Difficulty retrieving information (e.g., words) from memory is prevalent in neurogenic communication disorders (e.g., aphasia and dementia). Theoretical modeling of retrieval failures often relies on clinical data, despite methodological limitations (e.g., locus of retrieval failure, heterogeneity of individuals, and progression of disorder/disease). Techniques from network science are naturally capable of handling these limitations. This paper reviews recent work using a multiplex lexical network to account for word retrieval failures and highlights how network science can address the limitations of (...) clinical data. Critically, any model we employ could impact clinical practice and patient lives, harkening the need for theoretically well-informed network models. (shrink)

Ontological realism aims at the development of high quality ontologies that faithfully represent what is general in reality and to use these ontologies to render heterogeneous data collections comparable. To achieve this second goal for clinical research datasets presupposes not merely (1) that the requisite ontologies already exist, but also (2) that the datasets in question are faithful to reality in the dual sense that (a) they denote only particulars and relationships between particulars that do in fact exist (...) and (b) they do this in terms of the types and type-level relationships described in these ontologies. While much attention has been devoted to (1), work on (2), which is the topic of this paper, is comparatively rare. Using Referent Tracking as basis, we describe a technical data wrangling strategy which consists in creating for each dataset a template that, when applied to each particular record in the dataset, leads to the generation of a collection of Referent Tracking Tuples (RTT) built out of unique identifiers for the entities described by means of the data items in the record. The proposed strategy is based on (i) the distinction between data and what data are about, and (ii) the explicit descriptions of portions of reality which RTTs provide and which range not only over the particulars described by data items in a dataset, but also over these data items themselves. This last feature allows us to describe particulars that are only implicitly referred to by the dataset; to provide information about correspondences between data items in a dataset; and to assert which data items are unjustifiably or redundantly present in or absent from the dataset. The approach has been tested on a dataset collected from patients seeking treatment for orofacial pain at two German universities and made available for the NIDCR-funded OPMQoL project. (shrink)

Volume 25, Issue 2, February 2025, Page 87-90.

Evidence, as viewed through the lens of statistical significance, is not always as it appears! In the investigation of clinical research findings arising from statistical analyses, a fundamental initial step for the emerging fraud detective is to retrieve the source data for cross-examination with the study data. Recognizing that source data are not always forthcoming and that, realistically speaking, the investigator may be uninitiated in fraud detection and investigation, this paper will highlight some key methodological procedures (...) for providing a sounder evidence base for withdrawing from a study on grounds of integrity. The promotion of patient safety is paramount. However, there is a broader rationale for disseminating these ideas. This includes empowering researchers to optimize their personal integrity, make informed choices regarding membership of future research collaborations and successfully voice their concerns to journal editors, particularly where a conflict of interests can render such dialogues particularly difficult. Recommendations will be supported by topical case studies and practical steps involving data exploration, testing of baseline data and application of Benford’s Law. While this paper has a clinical focus, the advice provided is transferrable to a wide range of multidisciplinary research settings outside of Medicine. (shrink)

BackgroundThe aim of the present survey was to investigate newly discharged hospital patients’ opinions on secondary use of their hospital data and biospecimens within the context of health research in general and, more specifically, on genetic research, data sharing across borders and cooperation with the health industry.MethodsA paper questionnaire was sent to 1049 consecutive newly discharged hospital patients.ResultsThe vast majority of the respondents preferred to be informed or to receive no notification at all for secondary research on their (...) health data and biospecimens. The rest wanted to be asked for active consent. The same trend applied for the other aspects also. 81% of respondents were positive towards genetic research without active consent. 95% were positive towards cooperating with the health industry, and 90% were positive towards data sharing.ConclusionsThese results suggest that hospital patients generally are very positive to secondary research and support the concept of opting out rather than opting in. (shrink)

Volume 24, Issue 10, October 2024, Page 103-106.

