Documenting the de-identification process of clinical and imaging data for AI for health imaging projects.

Artificial intelligence (AI) is revolutionizing the field of medical imaging, holding the potential to shift medicine from a reactive "sick-care" approach to a proactive focus on healthcare and prevention. The successful development of AI in this domain relies on access to large, comprehensive, and standardized real-world datasets that accurately represent diverse populations and diseases. However, images and data are sensitive, and as such, before using them in any way the data needs to be modified to protect the privacy of the patients. This paper explores the approaches in the domain of five EU projects working on the creation of ethically compliant and GDPR-regulated European medical imaging platforms, focused on cancer-related data. It presents the individual approaches to the de-identification of imaging data, and describes the problems and the solutions adopted in each case. Further, lessons learned are provided, enabling future projects to optimally handle the problem of data de-identification. CRITICAL RELEVANCE STATEMENT: This paper presents key approaches from five flagship EU projects for the de-identification of imaging and clinical data offering valuable insights and guidelines in the domain. KEY POINTS: ΑΙ models for health imaging require access to large amounts of data. Access to large imaging datasets requires an appropriate de-identification process. This paper provides de-identification guidelines from the AI for health imaging (AI4HI) projects.

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

Artificial intelligence (AI) is transforming the field of medical imaging and has the potential to bring medicine from the era of 'sick-care' to the era of healthcare and prevention. The development of AI requires access to large, complete, and harmonized real-world datasets, representative of the population, and disease diversity. However, to date, efforts are fragmented, based on single-institution, size-limited, and annotation-limited datasets. Available public datasets (e.g., The Cancer Imaging Archive, TCIA, USA) are limited in scope, making model generalizability really difficult. In this direction, five European Union projects are currently working on the development of big data infrastructures that will enable European, ethically and General Data Protection Regulation-compliant, quality-controlled, cancer-related, medical imaging platforms, in which both large-scale data and AI algorithms will coexist. The vision is to create sustainable AI cloud-based platforms for the development, implementation, verification, and validation of trustable, usable, and reliable AI models for addressing specific unmet needs regarding cancer care provision. In this paper, we present an overview of the development efforts highlighting challenges and approaches selected providing valuable feedback to future attempts in the area.Key points• Artificial intelligence models for health imaging require access to large amounts of harmonized imaging data and metadata.• Main infrastructures adopted either collect centrally anonymized data or enable access to pseudonymized distributed data.• Developing a common data model for storing all relevant information is a challenge.• Trust of data providers in data sharing initiatives is essential.• An online European Union meta-tool-repository is a necessity minimizing effort duplication for the various projects in the area.

Electrical bioimpedance in patients after ischemic stroke, a civilization disease.

INTRODUCTION: Ischemic stroke is caused by artery blockage, resulting in damage to brain tissue. A significant factor in the further treatment of a patient is not only the time to reach a specialist centre, but also the state of hydration of the organism. Clinical situations involving the excess or deficiency of water can have extremely serious consequences for the functioning of the body and subsequent stroke-related disorders. One of the increasingly common methods of evaluating the composition of the human body is by electrical bioimpedance. OBJECTIVE: The aim of the study was to assess the state of human body hydration measured by bioimpedance in patients with an early stage of ischemic stroke. MATERIAL AND METHODS: The examination involved 81 patients with ischemic stroke in the Neurology Department, Subdivision of Stroke Treatment at the Province Specialist Hospital in Lublin, Poland, in 2015. Measurement of the composition and outer and intracellular space of the human body by the Whole Body Bioimpedance (WBIA) method was performed using the Body Composition Monitor (BCM) (Fresenius Medical Care GmbH, Bad Homburg, Germany). RESULTS: A group of patients were been examined with the use of the BIA apparatus three times: on the first, seventh, and tenth day of hospital stay, to determine the level of body hydration. Comparative analysis of data showed that on the first day of hospitalization all the measurements of electrical bioimpedance parameters in the patients were significantly different from those of the control group. In the case of TBW, ECW, ICW, the patients' scores were significantly higher than those of the control group. Only with respect to the over-hydration index, the patients achieved a significantly lower score than the control group. CONCLUSIONS: Assessment of hydration status in patients with a diagnosed stroke indicates a slight dehydration in relation to the control group, but falling within the scope of normovolaemia, according to bioimpedance measurement standards.

