National College of Ireland

Bethlehem R.A., Seidlitz J., White S.R., Vogel J.W., Anderson K.M., Adamson C., Adler S., Alexopoulos G.S., Anagnostou E., Areces-Gonzalez A., Astle D.E., Auyeung B., Ayub M., Bae J., Ball G., et. al.

Over the past few decades, neuroimaging has become a ubiquitous tool in basic research and clinical studies of the human brain. However, no reference standards currently exist to quantify individual differences in neuroimaging metrics over time, in contrast to growth charts for anthropometric traits such as height and weight1. Here we assemble an interactive open resource to benchmark brain morphology derived from any current or future sample of MRI data ( http://www.brainchart.io/ ). With the goal of basing these reference charts on the largest and most inclusive dataset available, acknowledging limitations due to known biases of MRI studies relative to the diversity of the global population, we aggregated 123,984 MRI scans, across more than 100 primary studies, from 101,457 human participants between 115 days post-conception to 100 years of age. MRI metrics were quantified by centile scores, relative to non-linear trajectories2 of brain structural changes, and rates of change, over the lifespan. Brain charts identified previously unreported neurodevelopmental milestones3, showed high stability of individuals across longitudinal assessments, and demonstrated robustness to technical and methodological differences between primary studies. Centile scores showed increased heritability compared with non-centiled MRI phenotypes, and provided a standardized measure of atypical brain structure that revealed patterns of neuroanatomical variation across neurological and psychiatric disorders. In summary, brain charts are an essential step towards robust quantification of individual variation benchmarked to normative trajectories in multiple, commonly used neuroimaging phenotypes. MRI data from more than 100 studies have been aggregated to yield new insights about brain development and ageing, and create an interactive open resource for comparison of brain structures throughout the human lifespan, including those associated with neurological and psychiatric disorders.

Razdan S., Sharma S.

In the Internet of Medical Things (IoMT), the Internet of Things (IoT) is integrated with medical devices, enabling improved patient comfort, cost-effective medical solutions, quick hospital treatm...

Dev S., Wang H., Nwosu C.S., Jain N., Veeravalli B., John D.

The negative impact of stroke in society has led to concerted efforts to improve the management and diagnosis of stroke. With an increased synergy between technology and medical diagnosis, caregivers create opportunities for better patient management by systematically mining and archiving the patients’ medical records. Therefore, it is vital to study the interdependency of these risk factors in patients’ health records and understand their relative contribution to stroke prediction. This paper systematically analyzes the various factors in electronic health records for effective stroke prediction. Using various statistical techniques and principal component analysis, we identify the most important factors for stroke prediction. We conclude that age, heart disease, average glucose level, and hypertension are the most important factors for detecting stroke in patients. Furthermore, a perceptron neural network using these four attributes provides the highest accuracy rate and lowest miss rate compared to using all available input features and other benchmarking algorithms. As the dataset is highly imbalanced concerning the occurrence of stroke, we report our results on a balanced dataset created via sub-sampling techniques. • We propose a predictive analytics approach for stroke prediction. • We use machine learning and neural networks in the proposed approach. • We identify the most important factors for stroke prediction. • Age, heart disease, average glucose level are important factors for predicting stroke. • We report our results on a balanced dataset created via sub-sampling techniques.

Longo C.J., Fitch M.I., Banfield L., Hanly P., Yabroff K.R., Sharp L.

Financial toxicity related to cancer diagnosis and treatment is a common issue in developed countries. We seek to systematically summarize the extent of the issue in very high development index countries with publicly funded healthcare. We identified articles published Jan 1, 2005, to March 7, 2019, describing financial burden/toxicity experienced by cancer patients and/or informal caregivers using OVID Medline Embase and PsychInfo, CINAHL, Business Source Complete, and EconLit databases. Only English language peer-reviewed full papers describing studies conducted in very high development index countries with predominantly publicly funded healthcare were eligible (excluded the USA). All stages of the review were evaluated in teams of two researchers excepting the final data extraction (CJL only). The searches identified 7117 unique articles, 32 of which were eligible. Studies were undertaken in Canada, Australia, Ireland, UK, Germany, Denmark, Malaysia, Finland, France, South Korea, and the Netherlands. Eighteen studies reported patient/caregiver out-of-pocket costs (range US$17–US$506/month), 18 studies reported patient/caregiver lost income (range 17.6–67.3%), 14 studies reported patient/caregiver travel and accommodation costs (range US$8–US$393/month), and 6 studies reported financial stress (range 41–48%), strain (range 7–39%), or financial burden/distress/toxicity among patients/caregivers (range 22–27%). The majority of studies focused on patients, with some including caregivers. Financial toxicity was greater in those with early disease and/or more severe cancers. Despite government-funded universal public healthcare, financial toxicity is an issue for cancer patients and their families. Although levels of toxicity vary between countries, the findings suggest financial protection appears to be inadequate in many countries.