The concept of ‘ownership’ is increasingly central to debates, in the media, health policy and bioethics, about the appropriate management of clinical data. I argue that the language of ownership acts as a metaphor and reflects multiple concerns about current data use and the disenfranchisement of citizens and collectives in the existing data ecosystem. But exactly which core interests and concerns ownership claims allude to remains opaque. Too often, we jump straight from ‘ownership’ to ‘private property’ (...) and conclude ‘the data belongs to the patient’. I will argue here that private property is only one type of relevant relationship between people, communities and data. There are several reasons to doubt that conceptualising data as private property presents a compelling response to concerns about clinical data ownership. In particular I argue that clinical data are co-constructed, so a property account would fail to confer exclusive rights to the patient. A non-property account of ownership acknowledges that the data are ‘about the patient’, and therefore the patient has relevant interests, without jumping to the conclusion that the data ‘belongs to the patient’. On this broader account of ownership, the relevant harm is the severing of the connection between the patient and their data, and the solution is to re-engage and re-connect patients to the data research enterprise. (shrink)

Peer commentary on Char, Abràmoff & Feudtner (2020) target article: "Identifying Ethical Considerations for Machine Learning Healthcare Applications" .

Secondary use of clinical data in research or learning activities (SeConts) has the potential to improve patient care and biomedical knowledge. Given this potential, the ethical question arises whether physicians have a professional duty to support SeConts. To investigate this question, we analyze prominent international declarations on physicians’ professional ethics to determine whether they include duties that can be considered as good reasons for a physicians’ professional duty to support SeConts. Next, we examine these documents to identify professional (...) duties that might conflict with a potential duty of physicians to support SeConts. (shrink)

Research question and aim Clinical Ethics Committees (CECs) aim to support healthcare professionals (HPs) and healthcare organizations to deal with the ethical issues of clinical practice. In 2020, a CEC was established in an Oncology Research Hospital in the North of Italy. This paper describes the development process and the activities performed 20 months from the CEC’s implementation, to increase knowledge about CEC’s implementation strategy. Research design We collected quantitative data related to number and characteristics of CEC (...) activities carried out from October 2020 to June 2022 using the CEC internal database. Data were reported descriptively and compared with data from the literature to provide a complete overview of the CEC’s development and implementation process. Participants and research context The study has been conducted at the local health authority (LHA) of Reggio Emilia. It is a report of the activities provided by the CEC, where no HPs or patients were involved. Ethical Considerations The report is part of a larger study named EVAluating a Clinical Ethics Committee implementation process (EvaCEC), which has been approved by the Local Ethics Committee (AUSLRE Protocollo n° 2022/0026554 of 24/02/2022). EvaCEC is also the first author's PhD project. Findings In total, the CEC performed 7 ethics consultations (EC), published three policies related to particular ethical questions of clinical and organizational practice, provided one educational online course on ethics consultation targeting employed HPs, and promoted a specific dissemination process among the different departments of the LHA. According to our results, the CEC widely fulfilled the standard threefold set of clinical ethics support services tasks (namely, ethics consultation, ethics education, and policy development), but further investigations are needed to evaluate the CEC’s impact on clinical practice. Conclusion Our findings may increase knowledge regarding the composition, role, and tasks of a CEC in an Italian setting, informing future strategies and efforts to regulate these institutions officially. (shrink)

The present paper deals with the problem of evaluating empirical evidence for therapeutic decisions in medicine. The article discusses the views of Nancy Cartwright and John Worrall on the function that randomization plays in ascertaining causal relations with reference to the therapies applied. The main purpose of the paper is to present a general idea of alternative method of evaluating empirical evidence. The method builds on data analysis that makes use of rough set theory. The first attempts to apply (...) the method show that it is an interesting alternative to randomized controlled trials. (shrink)

Research question The secondary use of clinical data for research and learning activities has the potential to significantly improve medical knowledge and clinical care. To realize this potential, an ethical and legal basis for data use is needed, preferably in the form of patient consent. This raises the question: Do patients have a moral duty to provide their clinical data for research and learning activities? Methods On the basis of an ethical approach that we (...) call “caring liberalism,” we evaluate plausibility and moral weight of the following arguments in favor of a duty on patients to provide their clinical data for research and learning activities: the general duty to help; solidarity; the duty to act in the public interest; the free-rider argument; transgenerational justice; the principle of giving back; the do-not-harm principle; freedom of research and the value of science. Results The general duty to help and the duty to act in the public interest are strong reasons for a moral duty of patients to provide their clinical data for research and learning activities. Transgenerational justice and the principle of giving back are ethically weak reasons for such a duty but might be motivational factors. The other reasons are not appropriate to justify a duty. The results are relevant in several respects: for patients who are asked to consent to the secondary use of their clinical data; for the ethical discussion of the question whether and to what extent deviations from the classical specific consent are ethically justifiable under certain conditions; for the legal discussion of the conditions for a proportionate secondary use of clinical data for research and learning activities. (shrink)