Comprehensive outpatient rehabilitation increases the ability of people over 60 to live independently.

INTRODUCTION: The answer to current social and health needs of people aged over 60 are the multidirectional and carefully planned, comprehensive activation and rehabilitation activities carried out as part of Daycare Centres (DCC). The aim of creating and the functioning of DCCs deployed all over Poland is to improve the health and psychophysical fitness of this group of people. Health factors and psychophysical fitness determine the ability to live independently, both today, and later in life. OBJECTIVE: The objective of the study was to assess the impact of comprehensive ambulatory rehabilitation, including tailored endurance training preceded by an ergospirometry test, on indicators demonstrating the ability to live independently and the risk ratio of future health problems in the elderly. MATERIAL AND METHODS: 60 people participating in a rehabilitation cycle implemented as part of the services provided to patients aged over 60 in the DCC of the Witold Chodzko Institute of Rural Medicine (IMW) in Lublin comprised the sample. The tests were carried out in the test-retest model on the first and last day of the kinesiotherapy cycle. Patients were tested using standardized Barthel, I-ADL and VES-13 questionnaires. The rehabilitation programme applied included systemic kinesiotherapy (endurance training) with a load determined according to individual exercise capacity, determined on the basis of a ergospirometry test, and varied rehabilitation activities resulting from the condition of the locomotor system, as provided for under the project. RESULTS: After completing the rehabilitation cycle, patients obtained higher results in comparison to the tests carried out before the beginning of the cycle in the Barthel index used to measure functional efficiency (Z = 5.41; p = 0.001), as well as lower in the I-ADL scale used to test the degree of dependence on the help of others when performing complex activities of everyday life (Z = 2.63; p = 0.009) and in VES-13 scale used to assess the risk of geriatric health problems (Z = 5.47; p = 0.001). CONCLUSIONS: As the result of the use of comprehensive rehabilitation, including obligatory endurance training, desired changes were achieved in terms of fitness and independence in performing advanced daily activities and reducing the risk of geriatric health problems.

Differences in the quality of life dependent on family status of the elderly living in rural areas - a cross-sectional survey.

INTRODUCTION: A factor that conditions the perception of the quality of life (QoL) is having a social network and relationships within it. The quality of life of seniors is assumed to be at a higher level if they are surrounded by those close to them in comparison to those living alone. The aim of the study was to assess differences in the quality of life of elderly rural residents depending on their family status. MATERIAL AND METHODS: Due to the random and mixed selection of respondents, the study comprised a group of 588 representatives living in rural areas of Eastern Poland. The differentiated criterion of the groups of senior respondents was their family situation: living with a family or living alone. Assessment of the quality of life was conducted by means of the WHOQoL-bref questionnaire. The Mann-Whitney tests and Kruskal-Wallis tests were used to carry out statistical analysis of the data. RESULTS: The respondents who lived with their families differed statistically to a significant extent (p<0.005) from those who lived alone. The former gave a better assessment of the majority of the QoL domains: physical, psychological and social. Obtaining higher mean values for the environmental domain among the respondents living alone (M=14.31) seemed to be an atypical and interesting phenomenon because seniors living with their relatives usually assessed that dimension better than those living alone. CONCLUSIONS: The family situation of seniors affected the level of quality of life. Living with their relatives may be expected to be favourable for seniors because it translates into better performance in physical, psychological and social domains. Loneliness, which frequently accompanies old age, leads to the deterioration of the quality of life.