Li P., Han L., Tao X., Zhang X., Grecos C., Plaza A., Ren P.

Fast and accurate remote sensing image retrieval from large data archives has been an important research topic in the remote sensing research literature. Recently, hashing-based remote sensing image retrieval has attracted extreme attention because of its efficient search capabilities. Especially, deep remote sensing image hashing algorithms have been developed based on convolutional neural networks (CNNs) and have shown effective retrieval performance. However, implementing a deep hashing network tends to be highly expensive in terms of storage space and computing resources to be suitable for on-orbit remote sensing image retrieval, which usually operates on resource-limited devices such as satellites and unmanned aerial vehicles (UAVs). To address this limitation, we propose to hash a deep network that in turn hashes remote sensing images. Specifically, we develop a quantized deep learning to hash (QDLH) framework for large-scale remote sensing image retrieval. The weights and activation functions in the QDLH framework are binarized to low-bit representations, which require comparatively much less storage space and computing resources. The QDLH results in a lightweight deep neural network for effective remote sensing image hashing. We conduct extensive experiments on two public remote sensing image data sets by incorporating several state-of-the-art network architectures into our QDLH methodology for remote sensing image hashing. The experimental results demonstrate that the proposed QDLH is effective in saving hardware resources in terms of both storage and computation. Moreover, superior remote sensing image retrieval performance is also achieved by our QDLH, compared with state-of-the-art deep remote sensing image hashing methods.

Constantinides C., Han L.K., Alloza C., Antonucci L.A., Arango C., Ayesa-Arriola R., Banaj N., Bertolino A., Borgwardt S., Bruggemann J., Bustillo J., Bykhovski O., Calhoun V., Carr V., Catts S., et. al.

AbstractSchizophrenia (SZ) is associated with an increased risk of life-long cognitive impairments, age-related chronic disease, and premature mortality. We investigated evidence for advanced brain ageing in adult SZ patients, and whether this was associated with clinical characteristics in a prospective meta-analytic study conducted by the ENIGMA Schizophrenia Working Group. The study included data from 26 cohorts worldwide, with a total of 2803 SZ patients (mean age 34.2 years; range 18–72 years; 67% male) and 2598 healthy controls (mean age 33.8 years, range 18–73 years, 55% male). Brain-predicted age was individually estimated using a model trained on independent data based on 68 measures of cortical thickness and surface area, 7 subcortical volumes, lateral ventricular volumes and total intracranial volume, all derived from T1-weighted brain magnetic resonance imaging (MRI) scans. Deviations from a healthy brain ageing trajectory were assessed by the difference between brain-predicted age and chronological age (brain-predicted age difference [brain-PAD]). On average, SZ patients showed a higher brain-PAD of +3.55 years (95% CI: 2.91, 4.19; I2 = 57.53%) compared to controls, after adjusting for age, sex and site (Cohen’s d = 0.48). Among SZ patients, brain-PAD was not associated with specific clinical characteristics (age of onset, duration of illness, symptom severity, or antipsychotic use and dose). This large-scale collaborative study suggests advanced structural brain ageing in SZ. Longitudinal studies of SZ and a range of mental and somatic health outcomes will help to further evaluate the clinical implications of increased brain-PAD and its ability to be influenced by interventions.

Gross N.

Large language models and generative AI, such as ChatGPT, have gained influence over people’s personal lives and work since their launch, and are expected to scale even further. While the promises of generative artificial intelligence are compelling, this technology harbors significant biases, including those related to gender. Gender biases create patterns of behavior and stereotypes that put women, men and gender-diverse people at a disadvantage. Gender inequalities and injustices affect society as a whole. As a social practice, gendering is achieved through the repeated citation of rituals, expectations and norms. Shared understandings are often captured in scripts, including those emerging in and from generative AI, which means that gendered views and gender biases get grafted back into social, political and economic life. This paper’s central argument is that large language models work performatively, which means that they perpetuate and perhaps even amplify old and non-inclusive understandings of gender. Examples from ChatGPT are used here to illustrate some gender biases in AI. However, this paper also puts forward that AI can work to mitigate biases and act to ‘undo gender’.