BackgroundThe diagnosis and treatment of cancer are associated with psychological distress that often leads to a significant reduction in emotional and physical well-being and quality of life. Early detection of psychological distress is therefore important. This study aims to assess the psychological distress of inpatient cancer patients using routine clinical data. Furthermore, variables and problems most strongly associated with psychological distress should be identified.Materials and MethodsN = 1,869 inpatients were investigated using the National Comprehensive Cancer Network Distress Thermometer (...) and problem checklist to assess distress as well as multiple possible problem areas. Visceral oncological cancer was the most common tumor diagnosis, followed by skin cancer and urological cancer.Results65.9% of the sample experienced high levels of distress. Female sex, stage 4 of disease, and visceral and head and neck cancer emerged as risk factors for high distress. A younger age was significantly correlated with higher distress. The most frequently self-reported problems were fears, worry, and fatigue. Patients with all 3 of these problems had 24 times higher risk [odds ratio = 23.9] for high levels of distress than patients without these problems. Women reported significantly more practical, emotional, and physical problems than men. Younger and middle-aged patients reported increased levels of practical, family, and emotional problems compared with older patients.DiscussionAlmost two-thirds of the sample reported high levels of distress. The most frequently reported problem areas were emotional and physical problems. These results can help to identify patients with high risk for psychological distress and, therefore, be used to optimize psychosocial and psycho-oncological care for patients with cancer. (shrink)

Wiggins and Wilbanks (2019) raise a number of interesting concerns vis-à-vis citizen science and research. However, one area of innovation in citizen science that has seen significant advancements...

Responsibilities of the data monitoring committee and motivating illustrations -- Composition of a data monitoring committee -- Independence of the data monitoring committee : avoiding conflicts of interest -- Confidentiality issues relating to the data monitoring committee -- Data monitoring committee meetings -- Data monitoring committee interactions with other trial components or related groups -- Statistical, philosophical and ethical issues in data monitoring -- Determining when a data monitoring committee is needed -- (...) Regulatory considerations for the operation of data monitoring committees -- Legal considerations for DMCs. (shrink)

Health professionals had difficulty choosing the right time to discuss life-sustaining treatments (LSTs) since the Korean Act was passed in 2018. This study aimed to understand how patients decide to undergo LSTs in clinical practice and to compare the perceptions of these decisions among health professionals, patients, and families with suggestions to support the self-directed decisions of patients. A retrospective observational study with electronic medical records (EMRs) and a descriptive survey was used. The data obtained from the EMRs (...) included all adult patients who died in end-of-life care at a university hospital in 2021. We also conducted a survey of 214 health professionals and 100 patients and their families (CNUH IRB approval no. 2022-07-006). Based on the EMR data of 916 patients in end-of-life care, 78.4% signed do-not-attempt-resuscitation consents, 5.6% completed the documents for LSTs, and 10.2% completed both forms. LST decisions were mostly made by family members (81.5%). Most survey participants agreed that meaningless LSTs should be suspended, and the decision should be made by patients. Patients and family members (42–56%) and health professionals (56–58%) recommended discussing LST suspension when the patient is still conscious but with predicted deterioration of their condition. The suffering experienced by the patient was considered to be a priority by most patients (58%) and families (54%) during the decision-making process, while health professionals considered “the possibility of the patient’s recovery” to be the highest priority (43–55%). There is still a significant discrepancy in the perceptions of LST decisions among health professionals, patients, and their families despite high awareness of the Act. This situation makes it challenging to implement the Act to ensure respect for the rights of patients to self-determination and dignified end-of-life. Further effort is needed to improve the awareness of LSTs and to clarify the ambiguity of document preparation timing. (shrink)

Background In earlier work, we found important selection biases when we tried to obtain consent for participation in a national stroke registry. Recognizing that not all registries will be exempt from requiring consent for participation, we examine here in greater depth the reasons for the poor accrual of patients from a systems perspective with a view to obtaining as representative sample as possible. Methods We determined the percent of eligible patients who were approached to participate and, among those approached, the (...) percent who actually consented to participate. In addition we examined the reasons why people were not approached or did not consent and the variation across sites in the percent of patients approached and consented. We also considered site variation in restrictions on the accrual and data collection process imposed by either the local research ethics board or the hospital. Results Seventy percent of stroke patients were approached, with wide variations in approach rates across sites (from: 41% to 86%), and considerable inter-site variation in hospital policies governing patient accrual. Chief reasons for not approaching were discharge or death before being approached for consent. Seventeen percent of those approached refused to participate (range: 5% to 75%). Finally, 11% of those approached did not participate due to language or communication difficulties. Conclusion We found wide variation in approach and agree rates across sites that were accounted for, in part, by different approaches to accrual and idiosyncratic policies of the hospitals. This wide variation in approach and agree rates raises important challenges for research ethics boards and data protection authorities in determining when to waive consent requirements, when to press for increased quality control, when to permit local adaptation of the consent process, and when to permit alternatives to individual express consent. We offer several suggestions for those registries that require consent for participation. (shrink)

