk of social isolation. OBJECTIVE: The objective of the RelAte trial was to evaluate the impact of such an intervention on energy intake, anthropometric measurements, and nutritional social cognitive variables among older adults living alone in the community. METHODS: There are 100 participants that will be recruited and randomized to either the treatment (n=50) or the control group. The treatment group will receive a visit from a trained peer volunteer once weekly for a period of 8 weeks. Outcomes of interest include: energy intake, social cognitive factors related to diet, abdominal circumference, body mass index, psychosocial well-being, frailty, nutritional status, and health utilities. Outcomes will be obtained at baseline, immediately postintervention (8 weeks after baseline), 12-week follow-up, and 26-week follow-up by assessors blinded to participants' randomized assignment. RESULTS: The Relate trial is currently active. We are currently at data analysis stage. The study started in June 2013 and will run until June 2015. CONCLUSIONS: Results from this study will primarily describe the effectiveness of a shared mealtime intervention for older adults living alone in terms of their dietary well-being, physical health, and psychosocial well-being. TRIAL REGISTRATION: Clinicaltrials.gov NCT02007551; http://clinicaltrials.gov/ct2/show/NCT00102401 (Archived by WebCite at http://www.webcitation/6WptuVTtz).