Fitch M.I., Sharp L., Hanly P., Longo C.J.

Understanding how patients and families experience, respond to, and cope with the financial burden associated with cancer could assist in identifying future research priorities and developing relevant interventions to assist patients and families facing financial hardship. This systematic review offers a synthesis of the qualitative evidence on cancer-related financial toxicity from the perspective of patients and/or informal caregivers in publicly funded healthcare systems where it might be expected that financial protection would be strongest. Articles published between January 1, 2005, and March 7, 2019, describing financial burden experienced by cancer patients and/or informal caregivers were identified using OVID MEDLINE Embase and PsychInfo, CINAHL, Business Source Complete, and EconLit databases. English language, peer-reviewed qualitative papers describing studies conducted in countries with predominantly publicly funded healthcare systems were eligible. Quality appraisal was conducted using CASP Quality Appraisal Checklist. Narrative synthesis was completed with extracted data and themes identified inductively by all team members. Twelve articles were identified as eligible. Articles reported on 10 studies conducted in Australia (n = 2), Canada (n = 2), England (n = 3), and Ireland (n = 3). The papers illustrate the complexity and multifaceted nature of experiencing financial hardship following a cancer diagnosis. Each contributes to the whole picture, providing different viewpoints regarding various and diverse forms of financial hardship, the process of confronting financial challenges, working to overcome difficulties, and coping with the resulting impacts. Synthesis of the studies suggested five themes: household and medical costs are increased, financial resources are reduced, financial change and financial hardship vary, financial hardship has many consequences, various mitigation strategies are used. Cancer patients and their families can experience a broad range of impacts when they are facing and coping with financial toxicity. Consistent gaps in support highlight that strategies to mitigate financial effects related to travel, accommodation, medications, family support, and income replacement are needed for many patients and families even in the context of publicly funded healthcare systems. Survivors need to be informed early in their cancer experience about the potential financial burden associated with cancer treatment and its impact on survivors and their family members.

Putkinen V., Nazari-Farsani S., Seppälä K., Karjalainen T., Sun L., Karlsson H.K., Hudson M., Heikkilä T.T., Hirvonen J., Nummenmaa L.

Abstract Music can induce strong subjective experience of emotions, but it is debated whether these responses engage the same neural circuits as emotions elicited by biologically significant events. We examined the functional neural basis of music-induced emotions in a large sample (n = 102) of subjects who listened to emotionally engaging (happy, sad, fearful, and tender) pieces of instrumental music while their hemodynamic brain activity was measured with functional magnetic resonance imaging (fMRI). Ratings of the four categorical emotions and liking were used to predict hemodynamic responses in general linear model (GLM) analysis of the fMRI data. Multivariate pattern analysis (MVPA) was used to reveal discrete neural signatures of the four categories of music-induced emotions. To map neural circuits governing non-musical emotions, the subjects were scanned while viewing short emotionally evocative film clips. The GLM revealed that most emotions were associated with activity in the auditory, somatosensory, and motor cortices, cingulate gyrus, insula, and precuneus. Fear and liking also engaged the amygdala. In contrast, the film clips strongly activated limbic and cortical regions implicated in emotional processing. MVPA revealed that activity in the auditory cortex and primary motor cortices reliably discriminated the emotion categories. Our results indicate that different music-induced basic emotions have distinct representations in regions supporting auditory processing, motor control, and interoception but do not strongly rely on limbic and medial prefrontal regions critical for emotions with survival value.

Fatokun T., Nag A., Sharma S.

Security and privacy of patients’ data is a major concern in the healthcare industry. In this paper, we propose a system that activates robust security and privacy of patients’ medical records as well as enables interoperability and data exchange between the different healthcare providers. The work proposes the shift from patient’s electronic health records being managed and controlled by the healthcare industry to a patient-centric application where patients are in control of their data. The aim of this research is to build an Electronic Healthcare Record (EHR) system that is layered on the Ethereum blockchain platform and smart contract in order to eliminate the need for third-party systems. With this system, the healthcare provider can search for patient’s data and request the patients’ consent to access it. Patients manage their data which enables an expedited data exchange across EHR systems. Each patient’s data are stored on the peer-to-peer node ledger. The proposed patient-centric EHR platform is cross-platform compliant, as it can be accessed via personal computers and mobile devices and facilitates interoperability across healthcare providers as patients’ medical records are gathered from different healthcare providers and stored in a unified format. The proposed framework is tested on a private Ethereum network using Ganache. The results show the effectiveness of the system with respect to security, privacy, performance and interoperability.