Die sekundäre Forschungsnutzung von Behandlungsdaten hat großes Potenzial, biomedizinisches Wissen zu erweitern und die Patientenversorgung zu verbessern. Gleichzeitig sind für eine bessere Ausschöpfung dieses Potenzials diverse Herausforderungen zu bewältigen. Dies gilt insbesondere in Deutschland, wo im Vergleich zu anderen Ländern, wie z.B. Dänemark oder Finnland, die sekundäre Forschungsnutzung von Behandlungsdaten unterentwickelt ist. Die Intensivierung der Nutzung der Daten aus Diagnose und Therapie von Patienten und die Entwicklung der dafür notwendigen Strukturen in Deutschland ist ethisch und politisch geboten: für die Verbesserung (...) der Gesundheitsversorgung durch neue Erkenntnisse, Therapien und Qualitätssicherung. Aus diesem Grund fordern die Autor:innen alle Akteure des Gesundheitssystems, von der Bundes- und den Landesregierungen über die Krankenkassen, Kliniken, Ärzt:innen und Patient:innen dazu auf, einen Beitrag dazu leisten, eine Kultur der sekundären Forschungsnutzung von Behandlungsdaten zu etablieren. Basierend auf den Ergebnissen eines dreijährigen Verbundprojekts beantworten die Autor:innen aus den Bereichen Medizin, Rechtswissenschaften, Ethik und Sozialwissenschaften die Frage was notwendig ist, damit in Deutschland die Daten von Patient:innen systematisch für medizinische Forschung und die Analyse der klinischen Versorgungsqualität verwendet werden können und wirklich auch verwendet werden. Sie nennen zehn zentrale Forderungen und legen eine Liste von 23 Empfehlungen mit konkreten Maßnahmen vor, welche von den genannten Akteuren umgesetzt werden sollten. (shrink)

Data gathered by investigators are used to test the validity of a specific scientific hypothesis. When the hypothesis relates to the biology of a disease or its treatment, then data sets may contain specific and identifiable medical information. Since the information in a clinical data set was gathered to test a specific hypothesis and there is usually a sponsor interested in the outcome, the issue of who owns the data is a critical one. In my (...) opinion, data from both publicly and privately funded research should be made available, in a format that protects confidentiality and intellectual property rights, to interested and responsible parties within a reasonable period of time after publication. (shrink)

Clinical Ethics and the Dynamics of Group Decision-Making: Applying the Psychological Data to Decisions Made by Ethics Committees Content Type Journal Article Pages 207-228 DOI 10.1007/s10730-009-9096-7 Authors Erica K. Rangel, Saint Louis University Department of Health Care Ethics 6333 North Rosebury Ave #3W St. Louis MO 63105 USA Journal HEC Forum Online ISSN 1572-8498 Print ISSN 0956-2737 Journal Volume Volume 21 Journal Issue Volume 21, Number 2.

Background The rapidly growing quantity of health data presents researchers with ample opportunity for innovation. At the same time, exploitation of the value of Big Data poses various ethical challenges that must be addressed in order to fulfil the requirements of responsible research and innovation (Gerke et al. 2020 ; Howe III and Elenberg 2020 ). Data sovereignty and its principles of self-determination and informed consent are central goals in this endeavor. However, their consistent implementation has enormous (...) consequences for the collection and processing of data in practice, especially given the complexity and growth of data in healthcare, which implies that artificial intelligence (AI) will increasingly be applied in the field due to its potential to unlock relevant, but previously hidden, information from the growing number of data (Jiang et al. 2017 ). Consequently, there is a need for ethically sound guidelines to help determine how data sovereignty and informed consent can be implemented in clinical research. Methods Using the method of a narrative literature review combined with a design thinking approach, this paper aims to contribute to the literature by answering the following research question: What are the practical requirements for the thorough implementation of data sovereignty and informed consent in healthcare? Results We show that privacy-preserving technologies, human-centered usability and interaction design, explainable and trustworthy AI, user acceptance and trust, patient involvement, and effective legislation are key requirements for data sovereignty and self-determination in clinical research. We outline the implications for the development of IT solutions in the German healthcare system. (shrink)

We face significant challenges in the translation of basic biomedical research into meaningful improvements in patients' health, moving research from “bench to bedside.” The federal government's ne...

Although data sharing platforms host diverse data types the features of these platforms are well-suited to facilitating biomarker research. Given the current state of biomarker discovery, an innovative paradigm to accelerate biomarker discovery is to utilize platforms such as Vivli to leverage researchers' abilities to integrate certain classes of biomarkers.

The focus of this paper are the ethical, legal and social challenges for ensuring the responsible use of “big brain data”—the recording, collection and analysis of individuals’ brain data on a large scale with clinical and consumer-directed neurotechnological devices. First, I highlight the benefits of big data and machine learning analytics in neuroscience for basic and translational research. Then, I describe some of the technological, social and psychological barriers for securing brain data from unwarranted access. (...) In this context, I then examine ways in which safeguards at the hardware and software level, as well as increasing “data literacy” in society, may enhance the security of neurotechnological devices and protect the privacy of personal brain data. Regarding ethical and legal ramifications of big brain data, I first discuss effects on the autonomy, the sense of agency and authenticity, as well as the self that may result from the interaction between users and intelligent, particularly closed-loop, neurotechnological devices. I then discuss the impact of the “datafication” in basic and clinical neuroscience research on the just distribution of resources and access to these transformative technologies. In the legal realm, I examine possible legal consequences that arises from the increasing abilities to decode brain states and their corresponding subjective phenomenological experiences on the hitherto inaccessible privacy of these information. Finally, I discuss the implications of big brain data for national and international regulatory policies and models of good data governance. (shrink)

Stopping rules — rules dictating when to stop accumulating data and start analyzing it for the purposes of inferring from the experiment — divide Bayesians, Likelihoodists and classical statistical approaches to inference. Although the relationship between Bayesian philosophy of science and stopping rules can be complex (cf. Steel 2003), in general, Bayesians regard stopping rules as irrelevant to what inference should be drawn from the data. This position clashes with classical statistical accounts. For orthodox statistics, stopping rules do (...) matter to what inference should be drawn from the data. "The dispute over stopping rule is far from being a marginal quibble, but is instead a striking illustration of the divergence of fundamental aims and standards separating Bayesians and advocates of orthodox statistical methods" (Steel 2004, 195) ... (shrink)

The reporting of clinical trial data is necessary not only for doctors to determine treatment efficacy, but also to explore new questions without unnecessarily repeating trials, and to protect patients and the public from dangers when data are withheld. This issue is particularly salient in those trials involving invasive neurosurgical interventions, such as deep brain stimulation (DBS), for ‘treatment refractory’ psychiatric disorders. Using the federal database ClinicalTrials.gov, it was discovered that out of the completed or unknown‐status trials (...) related to psychiatric DBS up to November 2018, only two had submitted results to ClinicalTrials.gov. These results suggest that, despite federal requirements to report clinical trial data, reporting on psychiatric DBS trials is problematically minimal. It is argued that a human rights approach to this problem establishes a legal and ethical foundation for the need to report clinical trial results in this area. (shrink)

Background There has been considerable investment and strategic planning to introduce genomic testing into Australia’s public health system. As more patients’ genomic data is being held by the public health system, there will be increased requests from researchers to access this data. It is important that public policy reflects public expectations for how genomic data that is generated from clinical tests is used. To inform public policy and discussions around genomic data sharing, we sought public (...) opinions on using genomic data contained in medical records for research purposes in the Australian state of Queensland. Methods A total of 1494 participants completed an online questionnaire between February and May 2019. Participants were adults living in Australia. The questionnaire explored participant preferences for sharing genomic data or biological samples with researchers, and concerns about genomic data sharing. Results Most participants wanted to be given the choice to have their genomic data from medical records used in research. Their expectations on whether and how often they needed to be approached for permission on using their genomic data, depended on whether the data was identifiable or anonymous. Their willingness to sharing data for research purposes depended on the type of information being shared, what type of research would be undertaken and who would be doing the research. Participants were most concerned with genomics data sharing that could lead to discrimination, data being used for marketing, data security, or commercial use. Conclusions Most participants were willing to share their genomic data from medical records with researchers, as long as permission for use was sought. However, the existing policies related to this process in Queensland do not reflect participant expectations for how this is achieved, particularly with anonymous genomics data. This inconsistency may be addressed by process changes, such as inclusion of research in addition to clinical consent or general research data consent programs. (shrink)

Clinical biobanks processing data of participants in the European Union fall under the scope of the General Data Protection Regulation, which among others includes requirements for consent. These requirements are further specified by the Article 29 Working Party —an EU advisory body currently known as the European Data Protection Board. Unfortunately, their guidance is cause for some confusion. While the GDPR allows participants to give broad consent for research when specific research purposes are still unknown, the (...) WP29 guidelines suggest that additional consent for specific uses should be obtained in addition to broad consent when this becomes applicable. This discrepancy elicits the question whether clinical biobanks can fail the requirement of consent if they obtain broad consent, but not a specific consent for each biomedical study. We analysed this discrepancy within the framework of contextual integrity, in order to describe the context-relative informational norms that govern information flows in clinical biobanks. However, our analysis demonstrates that there is no uniform set of norms that can be applied to all clinical biobanks. As such, neither the GDPR nor the WP29 guidance can act as a “one size fits all” approach to all clinical biobanks. Rather, differences between clinical biobanks—especially regarding the scientific aims and patient populations—make the case for context-relative norms that determine the appropriate type of consent. (shrink)

BackgroundClinical trials should be as inclusive as possible to facilitate equitable access to research and better reflect the population towards which any intervention is aimed. Informed by the UK’s National Institute for Health and Care Research (NIHR) Innovations in Clinical Trial Design and Delivery for the Under-served (INCLUDE) guidance, we audited oncology trials conducted by the Clinical Trials and Statistics Unit at The Institute of Cancer Research, London (ICR-CTSU) to identify whether essential documents were overtly excluding any groups (...) and whether sufficient data were collected to assess diversity of trial participants from groups suggested by INCLUDE as under-served by research in the UK.MethodsThirty cancer clinical trials managed by ICR-CTSU and approved between 2011–2021 were audited. The first ethics approved version of each trial’s protocol, patient information sheet, and patient completed questionnaire, together with the first case report forms (CRFs) version were reviewed. A range of items aligned with the INCLUDE under-served groups were assessed, including age, sex and gender, socio-economic and health factors. The scope did not cover trial processes in participating hospitals.ResultsData relating to participants’ age, ethnic group and health status were well collected and no upper age limit was specified in any trials’ eligibility criteria. 23/30 (77%) information sheets used at least one gendered term to address patients. Most CRFs did not specify whether they were collecting sex or gender and only included male or female categories. The median reading age for information sheets was 15–16 years (IQR: 14–15 – 16–17). Socio-economic factors were not routinely collected and not commonly mentioned in trial protocols.ConclusionsNo systemic issues were identified in protocols which would explicitly prevent any under-served group from participating. Areas for improvement include reducing use of gendered words and improving readability of patient information. The challenge of fully assessing adequate inclusion of under-served populations remains, as socio-economic factors are not routinely collected because they fall beyond the data generally required for protocol-specified trial endpoint assessments. This audit has highlighted the need to agree and standardise demographic data collection to permit adequate monitoring of the under-served groups identified by the NIHR. (shrink)

Agitation is one of the most common behavioural and psychological symptoms in people living with dementia. This behaviour can cause tremendous stress and anxiety on family caregivers and healthcare providers. Direct observation of PLwD is the traditional way to measure episodes of agitation. However, this method is subjective, bias-prone and timeconsuming. Importantly, it does not predict the onset of the agitation. Therefore, there is a need to develop a continuous monitoring system that can detect and/or predict the onset of agitation. (...) In this study, a multi-modal sensor platform with video cameras, motion and door sensors, wristbands and pressure mats were set up in a hospital-based dementia behavioural care unit to develop a predictive system to identify the onset of agitation. The research team faced several barriers in the development and initiation of the study, namely addressing concerns about the study ethics, logistics and costs of study activities, device design for PLwD and limitations of its use in the hospital. In this paper, the strategies and methodologies that were implemented to address these challenges are discussed for consideration by future researchers who will conduct similar studies in a hospital setting. (shrink)